PD27-09 A PRECISE PERSONALIZED INTELLIGENT KNOWLEDGE PLATFORM FOR ASSISTING CLINICAL PRACTICE OF ROBOTIC SURGERY FOR PROSTATE CANCER

Abstract

You have accessJournal of UrologySurgical Technology & Simulation: Artificial Intelligence II (PD27)1 May 2024PD27-09 A PRECISE PERSONALIZED INTELLIGENT KNOWLEDGE PLATFORM FOR ASSISTING CLINICAL PRACTICE OF ROBOTIC SURGERY FOR PROSTATE CANCER Jiakun Li, Bairong Shen, and Qiang Wei Jiakun LiJiakun Li , Bairong ShenBairong Shen , and Qiang WeiQiang Wei View All Author Informationhttps://doi.org/10.1097/01.JU.0001008580.58088.27.09AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract INTRODUCTION AND OBJECTIVE: Robot-Assisted Radical Prostatectomy (RARP) has emerged as a pivotal surgical intervention for treating prostate cancer. However, the complexity of clinical cases, the heterogeneity of prostate cancer, and limitations in physician expertise pose challenges to rational decision-making in RARP. To address these challenges, we organized knowledge of previously complex cohorts and established a online platform named RARP Knowledge Base (RARPKB), aiming to providing reference evidence for personalized treatment plan. METHODS: PubMed searches were conducted to identify publications describing RARP in the past two decades. We collected, classified, and structured the surgical details, patients information, surgical data, and various statistical results from the literature. A Knowledge-guide Decision Support Tool was established using tools such as MySQL, DataTable, ECharts and JavaScript. ChatGPT-4 and two different assessment scales were used for the validation and comparison of the platform. RESULTS: The platform composes 583 studies, 1589 cohorts, 1,911,968 patients, and 11,986 records, resulting in 54,834 data entries. The knowledge-guide decision support tool can provide personalized surgical plan recommendations and potential complications based on inputting the patient's baseline and surgical information. Compared to ChatGPT-4, RARPKB outperformed in authenticity (100% vs. 73%), matching (100% vs. 53%), personalized recommendations (100% vs. 20%), matching of patients (100% vs. 0%), and personalized recommendations for complications (100% vs. 20%). Post-use, the average System Usability Scale score was 88.88±15.03, and the Net Promoter Score of RARPKB was 85. CONCLUSIONS: We have introduced the pioneering RARPKB, which is the first knowledge base for robot-assisted surgery, with an emphasis on prostate cancer. RARPKB assisted in personalized and complex surgical planning for prostate cancer to improve efficacy. RARPKB provided a reference for the future application of artificial intelligence in clinical practice. Download PPT Source of Funding: This work was supported by "The Fundamental Research Funds for the Central Universities." (No. 2023SCU12057), National Natural Science Foundation of China (Grant No. 32070671 and 32270690) and the regional innovation cooperation between Sichuan and Guangxi provinces (Project No. 2020YFQ0019) © 2024 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 211Issue 5SMay 2024Page: e554 Advertisement Copyright & Permissions© 2024 by American Urological Association Education and Research, Inc.Metrics Author Information Jiakun Li More articles by this author Bairong Shen More articles by this author Qiang Wei More articles by this author Expand All Advertisement PDF downloadLoading ...

Ähnliche Arbeiten