An AI-Enabled Framework Within Reach for Enhancing Healthcare Sustainability and Fairness

TL;DR

This paper proposes a Camera-Based Public Health (CBPH) framework that leverages Visual-Based Physiological Monitoring (VBPM) to collect large-scale, diverse health data for public health and AI-enabled medical discovery. It outlines a three-layer architecture—database, AIaMD (AI as Medical Device), and AI4Medicine—underpinned by a Large Medical Model (PHAI) trained on a Large-Scale Public Health (LSPH) database, with a focus on explainability and digital biomarkers. The framework envisions a Large Physiological Model (LPM) and MM-LLM integration to support precision medicine, medical science discovery, and evidence-based medicine, enabling early disease detection and ecosystem-level health optimization. By addressing data equity, privacy, and global health disparities, CBPH aims to advance Universal Health Coverage and prepare for future pandemics, while accelerating AI4Medicine innovations and medical knowledge.

Abstract

Good health and well-being is among key issues in the United Nations 2030 Sustainable Development Goals. The rising prevalence of large-scale infectious diseases and the accelerated aging of the global population are driving the transformation of healthcare technologies. In this context, establishing large-scale public health datasets, developing medical models, and creating decision-making systems with a human-centric approach are of strategic significance. Recently, by leveraging the extraordinary number of accessible cameras, groundbreaking advancements have emerged in AI methods for physiological signal monitoring and disease diagnosis using camera sensors. These approaches, requiring no specialized medical equipment, offer convenient manners of collecting large-scale medical data in response to public health events. Therefore, we outline a prospective framework and heuristic vision for a camera-based public health (CBPH) framework utilizing visual physiological monitoring technology. The CBPH can be considered as a convenient and universal framework for public health, advancing the United Nations Sustainable Development Goals, particularly in promoting the universality, sustainability, and equity of healthcare in low- and middle-income countries or regions. Furthermore, CBPH provides a comprehensive solution for building a large-scale and human-centric medical database, and a multi-task large medical model for public health and medical scientific discoveries. It has a significant potential to revolutionize personal monitoring technologies, digital medicine, telemedicine, and primary health care in public health. Therefore, it can be deemed that the outcomes of this paper will contribute to the establishment of a sustainable and fair framework for public health, which serves as a crucial bridge for advancing scientific discoveries in the realm of AI for medicine (AI4Medicine).

Figures (4)

• Figure 1: A landscape of the CBPH framework. CBPH consists of three layers: the database, AIaMD and AI4Medicine layers. a, Data collection from the entire population utilizing camera sensors at hand. b, Extraction of physiological information using VBPM technologies. c, The constructed LSPH database, comprising 1) user-uploaded raw video data (voluntarily); 2) physiological information; 3) diagnosis information of patients. d, Monitoring, prediction and diagnosis of some specific diseases, such as AF, hypertension, and vascular aging. e, Development of a multi-task public health AI model. f, Global public health monitoring and decision-making in response to emergency events, such as COVID-19 or Disease X. g, Considering the distinction in various populations (e.g., the elderly and neonates) and those with different underlying diseases, the comprehensive studies on the evolution of diseases provide support for the formulation of personalized treatment plans. h, Medical scientific discoveries and pathological research based on large-scale data and model. i, Discovery of novel digital biomarkers and endpoints for evidence-based medicine and precision medicine.
• Figure 2: An overview of VBPM technologies for monitoring multiple physiological parameters. VBPM can be conveniently employed in various application scenarios, times, and regions. a, It can be conveniently applied to diverse populations and scenarios. b, It has the ability to collect physiological information data at any time, and these physiological signals are collected across weeks and seasons. c, The potential for data collection across regions and countries can provide a data foundation for studies on the correlation between regional environments and related diseases.
• Figure 3: Illustration of the PHAI model showcases its versatility and exciting potential applications across various domains. PHAI can be employed to monitor the progression of public health emergencies, facilitate the healthcare of aging population, forecast and diagnose illnesses like cardiovascular disease, conduct large-scale dataset-driven medical scientific discoveries, and more.
• Figure 4: Data-driven AI technologies for medical scientific discoveries. Traditional AI medical technologies model from representations to outcomes. The CBPH system emphasizes its role in facilitating the transition from new medical scientific discoveries based on large-scale data-driven AI technology to novel medical theories. It establishes a positive cyclical research process between "data-AI technology-medical theory" based on the studies of interpretability and discoveries of digital biomarkers.