Machine learning-based multimodal prognostic models integrating pathology images and high-throughput omic data for overall survival prediction in cancer: a systematic review

TL;DR

This systematic review evaluates the use of machine learning models that combine pathology images and omic data for cancer survival prediction, highlighting promising results but also methodological limitations and the need for clinical validation.

Contribution

It provides a comprehensive synthesis of recent multimodal ML approaches for cancer prognosis, emphasizing the current state, challenges, and future directions.

Findings

Multimodal models often outperform unimodal models in survival prediction.

Reported c-indices ranged from 0.550 to 0.857.

All studies showed high or unclear bias and limited external validation.

Abstract

Multimodal machine learning integrating histopathology and molecular data shows promise for cancer prognostication. We systematically reviewed studies combining whole slide images (WSIs) and high-throughput omics to predict overall survival. Searches of EMBASE, PubMed, and Cochrane CENTRAL (12/08/2024), plus citation screening, identified eligible studies. Data extraction used CHARMS; bias was assessed with PROBAST+AI; synthesis followed SWiM and PRISMA 2020. Protocol: PROSPERO (CRD42024594745). Forty-eight studies (all since 2017) across 19 cancer types met criteria; all used The Cancer Genome Atlas. Approaches included regularised Cox regression (n=4), classical ML (n=13), and deep learning (n=31). Reported c-indices ranged 0.550-0.857; multimodal models typically outperformed unimodal ones. However, all studies showed unclear/high bias, limited external validation, and little focus on clinical utility. Multimodal WSI-omics survival prediction is a fast-growing field with promising results but needs improved methodological rigor, broader datasets, and clinical evaluation. Funded by NPIC, Leeds Teaching Hospitals NHS Trust, UK (Project 104687), supported by UKRI Industrial Strategy Challenge Fund.