Explainable artificial intelligence to predict the risk of side-specific extraprostatic extension in pre-prostatectomy patients

• Published in: Canadian Urological Association journal Vol. 16; no. 6; pp. 213 - 221
• Main Authors: Kwong, Jethro C C, Khondker, Adree, Tran, Christopher, Evans, Emily, Cozma, Adrian I, Javidan, Ashkan, Ali, Amna, Jamal, Munir, Short, Thomas, Papanikolaou, Frank, Srigley, John R, Fine, Benjamin, Feifer, Andrew
• Format: Journal Article
• Language: English
• Published: Canada Canadian Urological Association 01.06.2022; Canadian Medical Association
• Subjects: Machine learning; Original Research; Patient outcomes; Preoperative care; Prognosis; Prostatectomy; Technology application; Canada
• ISSN: 1911-6470; 1920-1214
• DOI: 10.5489/cuaj.7473

We aimed to develop an explainable machine learning (ML) model to predict side-specific extraprostatic extension (ssEPE) to identify patients who can safely undergo nerve-sparing radical prostatectomy using preoperative clinicopathological variables. A retrospective sample of clinicopathological data from 900 prostatic lobes at our institution was used as the training cohort. Primary outcome was the presence of ssEPE. The baseline model for comparison had the highest performance out of current biopsy-derived predictive models for ssEPE. A separate logistic regression (LR) model was built using the same variables as the ML model. All models were externally validated using a testing cohort of 122 lobes from another institution. Models were assessed by area under receiver-operating-characteristic curve (AUROC), precision-recall curve (AUPRC), calibration, and decision curve analysis. Model predictions were explained using SHapley Additive exPlanations. This tool was deployed as a publicly available web application. Incidence of ssEPE in the training and testing cohorts were 30.7 and 41.8%, respectively. The ML model achieved AUROC 0.81 (LR 0.78, baseline 0.74) and AUPRC 0.69 (LR 0.64, baseline 0.59) on the training cohort. On the testing cohort, the ML model achieved AUROC 0.81 (LR 0.76, baseline 0.75) and AUPRC 0.78 (LR 0.75, baseline 0.70). The ML model was explainable, well-calibrated, and achieved the highest net benefit for clinically relevant cutoffs of 10-30%. We developed a user-friendly application that enables physicians without prior ML experience to assess ssEPE risk and understand factors driving these predictions to aid surgical planning and patient counselling (https://share.streamlit.io/jcckwong/ssepe/main/ssEPE_V2.py).