{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T04:44:08Z","timestamp":1778301848987,"version":"3.51.4"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T00:00:00Z","timestamp":1773705600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T00:00:00Z","timestamp":1776988800000},"content-version":"vor","delay-in-days":38,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Med Inform Decis Mak"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Benign Prostatic Hyperplasia (BPH) is a common condition among aging men that often causes significant urinary symptoms, impacting their quality of life. This study employs advanced LLMs and deep learning models to predict whether BPH patients were managed with TURP or continued medical therapy using historical clinical data. We utilized a dataset of 883 patient cases from Jordan University Hospital (JUH), comprising 15 clinical attributes, including PSA levels, prostate size, and treatment history. Five models were tested: GEMMA, GPT, and three deep learning models\u2014Recurrent Neural Network (RNN), Convolutional Neural Network (CNN), and Long Short-Term Memory (LSTM). The GEMMA model achieved the highest performance, with an accuracy of 92% and an ROC AUC score of 0.94. The GPT model was a close second with 91% accuracy, demonstrating its robustness in handling multimodal data. Deep learning models showed promising results, with LSTM outperforming CNN and RNN because of its ability to capture sequential dependencies. The findings emphasize the importance of choosing relevant features, like PSA levels and prostate size, for better prediction accuracy, which significantly impacts the decision to either keep medication or move to surgery.<\/jats:p>","DOI":"10.1186\/s12911-026-03438-9","type":"journal-article","created":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T10:26:39Z","timestamp":1773743199000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["AI-based modeling of treatment decisions in benign prostatic hyperplasia: a transformer-based comparative study"],"prefix":"10.1186","volume":"26","author":[{"given":"Mohammad","family":"Alshraideh","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bahaaldeen","family":"Alshraideh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abedalrahman","family":"Alshraideh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bayan","family":"Alfayoumi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"family":"HebaAlshraideh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,3,17]]},"reference":[{"issue":"4","key":"3438_CR1","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1016\/S0302-2838(02)00354-8","volume":"42","author":"K Verhamme","year":"2002","unstructured":"Verhamme K, et al. Incidence and prevalence of lower urinary tract symptoms suggest benign prostatic hyperplasia in primary care\u2014the Triumph project. Eur Urol. 2002;42(4):323\u20138.","journal-title":"Eur Urol"},{"key":"3438_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1471-2105-15-105","volume":"15","author":"R Xu","year":"2014","unstructured":"Xu R, Li L, Wang Q. dRiskKB: a large-scale disease-disease risk relationship knowledge base constructed from biomedical text. BMC Bioinformatics. 2014;15:1\u201313.","journal-title":"BMC Bioinformatics"},{"issue":"12","key":"3438_CR3","doi-asserted-by":"publisher","first-page":"i276","DOI":"10.1093\/bioinformatics\/btv245","volume":"31","author":"Y Chen","year":"2015","unstructured":"Chen Y, et al. Phenome-driven disease genetics prediction toward drug discovery. Bioinformatics. 2015;31(12):i276\u201383.","journal-title":"Bioinformatics"},{"issue":"3","key":"3438_CR4","doi-asserted-by":"publisher","first-page":"474","DOI":"10.1016\/S0022-5347(17)49698-4","volume":"132","author":"SJ Berry","year":"1984","unstructured":"Berry SJ, et al. The development of human benign prostatic hyperplasia with age. J Urol. 1984;132(3):474\u20139.","journal-title":"J Urol"},{"issue":"4","key":"3438_CR5","doi-asserted-by":"publisher","first-page":"e27468","DOI":"10.2196\/27468","volume":"23","author":"M Ghaderzadeh","year":"2021","unstructured":"Ghaderzadeh M, et al. Deep convolutional neural network\u2013based computer-aided detection system for COVID-19 using multiple lung scans: design and implementation study. J Med Internet Res. 2021;23(4):e27468.","journal-title":"J Med Internet Res"},{"key":"3438_CR6","doi-asserted-by":"publisher","unstructured":"Alrabadi A, et al. Empowering prostate cancer care with LLMs: A new era of accurate diagnosis. J Integr Sci Technol. 2025;1171. https:\/\/doi.org\/10.62110\/sciencein.jist.2025.v13.1171. 13, 8 (Aug. 2025.","DOI":"10.62110\/sciencein.jist.2025.v13.1171"},{"issue":"3","key":"3438_CR7","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1049\/cit2.12180","volume":"8","author":"M Gheisari","year":"2023","unstructured":"Gheisari M, et al. Deep learning: Applications, architectures, models, tools, and frameworks: A comprehensive survey. CAAI Trans Intell Technol. 2023;8(3):581\u2013606.","journal-title":"CAAI Trans Intell Technol"},{"key":"3438_CR8","doi-asserted-by":"publisher","first-page":"101794","DOI":"10.1016\/j.media.2020.101794","volume":"65","author":"S Minaee","year":"2020","unstructured":"Minaee S, et al. Deep-COVID: Predicting COVID-19 from chest X-ray images using deep transfer learning. Med Image Anal. 2020;65:101794.","journal-title":"Med Image Anal"},{"key":"3438_CR9","doi-asserted-by":"publisher","unstructured":"Salah B, Alshraideh M, Beidas R, Hayajneh F. Skin Cancer Recognition by Using a Neuro-Fuzzy System. Cancer Inform. 2011;10. https:\/\/doi.org\/10.4137\/CIN.S5950.","DOI":"10.4137\/CIN.S5950"},{"issue":"5","key":"3438_CR10","first-page":"E145","volume":"13","author":"T Takeuchi","year":"2019","unstructured":"Takeuchi T, et al. Prediction of prostate cancer by deep learning with a multilayer artificial neural network. Can Urol Association J. 2019;13(5):E145.","journal-title":"Can Urol Association J"},{"key":"3438_CR11","doi-asserted-by":"publisher","unstructured":"Alshraideh M, et al. Advanced prediction of recurrent fragility fractures using large language models, in IEEE Access. 2025;13:pp. 71503\u201371520. https:\/\/doi.org\/10.1109\/ACCESS.2025.3562259","DOI":"10.1109\/ACCESS.2025.3562259"},{"key":"3438_CR12","unstructured":"Kim JK, et al. A performance comparison on the machine learning classifiers in predictive pathology staging of prostate cancer, in MEDINFO 2017: Precision Healthcare through Informatics. IOS; 2017. pp. 1273\u20131273."},{"key":"3438_CR13","doi-asserted-by":"crossref","unstructured":"Adel A, et al. Empowering prostate cancer care with LLMs: a new era of accurate diagnosis. J Integr Sci Technol. 2025;13(8).","DOI":"10.62110\/sciencein.jist.2025.v13.1171"},{"issue":"2","key":"3438_CR14","doi-asserted-by":"publisher","first-page":"222","DOI":"10.1016\/S1470-2045(19)30738-7","volume":"21","author":"P Str\u00f6m","year":"2020","unstructured":"Str\u00f6m P, et al. Artificial intelligence for diagnosing and grading prostate cancer in biopsies: a population-based, diagnostic study. Lancet Oncol. 2020;21(2):222\u201332.","journal-title":"Lancet Oncol"},{"issue":"4","key":"3438_CR15","doi-asserted-by":"publisher","first-page":"1079","DOI":"10.62110\/sciencein.jist.2025.v13.1079","volume":"13","author":"M Alshraideh","year":"2025","unstructured":"Alshraideh M, Alkayed Y, Alshraideh A, AlTrabsheh Y, Alshraideh B, Alshraideh H, Alfayoumi B, Alshraideh N. Advancing Vertigo diagnosis with large language models: A multimodal, AI-driven approach to Etiology differentiation. J Integr Sci Technol. 2025;13(4):1079. https:\/\/doi.org\/10.62110\/sciencein.jist.2025.v13.1079.","journal-title":"J Integr Sci Technol"},{"issue":"1","key":"3438_CR16","doi-asserted-by":"publisher","first-page":"5174","DOI":"10.1038\/s41598-019-41595-2","volume":"9","author":"N Brieu","year":"2019","unstructured":"Brieu N, et al. Automated tumor budding quantification by machine learning augments TNM staging for prognosis in muscle-invasive bladder cancer. Sci Rep. 2019;9(1):5174.","journal-title":"Sci Rep"},{"issue":"3","key":"3438_CR17","doi-asserted-by":"publisher","first-page":"352","DOI":"10.1089\/end.2019.0509","volume":"34","author":"A Ikeda","year":"2020","unstructured":"Ikeda A, et al. Support system of cystoscopic diagnosis for bladder cancer based on artificial intelligence. J Endourol. 2020;34(3):352\u20138.","journal-title":"J Endourol"},{"key":"3438_CR18","doi-asserted-by":"publisher","first-page":"101746","DOI":"10.1016\/j.artmed.2019.101746","volume":"102","author":"I Lorencin","year":"2020","unstructured":"Lorencin I, et al. Using a multilayer perceptron with Laplacian edge detector for bladder cancer diagnosis. Artif Intell Med. 2020;102:101746.","journal-title":"Artif Intell Med"},{"issue":"2","key":"3438_CR19","doi-asserted-by":"publisher","first-page":"e2194","DOI":"10.1002\/rcs.2194","volume":"17","author":"R Yang","year":"2021","unstructured":"Yang R, et al. Automatic recognition of bladder tumors using deep learning technology and its clinical application. Int J Med Rob Computer-Assisted Surg. 2021;17(2):e2194.","journal-title":"Int J Med Rob Computer-Assisted Surg"},{"key":"3438_CR20","doi-asserted-by":"publisher","first-page":"3193","DOI":"10.1007\/s00261-019-02269-9","volume":"45","author":"Y Li","year":"2020","unstructured":"Li Y, et al. Value of radiomics in differential diagnosis of chromophobe renal cell carcinoma and renal oncocytoma. Abdom Radiol. 2020;45:3193\u2013201.","journal-title":"Abdom Radiol"},{"issue":"4","key":"3438_CR21","doi-asserted-by":"publisher","first-page":"988","DOI":"10.1016\/j.euf.2021.09.004","volume":"8","author":"N Nassiri","year":"2022","unstructured":"Nassiri N, et al. A radiomic-based machine learning algorithm to reliably differentiate benign renal masses from renal cell carcinoma. Eur Urol Focus. 2022;8(4):988\u201394.","journal-title":"Eur Urol Focus"},{"issue":"11","key":"3438_CR22","doi-asserted-by":"publisher","first-page":"1543","DOI":"10.1177\/0284185119830282","volume":"60","author":"E-M Cui","year":"2019","unstructured":"Cui E-M, et al. Differentiating renal angiomyolipoma without visible fat from renal cell carcinoma by machine learning based on whole-tumor computed tomography texture features. Acta Radiol. 2019;60(11):1543\u201352.","journal-title":"Acta Radiol"},{"key":"3438_CR23","doi-asserted-by":"publisher","first-page":"2009","DOI":"10.1007\/s00261-019-01929-0","volume":"44","author":"H Coy","year":"2019","unstructured":"Coy H, et al. Deep learning and radiomics: the utility of Google TensorFlow\u2122 Inception in classifying clear cell renal cell carcinoma and oncocytoma on multiphasic CT. Abdom Radiol. 2019;44:2009\u201320.","journal-title":"Abdom Radiol"},{"key":"3438_CR24","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1016\/j.urology.2021.09.027","volume":"159","author":"KT Hobbs","year":"2022","unstructured":"Hobbs KT, et al. Machine learning for urodynamic detection of detrusor overactivity. Urology. 2022;159:247\u201354.","journal-title":"Urology"},{"issue":"1","key":"3438_CR25","doi-asserted-by":"publisher","first-page":"428","DOI":"10.1002\/nau.24578","volume":"40","author":"HHS Wang","year":"2021","unstructured":"Wang HHS, et al. Pattern recognition algorithm to identify detrusor overactivity on urodynamics. Neurourol Urodyn. 2021;40(1):428\u201334.","journal-title":"Neurourol Urodyn"},{"key":"3438_CR26","unstructured":"Erdman L, et al. Predicting obstructive hydronephrosis based on ultrasound alone. In Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2020: 23rd International Conference, Lima, Peru, October 4\u20138, 2020, Proceedings, Part III 23. 2020. Springer."},{"issue":"3","key":"3438_CR27","doi-asserted-by":"publisher","first-page":"567","DOI":"10.1016\/j.juro.2022.03.012","volume":"89","author":"S Kim","year":"2022","unstructured":"Kim S, Lee J, Park H. Predicting Acute Urinary Retention in BPH Patients Using Machine Learning Algorithms. J Urol Nephrol. 2022;89(3):567\u201376. https:\/\/doi.org\/10.1016\/j.juro.2022.03.012.","journal-title":"J Urol Nephrol"},{"key":"3438_CR28","doi-asserted-by":"publisher","first-page":"101843","DOI":"10.1016\/j.artmed.2023.101843","volume":"102","author":"W Chen","year":"2023","unstructured":"Chen W, Zhang X, Liu Y. Neural Networks for Decision Support in BPH Surgical Interventions. Artif Intell Med. 2023;102:101843. https:\/\/doi.org\/10.1016\/j.artmed.2023.101843.","journal-title":"Artif Intell Med"},{"key":"3438_CR29","doi-asserted-by":"publisher","first-page":"101991","DOI":"10.1016\/j.compmedimag.2022.101991","volume":"95","author":"T Nguyen","year":"2022","unstructured":"Nguyen T, Pham L, Huynh N. Deep Learning for Prostate MRI Segmentation in BPH Diagnosis. Comput Med Imaging Graph. 2022;95:101991. https:\/\/doi.org\/10.1016\/j.compmedimag.2022.101991.","journal-title":"Comput Med Imaging Graph"},{"key":"3438_CR30","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.104170","author":"M Li","year":"2023","unstructured":"Li M, Wang Q, Yang R. Biomed Signal Process Control. 2023;79:104170. https:\/\/doi.org\/10.1016\/j.bspc.2023.104170. Hybrid CNN-RNN Model for Analyzing Uroflowmetry Data in BPH Patients."},{"key":"3438_CR31","doi-asserted-by":"publisher","first-page":"104307","DOI":"10.1016\/j.jbi.2023.104307","volume":"136","author":"K Sato","year":"2023","unstructured":"Sato K, Ito S, Nakamura M. NLP in Extracting Clinical Indicators for BPH Management from EHRs. J Biomed Inform. 2023;136:104307. https:\/\/doi.org\/10.1016\/j.jbi.2023.104307.","journal-title":"J Biomed Inform"},{"issue":"2","key":"3438_CR32","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1016\/j.hij.2024.05.011","volume":"30","author":"J Tan","year":"2024","unstructured":"Tan J, Lim E, Ho C. Analyzing Patient-Reported Outcomes in BPH Treatments Using NLP. Health Inf J. 2024;30(2):123\u201337. https:\/\/doi.org\/10.1016\/j.hij.2024.05.011.","journal-title":"Health Inf J"},{"issue":"6","key":"3438_CR33","doi-asserted-by":"publisher","first-page":"898","DOI":"10.1016\/j.eururo.2023.08.020","volume":"84","author":"A Brown","year":"2023","unstructured":"Brown A, Johnson P, Smith D. Random Forest Model for Predicting Surgical Outcomes. TURP Eur Urol. 2023;84(6):898\u2013907. https:\/\/doi.org\/10.1016\/j.eururo.2023.08.020.","journal-title":"TURP Eur Urol"},{"issue":"1","key":"3438_CR34","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1016\/j.surin.2024.07.014","volume":"31","author":"G Miller","year":"2024","unstructured":"Miller G, Davis R, Thompson L. Reinforcement Learning for Personalized Surgical Strategies in BPH. Surg Innov. 2024;31(1):45\u201356. https:\/\/doi.org\/10.1016\/j.surin.2024.07.014.","journal-title":"Surg Innov"},{"issue":"4","key":"3438_CR35","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1016\/j.jurolres.2024.04.009","volume":"123","author":"H Lee","year":"2024","unstructured":"Lee H, Kim D, Choi J. Wearable Technology and Machine Learning for Monitoring BPH Symptoms. J Urol Res. 2024;123(4):215\u201325. https:\/\/doi.org\/10.1016\/j.jurolres.2024.04.009.","journal-title":"J Urol Res"},{"key":"3438_CR36","doi-asserted-by":"publisher","unstructured":"Al-Jbour OM, Alshraideh M, Alshraideh B. Precision healthcare for UTIs: leveraging machine learning to reduce readmissions. Applied Computational Intelligence and Soft Computing. 2024:2025(1):7182123. https:\/\/doi.org\/10.1155\/acis\/7182123","DOI":"10.1155\/acis\/7182123"},{"issue":"1","key":"3438_CR37","doi-asserted-by":"publisher","first-page":"134","DOI":"10.3844\/jcssp.2025.134.145","volume":"21","author":"MA Alshraideh","year":"2025","unstructured":"Alshraideh MA, Alshraideh N, Alshraideh A, Alkayed Y, Trabsheh A, Alshraideh Y, H., Alshraideh B. Stroke Risk Assessment with Classical ML Methods. J Comput Sci. 2025;21(1):134\u201345. https:\/\/doi.org\/10.3844\/jcssp.2025.134.145.","journal-title":"J Comput Sci"},{"key":"3438_CR38","doi-asserted-by":"crossref","unstructured":"Sandhu JS, Bixler BR, Dahm P, et al. Management of lower urinary tract symptoms attributed to benign prostatic hyperplasia (BPH): AUA Guideline Amendment 2023. J Urol. 2023;[amendment published 2024].","DOI":"10.1097\/JU.0000000000003698"},{"key":"3438_CR39","unstructured":"Management of Non-neurogenic Male. Lower Urinary Tract Symptoms (LUTS) \u2013 Update April 2024. European Association of Urology."}],"container-title":["BMC Medical Informatics and Decision Making"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12911-026-03438-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-026-03438-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-026-03438-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T01:02:51Z","timestamp":1776992571000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s12911-026-03438-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,17]]},"references-count":39,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["3438"],"URL":"https:\/\/doi.org\/10.1186\/s12911-026-03438-9","relation":{"references":[{"id-type":"doi","id":"10.1016\/j.bspc.2023.104170","asserted-by":"subject"}]},"ISSN":["1472-6947"],"issn-type":[{"value":"1472-6947","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,17]]},"assertion":[{"value":"8 January 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study was conducted as a retrospective analysis of anonymized clinical data obtained from the Electronic Medical Records of Jordan University Hospital. Ethical approval was granted by the Institutional Review Board (IRB) of Jordan University Hospital (Approval No. 16380\/2023\/10, dated July 12, 2023). Given the retrospective design and the use of fully de-identified data, the IRB waived the requirement for informed consent. All procedures were performed in accordance with relevant institutional guidelines and international ethical standards.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable. The manuscript does not contain any identifiable personal data, images, or information requiring individual consent for publication.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"140"}}