Development of a multimodal magnetic resonance imaging-based machine learning prediction model for flight cadets

Article Figures and data Abstract Editor's evaluation eLife digest Introduction Methods Results Discussion Data availability References Decision letter Author response Article and author information Metrics Abstract Background: Estimates of ‘brain-predicted age’ quantify apparent brain age compared to normative trajectories of neuroimaging features. The brain age gap (BAG) between predicted and chronological age is elevated in symptomatic Alzheimer disease (AD) but has not been well explored in presymptomatic AD. Prior studies have typically modeled BAG with structural MRI, but more recently other modalities, including functional connectivity (FC) and multimodal MRI, have been explored. Methods: We trained three models to predict age from FC, structural (S), or multimodal MRI (S+FC) in 390 amyloid-negative cognitively normal (CN/A−) participants (18–89 years old). In independent samples of 144 CN/A−, 154 CN/A+, and 154 cognitively impaired (CI; CDR > 0) participants, we tested relationships between BAG and AD biomarkers of amyloid and tau, as well as a global cognitive composite. Results: All models predicted age in the control training set, with the multimodal model outperforming the unimodal models. All three BAG estimates were significantly elevated in CI compared to controls. FC-BAG was significantly reduced in CN/A+ participants compared to CN/A−. In CI participants only, elevated S-BAG and S+FC BAG were associated with more advanced AD pathology and lower cognitive performance. Conclusions: Both FC-BAG and S-BAG are elevated in CI participants. However, FC and structural MRI also capture complementary signals. Specifically, FC-BAG may capture a unique biphasic response to presymptomatic AD pathology, while S-BAG may capture pathological progression and cognitive decline in the symptomatic stage. A multimodal age-prediction model improves sensitivity to healthy age differences. Funding: This work was supported by the National Institutes of Health (P01-AG026276, P01- AG03991, P30-AG066444, 5-R01-AG052550, 5-R01-AG057680, 1-R01-AG067505, 1S10RR022984-01A1, and U19-AG032438), the BrightFocus Foundation (A2022014F), and the Alzheimer’s Association (SG-20-690363-DIAN). Editor's evaluation This is a useful study exploring multi-modality brain age (structural plus resting state MRI) in people in the early stages or at risk of Alzheimer's disease. They found solid evidence that people with cognitive impairment had older-appearing brains and that older-appearing brains were related to Alzheimer's risk factors such as amyloid and tau deposition. Their data suggest that the multi-modality brain age model is more accurate than a unimodal structural MRI model. https://doi.org/10.7554/eLife.81869.sa0 Decision letter Reviews on Sciety eLife's review process eLife digest The brains of people with advanced Alzheimer’s disease often look older than expected based on the patients’ actual age. This ‘brain age gap’ (how old a brain appears compared to the person’s chronological age) can be calculated thanks to machine learning algorithms which analyse images of the organ to detect changes related to aging. Traditionally, these models have relied on images of the brain structure, such as the size and thickness of various brain areas; more recent models have started to use activity data, such as how different brain regions work together to form functional networks. While the brain age gap is a useful measure for researchers who investigate aging and disease, it is not yet helpful for clinicians. For example, it is unclear whether the machine learning algorithm could detect changes in the brains of individuals in the initial stages of Alzheimer’s disease, before they start to manifest cognitive symptoms. Millar et al. explored this question by testing whether models which incorporate structural and activity data could be more sensitive to these early changes. Three machine learning algorithms (relying on either structural data, activity data, or combination of both) were used to predict the brain ages of participants with no sign of disease; with biological markers of Alzheimer’s disease but preserved cognitive functions; and with marked cognitive symptoms of the condition. Overall, the combined model was slightly better at predicting the brain age of healthy volunteers, and all three models indicated that patients with dementia had a brain which looked older than normal. For this group, the model based on structural data was also able to make predictions which reflected the severity of cognitive decline. Crucially, the algorithm which used activity data predicted that, in individuals with biological markers of Alzheimer’s disease but no cognitive impairment, the brain looked in fact younger than chronological age. Exactly why this is the case remains unclear, but this signal may be driven by neural processes which unfold in the early stages of the disease. While more research is needed, the work by Millar et al. helps to explore how various types of machine learning models could one day be used to assess and predict brain health. Introduction Alzheimer disease (AD) is marked by structural and functional disruptions in the brain, some of which can be observed through multimodal magnetic resonance imaging (MRI) in preclinical and symptomatic stages of the disease (Frisoni et al., 2010; Brier et al., 2014a). More recently, the ‘brain-predicted age’ framework has emerged as a promising tool for neuroimaging analyses, leveraging recent developments and accessibility of machine-learning techniques, as well as large-scale, publicly available neuroimaging datasets (Cole and Franke, 2017b; Franke and Gaser, 2019). These models are trained to quantify how ‘old’ a brain appears, as compared to a normative sample of training data - typically consisting of cognitively normal participants across the adult lifespan (e.g., Cole et al., 2015). Thus, the framework allows for a residual-based interpretation of the brain age gap (BAG), defined as the difference between model-predicted age and chronological age, as an index of vulnerability and/or resistance to underlying disease pathology. Indeed, several studies have demonstrated that BAG is elevated (i.e. the brain ‘appears older’ than expected) in a host of neurological and psychiatric disorders, including symptomatic AD (Franke et al., 2010; Franke and Gaser, 2012; Gaser et al., 2013), as well as schizophrenia (e.g., Koutsouleris et al., 2014), HIV (e.g., Cole et al., 2017c), and type-2 diabetes (e.g., Franke et al., 2013), and moreover, predicts mortality (Cole et al., 2018). Conversely, lower BAG is associated with lower risk of disease progression (Gaser et al., 2013; Wang et al., 2019; Bocancea et al., 2021). Critically, at least one comparison suggests that BAG exceeds other established MRI (hippocampal volume) and CSF (pTau and Aβ42) biomarkers in sensitivity to AD progression (Gaser et al., 2013). Thus, by summarizing complex, non-linear, highly multivariate patterns of neuroimaging features into a simple, interpretable summary metric, BAG may reflect a comprehensive biomarker of brain health. Several studies have established that symptomatic AD and mild cognitive impairment (MCI) are associated with elevated BAG (Cole and Franke, 2017b; Franke and Gaser, 2019). However, the sensitivity of these model estimates to AD in the presymptmatic stage (i.e. present amyloid pathology in the absence of cognitive decline [Sperling et al., 2011]) is less clear. The development of sensitive, reliable, non-invasive biomarkers of preclinical AD pathology is critical for the assessment of individual AD risk, as well as the evaluation of AD clinical prevention trials. Recent studies have demonstrated that greater BAG is associated with greater amyloid PET burden in a Down syndrome cohort (Cole et al., 2017a) and with greater tau PET burden in sporadic MCI and symptomatic AD (Lee et al., 2022). One approach to maximize sensitivity of BAG to presymptomatic AD pathology may be to train brain age models exclusively on amyloid-negative participants. As undetected AD pathology might influence MRI measures, and thus confound effects otherwise attributed to ‘healthy aging’ (Brier et al., 2014b), including the patterns learned by a traditional brain age model, an alternative model trained on amyloid-negative participants only might be more sensitive to detect presymptomatic AD pathology as deviations in BAG. Indeed, one recent study demonstrated that an amyloid-negative trained brain age model (Ly et al., 2020) is more sensitive to progressive stages of AD than a typical amyloid-insensitive model (Cole et al., 2015). However, this comparison included amyloid-negative and amyloid-positive test samples from two separate cohorts and thus may be driven by cohort, scanner, and/or site differences. To validate the applicability of the brain-predicted age approach to presymptomatic AD, it is important to test a model’s sensitivity to amyloid status, as well as continuous relationships with AD biomarkers, within a single cohort. Another recent comparison demonstrated that both traditional and amyloid-negative trained brain age models were similarly related to molecular AD biomarkers, but that further attempts to ‘disentangle’ AD from brain age by including more advanced AD continuum participants in the training sample significantly reduced relationships between brain age and AD markers (Hwang et al., 2022). Thus, in this study, we will apply the amyloid-negative training approach to a multimodal MRI dataset in order to maximize sensitivity to AD pathology in the presymptomatic stage. Most of the brain-predicted age reports described above focused primarily on structural MRI. However, other studies have successfully modeled brain age using a variety of other modalities, including metabolic PET (Goyal et al., 2019; Lee et al., 2022), diffusion MRI (Cherubini et al., 2016; Petersen et al., 2022), and functional connectivity (FC) (Dosenbach et al., 2010; Liem et al., 2017; Eavani et al., 2018; Nielsen et al., 2019). Integration of multiple neuroimaging modalities may maximize sensitivity of BAG estimates to preclinical AD. Indeed, recent multimodal comparisons suggest that structural MRI and FC capture complementary age-related signals (Eavani et al., 2018; Dunås et al., 2021) and that age prediction may be improved by incorporating multiple modalities (Liem et al., 2017; Engemann et al., 2020). One recent study has shown that BAG estimates from an FC graph theory-based model are significantly elevated in autosomal dominant AD mutation carriers and are positively associated with amyloid PET (Gonneaud et al., 2021). Furthermore, we have recently demonstrated that FC correlation-based BAG estimates are surprisingly reduced in cognitively normal participants with evidence of amyloid pathology and elevated pTau, as well as in cognitively normal APOE ε4 carriers at genetic risk of AD (Millar et al., 2022). Thus, incorporating FC into BAG models may improve sensitivity to early AD. This project aimed to develop multimodal models of brain-predicted age, incorporating both FC and structural MRI. Participants with presymptomatic AD pathology were excluded from the training set to maximize sensitivity. We hypothesized that BAG estimates would be sensitive to the presence of AD biomarkers and early cognitive impairment. We further considered whether estimates were continuously associated with AD biomarkers of amyloid and tau, as well as cognition. We hypothesized that FC and structural MRI would capture complementary signals related to age and AD. Thus, we systematically compared models trained on unimodal FC, structural MRI, and combined modalities to test the added utility of multimodal integration in accurately predicting age and whether each modality captures unique relationships with AD biomarkers and cognition. Methods Participants We formed a training sample of healthy controls spanning the adult lifespan by combining structural and FC-MRI data from three sources, as described previously (Millar et al., 2022): the Charles F. and Joanne Knight AD Research Center (ADRC) at Washington University in St. Louis (WUSTL), healthy controls from studies in the Ances lab at WUSTL (Thomas et al., 2013; Petersen et al., 2021), and mutation-negative controls from the Dominantly Inherited Alzheimer Network (DIAN) study of autosomal dominant AD at multiple international sites including WUSTL (McKay et al., 2022). To minimize the likelihood of undetected AD pathology in our training set, participants over the age of 50 were only included in the training set if they were cognitively normal, as assessed by the Clinical Dementia Rating (CDR 0; Morris, 1993), and had at least one biomarker indicating the absence of amyloid pathology (CN/A−, see below). We excluded 59 participants who did not have available CDR or biomarker measures (see Figure 1—figure supplement 1). As CDR and amyloid biomarkers were not available in the Ances lab controls, we included only participants at or below age 50 from this cohort in the training set. These healthy control participants were randomly divided into a training set (~80%; N=390) and a held-out test set (~20%; N=97), which did not significantly differ in age, sex, education, or race, see Table 1. Table 1 Demographic information of the combined samples. MeasureTraining sets (total N=390)Test sets (total N=97) §Analysis sets (total N=452)Ances Controls(CN/<50)DIAN Controls(CN/A−)Knight ADRC Controls(CN/A−)Ances Controls(CN/<50)DIAN Controls(CN/A−)Knight ADRC Controls(CN/A−)CN/A−CN/A+CIN136120134382633144154154Age (mean, SD)29.92 (9.92)40.02 (10.26)64.97 (10.57)26.68 (7.11)41.46 (12.34)64.73 (10.57)66.93 (8.53)72.56 (7.15)‡75.67 (6.86) ‡CDR (N 0 / N 0.5 / N 1.0 / N 2.0)NA120 / 0 / 0 / 0134 / 0 / 0 / 0NA26 / 0 / 0 / 033 / 0 / 0 / 0144 / 0 / 0 / 0154 / 0 / 0 / 00 / 119 / 35 / 2Amyloid status (N + / N -)NA120 / 0134 / 0NA26 / 033 / 0144 / 00 / 1540 / 57Biomarkers available (N PET / CSF / both)NA30 / 6 / 7911 / 22 / 91NA3 / 1 / 215 / 0 / 2824 / 0 / 12017 / 0 / 13714 / 0 / 43APOE ε4 carrier status (N + / N -)NA76 / 4499 / 34NA19 / 728 / 5115 / 2971 / 83 ‡55 / 98 ‡MMSE (mean, SD)NANA29.26 (1.05)NANA29.45 (0.94)29.13 (1.17)28.97 (1.33)25.37 (3.55) ‡Sex (N female / N male)70 / 6485 / 3584 / 5019 / 1816 / 1022 / 1189 / 5591 / 6368 / 86†Years of education (mean, SD)13.68 (2.16)14.78 (3.04)16.16 (2.43)13.95 (1.99)14.92 (2.83)16.48 (2.43)15.71 (2.65)15.90 (2.64)15.05 (2.97)*Race (N American Indian or Alaska Native)100100000Race (N Asian)112000010Race (N Black)670201707171620Race (N Native Hawaiian or Other Pacifc Islander)200200000Race (N White)57118112172626127137134SiteWUSTLMultiple sitesWUSTLWUSTLMultiple sitesWUSTLWUSTLWUSTLWUSTLScannerSiemens TrioSiemens Trio / VerioSiemens Trio / BiographSiemens TrioSiemens Trio / VerioSiemens Trio / BiographSiemens Trio / BiographSiemens Trio / BiographSiemens Trio / BiographField strength3T3T3T3T3T3T3T3T3T CN = Cognitively Normal, <50 = less than age 50, A− = amyloid negative, A+ = amyloid positive, CI = cognitively Impaired, DIAN = Dominantly Inherited Alzheimer Network, ADRC = Alzheimer Disease Research Center, AD = Alzheimer disease, CDR = Clinical Dementia Rating, MMSE = Mini Mental State Examination, WUSTL = Washington University in St. Louis, T = Tesla. Group differences from the CN/A− analysis set were tested with t tests for continuous variables and χ2 tests for categorical variables. * p < 0.05, ^ p < 0.10. † p < 0.01. ‡ p < 0.001. § Test sets include randomly-selected, non-overlapping subsets of participants drawn from the same studies as the training sets. Finally, independent samples for hypothesis testing included three groups from the Knight ADRC: a randomly selected sample of 144 CN/A− controls who did not overlap with the training or testing sets, 154 CN/A+ participants, and 154 cognitively impaired (CI) participants (CDR > 0 with a biomarker measure consistent with amyloid pathology [see below] and/or a primary diagnosis of AD or uncertain dementia [McKhann et al., 2011]). See Table 1 for demographic details of each sample. All participants provided written informed consent in accordance with the Declaration of Helsinki and their local institutional review board. All procedures were approved by the Human Research Protection Office at WUSTL (IRB ID # 201204041). PET and CSF biomarkers Amyloid burden was imaged with PET using (11 C)-Pittsburgh Compound B (PIB; Klunk et al., 2004) or (18 F)-Florbetapir (AV45; Wong et al., 2010). Regional standard uptake ratios (SUVRs) were modeled from 30 to 60 min after injection for PIB and from 50 to 70 min for AV45, using cerebellar gray as the reference region (Su et al., 2013). Regions of interest were segmented automatically using FreeSurfer 5.3 (Fischl, 2012). Global amyloid burden was defined as the mean of partial-volume-corrected (PVC) SUVRs from bilateral precuneus, superior and rostral middle frontal, lateral and medial orbitofrontal, and superior and middle temporal regions (Su et al., 2013). Amyloid summary SUVRs were harmonized across tracers using a centiloid conversion (Su et al., 2018). Tau deposition was imaged with PET using (18 F)-Flortaucipir (AV-1451; Chien et al., 2013). Regional SUVRs were modeled from 80 to 100 min after injection, using cerebellar gray as the reference region. A tau summary measure was defined in the mean PVC SUVRs from bilateral amygdala, entorhinal, inferior temporal, and lateral occipital regions (Mishra et al., 2017). CSF was collected via lumbar puncture using methods described previously (Fagan et al., 2006). After overnight fasting, 20–30 mL samples of CSF were collected, centrifuged, then aliquoted (500 µL) in polypropylene tubes, and stored at –80°C. CSF amyloid β peptide 42 (Aβ42), Aβ40, and phosphorylated tau-181 (pTau) were measured with automated Lumipulse immunoassays (Fujirebio, Malvern, PA, USA) using a single lot of assays for each analyte. Aβ42 and pTau estimates were each normalized for individual differences in CSF production rates by forming a ratio with Aβ40 as the denominator (Hansson et al., 2019; Guo et al., 2020). As pTau/Aβ40 was highly skewed, we applied a log transformation to these estimates before statistical analysis. Amyloid positivity was defined using previously published cutoffs for PIB (SUVR > 1.42; Vlassenko et al., 2016) or AV45 (SUVR > 1.19; Su et al., 2019). Additionally, the CSF Aβ42/Aβ40 ratio has been shown to be highly concordant with amyloid PET (positivity cutoff < 0.0673; Schindler et al., 2018; Volluz et al., 2021). Thus, participants were defined as amyloid-positive (for CN/A+ and CI groups) if they had either a PIB, AV45, or CSF Aβ42/Aβ40 ratio measure in the positive range. Participants with discordant positivity between PET and CSF estimates were defined as amyloid-positive. Cognitive battery Knight ADRC participants completed a 2 hr battery of cognitive tests. We examined global cognition by forming a composite of tasks across cognitive domains, including processing speed (Trail Making A; Schindler et al., 2018), executive function (Trail Making B; Schindler et al., 2018), semantic fluency (Animal Naming; Armitage, 1946), and episodic memory (Free and Cued Selective Reminding Test free recall score; Goodglass and Kaplan, et al., This composite has recently been used to study individual differences in cognition in the preclinical AD biomarkers and structural MRI et al., 2018), as well as functional MRI measures (Millar et al., 2021). MRI All MRI data were using a scanner, was a variety of models within and across As described previously (Millar et al., 2022), participants in the Knight ADRC and Ances lab studies completed one of two structural MRI by with = or = or = or = of = or 1 or with = = 1 and an imaging with = = = of = for two 6 min of DIAN participants completed a = = = of = et al., 2022). for the DIAN participants across sites and with the difference min of see 1 for summary of structural and functional MRI et al., 2022). FC and features All MRI data were using as described previously et al., 2010; Millar et al., 2022), including and of to a of et al., 2012). to an on independent samples of either younger or CN older was using a of the functional with the and was included in a single that a of the in As described previously et al., Millar et al., 2022), processing was to for Data based on estimates > and/or of > above To further minimize the influence of on FC estimates et al., in all we only included with < and > after data a temporal < < and including from FreeSurfer (Fischl, brain and as well as the of these signals. Finally, data were at data were across within a set of regions of interest in and cerebellar et al., 2020). For each we calculated the of the between all We then used the of each as features for predicting age. site and/or differences between samples might confound neuroimaging we harmonized FC using an approach et al., et al., which has previously been applied to FC data et al., 2018). MRI processing and features All images and structural through a with FreeSurfer 5.3 et al., 2012). processing included of and gray to a and of the based on the et al., 2006). and of and were and by a of trained research to (Su et al., 2013). We then used the thickness estimates from regions et al., with estimates from regions et al., as features for predicting age. We harmonized structural features across sites and using the same approach et al., et al., which has also been applied to structural MRI data et al., 2018). process As described previously (Millar et al., 2022), machine-learning were using the in 2021). We trained two process et al., 2004) each with a function to predict chronological age using harmonized MRI features or in the training set. The was within each model by a of from to using across 100 training The of for each model was found (see Figure 1—figure supplement and was applied for all of that model. All other were set to function = and = in the training set was assessed using via the the of the mean and between chronological age and the age predictions across the We then of the models to predict age in data by the trained models to the held-out test set of healthy controls. Finally, we applied the same models to separate analysis sets of 154 154 CN/A+, and 144 CN/A− controls to test our effects and individual difference models were each with a single model. The multimodal model was by the predictions from each unimodal model as features for training a model (Liem et al., 2017; Engemann et al., Dunås et al., 2021). For each we calculated BAG estimates as the difference between chronological age and age predictions from the unimodal FC model structural model and multimodal model To for observed in models et al., 2018; et al., 2019; et al., we included chronological age as a in all statistical tests of BAG (Cole et al., et al., 2018). However, to estimates of prediction et al., 2021), only age prediction were used for model in the training and test sets. analysis All statistical were in 2020). Demographic differences in the AD samples were tested with t tests for continuous variables and χ2 tests for categorical using CN/A− controls as a reference in brain age model were tested using test of difference between one between age and each model prediction of age. To for age-related in BAG et al., 2018; as previously we for age as a all statistical tests. Group differences in each BAG were tested using an test with t tests on BAG using a for multiple of were tested by of of of were tested with models tested the effects of cognitive impairment (CDR > 0 CDR 0) and amyloid positivity on BAG estimates from each model, for age sex, and years of the influence of on measures et al., 2012; et al., 2012; et al., we also included mean as an of in the FC and S+FC models. We tested continuous relationships with AD biomarkers and cognitive estimates using including the same demographic and the of amyloid biomarkers was reduced in the CN/A− we excluded these participants from models testing continuous amyloid were as Results and Demographic of the training sets, test sets, and analysis sets are in Table 1. CN/A+ participants were older = p < and more to be APOE ε4 carriers = p < than amyloid-negative controls. Furthermore, CI participants were older = p < more = p = more to be APOE ε4 carriers = p < and had years of education = p < and lower MMSE = p < than amyloid-negative controls. of model All models accurately predicted chronological age in the training sets, as

Article Figures and data Abstract Editor's evaluation eLife digest Introduction Methods Results Discussion Data availability References Decision letter Author response Article and author information Metrics Abstract Background: Estimates of ‘brain-predicted age’ quantify apparent brain age compared to normative trajectories of neuroimaging features. The brain age gap (BAG) between predicted and chronological age is elevated in symptomatic Alzheimer disease (AD) but has not been well explored in presymptomatic AD. Prior studies have typically modeled BAG with structural MRI, but more recently other modalities, including functional connectivity (FC) and multimodal MRI, have been explored. Methods: We trained three models to predict age from FC, structural (S), or multimodal MRI (S+FC) in 390 amyloid-negative cognitively normal (CN/A−) participants (18–89 years old). In independent samples of 144 CN/A−, 154 CN/A+, and 154 cognitively impaired (CI; CDR > 0) participants, we tested relationships between BAG and AD biomarkers of amyloid and tau, as well as a global cognitive composite. Results: All models predicted age in the control training set, with the multimodal model outperforming the unimodal models. All three BAG estimates were significantly elevated in CI compared to controls. FC-BAG was significantly reduced in CN/A+ participants compared to CN/A−. In CI participants only, elevated S-BAG and S+FC BAG were associated with more advanced AD pathology and lower cognitive performance. Conclusions: Both FC-BAG and S-BAG are elevated in CI participants. However, FC and structural MRI also capture complementary signals. Specifically, FC-BAG may capture a unique biphasic response to presymptomatic AD pathology, while S-BAG may capture pathological progression and cognitive decline in the symptomatic stage. A multimodal age-prediction model improves sensitivity to healthy age differences. Funding: This work was supported by the National Institutes of Health (P01-AG026276, P01- AG03991, P30-AG066444, 5-R01-AG052550, 5-R01-AG057680, 1-R01-AG067505, 1S10RR022984-01A1, and U19-AG032438), the BrightFocus Foundation (A2022014F), and the Alzheimer’s Association (SG-20-690363-DIAN). Editor's evaluation This is a useful study exploring multi-modality brain age (structural plus resting state MRI) in people in the early stages or at risk of Alzheimer's disease. They found solid evidence that people with cognitive impairment had older-appearing brains and that older-appearing brains were related to Alzheimer's risk factors such as amyloid and tau deposition. Their data suggest that the multi-modality brain age model is more accurate than a unimodal structural MRI model. https://doi.org/10.7554/eLife.81869.sa0 Decision letter Reviews on Sciety eLife's review process eLife digest The brains of people with advanced Alzheimer’s disease often look older than expected based on the patients’ actual age. This ‘brain age gap’ (how old a brain appears compared to the person’s chronological age) can be calculated thanks to machine learning algorithms which analyse images of the organ to detect changes related to aging. Traditionally, these models have relied on images of the brain structure, such as the size and thickness of various brain areas; more recent models have started to use activity data, such as how different brain regions work together to form functional networks. While the brain age gap is a useful measure for researchers who investigate aging and disease, it is not yet helpful for clinicians. For example, it is unclear whether the machine learning algorithm could detect changes in the brains of individuals in the initial stages of Alzheimer’s disease, before they start to manifest cognitive symptoms. Millar et al. explored this question by testing whether models which incorporate structural and activity data could be more sensitive to these early changes. Three machine learning algorithms (relying on either structural data, activity data, or combination of both) were used to predict the brain ages of participants with no sign of disease; with biological markers of Alzheimer’s disease but preserved cognitive functions; and with marked cognitive symptoms of the condition. Overall, the combined model was slightly better at predicting the brain age of healthy volunteers, and all three models indicated that patients with dementia had a brain which looked older than normal. For this group, the model based on structural data was also able to make predictions which reflected the severity of cognitive decline. Crucially, the algorithm which used activity data predicted that, in individuals with biological markers of Alzheimer’s disease but no cognitive impairment, the brain looked in fact younger than chronological age. Exactly why this is the case remains unclear, but this signal may be driven by neural processes which unfold in the early stages of the disease. While more research is needed, the work by Millar et al. helps to explore how various types of machine learning models could one day be used to assess and predict brain health. Introduction Alzheimer disease (AD) is marked by structural and functional disruptions in the brain, some of which can be observed through multimodal magnetic resonance imaging (MRI) in preclinical and symptomatic stages of the disease (Frisoni et al., 2010; Brier et al., 2014a). More recently, the ‘brain-predicted age’ framework has emerged as a promising tool for neuroimaging analyses, leveraging recent developments and accessibility of machine-learning techniques, as well as large-scale, publicly available neuroimaging datasets (Cole and Franke, 2017b; Franke and Gaser, 2019). These models are trained to quantify how ‘old’ a brain appears, as compared to a normative sample of training data - typically consisting of cognitively normal participants across the adult lifespan (e.g., Cole et al., 2015). Thus, the framework allows for a residual-based interpretation of the brain age gap (BAG), defined as the difference between model-predicted age and chronological age, as an index of vulnerability and/or resistance to underlying disease pathology. Indeed, several studies have demonstrated that BAG is elevated (i.e. the brain ‘appears older’ than expected) in a host of neurological and psychiatric disorders, including symptomatic AD (Franke et al., 2010; Franke and Gaser, 2012; Gaser et al., 2013), as well as schizophrenia (e.g., Koutsouleris et al., 2014), HIV (e.g., Cole et al., 2017c), and type-2 diabetes (e.g., Franke et al., 2013), and moreover, predicts mortality (Cole et al., 2018). Conversely, lower BAG is associated with lower risk of disease progression (Gaser et al., 2013; Wang et al., 2019; Bocancea et al., 2021). Critically, at least one comparison suggests that BAG exceeds other established MRI (hippocampal volume) and CSF (pTau and Aβ42) biomarkers in sensitivity to AD progression (Gaser et al., 2013). Thus, by summarizing complex, non-linear, highly multivariate patterns of neuroimaging features into a simple, interpretable summary metric, BAG may reflect a comprehensive biomarker of brain health. Several studies have established that symptomatic AD and mild cognitive impairment (MCI) are associated with elevated BAG (Cole and Franke, 2017b; Franke and Gaser, 2019). However, the sensitivity of these model estimates to AD in the presymptmatic stage (i.e. present amyloid pathology in the absence of cognitive decline [Sperling et al., 2011]) is less clear. The development of sensitive, reliable, non-invasive biomarkers of preclinical AD pathology is critical for the assessment of individual AD risk, as well as the evaluation of AD clinical prevention trials. Recent studies have demonstrated that greater BAG is associated with greater amyloid PET burden in a Down syndrome cohort (Cole et al., 2017a) and with greater tau PET burden in sporadic MCI and symptomatic AD (Lee et al., 2022). One approach to maximize sensitivity of BAG to presymptomatic AD pathology may be to train brain age models exclusively on amyloid-negative participants. As undetected AD pathology might influence MRI measures, and thus confound effects otherwise attributed to ‘healthy aging’ (Brier et al., 2014b), including the patterns learned by a traditional brain age model, an alternative model trained on amyloid-negative participants only might be more sensitive to detect presymptomatic AD pathology as deviations in BAG. Indeed, one recent study demonstrated that an amyloid-negative trained brain age model (Ly et al., 2020) is more sensitive to progressive stages of AD than a typical amyloid-insensitive model (Cole et al., 2015). However, this comparison included amyloid-negative and amyloid-positive test samples from two separate cohorts and thus may be driven by cohort, scanner, and/or site differences. To validate the applicability of the brain-predicted age approach to presymptomatic AD, it is important to test a model’s sensitivity to amyloid status, as well as continuous relationships with AD biomarkers, within a single cohort. Another recent comparison demonstrated that both traditional and amyloid-negative trained brain age models were similarly related to molecular AD biomarkers, but that further attempts to ‘disentangle’ AD from brain age by including more advanced AD continuum participants in the training sample significantly reduced relationships between brain age and AD markers (Hwang et al., 2022). Thus, in this study, we will apply the amyloid-negative training approach to a multimodal MRI dataset in order to maximize sensitivity to AD pathology in the presymptomatic stage. Most of the brain-predicted age reports described above focused primarily on structural MRI. However, other studies have successfully modeled brain age using a variety of other modalities, including metabolic PET (Goyal et al., 2019; Lee et al., 2022), diffusion MRI (Cherubini et al., 2016; Petersen et al., 2022), and functional connectivity (FC) (Dosenbach et al., 2010; Liem et al., 2017; Eavani et al., 2018; Nielsen et al., 2019). Integration of multiple neuroimaging modalities may maximize sensitivity of BAG estimates to preclinical AD. Indeed, recent multimodal comparisons suggest that structural MRI and FC capture complementary age-related signals (Eavani et al., 2018; Dunås et al., 2021) and that age prediction may be improved by incorporating multiple modalities (Liem et al., 2017; Engemann et al., 2020). One recent study has shown that BAG estimates from an FC graph theory-based model are significantly elevated in autosomal dominant AD mutation carriers and are positively associated with amyloid PET (Gonneaud et al., 2021). Furthermore, we have recently demonstrated that FC correlation-based BAG estimates are surprisingly reduced in cognitively normal participants with evidence of amyloid pathology and elevated pTau, as well as in cognitively normal APOE ε4 carriers at genetic risk of AD (Millar et al., 2022). Thus, incorporating FC into BAG models may improve sensitivity to early AD. This project aimed to develop multimodal models of brain-predicted age, incorporating both FC and structural MRI. Participants with presymptomatic AD pathology were excluded from the training set to maximize sensitivity. We hypothesized that BAG estimates would be sensitive to the presence of AD biomarkers and early cognitive impairment. We further considered whether estimates were continuously associated with AD biomarkers of amyloid and tau, as well as cognition. We hypothesized that FC and structural MRI would capture complementary signals related to age and AD. Thus, we systematically compared models trained on unimodal FC, structural MRI, and combined modalities to test the added utility of multimodal integration in accurately predicting age and whether each modality captures unique relationships with AD biomarkers and cognition. Methods Participants We formed a training sample of healthy controls spanning the adult lifespan by combining structural and FC-MRI data from three sources, as described previously (Millar et al., 2022): the Charles F. and Joanne Knight AD Research Center (ADRC) at Washington University in St. Louis (WUSTL), healthy controls from studies in the Ances lab at WUSTL (Thomas et al., 2013; Petersen et al., 2021), and mutation-negative controls from the Dominantly Inherited Alzheimer Network (DIAN) study of autosomal dominant AD at multiple international sites including WUSTL (McKay et al., 2022). To minimize the likelihood of undetected AD pathology in our training set, participants over the age of 50 were only included in the training set if they were cognitively normal, as assessed by the Clinical Dementia Rating (CDR 0; Morris, 1993), and had at least one biomarker indicating the absence of amyloid pathology (CN/A−, see below). We excluded 59 participants who did not have available CDR or biomarker measures (see Figure 1—figure supplement 1). As CDR and amyloid biomarkers were not available in the Ances lab controls, we included only participants at or below age 50 from this cohort in the training set. These healthy control participants were randomly divided into a training set (~80%; N=390) and a held-out test set (~20%; N=97), which did not significantly differ in age, sex, education, or race, see Table 1. Table 1 Demographic information of the combined samples. MeasureTraining sets (total N=390)Test sets (total N=97) §Analysis sets (total N=452)Ances Controls(CN/<50)DIAN Controls(CN/A−)Knight ADRC Controls(CN/A−)Ances Controls(CN/<50)DIAN Controls(CN/A−)Knight ADRC Controls(CN/A−)CN/A−CN/A+CIN136120134382633144154154Age (mean, SD)29.92 (9.92)40.02 (10.26)64.97 (10.57)26.68 (7.11)41.46 (12.34)64.73 (10.57)66.93 (8.53)72.56 (7.15)‡75.67 (6.86) ‡CDR (N 0 / N 0.5 / N 1.0 / N 2.0)NA120 / 0 / 0 / 0134 / 0 / 0 / 0NA26 / 0 / 0 / 033 / 0 / 0 / 0144 / 0 / 0 / 0154 / 0 / 0 / 00 / 119 / 35 / 2Amyloid status (N + / N -)NA120 / 0134 / 0NA26 / 033 / 0144 / 00 / 1540 / 57Biomarkers available (N PET / CSF / both)NA30 / 6 / 7911 / 22 / 91NA3 / 1 / 215 / 0 / 2824 / 0 / 12017 / 0 / 13714 / 0 / 43APOE ε4 carrier status (N + / N -)NA76 / 4499 / 34NA19 / 728 / 5115 / 2971 / 83 ‡55 / 98 ‡MMSE (mean, SD)NANA29.26 (1.05)NANA29.45 (0.94)29.13 (1.17)28.97 (1.33)25.37 (3.55) ‡Sex (N female / N male)70 / 6485 / 3584 / 5019 / 1816 / 1022 / 1189 / 5591 / 6368 / 86†Years of education (mean, SD)13.68 (2.16)14.78 (3.04)16.16 (2.43)13.95 (1.99)14.92 (2.83)16.48 (2.43)15.71 (2.65)15.90 (2.64)15.05 (2.97)*Race (N American Indian or Alaska Native)100100000Race (N Asian)112000010Race (N Black)670201707171620Race (N Native Hawaiian or Other Pacifc Islander)200200000Race (N White)57118112172626127137134SiteWUSTLMultiple sitesWUSTLWUSTLMultiple sitesWUSTLWUSTLWUSTLWUSTLScannerSiemens TrioSiemens Trio / VerioSiemens Trio / BiographSiemens TrioSiemens Trio / VerioSiemens Trio / BiographSiemens Trio / BiographSiemens Trio / BiographSiemens Trio / BiographField strength3T3T3T3T3T3T3T3T3T CN = Cognitively Normal, <50 = less than age 50, A− = amyloid negative, A+ = amyloid positive, CI = cognitively Impaired, DIAN = Dominantly Inherited Alzheimer Network, ADRC = Alzheimer Disease Research Center, AD = Alzheimer disease, CDR = Clinical Dementia Rating, MMSE = Mini Mental State Examination, WUSTL = Washington University in St. Louis, T = Tesla. Group differences from the CN/A− analysis set were tested with t tests for continuous variables and χ2 tests for categorical variables. * p < 0.05, ^ p < 0.10. † p < 0.01. ‡ p < 0.001. § Test sets include randomly-selected, non-overlapping subsets of participants drawn from the same studies as the training sets. Finally, independent samples for hypothesis testing included three groups from the Knight ADRC: a randomly selected sample of 144 CN/A− controls who did not overlap with the training or testing sets, 154 CN/A+ participants, and 154 cognitively impaired (CI) participants (CDR > 0 with a biomarker measure consistent with amyloid pathology [see below] and/or a primary diagnosis of AD or uncertain dementia [McKhann et al., 2011]). See Table 1 for demographic details of each sample. All participants provided written informed consent in accordance with the Declaration of Helsinki and their local institutional review board. All procedures were approved by the Human Research Protection Office at WUSTL (IRB ID # 201204041). PET and CSF biomarkers Amyloid burden was imaged with PET using (11 C)-Pittsburgh Compound B (PIB; Klunk et al., 2004) or (18 F)-Florbetapir (AV45; Wong et al., 2010). Regional standard uptake ratios (SUVRs) were modeled from 30 to 60 min after injection for PIB and from 50 to 70 min for AV45, using cerebellar gray as the reference region (Su et al., 2013). Regions of interest were segmented automatically using FreeSurfer 5.3 (Fischl, 2012). Global amyloid burden was defined as the mean of partial-volume-corrected (PVC) SUVRs from bilateral precuneus, superior and rostral middle frontal, lateral and medial orbitofrontal, and superior and middle temporal regions (Su et al., 2013). Amyloid summary SUVRs were harmonized across tracers using a centiloid conversion (Su et al., 2018). Tau deposition was imaged with PET using (18 F)-Flortaucipir (AV-1451; Chien et al., 2013). Regional SUVRs were modeled from 80 to 100 min after injection, using cerebellar gray as the reference region. A tau summary measure was defined in the mean PVC SUVRs from bilateral amygdala, entorhinal, inferior temporal, and lateral occipital regions (Mishra et al., 2017). CSF was collected via lumbar puncture using methods described previously (Fagan et al., 2006). After overnight fasting, 20–30 mL samples of CSF were collected, centrifuged, then aliquoted (500 µL) in polypropylene tubes, and stored at –80°C. CSF amyloid β peptide 42 (Aβ42), Aβ40, and phosphorylated tau-181 (pTau) were measured with automated Lumipulse immunoassays (Fujirebio, Malvern, PA, USA) using a single lot of assays for each analyte. Aβ42 and pTau estimates were each normalized for individual differences in CSF production rates by forming a ratio with Aβ40 as the denominator (Hansson et al., 2019; Guo et al., 2020). As pTau/Aβ40 was highly skewed, we applied a log transformation to these estimates before statistical analysis. Amyloid positivity was defined using previously published cutoffs for PIB (SUVR > 1.42; Vlassenko et al., 2016) or AV45 (SUVR > 1.19; Su et al., 2019). Additionally, the CSF Aβ42/Aβ40 ratio has been shown to be highly concordant with amyloid PET (positivity cutoff < 0.0673; Schindler et al., 2018; Volluz et al., 2021). Thus, participants were defined as amyloid-positive (for CN/A+ and CI groups) if they had either a PIB, AV45, or CSF Aβ42/Aβ40 ratio measure in the positive range. Participants with discordant positivity between PET and CSF estimates were defined as amyloid-positive. Cognitive battery Knight ADRC participants completed a 2 hr battery of cognitive tests. We examined global cognition by forming a composite of tasks across cognitive domains, including processing speed (Trail Making A; Schindler et al., 2018), executive function (Trail Making B; Schindler et al., 2018), semantic fluency (Animal Naming; Armitage, 1946), and episodic memory (Free and Cued Selective Reminding Test free recall score; Goodglass and Kaplan, et al., This composite has recently been used to study individual differences in cognition in the preclinical AD biomarkers and structural MRI et al., 2018), as well as functional MRI measures (Millar et al., 2021). MRI All MRI data were using a scanner, was a variety of models within and across As described previously (Millar et al., 2022), participants in the Knight ADRC and Ances lab studies completed one of two structural MRI by with = or = or = or = of = or 1 or with = = 1 and an imaging with = = = of = for two 6 min of DIAN participants completed a = = = of = et al., 2022). for the DIAN participants across sites and with the difference min of see 1 for summary of structural and functional MRI et al., 2022). FC and features All MRI data were using as described previously et al., 2010; Millar et al., 2022), including and of to a of et al., 2012). to an on independent samples of either younger or CN older was using a of the functional with the and was included in a single that a of the in As described previously et al., Millar et al., 2022), processing was to for Data based on estimates > and/or of > above To further minimize the influence of on FC estimates et al., in all we only included with < and > after data a temporal < < and including from FreeSurfer (Fischl, brain and as well as the of these signals. Finally, data were at data were across within a set of regions of interest in and cerebellar et al., 2020). For each we calculated the of the between all We then used the of each as features for predicting age. site and/or differences between samples might confound neuroimaging we harmonized FC using an approach et al., et al., which has previously been applied to FC data et al., 2018). MRI processing and features All images and structural through a with FreeSurfer 5.3 et al., 2012). processing included of and gray to a and of the based on the et al., 2006). and of and were and by a of trained research to (Su et al., 2013). We then used the thickness estimates from regions et al., with estimates from regions et al., as features for predicting age. We harmonized structural features across sites and using the same approach et al., et al., which has also been applied to structural MRI data et al., 2018). process As described previously (Millar et al., 2022), machine-learning were using the in 2021). We trained two process et al., 2004) each with a function to predict chronological age using harmonized MRI features or in the training set. The was within each model by a of from to using across 100 training The of for each model was found (see Figure 1—figure supplement and was applied for all of that model. All other were set to function = and = in the training set was assessed using via the the of the mean and between chronological age and the age predictions across the We then of the models to predict age in data by the trained models to the held-out test set of healthy controls. Finally, we applied the same models to separate analysis sets of 154 154 CN/A+, and 144 CN/A− controls to test our effects and individual difference models were each with a single model. The multimodal model was by the predictions from each unimodal model as features for training a model (Liem et al., 2017; Engemann et al., Dunås et al., 2021). For each we calculated BAG estimates as the difference between chronological age and age predictions from the unimodal FC model structural model and multimodal model To for observed in models et al., 2018; et al., 2019; et al., we included chronological age as a in all statistical tests of BAG (Cole et al., et al., 2018). However, to estimates of prediction et al., 2021), only age prediction were used for model in the training and test sets. analysis All statistical were in 2020). Demographic differences in the AD samples were tested with t tests for continuous variables and χ2 tests for categorical using CN/A− controls as a reference in brain age model were tested using test of difference between one between age and each model prediction of age. To for age-related in BAG et al., 2018; as previously we for age as a all statistical tests. Group differences in each BAG were tested using an test with t tests on BAG using a for multiple of were tested by of of of were tested with models tested the effects of cognitive impairment (CDR > 0 CDR 0) and amyloid positivity on BAG estimates from each model, for age sex, and years of the influence of on measures et al., 2012; et al., 2012; et al., we also included mean as an of in the FC and S+FC models. We tested continuous relationships with AD biomarkers and cognitive estimates using including the same demographic and the of amyloid biomarkers was reduced in the CN/A− we excluded these participants from models testing continuous amyloid were as Results and Demographic of the training sets, test sets, and analysis sets are in Table 1. CN/A+ participants were older = p < and more to be APOE ε4 carriers = p < than amyloid-negative controls. Furthermore, CI participants were older = p < more = p = more to be APOE ε4 carriers = p < and had years of education = p < and lower MMSE = p < than amyloid-negative controls. of model All models accurately predicted chronological age in the training sets, as

The heterogeneity of cerebral small vessel disease (CSVD) with mild cognitive impairment (MCI) presents a challenge for diagnosis and classification. This study aims to propose a multimodal magnetic resonance imaging (MRI)-based machine learning framework to effectively classify MCI and NCI in CSVD patients. We enrolled 165 CSVD patients, categorized into NCI (n = 81) and MCI (n = 84) groups based on neurocognitive assessments. Multimodal MRI data, including T1-weighted, resting-state functional MRI, and diffusion tensor images, were collected. Image preprocessing, feature extraction and selection were applied to obtain MRI features from three modalities. The AutoGluon platform was utilized for model development, and traditional machine learning algorithms were applied for comparison. The models were validated using a validation cohort of 83 CSVD patients, and their performance was assessed via receiver operating characteristic curve analysis. The AutoGluon model to distinguish MCI from NCI based on multimodal MRI features demonstrated high area under the curve (AUC), accuracy, sensitivity, specificity, precision, balanced accuracy, and F1-score in the training cohort (0.926, 88.48%, 88.10%, 88.89%, 89.16%, 88.50%, and 88.63%, respectively) and validation cohort (0.878, 81.93%, 86.36%, 76.92%, 80.85%, 81.64%, and 83.51%, respectively). Other traditional machine learning models had AUCs of 0.755–0.831, and their prediction accuracies were significantly lower than that of AutoGluon model (P < 0.001). Our study provides a multimodal MRI-based machine learning framework, utilizing the AutoGluon platform, that outperforms traditional algorithms in classifying MCI and NCI, offering a promising tool for the early prediction of MCI in CSVD.

Interest in the application of machine learning (ML) techniques to multimodal magnetic resonance imaging (MRI) data for the diagnosis of schizophrenia (SZ) at the individual level is growing. However, a few studies have applied the features of structural and functional brain networks derived from multimodal MRI data to the discriminative analysis of SZ patients at different clinical stages. In this study, 205 normal controls (NCs), 61 first-episode drug-naive SZ (FESZ) patients, and 79 chronic SZ (CSZ) patients were recruited. We acquired their structural MRI, diffusion tensor imaging, and resting-state functional MRI data and constructed brain networks for each participant, including the gray matter network (GMN), white matter network (WMN), and functional brain network (FBN). We then calculated 3 nodal properties for each brain network, including degree centrality, nodal efficiency, and betweenness centrality. Two classifications (SZ vs. NC and FESZ vs. CSZ) were performed using five ML algorithms. We found that the SVM classifier with the input features of the combination of nodal properties of both the GMN and FBN achieved the best performance to discriminate SZ patients from NCs [accuracy, 81.2%; area under the receiver operating characteristic curve (AUC), 85.2%; p < 0.05]. Moreover, the SVM classifier with the input features of the combination of the nodal properties of both the GMN and WMN achieved the best performance to discriminate FESZ from CSZ patients (accuracy, 86.2%; AUC, 92.3%; p < 0.05). Furthermore, the brain areas in the subcortical/cerebellum network and the frontoparietal network showed significant importance in both classifications. Together, our findings provide new insights to understand the neuropathology of SZ and further highlight the potential advantages of multimodal network properties for identifying SZ patients at different clinical stages.

Characterizing Typhoon-related Posttraumatic Stress Disorder Based on Multimodal Fusion of Structural, Diffusion, and Functional Magnetic Resonance Imaging

Schizophrenia is a neurodivergent disorder that can be studied using neuroimaging-based machine learning models for early diagnosis and classification. Despite advances in neuroimaging, a gap remains in visualising multimodal magnetic resonance imaging (MRI) data, compounded by challenges in interpretability and complex feature extraction. In this study, we propose a novel framework that integrates structural MRI (sMRI) and functional MRI (fMRI) data to improve schizophrenia classification accuracy while visualizing disorder-specific abnormalities. We employed the MLSP 2014 Schizophrenia Classification Challenge dataset comprising 86 subjects (40 schizophrenia patients and 46 healthy controls) and extracted 410 neuroimaging features, 378 FNC features from fMRI, and 32 SBM features from sMRI, using independent component analysis (ICA). To enhance clinical relevance, we further validated our approach on the publicly available COBRE (Center for Biomedical Research Excellence) dataset, which provides high-resolution anatomical MRI and resting-state fMRI scans for 147 participants (72 schizophrenia patients and 75 healthy controls) along with phenotypic details such as age, gender, handedness, and diagnostic information. The proposed multi-scale recurrent neural network (MsRNN) achieved 83.33% accuracy on the MLSP dataset and 89.8% on the COBRE dataset. To improve interpretability, layer-wise relevance propagation and gradient-weighted class activation mapping generated clinically meaningful visualizations of discriminative brain regions. These results demonstrate that the proposed multimodal, XAI-integrated framework outperforms conventional models while offering transparent, clinically useful explanations to aid diagnostic decision-making.

Machine-learning based prediction of future outcome using multimodal MRI during early childhood

Bilateral common carotid artery occlusion (BCCAo) in the rat is a widely used animal model of vascular dementia and a valuable tool for preclinical pharmacological drug testing, although the varying degrees of acute focal ischemic lesions it induces could interfere with its translational value. Recently, a modification to the BCCAo model, the stepwise occlusion of the two carotid arteries, has been introduced. To acquire objective translatable measures, we used longitudinal multimodal magnetic resonance imaging (MRI) to assess the effects of semi-chronic (8 days) donepezil treatment in this model, with half of the Wistar rats receiving the treatment one week after the stepwise BCCAo. With an ultrahigh field MRI, we measured high-resolution anatomy, diffusion tensor imaging, cerebral blood flow measurements and functional MRI in response to whisker stimulation, to evaluate both the structural and functional effects of the donepezil treatment and stepwise BCCAo up to 5 weeks post-occlusion. While no large ischemic lesions were detected, atrophy in the striatum and in the neocortex, along with widespread white matter microstructural changes, were found. Donepezil ameliorated the transient drop in the somatosensory BOLD response in distant cortical areas, as detected 2 weeks after the occlusion but the drug had no effect on the long term structural changes. Our results demonstrate a measurable functional MRI effect of the donepezil treatment and the importance of diffusion MRI and voxel based morphometry (VBM) analysis in the translational evaluation of the rat BCCAo model.

BackgroundChronic kidney disease is strongly linked to neurocognitive deficits in adults and children, but the pathophysiologic processes leading to these deficits remain poorly understood. The NiCK study (Neurocognitive Assessment and Magnetic Resonance Imaging Analysis of Children and Young Adults with Chronic Kidney Disease) seeks to address critical gaps in our understanding of the biological basis for neurologic abnormalities in chronic kidney disease. In this report, we describe the objectives, design, and methods of the NiCK study.Design/methodsThe NiCK Study is a cross-sectional cohort study in which neurocognitive and neuroimaging phenotyping is performed in children and young adults, aged 8 to 25 years, with chronic kidney disease compared to healthy controls. Assessments include (1) comprehensive neurocognitive testing (using traditional and computerized methods); (2) detailed clinical phenotyping; and (3) multimodal magnetic resonance imaging (MRI) to assess brain structure (using T1-weighted MRI, T2-weighted MRI, and diffusion tensor imaging), functional connectivity (using functional MRI), and blood flow (using arterial spin labeled MRI). Primary analyses will examine group differences in neurocognitive testing and neuroimaging between subjects with chronic kidney disease and healthy controls. Mechanisms responsible for neurocognitive dysfunction resulting from kidney disease will be explored by examining associations between neurocognitive testing and regional changes in brain structure, functional connectivity, or blood flow. In addition, the neurologic impact of kidney disease comorbidities such as anemia and hypertension will be explored. We highlight aspects of our analytical approach that illustrate the challenges and opportunities posed by data of this scope.DiscussionThe NiCK study provides a unique opportunity to address key questions about the biological basis of neurocognitive deficits in chronic kidney disease. Understanding these mechanisms could have great public health impact by guiding screening strategies, delivery of health information, and targeted treatment strategies for chronic kidney disease and its related comorbidities.

Predicting the transition from mild cognitive impairment (MCI) to Alzheimer's disease (AD) has important clinical significance for dementia prevention and improving patient prognosis. Multimodal magnetic resonance imaging (MRI) techniques (including structural MRI, functional MRI, and cerebral perfusion MRI) can yield information on the morphology, structure, and function of the brain from multiple dimensions, providing a key basis for revealing the pathophysiological mechanisms during the conversion from MCI to AD. Artificial intelligence (AI) methods based on deep learning and machine learning, with their powerful data processing and pattern recognition capabilities, have shown great potential in mining the features of multimodal MRI data and constructing prediction models for MCI conversion. Therefore, this paper systematically reviews the research progress of multimodal MRI techniques in capturing brain changes related to MCI conversion, as well as the practical experience of AI algorithms in constructing efficient prediction models, analyses the current technical challenges faced by the research, and discusses future directions, with the goal of providing a scientific reference for the early and accurate prediction of MCI conversion and the formulation of intervention strategies.

The integration of multi-modal Magnetic Resonance Imaging (MRI) and clinical data holds great promise for enhancing the diagnosis of neurological disorders (NDs) in real-world clinical settings. Deep Learning (DL) has recently emerged as a powerful tool for extracting meaningful patterns from medical data to aid in diagnosis. However, existing DL approaches struggle to effectively leverage multi-modal MRI and clinical data, leading to suboptimal performance.To address this challenge, we utilize a unique, proprietary multi-modal clinical dataset curated for ND research. Based on this dataset, we propose a novel transformer-based Mixture-of-Experts (MoE) framework for ND classification, leveraging multiple MRI modalities-anatomical (aMRI), Diffusion Tensor Imaging (DTI), and functional (fMRI)-alongside clinical assessments. Our framework employs transformer encoders to capture spatial relationships within volumetric MRI data while utilizing modality-specific experts for targeted feature extraction. A gating mechanism with adaptive fusion dynamically integrates expert outputs, ensuring optimal predictive performance. Comprehensive experiments and comparisons with multiple baselines demonstrate that our multi-modal approach significantly enhances diagnostic accuracy, particularly in distinguishing overlapping disease states. Our framework achieves a validation accuracy of 82.47%, outperforming baseline methods by over 10%, highlighting its potential to improve ND diagnosis by applying multi-modal learning to real-world clinical data.Clinical Relevance- In neurological disorder (ND) research, a critical gap remains in mapping the continuum of disease progression, from prodromal conditions such as idiopathic REM Sleep Behavior Disorder (iRBD) to fully developed disorders like Parkinson's Disease (PD). A robust multimodal approach that seamlessly integrates diverse data modalities is essential for accurately predicting and understanding this progression. Advancements in this area would provide the foundation for developing models capable of distinguishing overlapping disease states (e.g., PD, dementia with Lewy bodies, and multiple system atrophy) and predicting the transition from presymptomatic conditions like iRBD to established NDs.

Background and Purpose:Mild cognitive impairment (MCI) is a focus of considerable research. The present study aimed to test the utility of a logistic regression-derived classifier, combining specific quantitative multimodal magnetic resonance imaging (MRI) data for the early objective phenotyping of MCI in the clinic, over structural MRI data.Methods:Thirty-three participants with cognitively stable amnestic MCI; 15 MCI converters to early Alzheimer's disease (AD; diseased controls) and 20 healthy controls underwent high-resolution T1-weighted volumetric MRI, diffusion tensor imaging (DTI), and proton magnetic resonance spectroscopy (1H MR spectroscopy). The regional volumes were obtained from T1-weighted MRI. The fractional anisotropy and mean diffusivity maps were derived from DTI over multiple white matter regions. The 1H MRS voxels were placed over posterior cingulate gyri, and N-acetyl aspartate (NAA)/creatine (Cr), choline (Cho)/Cr, myoinositol (mI/Cr), and NAA/mI ratios were obtained. A multimodal classifier comprising MR volumetry, DTI, and MRS was prepared. A cutoff point was arrived based on receiver operator characteristics analysis. Results were considered significant, if P < 0.05.Results:The most sensitive individual marker to discriminate MCI from controls was DTI (90.9%), with a specificity of 50%. For classifying MCI from AD, the best individual modality was DTI (72.7%), with a high specificity of 87.9%. The multimodal classifier approach for MCI control classification achieved an area under curve (AUC) (AUC = 0.89; P < 0.001), with 93.9% sensitivity and 70% specificity. The combined classifier for MCI-AD achieved a highest AUC (AUC = 0.93; P < 0.001), with 93% sensitivity and 85.6% specificity.Conclusions:The combined method of gray matter atrophy, white matter tract changes, and metabolite variation achieved a better performance at classifying MCI compared to the application of individual MRI biomarkers.

Cortical Thinning and Neuropsychologic Measures Predict CD19 CAR T Cell Therapy-Associated Neurotoxicity

Training activities in alpine environments, characterized by low temperatures, hypoxia, and high physical demand, predispose individuals to craniomaxillofacial (CMF) complex injuries with potential involvement of the central nervous system in the event of accidents. However, the imaging manifestations and multimodal features of brain injury within this specific environmental context remain insufficiently characterized. This study aimed to retrospectively analyze the brain injury patterns in patients with CMF injuries sustained during alpine training, utilizing multimodal magnetic resonance imaging (MRI) data from the acute phase. It further sought to explore the interrelationships among structural damage, white matter microstructural alterations, and functional brain network abnormalities, thereby providing an imaging foundation for clinical assessment and risk stratification. This retrospective observational imaging study enrolled patients who sustained CMF injuries during alpine training and subsequently underwent multimodal MRI. All imaging data were derived from prior clinical examinations. MRI evaluations were performed during the acute post-injury period, with a median interval from injury to MRI of 2.6 days (interquartile range: 1.8-3.4 d). Short-term clinical follow-up data during the acute hospitalization phase were available for a subset of patients, with the endpoint defined as hospital discharge or completion of acute-phase treatment. No standardized longitudinal imaging follow-up was conducted. The MRI protocol encompassed conventional T1-weighted and T2-weighted imaging, diffusion-weighted imaging (DWI), susceptibility-weighted imaging (SWI), diffusion tensor imaging (DTI), and resting-state functional MRI (rs-fMRI). Primary analysis metrics included cerebral contusion/laceration and structural injury burden, the quantity and spatial distribution of cerebral microbleeds detected by SWI, DTI-derived white matter microstructural parameters, and topological indices of structural and functional brain networks constructed through connectomics methods. Multimodal integrative analysis was used to assess the associative characteristics between structural injury, white matter microstructural changes, and brain network dysfunction. The findings revealed that patients with CMF injuries from alpine training exhibited multilevel brain injury features during the acute phase, including cerebral contusions, microbleeds, and diminished white matter microstructural integrity. Microbleeds were predominantly distributed in the corpus callosum and subcortical deep white matter regions. Their burden was closely associated with reduced white matter fractional anisotropy (FA) and weakened functional network connectivity. Structural and functional connectivity analyses demonstrated a widespread reduction in global network efficiency and clustering coefficient among the injured individuals, alongside a relative enhancement of connectivity in certain frontal lobe-related networks, suggesting the presence of network reorganization and compensation during the acute phase. Multimodal analysis further indicated that, within the alpine training context, structural lesions, white matter injury, and brain network dysfunction exhibited significant coupling. The overall injury phenotype seemed more severe compared with general trauma backgrounds. Craniomaxillofacial complex injuries sustained during training in alpine environments can induce environmentally sensitive, multiscale brain damage in the acute phase, manifesting as coordinated alterations in structural injury, white matter microstructural abnormalities, and brain network functional disruption. Combined multimodal MRI analysis facilitates a comprehensive delineation of the imaging phenotype associated with such injuries, enhances the detection rate of occult brain damage, and provides critical reference for the clinical assessment, risk stratification, and intervention decision-making related to alpine environment-associated brain injury.

Background: Antipsychotic medications provide limited long-term benefit to approximately 30% of schizophrenia patients. Multimodal magnetic resonance imaging (MRI) data have been used to investigate brain features between responders and nonresponders to antipsychotic treatment; however, these analytical techniques are unable to weigh the interrelationships between modalities. Here, we used multiset canonical correlation and joint independent component analysis (mCCA + jICA) to fuse MRI data to examine the shared and specific multimodal features between the patients and healthy controls (HCs) and between the responders and nonresponders. Method: Resting-state functional and structural MRI data were collected from 55 patients with drug-naïve first-episode schizophrenia (FES) and demographically-matched HCs. Based on the decrease in Positive and Negative Syndrome Scale scores from baseline to the 1-year follow-up, FES patients were divided into a responder group (RG) and a nonresponder group (NRG). Gray matter volume (GMV), fractional amplitude of low-frequency fluctuation (fALFF) and regional homogeneity (ReHo) maps were used as features in mCCA + jICA. Results: Between FES patients and HCs, there were three modality-specific discriminative independent components (ICs) showing the difference in mixing coefficients (GMV-IC7, GMV-IC8, and fALFF-IC5). The fusion analysis indicated one modality-shared IC (GMV-IC2 and ReHo-IC2) and three modality-specific ICs (GMV-IC1, GMV-IC3, and GMV-IC6) between the RG and NRG. The right postcentral gyrus showed a significant difference in GMV features between FES patients and HCs and modality-shared features (GMV and ReHo) between responders and nonresponders. The modality-shared component findings were highlighted by GMV, mainly in the bilateral temporal gyrus and the right cerebellum associated with ReHo in the right postcentral gyrus. Conclusions: This study suggests that joint anatomical and functional features of the cortices may reflect an early pathophysiological mechanism that is related to a 1-year treatment response.