A novel methodology for predictive modeling of patient outcomes using multi-modal transformer networks and SHAP models

Vollständiger Abstract

Worum geht es in dieser Arbeit?

Abstract Precision medicine requires predictive models that can exploit genomic, clinical, imaging and continuously monitored physiological data at the same time, yet most existing models operate on a single modality and behave as black boxes. This paper proposes the Integrated Multi-Modal Contextual Network (IMCN), a predictive modelling framework that combines multi-modal transformer networks for cross-modal fusion, recurrent neural networks with attention for real-time sequential signals, pre-trained autoencoder networks for dimensionality reduction of high-dimensional genomic data, and a context-aware multi-task learning network for personalised risk and treatment predictions. SHapley Additive exPlanations (SHAP) are integrated to provide global and local feature attributions, so that clinicians can see which genomic markers, clinical variables and contextual factors drive each prediction. Across breast, lung, colorectal, cardiovascular, diabetic and chronic kidney disease cohorts derived from The Cancer Genome Atlas, the framework reports higher AUC, precision, sensitivity, recall and F1-score than the literature-reported benchmarks used for comparison, together with a reduction in false positives. Limitations, including the use of simulated physiological monitoring signals and the absence of independently re-implemented baselines, are stated explicitly.