Context-aware deep learning using individualized prior information reduces false positives in disease risk prediction and longitudinal health assessment

2025-10-17

AI Summary

This study addresses the high false-positive rate (FPR) and poor predictive accuracy—particularly in sparse-visit scenarios—of longitudinal health assessments. We propose a context-aware deep learning framework incorporating individualized priors, which, for the first time, enables dynamic fusion of multi-temporal, heterogeneous medical data—including medical images and clinical biomarkers—by explicitly modeling patient-specific longitudinal trajectories to enhance temporal contextual understanding. In prostate cancer risk prediction, using at most three prior imaging studies alone reduces the FPR from 51% to 33%; integrating clinical data further lowers it to 24%. For five-year risk prediction, the FPR drops significantly from 64% to 9%. Concurrently, both sensitivity and specificity improve. The method thus provides a scalable, high-accuracy, low-FPR technical pathway for long-term population-level health monitoring.

Technology Category

• Machine Learning: Life-Long and Continual Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Multi-modal Vision

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Studies of user behavior, including longitudinal effects of personalized systems
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Temporal context in medicine is valuable in assessing key changes in patient health over time. We developed a machine learning framework to integrate diverse context from prior visits to improve health monitoring, especially when prior visits are limited and their frequency is variable. Our model first estimates initial risk of disease using medical data from the most recent patient visit, then refines this assessment using information digested from previously collected imaging and/or clinical biomarkers. We applied our framework to prostate cancer (PCa) risk prediction using data from a large population (28,342 patients, 39,013 magnetic resonance imaging scans, 68,931 blood tests) collected over nearly a decade. For predictions of the risk of clinically significant PCa at the time of the visit, integrating prior context directly converted false positives to true negatives, increasing overall specificity while preserving high sensitivity. False positive rates were reduced progressively from 51% to 33% when integrating information from up to three prior imaging examinations, as compared to using data from a single visit, and were further reduced to 24% when also including additional context from prior clinical data. For predicting the risk of PCa within five years of the visit, incorporating prior context reduced false positive rates still further (64% to 9%). Our findings show that information collected over time provides relevant context to enhance the specificity of medical risk prediction. For a wide range of progressive conditions, sufficient reduction of false positive rates using context could offer a pathway to expand longitudinal health monitoring programs to large populations with comparatively low baseline risk of disease, leading to earlier detection and improved health outcomes.

Problem

• Reduces false positives in disease risk prediction using prior patient data
• Integrates temporal context from limited prior visits for health monitoring
• Improves specificity in prostate cancer risk assessment while maintaining sensitivity

Innovation

• Integrates prior visit data for health monitoring
• Refines risk using historical imaging and biomarkers
• Reduces false positives by incorporating temporal context