Can AI fix broken healthcare? New study says system must treat the whole human

A new study calls for a systemic overhaul, proposing a unified, AI-enabled framework that redefines how care is delivered, measured, and governed across populations.

Published in the International Journal of Environmental Research and Public Health, the study titled "Reintegrating the Human in Health: A Triadic Blueprint for Whole-Person Care in the Age of AI" outlines a comprehensive model designed to address the structural, operational, and philosophical divides that continue to undermine healthcare systems globally.

Fragmented medicine drives rising costs and poor outcomes

The study identifies fragmentation as the defining weakness of contemporary healthcare, operating at multiple levels simultaneously. Clinically, patients are split across specialties, with each provider addressing isolated symptoms rather than synthesizing a complete picture of health. Informationally, medical records remain scattered across incompatible systems, limiting continuity of care. Financially, reimbursement structures reward volume over prevention, while policy frameworks separate physical health, mental health, and public health into disconnected silos.

This layered fragmentation produces measurable consequences. Patients often undergo duplicate testing, experience delayed diagnoses, and receive conflicting treatment plans. The study highlights how fragmented care contributes to higher mortality rates, increased hospitalizations, and escalating healthcare expenditure, particularly in systems where no single provider is responsible for long-term, integrated care trajectories.

The issue is especially acute in chronic disease management, where conditions such as diabetes, cardiovascular disease, and mental health disorders require coordinated, long-term intervention. Instead, patients frequently navigate a disjointed system where care is episodic and reactive rather than continuous and preventive.

The authors argue that this is not simply a coordination failure but a deeper conceptual problem rooted in how medicine defines illness. By prioritizing measurable biological indicators while sidelining behavioral, social, and environmental factors, the system inherently limits its ability to deliver holistic care.

AI and digital technologies enable a shift to whole-person care

To address these structural shortcomings, the study introduces a three-part framework that integrates clinical philosophy, technological capability, and policy governance into a single operating model.

The first pillar, known as Precision and Personalized Population Health (P3H), reframes healthcare around the individual's full life context. Rather than focusing solely on disease treatment, P3H emphasizes prevention, personalization, and population-level risk management. It requires healthcare systems to account for social determinants such as housing, income, and lifestyle alongside biological data, effectively redefining what constitutes a clinical diagnosis.

The second pillar focuses on general-purpose technologies, particularly artificial intelligence, biosensors, and digital health platforms. These tools enable the continuous collection and integration of multimodal data, including clinical records, wearable device outputs, behavioral patterns, and environmental exposures. By synthesizing this information, AI systems can identify risk patterns, predict disease progression, and support proactive interventions before conditions worsen.

The study points to emerging evidence that such technologies can reduce hospitalizations and mortality when deployed effectively. Continuous monitoring systems, for example, allow clinicians to detect early signs of deterioration in conditions like heart failure, enabling timely intervention and reducing emergency care dependence.

Notably, the authors stress that technology alone cannot solve fragmentation. Without integration into clinical workflows and system-wide coordination, digital tools risk becoming isolated solutions that replicate existing silos rather than eliminating them.

Policy gaps threaten to undermine AI's potential in healthcare

The third pillar of the framework, the AI-WHOLE policy model, addresses what the authors describe as the "missing layer" in healthcare transformation: governance. While many countries have introduced policies to regulate data exchange and AI deployment, these efforts remain fragmented and largely focused on individual tools rather than system-wide outcomes.

The AI-WHOLE framework introduces seven domains: Alignment, Integration, Workflow, Holism, Outcomes, Learning, and Equity. Together, these elements create a policy structure that ensures AI systems are designed, deployed, and evaluated in ways that support whole-person care rather than isolated efficiencies.

For example, the framework requires that AI tools be aligned with clearly defined clinical goals, integrated into care pathways, and evaluated based on patient outcomes rather than technical performance alone. It also mandates continuous monitoring to detect biases and performance drift, ensuring that AI systems remain effective and equitable over time.

The study highlights real-world cases that illustrate both the promise and risks of AI adoption. In one example, ambient AI documentation tools reduced clinician burnout significantly within 30 days of use. However, inconsistencies in patient consent and implementation practices revealed gaps in governance that could undermine trust and accountability if left unaddressed.

These findings underscore the need for policy frameworks that move beyond regulation toward active system design, ensuring that AI contributes to integrated, patient-centered care.

Global South positioned to leapfrog legacy systems

The study places particular stress on the Global South, arguing that countries with less entrenched healthcare infrastructure have a unique opportunity to adopt integrated, AI-enabled systems from the outset. Without the burden of legacy systems, these regions can implement whole-person care models that combine digital infrastructure, community-based care, and policy alignment.

Examples cited include Brazil's Family Health Strategy, which uses multidisciplinary teams and digital tools to deliver coordinated primary care, and Rwanda's national digital health initiatives, which integrate community health workers with mobile technologies to improve access and continuity.

These cases demonstrate that effective healthcare transformation requires alignment across clinical practice, technology, and governance. Where these elements are integrated, systems can achieve measurable improvements in mortality rates, care continuity, and cost efficiency.

The study also highlights cross-sector initiatives such as urban heat action plans and emissions control policies, showing that health outcomes are shaped by factors beyond the healthcare system itself. This reinforces the need for a broader, multi-sector approach to whole-person care that includes environmental, social, and economic interventions.