Machine learning algorithms can more efficiently predict biochemical recurrence after robot‐assisted radical prostatectomy

Abstract

Objectives: To develop a model for predicting biochemical recurrence (BCR) in patients with long follow-up periods using clinical parameters and the machine learning (ML) methods.Materials Method: Patients who underwent robot-assisted radical prostatectomy between January 2014 and December 2019 were retrospectively reviewed. Patients who did not have BCR were assigned to Group 1, while those diagnosed with BCR were assigned to Group 2. The patient's demographic data, preoperative and postoperative parameters were all recorded in the database. Three different ML algorithms were employed: random forest, K-nearest neighbour, and logistic regression.Results: Three hundred and sixty-eight patients were included in this study. Among these patients, 295 (80.1%) did not have BCR (Group 1), while 73 (19.8%) had BCR (Group 2). The mean duration of follow-up and duration until the diagnosis of BCR was calculated as 35.2 ± 16.7 and 11.5 ± 11.3 months, respectively. The multivariate analysis revealed that NLR, PSAd, risk classification, PIRADS score, T stage, presence or absence of positive surgical margin, and seminal vesicle invasion were predictive for BCR. Classic Cox regression analysis had an area under the curve (AUC) of 0.915 with a sensitivity and specificity of 90.6% and 79.8%. The AUCs for receiver-operating characteristic curves for random forest, K nearest neighbour, and logistic regression were 0.95, 0.93, and 0.93, respectively. All ML models outperformed the conventional statistical regression model in the prediction of BCR after prostatectomy. Conclusion:The construction of more reliable and potent models will provide the clinicians and patients with advantages such as more accurate risk classification, prognosis estimation, early intervention, avoidance of unnecessary treatments, relatively lower morbidity and mortality. The ML methods are cheap, and their powers increase with increasing data input; we believe that their clinical use will increase over time.

Factors predicting biochemical recurrence following robot-assisted radical prostatectomy: single-center experience

“…Another study on BCR showed that GS detected in the specimen and the pathological stage was closely related to BCR (25). Similarly, Tağcı et al reported a relationship between LNI and early BCR (26) another study by Ekşi et al, risk classification, mpMRI findings, PSM, SVI, and T stage were noted as significant parameters predicting BCR (11). In our study, the multivariate analysis revealed PSA, risk classification, specimen GS, PSM, SVI, and T stage to be the predictive parameters of BCR.…”

“…In our study, the multivariate analysis revealed PSA, risk classification, specimen GS, PSM, SVI, and T stage to be the predictive parameters of BCR. In addition to the nomograms established for this purpose, more advanced algorithms can be created by integrating artificial intelligence and machine learning methods into hospital information systems (5,11). We consider that as the external validation of such created models is undertaken and current knowledge increases, there will be more common and widely accepted models that can predict BCR.…”

“…Many studies have been conducted, and models such as CAPRA score and Kattan nomograms have been established based on data obtained from large series to predict BCR (3,(8)(9)(10)(11). The search for more predictive models has increasingly continued with the multiparametric magnetic resonance imaging (mp-MRI) technique and better identification of lesions, coupled with developments in nuclear medicine (9,10) .…”

Machine-learning predicts time-series prognosis factors in metastatic prostate cancer patients treated with androgen deprivation therapy

“…Developments in computer technology have improved analytical methods for handling large-scale data, and machine learning has attracted attention also in the medical eld. Machine-learning techniques are commonly used for data-driven diagnostic and prognostic predictions (9,10) . The greatest advantage of using machine learning is that it can be used to account for the combined, nonlinear effects of numerous variables and can make precise individualized predictions for heterogeneous patient populations.…”

Machine-learning predicts time-series prognosis factors in metastatic prostate cancer patients treated with androgen deprivation therapy

“…Developments in computer technology have improved analytical methods for handling large-scale data, and machine learning has attracted attention also in the medical field. Machine-learning techniques are commonly used for data-driven diagnostic and prognostic predictions 9 , 10 . The greatest advantage of using machine learning is that it can be used to account for the combined, nonlinear effects of numerous variables and can make precise individualized predictions for heterogeneous patient populations.…”