Machine learning analyses identify multi-modal frailty factors that selectively discriminate four cohorts in the Alzheimer's disease spectrum: a COMPASS-ND study.

BACKGROUND: Frailty indicators can operate in dynamic amalgamations of disease conditions, clinical symptoms, biomarkers, medical signals, cognitive characteristics, and even health beliefs and practices. This study is the first to evaluate which, among these multiple frailty-related indicators, are important and differential predictors of clinical cohorts that represent progression along an Alzheimer's disease (AD) spectrum. We applied machine-learning technology to such indicators in order to identify the leading predictors of three AD spectrum cohorts; viz., subjective cognitive impairment (SCI), mild cognitive impairment (MCI), and AD. The common benchmark was a cohort of cognitively unimpaired (CU) older adults. METHODS: The four cohorts were from the cross-sectional Comprehensive Assessment of Neurodegeneration and Dementia dataset. We used random forest analysis (Python 3.7) to simultaneously test the relative importance of 83 multi-modal frailty indicators in discriminating the cohorts. We performed an explainable artificial intelligence method (Tree Shapley Additive exPlanation values) for deep interpretation of prediction effects. RESULTS: We observed strong concurrent prediction results, with clusters varying across cohorts. The SCI model demonstrated excellent prediction accuracy (AUC = 0.89). Three leading predictors were poorer quality of life ([QoL]; memory), abnormal lymphocyte count, and abnormal neutrophil count. The MCI model demonstrated a similarly high AUC (0.88). Five leading predictors were poorer QoL (memory, leisure), male sex, abnormal lymphocyte count, and poorer self-rated eyesight. The AD model demonstrated outstanding prediction accuracy (AUC = 0.98). Ten leading predictors were poorer QoL (memory), reduced olfaction, male sex, increased dependence in activities of daily living (n = 6), and poorer visual contrast. CONCLUSIONS: Both convergent and cohort-specific frailty factors discriminated the AD spectrum cohorts. Convergence was observed as all cohorts were marked by lower quality of life (memory), supporting recent research and clinical attention to subjective experiences of memory aging and their potentially broad ramifications. Diversity was displayed in that, of the 14 leading predictors extracted across models, 11 were selectively sensitive to one cohort. A morbidity intensity trend was indicated by an increasing number and diversity of predictors corresponding to clinical severity, especially in AD. Knowledge of differential deficit predictors across AD clinical cohorts may promote precision interventions.

Identifying key multi-modal predictors of incipient dementia in Parkinson's disease: a machine learning analysis and Tree SHAP interpretation.

Background: Persons with Parkinson's disease (PD) differentially progress to cognitive impairment and dementia. With a 3-year longitudinal sample of initially non-demented PD patients measured on multiple dementia risk factors, we demonstrate that machine learning classifier algorithms can be combined with explainable artificial intelligence methods to identify and interpret leading predictors that discriminate those who later converted to dementia from those who did not. Method: Participants were 48 well-characterized PD patients (Mbaseline age = 71.6; SD = 4.8; 44% female). We tested 38 multi-modal predictors from 10 domains (e.g., motor, cognitive) in a computationally competitive context to identify those that best discriminated two unobserved baseline groups, PD No Dementia (PDND), and PD Incipient Dementia (PDID). We used Random Forest (RF) classifier models for the discrimination goal and Tree SHapley Additive exPlanation (Tree SHAP) values for deep interpretation. Results: An excellent RF model discriminated baseline PDID from PDND (AUC = 0.84; normalized Matthews Correlation Coefficient = 0.76). Tree SHAP showed that ten leading predictors of PDID accounted for 62.5% of the model, as well as their relative importance, direction, and magnitude (risk threshold). These predictors represented the motor (e.g., poorer gait), cognitive (e.g., slower Trail A), molecular (up-regulated metabolite panel), demographic (age), imaging (ventricular volume), and lifestyle (activities of daily living) domains. Conclusion: Our data-driven protocol integrated RF classifier models and Tree SHAP applications to selectively identify and interpret early dementia risk factors in a well-characterized sample of initially non-demented persons with PD. Results indicate that leading dementia predictors derive from multiple complementary risk domains.

Gender specific factors contributing to cognitive resilience in APOE ɛ4 positive older adults in a population-based sample.

Although APOE ɛ4 has been identified as the strongest genetic risk factor for Alzheimer's Disease, there are some APOE ɛ4 carriers who do not go on to develop Alzheimer's disease or cognitive impairment. This study aims to investigate factors contributing to this "resilience" separately by gender. Data were drawn from APOE ɛ4 positive participants who were aged 60 + at baseline in the Personality and Total Health Through Life (PATH) Study (N = 341, Women = 46.3%). Participants were categorised into "resilient" and "non-resilient" groups using Latent Class Analysis based on their cognitive impairment status and cognitive trajectory across 12 years. Logistic regression was used to identify the risk and protective factors that contributed to resilience stratified by gender. For APOE ɛ4 carriers who have not had a stroke, predictors of resilience were increased frequency of mild physical activity and being employed at baseline for men, and increased number of mental activities engaged in at baseline for women. The results provide insights into a novel way of classifying resilience among APOE ɛ4 carriers and risk and protective factors contributing to resilience separately for men and women.

Data-Driven Analyses of Longitudinal Hippocampal Imaging Trajectories: Discrimination and Biomarker Prediction of Change Classes.

BACKGROUND: Hippocampal atrophy is a well-known biomarker of neurodegeneration, such as that observed in Alzheimer's disease (AD). Although distributions of hippocampal volume trajectories for asymptomatic individuals often reveal substantial heterogeneity, it is unclear whether interpretable trajectory classes can be objectively detected and used for prediction analyses. OBJECTIVE: To detect and predict hippocampal trajectory classes in a computationally competitive context using established AD-related risk factors/biomarkers. METHODS: We used biomarker/risk factor and longitudinal MRI data in asymptomatic adults from the AD Neuroimaging Initiative (n = 351; Mean = 75 years; 48.7% female). First, we applied latent class growth analyses to left (LHC) and right (RHC) hippocampal trajectory distributions to identify distinct classes. Second, using random forest analyses, we tested 38 multi-modal biomarkers/risk factors for their relative importance in discriminating the lower (potentially elevated atrophy risk) from the higher (potentially reduced risk) class. RESULTS: For both LHC and RHC trajectory distribution analyses, we observed three distinct trajectory classes. Three biomarkers/risk factors predicted membership in LHC and RHC lower classes: male sex, higher education, and lower plasma Aß1-42. Four additional factors selectively predicted membership in the lower LHC class: lower plasma tau and Aß1-40, higher depressive symptomology, and lower body mass index. CONCLUSION: Data-driven analyses of LHC and RHC trajectories detected three classes underlying the heterogeneous distributions. Machine learning analyses determined three common and four unique biomarkers/risk factors discriminating the higher and lower LHC/RHC classes. Our sequential analytic approach produced evidence that the dynamics of preclinical hippocampal trajectories can be predicted by AD-related biomarkers/risk factors from multiple modalities.

Subjective memory concerns, poor vascular health, and male sex predict exacerbated memory decline trajectories: An integrative data-driven class and prediction analysis.

OBJECTIVE: Subjective memory decline (SMD) has been identified as a potential early marker of nonnormal and accelerated cognitive decline. We performed data-driven analyses that integrated trajectory classification with prediction modeling to test declining trajectory class prediction by SMD facets, pulse pressure (PP; i.e., a robust proxy for vascular health), and sex. METHOD: The longitudinal design featured memory trajectories across a 40-year band (55-95 years) of nondemented aging (N = 580; Mage = 70.2 years; 65% female) from the Victoria Longitudinal Study. First, latent class growth analyses identified distinct classes of memory trajectories. Second, we used the three-step method (R3STEP) to predict membership in the declining memory classes using six measures: memory complaints, memory concerns, memory compensation, memory self-efficacy, PP, and sex. RESULTS: First, we identified four classes of memory aging trajectories: (a) stable memory aging (STABLE), (b) typical memory aging (TYPICAL), (c) slowly declining memory aging (SLOW), and (d) rapidly declining memory aging (RAPID). Second, more memory concerns predicted membership in the SLOW and RAPID classes. Higher PP predicted membership in the SLOW class. Male sex predicted membership in the declining (TYPICAL, SLOW, RAPID) classes. CONCLUSION: Among SMD facets, memory concerns represent the most severe degree of apprehension about subjectively experienced memory losses. The present integrative data-driven analysis indicated that such concerns predicted membership in declining memory trajectory classes in addition to worse vascular health (higher PP) and sex (male). In nondemented aging, concerns about increasing memory failures may be veridical indicators of memory loss, especially when coupled with vascular comorbidity and being male. (PsycInfo Database Record (c) 2022 APA, all rights reserved).

In multiple facets of subjective memory decline sex moderates memory predictions.

INTRODUCTION: Two established subjective memory decline facets (SMD; complaints, concerns) are early indicators of memory decline and Alzheimer's disease. We report (1) a four-facet SMD inventory (memory complaints, concerns, compensation, self-efficacy) and (2) prediction of memory change and moderation by sex. METHODS: The longitudinal design featured 40 years (53 to 97) of non-demented aging (n = 580) from the Victoria Longitudinal Study. Statistical analyses included confirmatory factor analyses and conditional latent growth modeling. RESULTS: The four-facet SMD Inventory was psychometrically confirmed. Longitudinal analyses revealed significant variability in level and change for SMD and memory. Prediction analyses showed complaints and concerns predicted lower level and steeper memory decline; however, follow-up moderation analyses revealed selective predictions for females. Memory compensation predicted decline overall. Lower memory self-efficacy predicted steeper decline selectively for males. DISCUSSION: Although traditional and novel SMD facets predicted memory decline, differential sex moderation was observed. SMD research benefits from conceptual complementarity and precision prediction.

T-Cell Mediation of Pregnancy Analgesia Affecting Chronic Pain in Mice.

It has been reported consistently that many female chronic pain sufferers have an attenuation of symptoms during pregnancy. Rats display increased pain tolerance during pregnancy due to an increase in opioid receptors in the spinal cord. Past studies did not consider the role of non-neuronal cells, which are now known to play an important role in chronic pain processing. Using an inflammatory (complete Freund's adjuvant) or neuropathic (spared nerve injury) model of persistent pain, we observed that young adult female mice in early pregnancy switch from a microglia-independent to a microglia-dependent pain hypersensitivity mechanism. During late pregnancy, female mice show no evidence of chronic pain whatsoever. This pregnancy-related analgesia is reversible by intrathecal administration of naloxone, suggesting an opioid-mediated mechanism; pharmacological and genetic data suggest the importance of δ-opioid receptors. We also observe that T-cell-deficient (nude and Rag1-null mutant) pregnant mice do not exhibit pregnancy analgesia, which can be rescued with the adoptive transfer of CD4+ or CD8+ T cells from late-pregnant wild-type mice. These results suggest that T cells are a mediator of the opioid analgesia exhibited during pregnancy.SIGNIFICANCE STATEMENT Chronic pain symptoms often subside during pregnancy. This pregnancy-related analgesia has been demonstrated for acute pain in rats. Here, we show that pregnancy analgesia can produce a complete cessation of chronic pain behaviors in mice. We show that the phenomenon is dependent on pregnancy hormones (estrogen and progesterone), δ-opioid receptors, and T cells of the adaptive immune system. These findings add to the recent but growing evidence of sex-specific T-cell involvement in chronic pain processing.