Hisashi Tsujimura

This study developed a two-stage, explainable machine learning framework to predict 18-month MMSE-based cognitive status from baseline multimodal data in community-dwelling older adults in Japan. A hierarchical design was used in which Stage 1 distinguished cognitively Normal participants from those with any abnormality (Possible Mild Cognitive Impairment (MCI) or Impaired), and Stage 2 further separated Possible MCI from Impaired within the abnormal subgroup. Both an Imbalanced-Learn Random Forest and a penalized logistic regression baseline were trained under Leave-One-Out Cross-Validation, yielding fair discrimination in Stage 1 (Random Forest AUC = 0.72, accuracy = 0.71; logistic regression AUC = 0.71, accuracy = 0.76) and apparently strong separability in Stage 2 (Random Forest AUC = 0.95, accuracy = 0.96; logistic regression AUC = 0.82, accuracy = 0.92) in a small sample size with high class imbalance. SHapley Additive exPlanations (SHAP) with TreeExplainer for Random Forest and LinearExplainer for logistic regression were used to identify interpretable biomarkers at each stage though feature attribution. In Stage 1, both models highlighted renal and systemic metabolic markers (e.g., creatinine, uric acid, blood urea nitrogen), amino acid and redox-related metabolites (including D-serine, D-amino acid proportions, L-asparagine, alanine, L-glutamic acid, cysteine, methionine sulfoxide), and wearable-derived activity variability (e.g., fluctuation coefficients and steps per minute), with the Simpson index of gut microbiome diversity also contributing in the logistic model. In Stage 2, the models converged on a distinct signature involving glucose and albumin, uric acid and uridine, choline and carnitine, multiple amino acids (such as phenylalanine, proline, ornithine, tryptophan, threonine, and short-chain amino acids), oxidative/energy markers (niacinamide, methionine, methionine sulfoxide, ergothioneine), hematologic indices, and high-MET activity fluctuation metrics. Collectively, these results support a stage-dependent, multisystem view of cognitive aging in which broad renal–metabolic, amino acid, and behavioral vulnerabilities characterize early abnormality, whereas more pronounced alterations in energy metabolism, nucleotide and choline pathways, oxidative stress, and activity irregularity accompany progression from Possible MCI to Impaired status. By combining routine clinical chemistry, targeted metabolomics, gut microbiome diversity, and wearable-derived behavioral measures within an explainable AI framework, this two-stage approach illustrates a scalable, biologically grounded strategy for stage-aware risk stratification and monitoring of cognitive decline in community settings.

Sex differences in gut microbiota may affect health and aging, but evidence in elderly populations is limited and inconsistent. This study examined sex-specific similarities and differences in gut microbiota diversity and composition among apparently healthy elderly Japanese individuals using shotgun metagenomic sequencing. A cross-sectional study was conducted in 100 community-dwelling adults aged 75–83 years (54 males, 46 females). Fecal samples underwent metagenomic sequencing. Alpha and beta diversity were assessed across six taxonomic levels, and taxonomic differences were evaluated using non-parametric tests. No significant sex differences were observed in alpha diversity indices (Shannon, Simpson, evenness, Chao1) at any taxonomic level. Beta diversity based on Bray–Curtis dissimilarity and PCoA also showed no sex-specific clustering. However, certain taxa differed in relative abundance. Males showed higher abundances of Bacteroidota (phylum), Bacteroidia and Betaproteobacteria (class), and Bacteroidales and Burkholderiales (order) (p < 0.05). No significant differences were detected at the family, genus, or species levels. Overall, gut microbial diversity and community structure were largely similar between elderly males and females, with only modest sex-associated differences at higher taxonomic levels. These findings suggest that biological sex may have a limited influence on gut microbiota composition in advanced age and provide population-level reference data for future longitudinal and interventional studies in elderly cohorts.

Background: Human health status can be measured on the basis of many different parameters. Statistical relationships among these different health parameters will enable several possible health care applications and an approximation of the current health status of individuals, which will allow for more personalized and preventive health care by informing the potential risks and developing personalized interventions. Furthermore, a better understanding of the modifiable risk factors related to lifestyle, diet, and physical activity will facilitate the design of optimal treatment approaches for individuals. Objective: This study aims to provide a high-dimensional, cross-sectional data set of comprehensive health care information to construct a combined statistical model as a single joint probability distribution and enable further studies on individual relationships among the multidimensional data obtained. Methods: In this cross-sectional observational study, data were collected from a population of 1000 adult men and women (aged ≥20 years) matching the age ratio of the typical adult Japanese population. Data include biochemical and metabolic profiles from blood, urine, saliva, and oral glucose tolerance tests; bacterial profiles from feces, facial skin, scalp skin, and saliva; messenger RNA, proteome, and metabolite analyses of facial and scalp skin surface lipids; lifestyle surveys and questionnaires; physical, motor, cognitive, and vascular function analyses; alopecia analysis; and comprehensive analyses of body odor components. Statistical analyses will be performed in 2 modes: one to train a joint probability distribution by combining a commercially available health care data set containing large amounts of relatively low-dimensional data with the cross-sectional data set described in this paper and another to individually investigate the relationships among the variables obtained in this study. Results: Recruitment for this study started in October 2021 and ended in February 2022, with a total of 997 participants enrolled. The collected data will be used to build a joint probability distribution called a Virtual Human Generative Model. Both the model and the collected data are expected to provide information on the relationships between various health statuses. Conclusions: As different degrees of health status correlations are expected to differentially affect individual health status, this study will contribute to the development of empirically justified interventions based on the population. International Registered Report Identifier (IRRID): DERR1-10.2196/47024