EUVIMEDEUVIMED entdecken
Beobachtungsstudie

Development of Machine Learning Algorithm to Predict the Risk of Incontinence After Robot-Assisted Radical Prostatectomy

Entwicklung eines Machine-Learning-Algorithmus zur Vorhersage des Inkontinenzrisikos nach roboterassistierter radikaler Prostatektomie

Daniele Amparore, Sabrina De Cillis, Eugenio Alladio, Michele Sica, Federico Piramide, Paolo Verri iD, Enrico Checcucci, Alberto Piana, Alberto Quarà, Edoardo Cisero, Matteo Manfredi, Michele Di Dio und 2 weitere

Journal of Endourology · 2024-08 · 38 (8) · 871-878

DOI: 10.1089/end.2024.0057 ↗

Auf einen Blick

Eine prospektive Beobachtungsstudie mit 227 Patient:innen entwickelte ein Machine-Learning-Modell zur Vorhersage von Inkontinenz nach RARP. XGBoost war dafür das wirksamste Modell.

Fragestellung

Lässt sich das Risiko einer postoperativen Inkontinenz nach roboterassistierter radikaler Prostatektomie mit Machine Learning vorhersagen?

Methode

Prospektive Beobachtungsstudie bei Patient:innen mit lokalisiertem Prostatakarzinom unter RARP zwischen April 2022 und Januar 2023; Vergleich von XGBoost, Random Forest und logistischer Regression; SHAP-Analyse.

Ergebnisse

227 Patient:innen. Kontinenzraten nach Katheterentfernung: 74,2 % nach 7 Tagen, 80,7 % nach 13 Tagen und 91,4 % nach 90 Tagen. XGBoost war das effektivste Modell; wichtige Variablen waren Nerverhalt, Alter, DRE und Gesamt-PSA.

Schlussfolgerung der Autor:innen

Die Vorhersage postoperativer Inkontinenz ist für eine angepasste Rehabilitation nach RARP wichtig. XGBoost kann die für die Kontinenz relevanten Variablen effektiv identifizieren und ein KI-gestütztes Modell unterstützen.

Kernaussagen

  • 227 Patient:innen nach RARP wurden in das Modell einbezogen.
  • XGBoost war das effektivste Vorhersagemodell.
  • Wichtige Variablen: Nerverhalt, Alter, DRE und Gesamt-PSA.

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

Kurz gefasst

Beobachtungsstudie in der Zeitschrift Journal of Endourology, online erschienen am 01.08.2024. Verfasst von Daniele Amparore und 13 weiteren Autor:innen. Beteiligte Einrichtung: Division of Urology, Department of Oncology, San Luigi Gonzaga Hospital, University of Turin, Turin, Italy. Hauptthemen laut MEDLINE: Postoperative Complications, Prostatectomy, Robotic Surgical Procedures, Urinary Incontinence. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 30 Literaturangaben.

Auf einen BlickAbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Predicting postoperative incontinence beforehand is crucial for intensified and personalized rehabilitation after robot-assisted radical prostatectomy. Although nomograms exist, their retrospective limitations highlight artificial intelligence (AI)'s potential. This study seeks to develop a machine learning algorithm using robot-assisted radical prostatectomy (RARP) data to predict postoperative incontinence, advancing personalized care. Materials and Methods: In this propsective observational study, patients with localized prostate cancer undergoing RARP between April 2022 and January 2023 were assessed. Preoperative variables included age, body mass index, prostate-specific antigen (PSA) levels, digital rectal examination (DRE) results, Gleason score, International Society of Urological Pathology grade, and continence and potency questionnaires responses. Intraoperative factors, postoperative outcomes, and pathological variables were recorded. Urinary continence was evaluated using the Expanded Prostate cancer Index Composite questionnaire, and machine learning models (XGBoost, Random Forest, Logistic Regression) were explored to predict incontinence risk. The chosen model's SHAP values elucidated variables impacting predictions.

Results

A dataset of 227 patients undergoing RARP was considered for the study. Post-RARP complications were predominantly low grade, and urinary continence rates were 74.2%, 80.7%, and 91.4% at 7, 13, and 90 days after catheter removal, respectively. Employing machine learning, XGBoost proved the most effective in predicting postoperative incontinence risk. Significant variables identified by the algorithm included nerve-sparing approach, age, DRE, and total PSA. The model's threshold of 0.67 categorized patients into high or low risk, offering personalized predictions about the risk of incontinence after surgery.

Conclusions

Predicting postoperative incontinence is crucial for tailoring rehabilitation after RARP. Machine learning algorithm, particularly XGBoost, can effectively identify those variables more heavily, impacting the outcome of postoperative continence, allowing to build an AI-driven model addressing the current challenges in post-RARP rehabilitation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Postoperative ComplicationsProstatectomyRobotic Surgical ProceduresUrinary IncontinenceMachine LearningAgedHumansMaleMiddle AgedProstatic NeoplasmsRetrospective StudiesRisk AssessmentRisk Factors

Stichwörter der Autor:innen

artificial intelligencecontinencedeep learningradical prostatectomyrehabilitationsurgical recovery

Autor:innen und Institutionen

  • Division of Urology, Department of Oncology, San Luigi Gonzaga Hospital, University of Turin, Turin, Italy.
  • Department of Chemistry, University of Turin, Turin, Italy.
  • Centro Regionale Antidoping "A. Bertinaria" of Orbassano (Turin), Turin, Italy.
  • Department of Surgery, Candiolo Cancer Institute, FPO-IRCCS, Turin, Italy.
  • Division of Urology, Department of Surgery, SS Annunziata Hospital, Cosenza, Italy.

ORCID-Profile: Paolo Verri

Zitieren

APA

Amparore, D., De Cillis, S., Alladio, E., Sica, M., Piramide, F., Verri, P., Checcucci, E., Piana, A., Quarà, A., Cisero, E., Manfredi, M., Di Dio, M., Fiori, C., & Porpiglia, F. (2024). Development of Machine Learning Algorithm to Predict the Risk of Incontinence After Robot-Assisted Radical Prostatectomy. Journal of Endourology, 38(8), 871-878. https://doi.org/10.1089/end.2024.0057

Vancouver

Amparore D, De Cillis S, Alladio E, Sica M, Piramide F, Verri P, et al. Development of Machine Learning Algorithm to Predict the Risk of Incontinence After Robot-Assisted Radical Prostatectomy. Journal of Endourology. 2024;38(8):871-878. doi:10.1089/end.2024.0057

BibTeX
@article{Amparore2024,
  author = {Amparore, Daniele and De Cillis, Sabrina and Alladio, Eugenio and Sica, Michele and Piramide, Federico and Verri, Paolo and Checcucci, Enrico and Piana, Alberto and Quarà, Alberto and Cisero, Edoardo and Manfredi, Matteo and Di Dio, Michele and Fiori, Cristian and Porpiglia, Francesco},
  title = {Development of Machine Learning Algorithm to Predict the Risk of Incontinence After Robot-Assisted Radical Prostatectomy},
  journal = {Journal of Endourology},
  year = {2024},
  volume = {38},
  number = {8},
  pages = {871--878},
  doi = {10.1089/end.2024.0057}
}
Kostenlos starten →