Personalized Health Care and Public Health in the Digital Age

Abstract

Personalized health care and public health are essential to one's well-being and societal welfare. The former focuses on symptoms and disease progression at the individual level, whereas the latter looks at health issues at the population level (from a group of patients to everyone on the planet). Recent years have seen a digital revolution in personalized health care and public health (1–4). As such, the World Health Organization regards mobile health (mHealth) as a vital resource for health services delivery and public health (5) and urges its Member States to prioritize the development and use of digital technologies in health to promote Universal Health Coverage and advance the Sustainable Development Goals (6). Here, we discuss how digital health contributes to personalized health care and public health and how it may evolve. Specifically, we present its roles, challenges, and potential future. Traditional health assessments require in-clinic visits, with bio-signals measured by professionals using specialized devices. To practice these frequently in a broad population is, however, inconvenient and expensive. Digital devices are mobile (or wearable), with fast data transmission done wirelessly. This enables remote and non-invasive health assessments and encourages users to self-care for their health (Figure 1A) (7, 8). Frequent assessments facilitate early disease discovery and longitudinal monitoring (7). Self-monitoring benefits those whose diseases may progress between hospital visits; the relatively affordable price (compared to hospital costs) makes health service accessible to many without in-hospital accesses (9). Self-monitoring does not confront in-clinic assessments. The former is as-of-yet not as accurate or comprehensive, but it provides complementary services and is more ecological to capture fluctuating symptoms. Figure 1. Building a Digitalized Ecosystem. (A) Digitalization cycle—bridging digital health, data, and digitally enabled decision-making. From 1 to 2: Phenotypic information is recorded by, and made available on, digital devices. From 2 to 4 via 3: Advanced modeling and analyses are applied on digital data to guide health-care decisions by physicians, such as recommending potential treatments (see bottom of item 4) and suggesting conducting further diagnostic tests or analyses (from 4 to 1). (B) Semi-automated disease diagnosis and monitoring. Individual data are de-identified, encrypted, and transferred remotely via the cloud to secured data centers—where population-level disease analyses are performed. The individual data are then analyzed and compared with the population features to generate an automated preliminary diagnosis report. Should red flags be raised, the report is passed on to a medical professional. The medical professional looks at both the report and the individual-specific data to offer medical recommendations or to arrange for an on-site visit or remote consultation (e.g., telemedicine), depending on which further tests are anticipated. This process continues between an individual's periodic health checks to ensure earliest possible detection of symptoms and to compensate for long consultation intervals when regular assessment is too expensive or inconvenient. (C) Automated deep-geno/phenotyping. The digital health applications facilitate ensemble-learning, where multivariate genotypic and phenotypic (e.g., digital biomarker, imaging, and molecular diagnostics) data are combined to provide rich subject-specific and group-level information, which are used to position individuals within a relevant population or to predict outcomes for individuals, based on population norms. (D) The marriage between personalized health care and public health. There is a powerful interdependent and synergistic relationship between personalized health care and public health in the digital age. Top: When shared, personal digital health data bring rich heterogeneous information into the population data pool. In return, features identified in large-scale public health data will provide a reference for individuals, positioning them relative to comparable cohorts in the population, based on age, sex, ethnicity, etc. Bottom: Integrating individual and population data. Data collected longitudinally over months and years enable risk estimation and disease forecasts, such as estimating the likelihood of disease progression or quantifying response to different treatments. Semi-automated health service alleviates a shortage in medical data, personnel, and equipment in several ways. First, it automates large-scale data collection. Next, automated data de-identification, encryption, and transfer (10) allow comparing personal data with population counterparts (11). Third, automation supports early disease detection, intervention, and treatment (12–15). For example, algorithms generate alerts suggesting medical consultation or delivering reports, with consent, to clinicians to assign interventions (16, 17) (see Figure 1B and telemedicine below). Naturally, one would ask, will digitalization and automation of health service result in job losses, for example, rendering health-care personnel, nurses, and physicians redundant? Likely not. First, such posts are in shortage (18). Although much of monitoring and assessment can be done digitally, the majority of high-value medical interventions cannot be automated at present or in the near future. The expansion of overall coverage, therefore, results in an increasing need for service to deal with the tasks that cannot be automated. Second, digital transformation and revolution (see section Long-Term Outlooks) grow the labor market by creating new jobs, such as data labeling, medical testing and analysis, and remote medical service (e.g., telemedicine). It also creates and expands domain-specific...