Mild Cognitive Impairment Stage Research Articles

Machine Learning-Driven GLCM Analysis of Structural MRI for Alzheimer’s Disease Diagnosis

Background: Alzheimer’s disease (AD) is a progressive and irreversible neurodegenerative condition that increasingly impairs cognitive functions and daily activities. Given the incurable nature of AD and its profound impact on the elderly, early diagnosis (at the mild cognitive impairment (MCI) stage) and intervention are crucial, focusing on delaying disease progression and improving patients’ quality of life. Methods: This work aimed to develop an automatic sMRI-based method to detect AD in three different stages, namely healthy controls (CN), mild cognitive impairment (MCI), and AD itself. For such a purpose, brain sMRI images from the ADNI database were pre-processed, and a set of 22 texture statistical features from the sMRI gray-level co-occurrence matrix (GLCM) were extracted from various slices within different anatomical planes. Different combinations of features and planes were used to feed classical machine learning (cML) algorithms to analyze their discrimination power between the groups. Results: The cML algorithms achieved the following classification accuracy: 85.2% for AD vs. CN, 98.5% for AD vs. MCI, 95.1% for CN vs. MCI, and 87.1% for all vs. all. Conclusions: For the pair AD vs. MCI, the proposed model outperformed state-of-the-art imaging source studies by 0.1% and non-imaging source studies by 4.6%. These results are particularly significant in the field of AD classification, opening the door to more efficient early diagnosis in real-world settings since MCI is considered a precursor to AD.

Unveiling the hippocampal subfield changes across the Alzheimer's disease continuum: a systematic review of neuroimaging studies.

Studies exploring the hippocampal subfield atrophy in Alzheimer's disease (AD) have shown contradictory results. This review aims to disentangle such heterogeneity by investigating the dynamic changes of hippocampal subfields across the AD continuum. We systematically searched the PubMed and EMBASE databases for case-control studies. Selected studies included investigations of biomarker-based amyloid status and reported data on hippocampal subfield atrophy using advanced MRI techniques. Twelve studies were included. Despite high heterogeneity, a distinguishable pattern of vulnerability of hippocampal subfields can be recognized from the cognitively unimpaired phase to the dementia stage, shedding light on hippocampal changes with disease progression. Consistent findings revealed atrophy in the subiculum and presubiculum, along with a potential increase in volume in the cornu ammonis (CA) among the cognitively unimpaired group, a feature not observed in patients experiencing subjective cognitive decline. Atrophy in the subiculum, presubiculum, CA 1-4, and the dentate gyrus characterized the mild cognitive impairment stage, with a more pronounced severity in the progression to dementia.

Validation of a functional human AD model with four AD therapeutics utilizing patterned ipsc-derived cortical neurons integrated with microelectrode arrays

Preclinical methods are needed for screening potential Alzheimer’s disease (AD) therapeutics that recapitulate phenotypes found in the Mild Cognitive Impairment (MCI) stage or even before this stage of the disease. This would require a phenotypic system that reproduces cognitive deficits without significant neuronal cell death to mimic the clinical manifestations of AD during these stages. Long-term potentiation (LTP), which is a correlate of learning and memory, was induced in mature human iPSC-derived cortical neurons cultured on microelectrode arrays utilizing circuit patterns connecting two adjacent electrodes. We demonstrated an LTP system that modeled the MCI and pre-MCI stages of Alzheimer’s and validated this functional system utilizing four AD therapeutics, which was also verified utilizing patch-clamp electrophysiology. LTP was induced by tetanic electrical stimulation, and LTP maintenance was significantly reduced in the presence of Amyloid-Beta 42 (Aβ42) oligomers compared to the controls, however, co-treatment with AD therapeutics (Donepezil, Memantine, Rolipram and Saracatinib) corrected Aβ42-induced LTP impairment. The results illustrate the utility of the system as a validated platform to model MCI AD pathology, and potentially for the pre-MCI phase before significant neuronal death. This system also has the potential to become an ideal platform for high-content therapeutic screening for other neurodegenerative diseases.

Ethnic differences in the prevalence of amyloid positivity and cognitive trajectories.

We investigated the prevalence of amyloid beta (Aβ) positivity (+) and cognitive trajectories in Koreans and non-Hispanic Whites (NHWs). We included 5121 Koreans from multiple centers across South Korea and 929 NHWs from the Alzheimer's Disease Neuroimaging Initiative (ADNI). Participants underwent Aβ positron emission tomography and were categorized into cognitively unimpaired (CU), mild cognitive impairment (MCI), and dementia stages. Age, sex, education, and apolipoprotein E. genotype were adjusted using multivariable logistic regression and stabilized inverse probability of treatment weights based on the propensity scores to mitigate imbalances in these variables. The prevalence of Aβ+ was lower in CU Koreans than in CU NHWs (adjusted odds ratio 0.60). Aβ+ Koreans showed a faster cognitive decline than Aβ+ NHWs in the CU (B=-0.314, p=.004) and MCI stages (B=-0.385, p<.001). Ethnic characteristics of Aβ biomarkers should be considered in research and clinical application of Aβ-targeted therapies in diverse populations. Koreans have a lower prevalence of Aβ positivity compared to NHWs in the CU stage. The effects of Alzheimer's risk factors on Aβ positivity differ between Koreans and NHWs. Aβ-positive (Aβ+) Koreans show faster cognitive decline than Aβ+ NHWs in the CU and MCI stages.

18F-FDG-PET-based deep learning for predicting cognitive decline in non-demented elderly across the Alzheimer’s disease clinical spectrum

Abstract Background With disease-modifying treatments for Alzheimer's disease (AD), prognostic tools for the pre-dementia stage are needed. This study aimed to evaluate the prognostic value of an 18F-fluorodeoxyglucose-positron emission tomography (18F-FDG-PET)-based deep-learning (DL) model in the pre-dementia stage of mild cognitive impairment (MCI) and normal cognition (NC). Materials and Methods A 18F-FDG-PET-based DL model was developed to classify diagnosis of AD-dementia vs NC using AD Neuroimaging Initiative (ADNI) and Japanese-ADNI (J-ADNI) datasets (n = 756), which provided the degree of similarity to AD-dementia. The prognostic value of the DL output for cognitive decline was assessed in the ADNI MCI (n = 663), J-ADNI MCI (n = 129), and Harvard Aging Brain Study (HABS) NC (n = 274) participants using Cox regression and calculating the integrated area under the time-dependent ROC curves (iAUC), along with clinical information and 18F-FDG-PET standardized uptake value ratio (SUVR). Subgroup analysis in the amyloid-positive ADNI MCI participants was performed using Cox regression and calculating the area under the time-dependent ROC (tdAUC) curves at 4-year follow-up to assess prognostic value of DL output over clinical information, 18F-FDG-PET SUVR, and amyloid PET Centiloids. Results DL output remained independently prognostic among other factors in all three datasets (P &amp;lt; .05 for all by Cox regression). By adding DL output to other prognostic factors, prediction significantly improved in ADNI-MCI (iAUC differences 0.020 [0.007-0.034] before and after adding DL output) and improved without statistical significance in J-ADNI (0.020 [−0.005 to 0.044], and HABS-NC sets (0.059 [−0.003 to 0.126]). DL output showed independent (P = .002 by Cox regression) and significant added prognostic value (tdROC difference 0.019 [&amp;lt;0.001-0.036]) over clinical information, 18F-FDG-PET SUVR, and Centiloids in the amyloid-positive ADNI MCI participants. Conclusion The 18F-FDG-PET-based DL model demonstrated the potential to improve cognitive decline prediction beyond clinical information, and conventional measures from 18F-FDG-PET and amyloid PET and may prove useful for clinical trial recruitment and individualized management.

Identification of profiles associated with conversions between the Alzheimer’s disease stages, using a machine learning approach

BackgroundThe identification of factors involved in the conversion across the different Alzheimer’s disease (AD) stages is crucial to prevent or slow the disease progression. We aimed to assess the factors and their combination associated with the conversion across the AD stages, from mild cognitive impairment to dementia, at a mild, moderate or severe stage and to identify profiles associated with earliest/latest conversion across the AD stages.MethodsIn this study conducted on the real-life MEMORA cohort data collected from January 1, 2013, and December 31, 2019, three cohorts were selected depending on the baseline neurocognitive stage from a consecutive sample of patients attending a memory center, aged between 50 and 90 years old, with a diagnosis of AD during the follow-up, and with at least 2 visits at 6 months to 1 year of interval. A machine learning approach was used to assess the relationship between factors including socio-demographic characteristics, comorbidities and history of diseases, prescription of drugs, and geriatric hospitalizations, and the censored time to conversion from mild cognitive impairment to AD dementia, from the mild stage of dementia to the moderate or severe stages of AD dementia, and from the moderate stage of AD dementia to the severe stage. Profiles of earliest/latest conversion compared to median time to conversion across stages were identified. The median time to conversion was estimated with a Kaplan-Meier estimator.ResultsOverall, 2891 patients were included (mean age 77±9 years old, 65% women). The median time of follow-up was 28 months for mild cognitive impairment (MCI) patients, 33 months for mild AD dementia and 30 months for moderate AD dementia. Among the 1264 patients at MCI stage, 61% converted to AD dementia (median time to conversion: 25 months). Among the 1142 patients with mild AD dementia, 59% converted to moderate/severe stage (median time: 23 months) and among the 1332 patients with moderate AD dementia, 23% converted to severe stage (Q3 time to conversion: 22 months). Among the studied factors, cardiovascular comorbidities, anxiety, social isolation, osteoporosis, and hearing disorders were identified as being associated with earlier conversion across stages. Symptomatic treatment i.e. cholinesterase inhibitors for AD was associated with later conversion from mild stage of dementia to moderate/severe stages.ConclusionThis study based on a machine learning approach allowed to identify potentially modifiable factors associated with conversion across AD stages for which timely interventions may be implemented to delay disease progression.

Heterogeneity of cerebral atrophic rate in mild cognitive impairment and its interactive association with proteins related to microglia activity on longitudinal cognitive changes

BackgroundHeterogeneity of cerebral atrophic rate commonly exists in mild cognitive impairment (MCI), which may be associated with microglia-involved neuropathology and have an influence on cognitive outcomes. ObjectiveWe aim to explore the heterogeneity of cerebral atrophic rate among MCI and its association with plasma proteins related to microglia activity, with further investigation of their interaction effects on long-term cognition. SubjectsA total of 630 MCI subjects in the ADNI database were included, of which 260 subjects were available with baseline data on plasma proteins. MethodsGroup-based multi-trajectory modeling (GBMT) was used to identify the latent classes with heterogeneous cerebral atrophic rates. Associations between latent classes and plasma proteins related to microglia activity were investigated with generalized linear models. Linear mixed effect models (LME) were implemented to explore the interaction effects between proteins related to microglia activity and identified latent classes on longitudinal cognitive changes. ResultsTwo latent classes were identified and labeled as the slow-atrophy class and the fast-atrophy class. Associations were found between such heterogeneity of atrophic rates and plasma proteins related to microglia activity, especially AXL receptor tyrosine kinase (AXL), CD40 antigen (CD40), and tumor necrosis factor receptor-like 2 (TNF-R2). Interaction effects on longitudinal cognitive changes showed that higher CD40 was associated with faster cognitive decline in the slow-atrophy class and higher AXL or TNF-R2 was associated with slower cognitive decline in the fast-atrophy class. ConclusionsHeterogeneity of atrophic rates at the MCI stage is associated with several plasma proteins related to microglia activity, which show either protective or adverse effects on long-term cognition depending on the variability of atrophic rates.

Development of disease-modifying therapies against Alzheimer's disease.

To successfully develop disease-modifying therapies (DMT) against Alzheimer's disease (AD), it is important to target the mild stage of the disease, before the pathological changes progress and dementia symptoms are fully manifested. To this end, the AD Neuroimaging Initiative (ADNI), a large-scale observational study, was initiated in the U.S. with the goal of development of DMT that are effective in the early stages of mild cognitive impairment (MCI) by utilizing imaging and biomarkers. In Japan, J-ADNI enrolled and followed up 537 patients, mainly with MCI, and established a platform for evaluation including amyloid PET, and demonstrated a high similarity in the clinical course of amyloid-positive MCI (prodromal AD) in Japan and the U.S. In 2023, the anti-Aβ antibody lecanemab successfully completed a Phase III clinical trial for early AD (prodromal AD + mild AD dementia) and was granted regulatory approval and made available both in the US and Japan. Also, phase III trial of donanemab was completed successful. The J-TRC study was initiated in Japan as a "trial ready cohort (TRC)" consisting of participants who met the eligibility criteria for participation in preclinical and prodromal AD trials. Based on such a platform, the development of DMT for AD will progress more rapidly in the future.

Estimating individual trajectories of structural and cognitive decline in mild cognitive impairment for early prediction of progression to dementia of the Alzheimer’s type

Only a third of individuals with mild cognitive impairment (MCI) progress to dementia of the Alzheimer’s type (DAT). Identifying biomarkers that distinguish individuals with MCI who will progress to DAT (MCI-Converters) from those who will not (MCI-Non-Converters) remains a key challenge in the field. In our study, we evaluate whether the individual rates of loss of volumes of the Hippocampus and entorhinal cortex (EC) with age in the MCI stage can predict progression to DAT. Using data from 758 MCI patients in the Alzheimer’s Disease Neuroimaging Database, we employ Linear Mixed Effects (LME) models to estimate individual trajectories of regional brain volume loss over 12 years on average. Our approach involves three key analyses: (1) mapping age-related volume loss trajectories in MCI-Converters and Non-Converters, (2) using logistic regression to predict progression to DAT based on individual rates of hippocampal and EC volume loss, and (3) examining the relationship between individual estimates of these volumetric changes and cognitive decline across different cognitive functions—episodic memory, visuospatial processing, and executive function. We find that the loss of Hippocampal volume is significantly more rapid in MCI-Converters than Non-Converters, but find no such difference in EC volumes. We also find that the rate of hippocampal volume loss in the MCI stage is a significant predictor of conversion to DAT, while the rate of volume loss in the EC and other additional regions is not. Finally, individual estimates of rates of regional volume loss in both the Hippocampus and EC, and other additional regions, correlate strongly with individual rates of cognitive decline. Across all analyses, we find significant individual variation in the initial volumes and the rates of changes in volume with age in individuals with MCI. This study highlights the importance of personalized approaches in predicting AD progression, offering insights for future research and intervention strategies.

Delineating the Heterogeneity of Alzheimer’s Disease and Mild Cognitive Impairment Using Normative Models of Dynamic Brain Functional Networks

BackgroundAlzheimer’s disease (AD), which has been identified as the most common type of dementia, presents considerable heterogeneity in its clinical manifestations. Early intervention at the stage of mild cognitive impairment (MCI) holds potential in AD prevention. However, characterizing the heterogeneity of neurobiological abnormalities and identifying MCI subtypes pose significant challenges. MethodsWe constructed sex-specific normative age models of dynamic brain functional networks and mapped the deviations of the brain characteristics for individuals from multiple datasets, including 295 patients with AD, 441 patients with MCI, and 1160 normal control participants. Then, based on these individual deviation patterns, subtypes for both AD and MCI were identified using the clustering method, and their similarities and differences were comprehensively assessed. ResultsIndividuals with AD and MCI were clustered into 2 subtypes, and these subtypes exhibited significant differences in their intrinsic brain functional phenotypes and spatial atrophy patterns, as well as in disease progression and cognitive decline trajectories. The subtypes with positive deviations in AD and MCI shared similar deviation patterns, as did those with negative deviations. There was a potential transformation of MCI with negative deviation patterns into AD, and participants with MCI had a more severe cognitive decline rate. ConclusionsIn this study, we quantified neurophysiological heterogeneity by analyzing deviation patterns from the dynamic functional connectome normative model and identified disease subtypes of AD and MCI using a comprehensive resting-state functional magnetic resonance imaging multicenter dataset. The findings provide new insights for developing early prevention and personalized treatment strategies for AD.

Visual search for real-world scenes in patients with Alzheimer's disease and amnestic mild cognitive impairment.

Visual attention-related processes that underlie visual search behavior are impaired in both the early stages of Alzheimer's disease (AD) and amnestic mild cognitive impairment (aMCI), which is considered a risk factor for AD. Although traditional computer-based array tasks have been used to investigate visual search, information on the visual search patterns of AD and MCI patients in real-world environments is limited. The objective of this study was to evaluate the differences in visual search behaviors among individuals with AD, aMCI, and healthy controls (HCs) in real-world scenes. A total of 92 participants were enrolled, including 28 with AD, 32 with aMCI, and 32 HCs. During the visual search task, participants were instructed to look at a single target object amid distractors, and their eye movements were recorded. The results indicate that patients with AD made more fixations on distractors and fewer fixations on the target, compared to patients with aMCI and HC groups. Additionally, AD patients had longer fixation durations on distractors and spent less time looking at the target than both patients with aMCI and HCs. These findings suggest that visual search behavior is impaired in patients with AD and can be distinguished from aMCI and healthy individuals. For future studies, it is important to longitudinally monitor visual search behavior in the progression from aMCI to AD. Our study holds significance in elucidating the interplay between impairments in attention, visual processes, and other underlying cognitive processes, which contribute to the functional decline observed in individuals with AD and aMCI.

ChatGPT's Inconsistency in the Diagnosis of Alzheimer's Disease.

A recent article by El Haj et al. provided evidence that ChatGPT could be a potential tool that complements the clinical diagnosis of various stages of Alzheimer's Disease (AD) as well as mild cognitive impairment (MCI). To reassess the accuracy and reproducibility of ChatGPT in the diagnosis of AD and MCI, we used the same prompt used by the authors. Surprisingly, we found that some of the responses of ChatGPT in the diagnoses of various stages of AD and MCI were different. In this commentary we discuss the possible reasons for these different results and propose strategies for future studies.

Machine Learning Model for Mild Cognitive Impairment Stage Based on Gait and MRI Images.

In patients with mild cognitive impairment (MCI), a lower level of cognitive function is associated with a higher likelihood of progression to dementia. In addition, gait disturbances and structural changes on brain MRI scans reflect cognitive levels. Therefore, we aimed to classify MCI based on cognitive level using gait parameters and brain MRI data. Eighty patients diagnosed with MCI from three dementia centres in Gangwon-do, Korea, were recruited for this study. We defined MCI as a Clinical Dementia Rating global score of ≥0.5, with a memory domain score of ≥0.5. Patients were classified as early-stage or late-stage MCI based on their mini-mental status examination (MMSE) z-scores. We trained a machine learning model using gait and MRI data parameters. The convolutional neural network (CNN) resulted in the best classifier performance in separating late-stage MCI from early-stage MCI; its performance was maximised when feature patterns that included multimodal features (GAIT + white matter dataset) were used. The single support time was the strongest predictor. Machine learning that incorporated gait and white matter parameters achieved the highest accuracy in distinguishing between late-stage MCI and early-stage MCI.

Generating real-world evidence in Alzheimer's disease: Considerations for establishing a core dataset.

Ongoing assessment of patients with Alzheimer's disease (AD) in postapproval studies is important for mapping disease progression and evaluating real-world treatment effectiveness and safety. However, interpreting outcomes in the real world is challenging owing to variation in data collected across centers and specialties and greater heterogeneity of patients compared with trial participants. Here, we share considerations for observational postapproval studies designed to collect harmonized longitudinal data from individuals with mild cognitive impairment or mild dementia stage of disease who receive therapies targeting the underlying pathological processes of AD in routine practice. This paper considers key study design parameters, including proposed aims and objectives, study populations, approaches to data collection, and measures of cognition, functional abilities, neuropsychiatric status, quality of life, health economics, safety, and drug utilization. Postapproval studies that capture these considerations will be important to provide standardized data on AD treatment effectiveness and safety in real-world settings.

Clinical validity of the Italian adaptation of the Uniform Data Set Neuropsychological Test Battery (I-UDSNB) in Mild Cognitive Impairment and Alzheimer’s Disease

BackgroundThe identification and staging of Alzheimer’s Disease (AD) represent a challenge, especially in the prodromal stage of Mild Cognitive Impairment (MCI), when cognitive changes can be subtle. Worldwide efforts were dedicated to select and harmonize available neuropsychological instruments. In Italy, the Italian Network of Neuroscience and Neuro-Rehabilitation has promoted the adaptation of the Uniform Data Set Neuropsychological Test Battery (I-UDSNB), collecting normative data from 433 healthy controls (HC).Here, we aimed to explore the ability of I-UDSNB to differentiate between a) MCI and HC, b) AD and HC, c) MCI and AD.MethodsOne hundred thirty-seven patients (65 MCI, 72 AD) diagnosed after clinical-neuropsychological assessment, and 137 HC were included. We compared the I-UDSNB scores between a) MCI and HC, b) AD and HC, c) MCI and AD, with t-tests. To identify the test(s) most capable of differentiating between groups, significant scores were entered in binary logistic and in stepwise regressions, and then in Receiver Operating Characteristic curve analyses.ResultsTwo episodic memory tests (Craft Story and Five Words test) differentiated MCI from HC subjects; Five Words test, Semantic Fluency (vegetables), and TMT-part B differentiated AD from, respectively, HC and MCI.ConclusionsOur findings indicate that the I-UDSNB is a suitable tool for the harmonized and concise assessment of patients with cognitive decline, showing high sensitivity and specificity for the diagnosis of MCI and AD.

Mechanism of action and clinical trial results of Lecanemab (Leqembi® 200 ‍mg, 500 ‍mg for Intravenous Infusion), a novel treatment for Alzheimer's disease

Lecanemab is a humanized monoclonal antibody directed against human soluble amyloid-β aggregates. It was developed for the treatment of early Alzheimer's disease (mild cognitive impairment or mild dementia stage of Alzheimer's disease). Among the amyloid-β (Aβ) involved in Alzheimer's disease, Lecanemab selectively binds to the highly neurotoxic Aβ protofibrils, and is thought to reduce Aβ protofibrils and amyloid plaques (Aβ plaques) in the brain. The efficacy and safety of Lecanemab in early Alzheimer's disease were investigated in an international Phase II placebo-controlled study (Study 201) and an international Phase III placebo-controlled study (Study 301). Both studies included Japanese subjects. Lecanemab was given accelerated approval in the United States in January 2023, followed by traditional approval in July 2023. In Japan, it was approved for "control of the progression of mild cognitive impairment or mild dementia stage of Alzheimer's disease" in September 2023, and was added to the NHI drug price list in December 2023.

Hemispheric asymmetries in hippocampal volume related to memory in left and right temporal variants of frontotemporal degeneration.

In addition to Alzheimer's disease (AD), the hippocampus is now known to be affected in variants of frontotemporal degeneration (FTD). In semantic variant primary progressive aphasia (svPPA), characterized by language impairments, hippocampal atrophy is greater in the left hemisphere. Nonverbal impairments (e.g., visual object recognition) are prominent in the right temporal variant of FTD (rtvFTD), and hippocampal atrophy may be greater in the right hemisphere. In this study we examined the hypothesis that leftward hippocampal asymmetry (predicted in svPPA) would be associated with selective verbal memory impairments (with relative preservation of visual memory), while rightward asymmetry (predicted in rtvFTD) would be associated with the opposite pattern (greater visual memory impairment). In contrast, we predicted that controls and individuals in the amnestic mild cognitive impairment stage of AD (aMCI), both of whom were expected to show symmetrical hippocampal volumes, would show roughly equivalent scores in verbal and visual memory. Participants completed delayed recall tests with words and geometric shapes, and hippocampal volumes were assessed with MRI. The aMCI sample showed symmetrical hippocampal atrophy, and similar degree of verbal and visual memory impairment. The svPPA sample showed greater left hippocampal atrophy and verbal memory impairment, while rtvFTD showed greater right hippocampal atrophy and visual memory impairment. Greater asymmetry in hippocampal volumes was associated with larger differences between verbal and visual memory in the FTD samples. Unlike AD, asymmetry is a core feature of brain-memory relationships in temporal variants of FTD.

Exploring inertial sensor-based balance biomarkers for early detection of mild cognitive impairment.

Dementia is characterized by a progressive loss of cognitive abilities, and diagnosing its early stages Mild Cognitive Impairment (MCI), is difficult since it is a transitory state that is different from total cognitive collapse. Recent clinical research studies have identified that balance impairments can be a significant indicator for predicting dementia in older adults. Accordingly, the current research focuses on finding innovative postural balance-based digital biomarkers by using wearable inertial sensors and pre-screening of MCI in home settings using machine learning techniques. For this research, sixty subjects (30 cognitively normal and 30 MCI) with waist-mounted inertial sensor performed balance tasks in four different standing postures: eyes-open, eyes-closed, right-leg-lift, and left-leg-lift. The significant balance biomarkers for MCI identification are discovered by our research, demonstrating specific characteristics in each of these four states. A robust feature selection approach is ensured by the multi-step methodology that combines the strengths of Filter techniques, Wrapper methods, and SHAP (Shapley Additive exPlanations) technique. The proposed balance biomarkers have the potential to detect MCI (with 75.8% accuracy), as evidenced by the results of machine learning algorithms for classification. This work adds to the growing body of literature targeted at enhancing understanding and proactive management of cognitive loss in older populations and lays the groundwork for future research efforts aimed at refining digital biomarkers, validating findings, and exploring longitudinal perspectives.

Predicting the Conversion from Mild Cognitive Impairment to Alzheimer’s Disease Using an Explainable AI Approach

Mild Cognitive Impairment (MCI) is a cognitive state frequently observed in older adults, characterized by significant alterations in memory, thinking, and reasoning abilities that extend beyond typical cognitive decline. It is worth noting that around 10–15% of individuals with MCI are projected to develop Alzheimer’s disease, effectively positioning MCI as an early stage of Alzheimer’s. In this study, a novel approach is presented involving the utilization of eXtreme Gradient Boosting to predict the onset of Alzheimer’s disease during the MCI stage. The methodology entails utilizing data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI). Through the analysis of longitudinal data, spanning from the baseline visit to the 12-month follow-up, a predictive model was constructed. The proposed model calculates, over a 36-month period, the likelihood of progression from MCI to Alzheimer’s disease, achieving an accuracy rate of 85%. To further enhance the precision of the model, this study implements feature selection using the Recursive Feature Elimination technique. Additionally, the Shapley method is employed to provide insights into the model’s decision-making process, thereby augmenting the transparency and interpretability of the predictions.

Network Analysis Revealed the Role of Helplessness as a Central Feature Among Late-Life Depressive Symptoms in Patients With Mild Cognitive Impairment and Early Stage Dementia.

It has been reported that depressive symptoms in older adults are different from those in younger adults, especially when accompanied by cognitive decline. However, few studies have investigated the network structure of depressive symptoms in this population. The participants consisted of 627 older adults (>60 yr) who were diagnosed with mild cognitive impairment (MCI) or early stage dementia. Among them, 36.7% were male and the mean age was 76.20±7.71 years. The Korean form of Geriatric Depression Scale (KGDS) was used to evaluate their depressive symptoms and network analyses were performed using bootnet R-package to identify the central features among depressive symptoms. Of all the KGDS items, we found that KGDS 2 (often feel helpless) had the highest node strength followed by KGDS 21 (in good spirits), KGDS 14 (not confident at all), and KGDS 15 (cheerful and happy). In terms of node betweenness, KGDS 2 also showed the highest value. The edge weights of edges connected to node KGDS 2 were strongest in KGDS 3 (restless and fidgety) and KGDS 28 (easily get tired). In this study, we presented which symptoms are central among the elderly with MCI and early stage dementia. This result not only increases the understanding of depressive symptoms in this group but would also help determine target symptoms in the treatment program.