{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T03:52:52Z","timestamp":1784605972619,"version":"3.55.0"},"reference-count":21,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Perioper Med"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Traditional statistical models often fail to capture the complex dynamics influencing survival outcomes in patients with bladder cancer after radical cystectomy, a procedure where approximately 50% of patients develop metastases within 2 years. The integration of artificial intelligence (AI) offers a promising avenue for enhancing prognostic accuracy and personalizing treatment strategies.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study aimed to develop and evaluate a machine learning algorithm for predicting disease-free survival (DFS), overall survival (OS), and the cause of death in patients with bladder cancer undergoing cystectomy, using a comprehensive dataset of clinical and pathological variables.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n \n Retrospective data of 370 patients with bladder cancer who underwent radical cystectomy at Fondazione Policlinico Universitario Agostino Gemelli IRCCS, Rome, Italy, were collected. The dataset comprised 20 input variables, encompassing demographics, tumor characteristics, treatment variables, and inflammatory markers. For specific analyses and models, we used patient subcohorts. The CatBoost algorithm was used for regression tasks (DFS in 346 patients, OS in 347 patients) and a binary classification task (tumor-related death in 312 patients). Model performance was assessed using mean absolute error (MAE) for regression and\n F<\/jats:italic>\n 1<\/jats:sub>\n -score for classification, prioritizing a minimum recall of 75% for tumor-related deaths. Five-fold cross-validation and Shapley additive explanations (SHAP) values were used to ensure robustness and interpretability.\n <\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n For DFS prediction, the CatBoost model achieved an MAE of 18.68 months, with clinical tumor stage and pathological tumor classification identified as the most influential predictors. OS prediction yielded an MAE of 17.2 months, which improved to 14.6 months after feature filtering, where tumor classification and the systemic immune-inflammation index (SII) were most impactful. For tumor-related death classification, the model achieved a recall of 78.6% and an\n F<\/jats:italic>\n 1<\/jats:sub>\n -score of 0.44 for the positive class (tumor-related deaths), correctly identifying 11 of 14 cases. Bladder tumor position was the most influential feature for cause-of-death prediction.\n <\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n The developed machine learning algorithm demonstrates promising accuracy in predicting survival and the cause of death in patients with bladder cancer after cystectomy. The key predictors include clinical and pathological tumor staging, systemic inflammation (SII), and bladder tumor position. These findings highlight the potential of AI in providing clinicians with an objective, data-driven tool to improve personalized prognostic assessment and guide clinical decision-making.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/86666","type":"journal-article","created":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T20:52:40Z","timestamp":1771534360000},"page":"e86666-e86666","source":"Crossref","is-referenced-by-count":2,"title":["Survival Prediction in Patients With Bladder Cancer Undergoing Radical Cystectomy Using a Machine Learning Algorithm: Retrospective Single-Center Study"],"prefix":"10.2196","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6545-3196","authenticated-orcid":false,"given":"Francesco Andrea","family":"Causio","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7857-5819","authenticated-orcid":false,"given":"Vittorio","family":"De Vita","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4246-7616","authenticated-orcid":false,"given":"Andrea","family":"Nappi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4700-7356","authenticated-orcid":false,"given":"Melissa","family":"Sawaya","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9135-0035","authenticated-orcid":false,"given":"Bernardo","family":"Rocco","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0464-0788","authenticated-orcid":false,"given":"Nazario","family":"Foschi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3909-6842","authenticated-orcid":false,"given":"Giuseppe","family":"Maioriello","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7789-9486","authenticated-orcid":false,"given":"Pierluigi","family":"Russo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,2,19]]},"reference":[{"issue":"6","key":"R1","doi-asserted-by":"publisher","first-page":"596","DOI":"10.1016\/s0302-2838(03)00133-7","article-title":"Artificial neural networks for decision-making in urologic oncology","volume":"43","author":"Anagnostou","journal-title":"Eur Urol"},{"issue":"2","key":"R2","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1053\/suro.2002.32492","article-title":"Artificial neural networks for diagnosis and prognosis in prostate cancer","volume":"20","author":"Schwarzer","journal-title":"Semin Urol Oncol"},{"issue":"8 Suppl","key":"R3","doi-asserted-by":"publisher","first-page":"1636","DOI":"10.1002\/1097-0142(20010415)91:8+<1636::aid-cncr1176>3.0.co;2-d","article-title":"Comparison of artificial neural networks with other statistical approaches: results from medical data sets","volume":"91","author":"Sargent","journal-title":"Cancer"},{"issue":"1","key":"R4","doi-asserted-by":"publisher","DOI":"10.1186\/s40779-024-00569-w","article-title":"Global burden of benign prostatic hyperplasia, urinary tract infections, urolithiasis, bladder cancer, kidney cancer, and prostate cancer from 1990 to 2021","volume":"11","author":"Zi","journal-title":"Mil Med Res"},{"issue":"4 Pt 1","key":"R5","doi-asserted-by":"publisher","first-page":"1150","DOI":"10.1016\/j.juro.2007.05.122","article-title":"Application of artificial intelligence to the management of urological cancer","volume":"178","author":"Abbod","journal-title":"J Urol"},{"issue":"6","key":"R6","doi-asserted-by":"publisher","DOI":"10.3390\/biomedicines12061220","article-title":"Artificial intelligence in pediatric emergency medicine: applications, challenges, and future perspectives","volume":"12","author":"Di Sarno","journal-title":"Biomedicines"},{"issue":"10","key":"R7","doi-asserted-by":"publisher","DOI":"10.3390\/jpm14101043","article-title":"Machine learning approaches for the prediction of postoperative major complications in patients undergoing surgery for bowel obstruction","volume":"14","author":"Mazzotta","journal-title":"J Pers Med"},{"issue":"3","key":"R8","doi-asserted-by":"publisher","first-page":"240","DOI":"10.4111\/icu.20230302","article-title":"Inflammation indexes and machine-learning algorithm in predicting urethroplasty success","volume":"65","author":"Tokuc","journal-title":"Investig Clin Urol"},{"issue":"6","key":"R9","doi-asserted-by":"publisher","first-page":"708","DOI":"10.1634\/theoncologist.2015-0440","article-title":"Neoadjuvant chemotherapy for muscle-invasive bladder cancer: a systematic review and two-step meta-analysis","volume":"21","author":"Yin","journal-title":"Oncologist"},{"key":"R10","unstructured":"Bladder cancer CatBoost analysis. Figshare. URL: https:\/\/figshare.com\/s\/ec2419a33ad7ad05f412 [Accessed 03-01-2026]"},{"issue":"11","key":"R11","doi-asserted-by":"publisher","first-page":"2283","DOI":"10.1002\/ijc.34463","article-title":"Age-related differences in cancer relative survival in the United States: a SEER-18 analysis","volume":"152","author":"Withrow","journal-title":"Int J Cancer"},{"key":"R12","doi-asserted-by":"publisher","DOI":"10.1016\/j.euros.2025.05.012","article-title":"Preoperative risk factors for failure after fixed sling implantation for postprostatectomy stress urinary incontinence (FORESEE): a systematic review and meta-analysis","volume":"77","author":"Sacco","journal-title":"Eur Urol Open Sci"},{"issue":"6","key":"R13","doi-asserted-by":"publisher","first-page":"1437","DOI":"10.1007\/s00345-019-02936-y","article-title":"Prognostic value of T1 substaging on oncological outcomes in patients with non-muscle-invasive bladder urothelial carcinoma: a systematic literature review and meta-analysis","volume":"38","author":"Kardoust Parizi","journal-title":"World J Urol"},{"issue":"7","key":"R14","doi-asserted-by":"publisher","first-page":"3895","DOI":"10.1007\/s10238-023-01035-y","article-title":"Systemic immune-inflammation index predicts prognosis and responsiveness to immunotherapy in cancer patients: a systematic review and meta\u2011analysis","volume":"23","author":"Kou","journal-title":"Clin Exp Med"},{"issue":"5","key":"R15","doi-asserted-by":"publisher","first-page":"965","DOI":"10.21037\/jgo.2019.05.03","article-title":"The prognostic value of systemic immune-inflammation index (SII) in patients after radical operation for carcinoma of stomach in gastric cancer","volume":"10","author":"Wang","journal-title":"J Gastrointest Oncol"},{"issue":"13","key":"R16","doi-asserted-by":"publisher","DOI":"10.3390\/cancers17132189","article-title":"Prognostic value of PLR, SIRI, PIV, SII, and NLR in non-muscle invasive bladder cancer: can inflammatory factors influence pathogenesis and outcomes?","volume":"17","author":"Bizzarri","journal-title":"Cancers (Basel)"},{"issue":"2","key":"R17","doi-asserted-by":"publisher","first-page":"700","DOI":"10.1097\/JS9.0000000000000904","article-title":"Impact of urinary diversion type on urethral recurrence following radical cystectomy for bladder cancer: propensity score matched and weighted analyses of retrospective cohort","volume":"110","author":"Yu","journal-title":"Int J Surg"},{"issue":"2","key":"R18","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0210976","article-title":"Machine learning models for predicting post-cystectomy recurrence and survival in bladder cancer patients","volume":"14","author":"Hasnain","journal-title":"PLoS One"},{"issue":"7","key":"R19","doi-asserted-by":"publisher","first-page":"761","DOI":"10.1080\/14737167.2023.2224963","article-title":"Use of machine learning to predict bladder cancer survival outcomes: a systematic literature review","volume":"23","author":"Liu","journal-title":"Expert Rev Pharmacoecon Outcomes Res"},{"key":"R20","unstructured":"Qi S Kumar N Farrokh M et al. An effective meaningful way to evaluate survival models. arXiv. Preprint posted online on Jun 1, 2023. [doi: 10.48550\/arXiv.2306.01196]"},{"issue":"1","key":"R21","doi-asserted-by":"publisher","DOI":"10.1136\/bmjhci-2023-100784","article-title":"Road map for clinicians to develop and evaluate AI predictive models to inform clinical decision-making","volume":"30","author":"Hassan","journal-title":"BMJ Health Care Inform"}],"container-title":["JMIR Perioperative Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/periop.jmir.org\/2026\/1\/e86666","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T17:14:26Z","timestamp":1782839666000},"score":1,"resource":{"primary":{"URL":"https:\/\/periop.jmir.org\/2026\/1\/e86666"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,19]]},"references-count":21,"URL":"https:\/\/doi.org\/10.2196\/86666","relation":{},"ISSN":["2561-9128"],"issn-type":[{"value":"2561-9128","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,19]]},"article-number":"v9i6e86666"}}