Morote Juan, Miró Berta, Hernando Patricia, Paesano Nahuel, Picola Natàlia, Muñoz-Rodriguez Jesús, Ruiz-Plazas Xavier, Muñoz-Rivero Marta V, Celma Ana, García-de Manuel Gemma, Servian Pol, Abascal José M, Trilla Enrique, Méndez Olga
Department of Urology, Vall Hebron University Hospital, 08035 Barcelona, Spain.
Department of Surgery, Universitat Autònoma de Barcelona, 08193 Bellaterra, Spain.
Cancers (Basel). 2025 Mar 25;17(7):1101. doi: 10.3390/cancers17071101.
: This study compares machine learning (ML) and logistic regression (LR) algorithms in developing a predictive model for sPCa using the seven predictive variables from the Barcelona (BCN-MRI) predictive model. : A cohort of 5005 men suspected of having PCa who underwent MRI and targeted and/or systematic biopsies was used for training, testing, and validation. A feedforward neural network (FNN)-based SimpleNet model (GMV) and a logistic regression-based model (BCN) were developed. The models were evaluated for discrimination ability, precision-recall, net benefit, and clinical utility. Both models demonstrated strong predictive performance. : The GMV model achieved an area under the curve of 0.88 in training and 0.85 in test cohorts (95% CI: 0.83-0.90), while the BCN model reached 0.85 and 0.84 (95% CI: 0.82-0.87), respectively ( > 0.05). The GMV model exhibited higher recall, making it more suitable for clinical scenarios prioritizing sensitivity, whereas the BCN model demonstrated higher precision and specificity, optimizing the reduction of unnecessary biopsies. Both models provided similar clinical benefit over biopsying all men, reducing unnecessary procedures by 27.5-29% and 27-27.5% of prostate biopsies at 95% sensitivity, respectively ( > 0.05). : Our findings suggest that both ML and LR models offer high accuracy in sPCa detection, with ML exhibiting superior recall and LR optimizing specificity. These results highlight the need for model selection based on clinical priorities.
本研究比较了机器学习（ML）算法和逻辑回归（LR）算法，利用巴塞罗那（BCN-MRI）预测模型中的七个预测变量，开发用于预测前列腺癌（sPCa）的模型。选取了5005名疑似患有前列腺癌且接受了MRI检查以及靶向和/或系统活检的男性队列用于训练、测试和验证。开发了基于前馈神经网络（FNN）的SimpleNet模型（GMV）和基于逻辑回归的模型（BCN）。对这些模型的判别能力、精确召回率、净效益和临床实用性进行了评估。两个模型均表现出强大的预测性能。GMV模型在训练队列中的曲线下面积为0.88，在测试队列中为0.85（95%置信区间：0.83 - 0.90），而BCN模型分别达到0.85和0.84（95%置信区间：0.82 - 0.87）（P>0.05）。GMV模型表现出更高的召回率，使其更适合优先考虑敏感性的临床场景，而BCN模型表现出更高的精确率和特异性，优化了不必要活检的减少。在95%敏感性时，与对所有男性进行活检相比，两个模型均提供了相似的临床效益，分别减少了27.5 - 29%和27 - 27.5%的前列腺活检不必要操作（P>0.05）。我们的研究结果表明，ML和LR模型在sPCa检测中均具有较高的准确性，ML表现出更高的召回率，而LR优化了特异性。这些结果凸显了根据临床优先级进行模型选择的必要性。
