An AI-Digital Pathology Algorithm Predicts Survival after Radical Prostatectomy from the PLCO Trial.

Abstract

Purpose: Clinical variables alone have limited ability to determine which patients will have recurrence after radical prostatectomy (RP). We evaluated the ability of locked multimodal artificial intelligence (MMAI) algorithms trained on prostate biopsy specimens to predict prostate cancer specific mortality (PCSM) and overall survival (OS) among patients undergoing radical prostatectomy with digitized RP specimens.

Materials and methods: The Prostate, Lung, Colorectal, and Ovarian Cancer Screening Randomized Controlled Trial randomized subjects from 1993-2001 to cancer screening or control. A subset of patients who underwent RP with available digitized histopathological images and subsequent survival data were identified. Distant metastasis (DM) and PCSM MMAIs originally trained on biopsy slides for patients undergoing radiation were evaluated for prediction of PCSM and OS. Cox proportional hazards modeling and Kaplan Meier survival curve analysis were utilized.

Results: 1032 patients who underwent RP with median follow up of 17 years (IQR 14.3, 19.3 years) were identified. MMAI algorithms for PCSM and DM both predicted PCSM (HR 2.31, 95% confidence interval [CI] 1.6-3.35, p<0.001, and HR 1.96, 95% CI 1.35-2.85, p<0.001, respectively). Similarly, DM and PCSM MMAI predicted OS (HR 1.22, 95% CI 1.01-1.47, p=0.04 and HR 1.19, 95% CI 1.02-1.4, p=0.03).

Conclusions: Locked MMAI algorithms previously developed and validated on biopsy specimens from patients undergoing radiation for prostate cancer successfully predicted clinical outcomes when applied to RP specimens from patients treated with surgery. MMAI models and other biomarkers may help select patients who may benefit from post-operative treatment intensification with androgen deprivation therapy or radiation.