Predicting health and disease: a conceptual framework for AI in preventive and precision medicine

Clinical Snapshot

Key Findings

• P Value: Not reported

• Effect Size: Not applicable — no empirical data presented

• Primary Outcome: Proposal of a conceptual framework integrating AI and multimodal biomedical datasets for pre-symptomatic disease prediction and preventive precision medicine

• Nnt Or Sensitivity: Not applicable — no clinical performance metrics, sensitivity, specificity, NNT, or hazard ratios are reported; the framework is entirely conceptual

• Confidence Interval: Not reported — conceptual article with no quantitative analysis

Clinical Application

Feasibility of the proposed framework in routine clinical practice is currently low. The article itself acknowledges significant remaining challenges in computational systems, real-world clinical validation, and preventive intervention delivery. Implementation would require substantial investment in data infrastructure, interoperability standards, regulatory approval of predictive tools, clinical workflow redesign, and clinician training. No implementation roadmap with timelines or resource requirements is provided. In the Australian context, the framework has conceptual relevance to several national health priorities including the Australian Government's National Preventive Health Strategy 2021–2030 and the Australian Digital Health Agency's National Digital Health Strategy. However, significant barriers exist: the Therapeutic Goods Administration (TGA) regulates AI-based Software as a Medical Device (SaMD) under the Digital Health regulatory framework, and any AI predictive tool entering clinical use would require TGA conformity assessment. The Pharmaceutical Benefits Scheme (PBS) does not currently fund AI-guided preventive interventions, and Medicare Benefits Schedule (MBS) items for AI-assisted diagnostics remain limited. The RACGP Standards for General Practice emphasise evidence-based preventive care, and GPs would require robust clinical validation data — not currently provided by this framework — before adopting AI-driven pre-symptomatic screening. Australia's My Health Record system provides a potential data infrastructure foundation, but privacy legislation under the Privacy Act 1988 and the Australian Privacy Principles would impose significant constraints on the multimodal data integration the framework envisions. Indigenous health equity considerations are entirely absent from the framework and would be essential for any Australian implementation. Potentially applicable to adult populations at risk of chronic disease in high-resource healthcare settings with established digital health infrastructure. The framework is most relevant to health systems with access to large-scale multimodal biomedical data including genomics, proteomics, wearable sensor data, and electronic health records. Direct applicability to individual patient care is not established.

Abstract

The conventional medical approach of treating symptoms as they appear with restricted screening often limits intervention to slowing disease progression rather than fully reversing it. A new approach leveraging artificial intelligence (AI) and computational technologies across expanding multimodal biomedical datasets holds the promise to enable predicting actionable future changes in health before symptom onset. This article presents a conceptual framework for a preventive paradigm in precision medicine and healthcare, integrating recent advancements in AI and biomedical datasets. Key remaining challenges facing computational systems, real-world clinical validation and implementation, and preventive interventions together with recommendations and prioritised future directions are highlighted. Such an approach could pave the way for more proactive and preventive medical interventions to effectively address the growing burden of chronic disease.

References

1. 1.Barmada, A. (2026). Predicting health and disease: a conceptual framework for AI in preventive and precision medicine. BMJ Health & Care Informatics. https://doi.org/10.1136/bmjhci-2025-101798