Explainable artificial intelligence reveals key surgical parameters in robot

Preoperative risk stratification for radical prostatectomy is crucial, yet predicting the wide range of postoperative outcomes remains a significant challenge. While machine learning (ML) shows promise, “black box” models limit clinical translatability. This study aimed to predict postoperative parameters using ML and employ explainable AI (XAI) to identify their key clinical drivers. In a retrospective study of 326 patients (224 robot-assisted [RARP], 102 open [ORP]), we developed predictive models for twelve outcomes, including length of stay and pathological ISUP grade. Four ML algorithms (Random Forest, Gradient Boosting, SVM, Neural Network) were evaluated via nested 5-fold cross-validation. A custom permutation-based Shapley sampling framework SHAP (SHapley Additive exPlanations) was applied to the best-performing models to quantify the predictive importance of preoperative features. ML models outperformed baseline heuristics for a subset of the prespecified outcomes, with strongest performance for postoperative hemoglobin (R2 up to 0.57) and the decision to perform frozen sections (AUC up to 0.89). Not all outcomes proved equally amenable to prediction, consistent with the heterogeneous nature of postoperative recovery. SHAP analysis revealed a clear dichotomy: procedural parameters, such as catheter dwell time and hospital stay, were almost exclusively predicted by the surgical approach (RARP vs. ORP). In contrast, pathological outcomes like ISUP grade were predominantly driven by preoperative tumor characteristics. Preoperative hemoglobin was identified as a strong predictive feature for postoperative anemia within this dataset, ranking above non-modifiable factors such as age. Explainable AI can deconstruct the complex interplay of factors influencing surgical success, providing a data-driven basis for hypothesis generation and clinical pathway optimization. As a single-centre proof-of-concept study without external validation, these findings require prospective confirmation in independent multi-centre cohorts before clinical translation can be considered.

American Society of Anesthesiologists Physical Status Classification System

High-intensity focused ultrasound

International consultation on incontinence questionnaire

International index of erectile function

International prostate symptom score

International Society of Urological Pathology Score

Robot-assisted radical prostatectomy

C.K. thanks P.H. for collecting and providing the urological data set and E.T. for calculating the machine learning results and Shapley values.

Open Access funding enabled and organized by Projekt DEAL. E.T. received funding by the German Federal Ministry of Education and Research within the project “BNTrAinee” under grant number 16DHBK1022. C.K. was supported by the German Federal Ministry of Education and Research under grant number 01KD25024.

Clinic of Internal Medicine III, Department of Oncology, Hematology, Immune-Oncology and Rheumatology, University Hospital Bonn, Bonn, Germany

Christian R. Klein & Peter Brossart

Department of Visual Computing, Institute for Computer Science, University of Bonn, Bonn, Germany

Department of Urology, University Hospital Bonn, Bonn, Germany

Pia Heuser, Manuel Ritter & Philipp Krausewitz

Institute of Pathology, University Hospital Bonn, Bonn, Germany

Center for Integrated Oncology Aachen Bonn Cologne Duesseldorf (CIO ABCD), Bonn, Germany

Christian R. Klein, Pia Heuser, Glen Kristiansen, Peter Brossart, Manuel Ritter & Philipp Krausewitz

Search author on:PubMed Google Scholar

Correspondence to Christian R. Klein.

The authors declare that they have no competing interests.

The study was conducted in accordance with the Declaration of Helsinki and was approved by the Ethics Committee of the Medical Faculty of the University of Bonn (identification number: 477/20). The need for written informed consent was waived by the ethics committee due to the retrospective nature of the analysis of anonymized routine clinical data. All data were anonymised in accordance with EU Regulation 2016/679 (General Data Protection Regulation).

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Below is the link to the electronic supplementary material.

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.

Klein, C.R., Heuser, P., Trunz, E. et al. Explainable artificial intelligence reveals key surgical parameters in robot-assisted and open radical prostatectomy. Sci Rep (2026). https://doi.org/10.1038/s41598-026-68074-9

DOI: https://doi.org/10.1038/s41598-026-68074-9