BACKGROUND
Human health status can be measured in several different ways and statistical relationships among various measurements can be represented as a joint probability distribution. Approximation of the current health status of individuals will allow for more personalized and preventive healthcare by informing the potential risks and developing personalized interventions. Understanding 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 dataset of comprehensive healthcare information to construct a virtual human generative model (VHGM) based on a joint probability distribution.
METHODS
In this cross-sectional observational study, data will be collected from a population of 1000 adult men and women (aged ≥20 years) matching the age ratio of the typical adult Japanese population. Data will include biochemical and metabolic profiles from blood, urine, saliva, and oral glucose tolerance tests; bacterial profiles from feces, facial skin, scalp skin, and saliva; mRNA, proteome, and metabolite analyses from facial and scalp skin surface lipids; lifestyle survey and questionnaire; physical, motor, cognitive, and vascular function analyses; alopecia; and comprehensive analyses of body odor components. Statistical analyses will examine multiple health-related items using a joint probability distribution model. We will train a joint probability distribution, the VHGM, by combining a commercially available healthcare dataset containing large amounts of relatively low-dimensional data with a high-dimensional, cross-sectional dataset. The trained VHGM is expected to enable various healthcare applications through application program interface calls.
RESULTS
Written informed consent will be required to participate in the study. The study has been approved by the Institutional Review Boards of the Kao Corporation (Approval # K0023-2108) and the Preferred Network, Inc. (Approval # ET22110047).
CONCLUSIONS
The collected data are expected to provide information on the relationships between various health statuses. Because different degrees of health status correlations are expected to have different effects on individual health status, this study will contribute to developing empirically justified interventions based on the population.
CLINICALTRIAL
The trial is registered with the University Hospital Medical Information Network (Registration No. UMIN000045746).