PMDF: Preference-based Multimodal Deep Forest for Overall Survival Prediction in Gastric Cancer

Overall survival (OS) analysis has a significant role in clinical treatment and prognosis. A singular data source’s samples may be biased, leading to low generalisable models. Multi-source data, however, may suffer from the problem of missing modalities due to different equipment and regional disparity. To address this issue, we propose a OS prediction model for gastric cancer called preference-based multimodal deep forest (PMDF). Simulating the diagnostic process of a physician, the initial input contains only basic modalities instead of complete data. Subsequently, PMDF learns from the doctor’s expertise and calculates the required supplementary examinations for each patient with these basic modalities. Finally, additional modalities are fused based on the cascade forest architecture. The efficiency of the proposed model is verified on the publicly accessible SEER database, and its applicability in clinical settings is assessed.