Cluster Membership Research Articles

EXPLORING OPEN STAR CLUSTER MEMBERSHIPS WITH N-BODY SIMULATIONS AND MACHINE LEARNING

This work explores the application of supervised machine learning algorithms on N-body simulations to analyze the membership of open star clusters. The simulations used in this study are based on the Plummer model, clusters formed with constant star-formation efficiency (SFE) per free-fall time. We use simulations with different SFE and initial random realization. The random forest model was trained using simulations based on a 15% SFE over a time period of 20-100 million years. Subsequently, the model was tested on other N-body simulations with SFEs ranging from 17% to 25%, demonstrating consistently high classification accuracy throughout the dynamic evolution of the tested simulations. The model successfully identified cluster members with minimal deviations despite variations in SFE. Additionally, the algorithm maintained robustness against noise and initial conditions. Most of the errors observed in the model were false positives (FP), often located within a 2 Jacobi radius, suggesting gravitational binding to the cluster's center. This framework and learning strategy exhibit effectiveness and hold promise for further application in analyzing mock observations obtained from N-body simulations. Future work will focus on extending this method to more realistic observational scenarios.

Understanding the intra-day and intra-week ridership patterns of urban rail transit stations in London using a fuzzy clustering approach

The needs for transit station classification are ever-growing as the planning process, be it at a strategic or operational level, becomes increasingly automated, data-oriented, and short-cycled. Whilst most existing models have used binary methods, this study applied a fuzzy clustering approach and examined cluster memberships (i.e., to what degree a station belongs to each cluster) of London rail transit stations by using entry and exit data with intra-day and intra-week variations. A method of hyperparameter selection in fuzzy clustering considering the context of transportation and a framework of ridership variation analysis was proposed. The results suggest that fuzzy clustering can maximise the information from high-resolution temporal passenger flow data of urban rail transit. The membership breakdowns allow users to have a better understanding of station characteristics and help to avoid inadequate plans by treating the stations belonging to multiple clusters in a different manner from the binary clustering, where each station only belongs to one cluster. Furthermore, fuzzy clustering can capture the ridership variation patterns and reveal special clusters. The results can be potentially applied in operation planning, such as service timetabling, station staff working-hour designs and fare strategy designs, etc.

Using GMM in open cluster membership: An insight

The unprecedented precision of Gaia has led to a paradigm shift in membership determination of open clusters where a variety of machine learning (ML) models can be employed. In this paper, we apply the unsupervised Gaussian Mixture Model (GMM) to a sample of thirteen clusters with varying ages (logt≈ 6.38-9.64) and distances (441-5183 pc) from Gaia DR3 data to determine membership. We use ASteca to determine parameters for the clusters from our revised membership data. We define a quantifiable metric Modified Silhouette Score (MSS) to evaluate its performance. We study the dependence of MSS on age, distance, extinction, galactic latitude and longitude, and other parameters to find the particular cases when GMM seems to be more efficient than other methods. We compared GMM for nine clusters with varying ages but we did not find any significant differences between GMM performance for younger and older clusters. But we found a moderate correlation between GMM performance and the cluster distance, where GMM works better for closer clusters. We find that GMM does not work very well for clusters at distances larger than 3 kpc.

Trail Runners’ Consumer Profiles: The Landscape Seekers, Sport Devotees, and Eco-Group Travellers

This study aims to segment trail runners employing psychographic segmentation, specifically sport commitment, as an understudied variable in sport tourism. The purpose is to identify specific trail runner profiles. An online survey was made available via Facebook through sponsored advertisements in South Africa. The final sample consisted of n=412 trail runners. Three distinct segments were identified using cluster analysis: landscape seekers, sport devotees, and eco-group travelers. These segments differed significantly regarding the factors influencing their sport commitment, with cluster membership influenced by demographic characteristics, behavioral intentions, and sought-after event attributes. To foster the expansion of trail running events in South Africa, it is imperative to concentrate efforts on enhancing accessibility through diverse routes across varied terrains, implementing comprehensive training programs catering to runners of all levels, and deploying strategic marketing initiatives to raise awareness and participation.

An interpretable clustering approach to safety climate analysis: Examining driver group distinctions

The transportation industry, particularly the trucking sector, is prone to workplace accidents and fatalities. Accidents involving large trucks accounted for a considerable percentage of overall traffic fatalities. Recognizing the crucial role of safety climate in accident prevention, researchers have sought to understand its factors and measure its impact within organizations. While existing data-driven safety climate studies have made remarkable progress, clustering employees based on their safety climate perception is innovative and has not been extensively utilized in research. Identifying clusters of drivers based on their safety climate perception allows the organization to profile its workforce and devise more impactful interventions. The lack of utilizing the clustering approach could be due to difficulties interpreting or explaining the factors influencing employees’ cluster membership. Moreover, existing safety-related studies did not compare multiple clustering algorithms, resulting in potential bias. To address these problems, this study introduces an interpretable clustering approach for safety climate analysis. This study compares five algorithms for clustering truck drivers based on their safety climate perceptions. It also proposes a novel method for quantitatively evaluating partial dependence plots (QPDP). Then, to better interpret the clustering results, this study introduces different interpretable machine learning measures (Shapley additive explanations, permutation feature importance, and QPDP). The Python code used in this study is available at https://github.com/NUS-DBE/truck-driver-safety-climate. This study explains the clusters based on the importance of different safety climate factors. Drawing on data collected from more than 7,000 American truck drivers, this study significantly contributes to the scientific literature. It highlights the critical role of supervisory care promotion in distinguishing various driver groups. Moreover, it showcases the advantages of employing machine learning techniques, such as cluster analysis, to enrich the scientific knowledge in this field. Future studies could involve experimental methods to assess strategies for enhancing supervisory care promotion, as well as integrating deep learning clustering techniques with safety climate evaluation.

Temporal Dietary Pattern Cluster Membership Varies on Weekdays and Weekends but Both Link to Health

BackgroundEnergy and dietary quality are known to differ between weekdays and weekends. Data-driven approaches that incorporate time, amount, and duration of dietary intake have previously been used to partition participants’ daily weekday dietary intake time series into clusters representing weekday temporal dietary patterns (TDPs) linked to health indicators in United States adults. Yet, neither the relationship of weekend day TDPs to health indicators nor how the TDP membership may change from weekday to weekend is known. ObjectivesThis study was conducted to determine the association between TDPs on weekdays and weekend days and health indicators [diet quality, waist circumference (WC), body mass index (BMI), and obesity] and their overlap among participants. MethodsA weekday and weekend day 24-hour dietary recall of 9494 nonpregnant United States adults aged 20–65 years from the cross-sectional National Health and Nutrition Examination Survey 2007–2018 was used to determine the timing and amount of energy intake. Modified dynamic time warping and kernel k-means algorithm clustered participants into 4 TDPs on weekdays and weekend days. Multivariate regression models determined the associations between TDPs and health indicators, controlling for potential confounders and adjusting for the survey design and multiple comparisons. The percentages of overlap in cluster membership between TDPs on weekdays and weekend days were also determined. ResultsUnited States adults with a TDP of evenly spaced, energy-balanced eating occasions, representing the TDP of more than one-third of all adults on weekdays and weekends, had significantly higher diet quality, lower BMI, WC, and odds of obesity when compared to those with other TDPs. Membership of most United States adults to TDPs varied from weekdays to weekends. ConclusionsBoth weekday and weekend TDPs were significantly associated with health indicators. TDP membership of most United States adults was not consistent on weekdays and weekends.

Are behavioural risk factors clusters associated with self-reported health complaints? University students in Finland.

No previous research of university students in Finland assessed lifestyle behavioural risk factors (BRFs) and categorized students into clusters, explored the associations of the clusters with self-reported health complaints (HCs), whilst controlling for potential confounders. The current study undertook this task. Students at the University of Turku (1,177) completed an online well-being questionnaire that assessed socio-demographic variables, 5 BRFs - problematic alcohol consumption, smoking, illicit drug use, food consumption habits, moderate-to-vigorous physical activity (MVPA), and 22 HCs. A food frequency questionnaire assessed students' consumption of a range of foods, and a dietary guideline adherence score was computed based on WHO dietary recommendations for Europe. Three separate regression models appraised the associations between the cluster membership and HCs factors, adjusting for sex, income sufficiency and self-rated health. Mean age was 23 ± 5.2 years, 77% had never smoked and 79% never used illicit drug/s. Factor analysis of HCs resulted in four-factors (psychological, circulatory/breathing, gastro-intestinal, pains/aches); cluster analysis of BRFs identified two distinctive student clusters. Cluster 1 represented more healthy students who never smoked/used illicit drugs, had no problematic drinking, and undertook MVPA on 4.42 ± 3.36 days/week. As for cluster 2 students, half the cluster smoked occasionally/daily, used illicit drug/s, and > 50% had problematic drinking and students undertook MVPA on 4.02 ± 3.12 days/week. More cluster 2 students adhered to healthy eating recommendations, but the difference was not significant between clusters. Regression analysis revealed that females, those with sufficient income, and with excellent/very good self-rated general health were significantly less likely to report all four HCs. Cluster 2 students were significantly more likely to report psychological complaints, circulatory/breathing and gastro-intestinal complaints. There was no significant association between BRFs clusters and pains/aches factor. Risk taking students with less healthy lifestyles and behaviour were consistently associated with poorer psychological and somatic health.

Cluster-based prognostication in glioblastoma: Unveiling heterogeneity based on diffusion and perfusion similarities.

While the association between diffusion and perfusion magnetic resonance imaging (MRI) and survival in glioblastoma is established, prognostic models for patients are lacking. This study employed clustering of functional imaging to identify distinct functional phenotypes in untreated glioblastomas, assessing their prognostic significance for overall survival. A total of 289 patients with glioblastoma who underwent preoperative multimodal MR imaging were included. Mean values of apparent diffusion coefficient normalized relative cerebral blood volume and relative cerebral blood flow were calculated for different tumor compartments and the entire tumor. Distinct imaging patterns were identified using partition around medoids (PAM) clustering on the training dataset, and their ability to predict overall survival was assessed. Additionally, tree-based machine-learning models were trained to ascertain the significance of features pertaining to cluster membership. Using the training dataset (231/289) we identified 2 stable imaging phenotypes through PAM clustering with significantly different overall survival (OS). Validation in an independent test set revealed a high-risk group with a median OS of 10.2 months and a low-risk group with a median OS of 26.6 months (P = 0.012). Patients in the low-risk cluster had high diffusion and low perfusion values throughout, while the high-risk cluster displayed the reverse pattern. Including cluster membership in all multivariate Cox regression analyses improved performance (P ≤ 0.004 each). Our research demonstrates that data-driven clustering can identify clinically relevant, distinct imaging phenotypes, highlighting the potential role of diffusion, and perfusion MRI in predicting survival rates of glioblastoma patients.

Bayesian Semiparametric Local Clustering of Multiple Time Series Data

In multiple time series data, clustering the component profiles can identify meaningful latent groups while also detecting interesting change points in their trajectories. Conventional time series clustering methods, however, suffer the drawback of requiring the co-clustered units to have the same cluster membership throughout the entire time domain. In contrast to these “global” clustering methods, we develop a Bayesian “local” clustering method that allows the functions to flexibly change their cluster memberships over time. We design a Markov chain Monte Carlo algorithm to implement our method. We illustrate the method in several real-world datasets, where time-varying cluster memberships provide meaningful inferences about the underlying processes. These include a public health dataset to showcase the more detailed inference our method can provide over global clustering alternatives, and a temperature dataset to demonstrate our method’s utility as a flexible change point detection method. Supplemental materials for this article, including R codes implementing the method, are available online.

Diagnostic structure of visual robotic inundated systems with fuzzy clustering membership correlation.

The process of using robotic technology to examine underwater systems is still a difficult undertaking because the majority of automated activities lack network connectivity. Therefore, the suggested approach finds the main hole in undersea systems and fills it using robotic automation. In the predicted model, an analytical framework is created to operate the robot within predetermined areas while maximizing communication ranges. Additionally, a clustering algorithm with a fuzzy membership function is implemented, allowing the robots to advance in accordance with predefined clusters and arrive at their starting place within a predetermined amount of time. A cluster node is connected in each clustered region and provides the central control center with the necessary data. The weights are evenly distributed, and the designed robotic system is installed to prevent an uncontrolled operational state. Five different scenarios are used to test and validate the created model, and in each case, the proposed method is found to be superior to the current methodology in terms of range, energy, density, time periods, and total metrics of operation.

Making Connections: Neurodevelopmental Changes in Brain Connectivity After Adverse Experiences in Early Adolescence.

Adverse childhood experiences have been linked to detrimental mental health outcomes in adulthood. This study investigates a potential neurodevelopmental pathway between adversity and mental health outcomes: brain connectivity. We used data from the prospective, longitudinal Adolescent Brain Cognitive Development (ABCD) study (N ≍ 12.000, participants aged 9-13 years, male and female) and assessed structural brain connectivity using fractional anisotropy (FA) of white matter tracts. The adverse experiences modeled included family conflict and traumatic experiences. K-means clustering and latent basis growth models were used to determine subgroups based on total levels and trajectories of brain connectivity. Multinomial regression was used to determine associations between cluster membership and adverse experiences. The results showed that higher family conflict was associated with higher FA levels across brain tracts (e.g., t (3) = -3.81, β = -0.09, p bonf = 0.003) and within the corpus callosum (CC), fornix, and anterior thalamic radiations (ATR). A decreasing FA trajectory across two brain imaging timepoints was linked to lower socioeconomic status and neighborhood safety. Socioeconomic status was related to FA across brain tracts (e.g., t (3) = 3.44, β = 0.10, p bonf = 0.01), the CC and the ATR. Neighborhood safety was associated with FA in the Fornix and ATR (e.g., t (1) = 3.48, β = 0.09, p bonf = 0.01). There is a complex and multifaceted relationship between adverse experiences and brain development, where adverse experiences during early adolescence are related to brain connectivity. These findings underscore the importance of studying adverse experiences beyond early childhood to understand lifespan developmental outcomes.

Identify adolescents' help-seeking intention on suicide through self- and caregiver's assessments of psychobehavioral problems: deep clustering of the Tokyo TEEN Cohort study

Psychopathological and behavioral problems in adolescence are highly comorbid, making their developmental trajectories complex and unclear partly due to technical limitations. We aimed to classify these trajectories using deep learning and identify predictors of cluster membership. We conducted a population-based cohort study on 3171 adolescents from three Tokyo municipalities, with 2344 pairs of adolescents and caregivers participating at all four timepoints (ages 10, 12, 14, and 16) from 2012 to 2021. Adolescent psychopathological and behavioral problems were assessed by using self-report questionnaires. Both adolescents and caregivers assessed depression/anxiety and psychotic-like experiences. Caregivers assessed obsession/compulsion, dissociation, sociality problem, hyperactivity/inattention, conduct problem, somatic symptom, and withdrawal. Adolescents assessed desire for slimness, self-harm, and suicidal ideation. These trajectories were clustered with variational deep embedding with recurrence, and predictors were explored using multinomial logistic regression. Five clusters were identified: unaffected (60.5%), minimal problems; internalizing (16.2%), persistent or worsening internalizing problems; discrepant (9.9%), subjective problems overlooked by caregivers; externalizing (9.6%), persistent externalizing problems; and severe (3.9%), chronic severe problems across symptoms. Stronger autistic traits and experience of bullying victimization commonly predicted the four "affected" clusters. The discrepant cluster, showing the highest risks for self-harm and suicidal ideation, was predicted by avoiding help-seeking for depression. The severe cluster predictors included maternal smoking during pregnancy, not bullying others, caregiver's psychological distress, and adolescent's dissatisfaction with family. Approximately 40% of adolescents were classified as "affected" clusters. Proactive societal attention is warranted toward adolescents in the discrepant cluster whose suicidality is overlooked and who have difficulty seeking help. Japan Ministry of Health, Labor and Welfare, Japan Agency for Medical Research and Development, and Japan Science and Technology Agency.

Dietary Patterns Among US Children: A Cluster Analysis

BackgroundMost children in the United States consume low-quality diets. Identifying children’s dietary patterns and their association with sociodemographic characteristics is important for designing tailored youth dietary interventions. ObjectiveThis study’s objective was to use cluster analysis to investigate children’s dietary patterns and these patterns’ associations with sociodemographic characteristics. DesignData from two cycles (2015-2016 and 2017-2018) of the National Health and Nutrition Examination Survey were evaluated to examine dietary patterns. Participants and settingParticipants included 3,044 US youth aged 2 to 11 years who completed at least 1 valid 24-hour diet recall. Main outcome measuresThe main outcome measures were Healthy Eating Index (HEI) 2015 component and composite scores. Statistical analyses performedA cluster analysis was performed on standardized scores of 11 components of the HEI-2015 to identify dietary patterns. One logistic analysis combined the two higher-HEI score clusters and the 2 lower-HEI score clusters to form a 3-category variable of higher-, medium-, and lower-HEI score clusters. Another logistic analysis contrasted 2 higher- and then the 2 lower-HEI clusters with each other to examine sociodemographic factors contributing to cluster membership. ResultsFive clusters were identified, each displaying a distinct dietary pattern. Older, non-Hispanic Black, and overweight children had higher odds of being in the higher-HEI clusters than the medium-HEI cluster. Being older and non-Hispanic Black were linked to higher odds of being in the lower-HEI clusters than the medium-HEI cluster. Conversely, being Mexican American and living with a college-educated reference person were associated with lower odds of being in the lower-HEI clusters compared with the medium-HEI cluster. Among the higher-HEI clusters, Mexican American and Asian American children had higher odds of being in the Pescatarian cluster. Among the lower-HEI clusters, children who were racially or ethnically minoritized had lower odds of being in the Excess Sugar cluster. ConclusionsChildren in this study displayed different dietary patterns, with key sociodemographic variation.

Access to basic infrastructure services in Ghanaian local government: a contextual approach

ABSTRACTThis study aims to empirically examine whether alternative combinations of economic and institutional conditions influence access to sanitation, drinking water and electricity services in Ghana using fuzzy clustering and regression analysis. Drawing on secondary data from 2021, five clusters of local government districts are identified: big, wealthy urban districts; rural, poor districts; middling districts; small districts and badly managed districts. The cluster membership scores for all districts are included in hierarchical regressions predicting access to sanitation, drinking water and electricity services. The main findings from this analysis are that big, wealthy, urban districts are associated with good infrastructure, whereas rural, poor districts and badly managed districts are associated with weak infrastructure access. To distribute infrastructure services more widely, initiatives addressing the economic disadvantages experienced by poor, rural communities and efforts to improve local public administration quality are needed.

Utility of Baseline Pathological, Neuroimaging and Clinical Markers for Progression Prognosis and Subtype Classification in Early Parkinson’s Disease: Implications for Cognitive Impairment

AbstractBackgroundCognitive dysfunction is a well‐recognised PD symptom, but it is highly heterogenous and under‐assessed clinically. Interestingly, PD motor subtypes are associated with different risk of cognitive decline. However, subtype classification is currently reliant on subjective clinician assessment and may consequently be misdiagnosed. Therefore, objective biomarkers of PD progression are critically needed, but must be validated prior to clinical deployment. We assessed the utility of various clinical, neuroimaging and pathological measures as predictors of cognitive outcomes up to 5‐years follow‐up in early PD.MethodData was extracted from the Parkinson’s Progression Markers Initiative. Cognitive assessments were compiled into an overall cognition score via principal component analysis. Distinct subgroups were identified via Fuzzy C‐Means clustering on Year‐5 Unified Parkinson’s Disease Rating Scale (UPDRS) motor scores. Models predicting cluster membership were created via logistic regression and a stratified cross‐validation machine learning pipeline, comparing two predictor inputs: 1) baseline motor assessments; and 2) incorporating additional measures, including prodromal assessments (sleep, olfactory and autonomic function), neuroimaging (proxy SN volume, striatal DaT binding) and biofluid markers (CSF alpha‐syn, p‐tau, a‐beta, and serum IGF‐1) at baseline. Finally, cluster membership was used for retroactive assessment of baseline and follow‐up cognitive data.ResultsTwo clusters were identified, with cluster two (n = 117) demonstrating higher rigidity, lower DaT binding, worsened motor outcomes and increased mood dysfunction at follow‐up compared to tremor‐dominant cluster one (n = 183). Additionally, rigid‐dominant membership was predicted by male sex, higher p‐tau, along with lower a‐beta, predicting 40% of variance (n = 111). This was significantly higher (P<0.001) than baseline motor scores alone, only accounting for 18% of variance. This was supported by machine learning, whereby incorporating additional assessments corresponded to a classification accuracy of 62%, compared to 26% when omitted. Finally, higher probability of belonging to the rigid‐dominant cluster yielded significant negative correlations cognition at baseline and follow‐up.ConclusionIncreased likelihood of rigid‐dominance corresponded to more profound cognitive decline, which may in part result from neuropathological marker concentrations as highlighted by predictive models. Therefore, further tracking of this cohort, specifically conversion into MCI or dementia, could provide insight into pathological contribution to differences in cognitive decline between PD subtypes.

EMPIRICAL ANALYSIS OF POTATO PRODUCTION: IN THE CASE OF SAMARKAND REGION, UZBEKISTAN

In this research work, an economic assessment of the state of potato cultivation by farms and the factors affecting it was given in order to ensure food security of the population. The analysis was based on the results of a social survey conducted in the farms of districts where potatoes are grown a lot in Samarkand region, using the OLS (Method of Least Squares) model. According to the results of the analysis, it was found that the age of the farm manager (*** p<.01) and cluster membership (** p<.05) have a negative effect on potato production in farms. However, the statistical significance of the work experience of the head of the farm (*** p<.01) and the presence of potato storage in the farm (* p<.1) is scientifically based. Based on the results of the analysis, scientifically based proposals and recommendations were developed.

Profiles of Youth Citizenship: A Cluster Analysis of Ethical Factors, Demographics, and Problem-Solving Disposition

Youth have the capacity to drive positive change in their communities through active and engaged citizenship (AEC). Teen leadership programs provide youth with opportunities to develop the skills necessary to participate as partners in community problem-solving efforts. Situated in relational developmental systems metatheory, this study examined how cluster membership based upon demographic characteristics, ethical factors, and problem-solving disposition impacted AEC. The findings indicated significant differences between clusters for AEC, civic duty, and civic skills. These differences were predominately observed through membership in long-term or short-term leadership programs, gender, enrollment in honors/AP courses, ethical views, and problem-solving disposition. Youth leadership practitioners should consider avenues for infusing problem-solving and character development in gender inclusive program curricula to increase the likelihood for contributing.

Amyloid and Tau Predominance Subtyping Identifies CI Patients With Different Clinical Phenotypes

AbstractBackgroundThe ATN classification system assumes a sequential model of disease progression. However, there are groups of individuals in the same ATN category that exhibit a predominance of abnormality (higher burden) of one of the biomarkers, creating heterogeneous ATN groups regarding pathological predominance. Thus, we tested the hypothesis that individuals clustered by ATN biomarker abnormality predominance may offer an alternative to groups defined using biomarkers cut‐offs.MethodWe assessed 103 cognitively impaired individuals(CDR> = 0.5) from the TRIAD cohort with available measures of plasma phosphorylated tau‐181, brain MRI, amyloid PET, and tau PET. We used the K‐means algorithm to stratify participants into three clusters. We compared the clusters on composite measures of memory, executive functioning, language, and visuospatial processing. To examine the utility of the discovered clusters, we compared them to traditional ATN categories in the prediction of neuropsychological measures. We did so by creating three categories: patients positive on all three ATN biomarkers, patients positive on two of the three biomarkers, and patients positive on either one or none. Additionally, we created an inflammation, amyloid and tau deposition probabilistic map anchored on young controls(n = 51, mean age = 23.74).ResultsWe uncovered 3 clusters: an amyloid predominant (AP) cluster, a tau/phosphor‐tau predominant cluster (TP), and a cluster showing no predominance with low levels on all biomarkers (CN)(figure 1). Notably, levels of neurodegeneration and inflammation were similar between the AP and TP clusters. The AP cluster significantly differed from the CN cluster in memory only. Participants in the TP cluster had significantly lower scores in memory, executive functioning, language, and visuospatial processing than the other two clusters. In comparison, using threshold‐based ATN groups showed milder differences in memory and executive functioning, and no differences in language and visuospatial processing(figure 2). Furthermore, cluster membership moderated the relationship between various biomarkers, to the point of reversing the direction of correlation(figure 3).ConclusionOur results highlight the biological heterogeneity present within the Alzheimer’s disease continuum and that the pathological predominance of amyloid and tau is associated with different disease phenotypes. Approaching dementia patients with an eye on the predominance of pathology rather than cutoffs for abnormality may provide a better understanding of AD pathological subtypes.

Amyloid and Tau Predominance Subtyping Identifies CI Patients With Different Clinical Phenotypes

AbstractBackgroundThe ATN classification system assumes a sequential model of disease progression. However, there are groups of individuals in the same ATN category that exhibit a predominance of abnormality (higher burden) of one of the biomarkers, creating heterogeneous ATN groups regarding pathological predominance. Thus, we tested the hypothesis that individuals clustered by ATN biomarker abnormality predominance may offer an alternative to groups defined using biomarkers cut‐offs.MethodWe assessed 103 cognitively impaired individuals(CDR> = 0.5) from the TRIAD cohort with available measures of plasma phosphorylated tau‐181, brain MRI, amyloid PET, and tau PET. We used the K‐means algorithm to stratify participants into three clusters. We compared the clusters on composite measures of memory, executive functioning, language, and visuospatial processing. To examine the utility of the discovered clusters, we compared them to traditional ATN categories in the prediction of neuropsychological measures. We did so by creating three categories: patients positive on all three ATN biomarkers, patients positive on two of the three biomarkers, and patients positive on either one or none. Additionally, we created an inflammation, amyloid and tau deposition probabilistic map anchored on young controls(n = 51, mean age = 23.74).ResultWe uncovered 3 clusters: an amyloid predominant (AP) cluster, a tau/phosphor‐tau predominant cluster (TP), and a cluster showing no predominance with low levels on all biomarkers (CN)(figure 1). Notably, levels of neurodegeneration and inflammation were similar between the AP and TP clusters. The AP cluster significantly differed from the CN cluster in memory only. Participants in the TP cluster had significantly lower scores in memory, executive functioning, language, and visuospatial processing than the other two clusters. In comparison, using threshold‐based ATN groups showed milder differences in memory and executive functioning, and no differences in language and visuospatial processing(figure 2). Furthermore, cluster membership moderated the relationship between various biomarkers, to the point of reversing the direction of correlation(figure 3).ConclusionOur results highlight the biological heterogeneity present within the Alzheimer’s disease continuum and that the pathological predominance of amyloid and tau is associated with different disease phenotypes. Approaching dementia patients with an eye on the predominance of pathology rather than cutoffs for abnormality may provide a better understanding of AD pathological subtypes.

Parkinson’s Disease Non-Motor Subtypes Classification in a Group of Slovenian Patients: Actuarial vs. Data-Driven Approach

Background and purpose: The aim of this study was to examine the risk factors, prodromal symptoms, non-motor symptoms (NMS), and motor symptoms (MS) in different Parkinson’s disease (PD) non-motor subtypes, classified using newly established criteria and a data-driven approach. Methods: A total of 168 patients with idiopathic PD underwent comprehensive NMS and MS examinations. NMS were assessed by the Non-Motor Symptom Scale (NMSS), Montreal Cognitive Assessment (MoCA), Hamilton Depression Scale (HAM-D), Hamilton Anxiety Rating Scale (HAM-A), REM Sleep Behavior Disorder Screening Questionnaire (RBDSQ), Epworth Sleepiness Scale (ESS), Starkstein Apathy Scale (SAS) and Fatigue Severity Scale (FSS). Motor subtypes were classified based on Stebbins’ method. Patients were classified into groups of three NMS subtypes (cortical, limbic, and brainstem) based on the newly designed inclusion criteria. Further, data-driven clustering was performed as an alternative, statistical learning-based classification approach. The two classification approaches were compared for consistency. Results: We identified 38 (22.6%) patients with the cortical subtype, 48 (28.6%) with the limbic, and 82 (48.8%) patients with the brainstem NMS PD subtype. Using a data-driven approach, we identified five different clusters. Three corresponded to the cortical, limbic, and brainstem subtypes, while the two additional clusters may have represented patients with early and advanced PD. Pearson chi-square test of independence revealed that a priori classification and cluster membership were significantly related to one another with a large effect size (χ2(8) = 175.001, p < 0.001, Cramer’s V = 0.722). The demographic and clinical profiles differed between NMS subtypes and clusters. Conclusion: Using the actuarial and clustering approach, marked differences between individual NMS subtypes were found. The newly established criteria have potential as a simplified tool for future clinical research of NMS subtypes of Parkinson’s disease.