Predicting Postoperative Complications in Glioblastoma Patients Using Machine Learning Models
DOI:
https://doi.org/10.56294/shp2025406Keywords:
Glioblastoma, postoperative complications, Machine Learning, Risk Prediction, Deep Learning, Long Short-Term MemoryAbstract
Introduction: Glioblastoma multiforme (GBM) is the most aggressive primary brain tumor in adults. Despite advanced treatments, postoperative complications remain common and significantly impact patient outcomes. This study aims to predict such complications using machine learning (ML) models.
Method: a retrospective analysis was conducted using GBM patient data from open-access sources (TCIA and Kaggle). Preoperative, intraoperative, and postoperative variables were collected. ML models including Logistic Regression, Random Forest, XGBoost, and Long Short-Term Memory (LSTM) were trained and evaluated using metrics such as AUROC, AUPRC, sensitivity, and specificity. Feature importance was assessed using SHAP values.
Results: The study included 498 patients (median age: 55 years; 60 % male). Postoperative complications occurred in 30 % of patients, with infections (15 %), hemorrhage (10 %), and neurological deficits (18 %) being most common. LSTM outperformed other models (AUROC: 0.88; AUPRC: 0.64), especially in Grade IV tumors. Key predictors included low preoperative KPS, eloquent tumor location, subtotal resection, and ICU stay >5 days.
Conclusions: ML models, especially deep learning (LSTM), effectively predicted postoperative complications in GBM patients. Their integration into clinical workflows may enhance risk stratification, surgical planning, and patient counseling.
References
1. Welling LC, Andrade R, Welling L, Lynch JC, Pereira C, Polycarpo Hidalgo F, et al. Glioblastoma Multiforme: The experience at the Hospital dos Servidores do Estado in Rio de Janeiro. researchgate.netL Welling, JC Lynch, C Pereira, R Andrade, FP Hidalgo, AGL Pereira, C EscoteguyJBNC-JORNAL BRASILEIRO DE NEUROCIRURGIA, 2013•researchgate.net [Internet]. 2014 Jan 1 [cited 2025 Jul 31];1:85–98. Available from: https://www.researchgate.net/profile/Jose-Lynch/publication/268817273_Glioblastoma_Multiforme_A_experiencia_do_Hospital_dos_Servidores_do_Estado_do_Rio_de_Janeiro_Glioblastoma_Multiforme_The_experience_at_the_Hospital_dos_Servidores_do_Estado_in_Rio_de_Janeiro/links/55ec7b4408aeb6516268c9e1/Glioblastoma-Multiforme-A-experiencia-do-Hospital-dos-Servidores-do-Estado-do-Rio-de-Janeiro-Glioblastoma-Multiforme-The-experience-at-the-Hospital-dos-Servidores-do-Estado-in-Rio-de-Janeiro.pdf
2. Czarnywojtek A, Borowska M, Dyrka K, Van Gool S, Sawicka-Gutaj N, Moskal J, et al. Glioblastoma multiforme: the latest diagnostics and treatment techniques. karger.comA Czarnywojtek, M Borowska, K Dyrka, S Van Gool, N Sawicka-Gutaj, J Moskal, J KościńskiPharmacology, 2023•karger.com [Internet]. 2023 Sep 1 [cited 2025 Jul 30];108(5):423–31. Available from: https://karger.com/pha/article/108/5/423/854342
3. Wang F, Huang Q, Su H, Sun M, Wang Z, Chen Z, et al. Self-assembling paclitaxel-mediated stimulation of tumor-associated macrophages for postoperative treatment of glioblastoma. pnas.orgF Wang, Q Huang, H Su, M Sun, Z Wang, Z Chen, M Zheng, RW Chakroun, MK MonroeProceedings of the National Academy of Sciences, 2023•pnas.org [Internet]. 2023 [cited 2025 Jul 30];120(118). Available from: https://www.pnas.org/doi/abs/10.1073/pnas.2204621120
4. Wu W, Klockow JL, Zhang M, Lafortune F, Chang E, Jin L, et al. Glioblastoma multiforme (GBM): An overview of current therapies and mechanisms of resistance. ElsevierW Wu, JL Klockow, M Zhang, F Lafortune, E Chang, L Jin, Y Wu, HE Daldrup-LinkPharmacological research, 2021•Elsevier [Internet]. 2021 Sep 1 [cited 2025 Jul 30];171. Available from: https://www.sciencedirect.com/science/article/pii/S1043661821003649
5. Kazim SF, Martinez E, Hough TJ, Spangler BQ, Bowers CA, Chohan MO. The Survival Benefit of Postoperative Bacterial Infections in Patients With Glioblastoma Multiforme: Myth or Reality? Front Neurol [Internet]. 2021 Feb 5 [cited 2025 Jul 30];12:615593. Available from: https://www.frontiersin.org/articles/10.3389/fneur.2021.615593/full
6. Niyazi M, Andratschke N, Bendszus M, Chalmers AJ, Erridge SC, Galldiks N, et al. ESTRO-EANO guideline on target delineation and radiotherapy details for glioblastoma. Radiotherapy and Oncology [Internet]. 2023 Jul 1 [cited 2025 Jul 30];184:109663. Available from: https://www.sciencedirect.com/science/article/pii/S0167814023002013
7. Holtzman Gazit M, Faran R, Stepovoy K, Peles O, Shamir RR. Post-operative glioblastoma multiforme segmentation with uncertainty estimation. Front Hum Neurosci [Internet]. 2022 Nov 3 [cited 2025 Jul 30];16:932441. Available from: https://www.frontiersin.org/articles/10.3389/fnhum.2022.932441/full
8. Shah Z, Bakhshi SK, Shamim MS. Effect of post-operative infections on glioblastoma outcomes. europepmc.orgZ Shah, SK Bakhshi, MS ShamimJPMA The Journal of the Pakistan Medical Association, 2023•europepmc.org [Internet]. 2023 Mar 1 [cited 2025 Jul 30];73(3):711–2. Available from: https://europepmc.org/article/med/36932792
9. Simińska D, Korbecki J, Kojder K, Kapczuk P, Fabiańska M, Gutowska I, et al. Epidemiology of anthropometric factors in glioblastoma multiforme—Literature review. mdpi.comD Simińska, J Korbecki, K Kojder, P Kapczuk, M Fabiańska, I GutowskaBrain sciences, 2021•mdpi.com [Internet]. 2021 Jan 1 [cited 2025 Jul 30];11(1):1–14. Available from: https://www.mdpi.com/2076-3425/11/1/116
10. Wen J, Chen W, Zhu Y, Zhang P. Clinical features associated with the efficacy of chemotherapy in patients with glioblastoma (GBM): a surveillance, epidemiology, and end results (SEER) analysis. SpringerJ Wen, W Chen, Y Zhu, P ZhangBMC cancer, 2021•Springer [Internet]. 2021 Dec 1 [cited 2025 Jul 30];21(1). Available from: https://link.springer.com/article/10.1186/s12885-021-07800-0
11. Chen L, Ma J, Zou Z, Liu H, Liu C, Gong S, et al. Clinical characteristics and prognosis of patients with glioblastoma: A review of survival analysis of 1674 patients based on SEER database. journals.lww.comL Chen, J Ma, Z Zou, H Liu, C Liu, S Gong, X Gao, G LiangMedicine, 2022•journals.lww.com [Internet]. 2022 Nov 25 [cited 2025 Jul 30];101(47):E32042. Available from: https://journals.lww.com/md-journal/fulltext/2022/11250/Clinical_characteristics_and_prognosis_of_patients.127.aspx
12. Torp SH, Solheim O, Skjulsvik AJ. The WHO 2021 Classification of Central Nervous System tumours: a practical update on what neurosurgeons need to know—a minireview. SpringerSH Torp, O Solheim, AJ SkjulsvikActa neurochirurgica, 2022•Springer [Internet]. 2022 Sep 1 [cited 2025 Jul 30];164(9):2453–64. Available from: https://link.springer.com/article/10.1007/s00701-022-05301-y
13. Wahed S, Information MWIJ of O, 2025 undefined. Predicting Post-Surgical Complications using Machine Learning Models for Patients with Brain Tumors. cyberleninka.ruSA Wahed, MA WahedInternational Journal of Open Information Technologies, 2025•cyberleninka.ru [Internet]. [cited 2025 Jul 30]; Available from: https://cyberleninka.ru/article/n/predicting-post-surgical-complications-using-machine-learning-models-for-patients-with-brain-tumors
14. Cozzi FM, Mayrand RC, Wan Y, Price SJ. Predicting glioblastoma progression using MR diffusion tensor imaging: A systematic review. Wiley Online LibraryFM Cozzi, RC Mayrand, Y Wan, SJ PriceJournal of Neuroimaging, 2025•Wiley Online Library [Internet]. 2025 Jan 1 [cited 2025 Jul 30];35(1). Available from: https://onlinelibrary.wiley.com/doi/abs/10.1111/jon.13251
15. Wahed S, (Montevideo) MWM, 2025 undefined. AI-Deep Learning Framework for Predicting Neuropsychiatric Outcomes Following Toxic Effects of Drugs on The Brain. multidisciplinar.ageditor.uySA Wahed, MA WahedMultidisciplinar (Montevideo), 2025•multidisciplinar.ageditor.uy [Internet]. 2025 [cited 2025 Jul 30];3:22. Available from: https://multidisciplinar.ageditor.uy/index.php/multidisciplinar/article/view/222
16. Awuah WA, Ben-Jaafar A, Roy S, Nkrumah-Boateng PA, Tan JK, Abdul-Rahman T, et al. Predicting survival in malignant glioma using artificial intelligence. SpringerWA Awuah, A Ben-Jaafar, S Roy, PA Nkrumah-Boateng, JK Tan, T Abdul-Rahman, O AtallahEuropean Journal of Medical Research, 2025•Springer [Internet]. 2025 Jan 31 [cited 2025 Jul 30];30(1):61. Available from: https://link.springer.com/article/10.1186/s40001-025-02339-3
17. Wahed M, (Montevideo) SWM, 2025 undefined. Bi-directional AI Framework for Differentiate Psychiatric Disorders and Predicting Symptoms from Drug-Induced Neurotoxicity. multidisciplinar.ageditor.uyMA Wahed, SA WahedMultidisciplinar (Montevideo), 2025•multidisciplinar.ageditor.uy [Internet]. 2025 [cited 2025 Jul 30];3:230. Available from: https://multidisciplinar.ageditor.uy/index.php/multidisciplinar/article/view/230
18. Morelli I, Greto D, Visani L, … GLC nutrition, 2025 undefined. Integrating nutritional status and hematological biomarkers for enhanced prognosis prediction in glioma patients: a systematic review. ElsevierI Morelli, D Greto, L Visani, G Lombardi, M Scorsetti, E Clerici, P Navarria, G Minniti, L LiviClinical nutrition ESPEN, 2025•Elsevier [Internet]. [cited 2025 Jul 30]; Available from: https://www.sciencedirect.com/science/article/pii/S2405457725000440
19. Wahed M, Intelligent SWADSS and, 2025 undefined. Autonomous Defense Systems for Surgical Robots Ensuring Cybersecurity in Robotic-Assisted Surgery. igi-global.comMA Wahed, SA WahedAI-Driven Security Systems and Intelligent Threat Response Using, 2025•igi-global.com [Internet]. [cited 2025 Jul 30]; Available from: https://www.igi-global.com/chapter/autonomous-defense-systems-for-surgical-robots-ensuring-cybersecurity-in-robotic-assisted-surgery/376927
20. Wahed M, Wahed S, and AAADSS, 2025 undefined. AI-Driven Cybersecurity for Telemedicine: Enhancing Protection Through Autonomous Defense Systems. igi-global.comMA Wahed, SA Wahed, AE AlzoubiAI-Driven Security Systems and Intelligent Threat Response Using, 2025•igi-global.com [Internet]. [cited 2025 Jul 30]; Available from: https://www.igi-global.com/chapter/ai-driven-cybersecurity-for-telemedicine/376926
21. Onciul R, Brehar F, Dumitru A, … CCF in, 2025 undefined. Predicting overall survival in glioblastoma patients using machine learning: an analysis of treatment efficacy and patient prognosis. pmc.ncbi.nlm.nih.govR Onciul, FM Brehar, AV Dumitru, C Crivoi, RA Covache-Busuioc, M Serban, PM RadoiFrontiers in Oncology, 2025•pmc.ncbi.nlm.nih.gov [Internet]. [cited 2025 Jul 30]; Available from: https://pmc.ncbi.nlm.nih.gov/articles/PMC12014569/
22. Wahed S, Reality MWG and A, 2025 undefined. Optimizing Antibiotics Prophylaxis in Neurosurgery through Machin Learning: Predicting Infections and Personalizing Treatment Strategies. dialnet.unirioja.esSA Wahed, MA WahedGamification and Augmented Reality, 2025•dialnet.unirioja.es [Internet]. [cited 2025 Jul 30]; Available from: https://dialnet.unirioja.es/servlet/articulo?codigo=10124784
23. Lakomy R, Kazda T, … ISF in, 2020 undefined. Real-world evidence in glioblastoma: stupp’s regimen after a decade. pmc.ncbi.nlm.nih.govR Lakomy, T Kazda, I Selingerova, A Poprach, P Pospisil, R Belanova, P Fadrus, V VybihalFrontiers in oncology, 2020•pmc.ncbi.nlm.nih.gov [Internet]. [cited 2025 Jul 30]; Available from: https://pmc.ncbi.nlm.nih.gov/articles/PMC7348058/
24. Wahed MA, Wahed SA. Assessing Internet Addiction Levels Among Medical Students in Jordan_ Insights from a Cross-Sectional Survey. International Journal of Advanced Health Science and Technology [Internet]. 2025 Mar 23 [cited 2025 Jul 30];5(1):12–8. Available from: https://ijahst.org/index.php/ijahst/article/view/428
25. Wahed S, Information MWIJ of O, 2025 undefined. A Deep Learning Framework for Unraveling Toxicokinetic-Neuropsychiatric Interactions. injoit.orgSA Wahed, MA WahedInternational Journal of Open Information Technologies, 2025•injoit.org [Internet]. [cited 2025 Jul 30]; Available from: http://injoit.org/index.php/j1/article/view/2145
26. Wahed S, Science MWIJ of AH, 2025 undefined. Automated Detection of Histological Hallmarks in Frontotemporal Lobar Degeneration Using Deep Learning. ijahst.orgSA Wahed, MA WahedInternational Journal of Advanced Health Science and Technology, 2025•ijahst.org [Internet]. 2025 [cited 2025 Jul 30];5(3):91–6. Available from: http://ijahst.org/index.php/ijahst/article/view/468
27. Duan L, Zhang Y, Tang H, Liao J, Zhou G, Zhou X. Recent Advances in High‐Entropy Layered Oxide Cathode Materials for Alkali Metal‐Ion Batteries. Wiley Online Library [Internet]. 2025 Jan 8 [cited 2025 Jul 30];37(1). Available from: https://advanced.onlinelibrary.wiley.com/doi/abs/10.1002/adma.202411426
28. Gupta A, Gonzalez-Rojas Y, Juarez E, Jama MC, 2022 undefined. Effect of sotrovimab on hospitalization or death among high-risk patients with mild to moderate COVID-19: a randomized clinical trial. jamanetwork.com [Internet]. [cited 2025 Jul 30]; Available from: https://jamanetwork.com/journals/jama/article-abstract/2790246
29. Ricciardi W, Barros PP, Bourek A, Brouwer W, Kelsey T, Lehtonen L. How to govern the digital transformation of health services. academic.oup.comW Ricciardi, P Pita Barros, A Bourek, W Brouwer, T Kelsey, L LehtonenEuropean journal of public health, 2019•academic.oup.com [Internet]. [cited 2025 Jul 30];29:7–12. Available from: https://academic.oup.com/eurpub/article-abstract/29/Supplement_3/7/5628049
30. Wahed S, … MW 2025 1st I, 2025 undefined. Optimizing Colorectal Cancer Treatment with Unconventional Therapies: A Data-Driven AI Approach for Comprehensive Image-Based Evaluation and Treatment. ieeexplore.ieee.orgSA Wahed, MA Wahed, AE Alzoubi2025 1st International Conference on Computational Intelligence, 2025•ieeexplore.ieee.org [Internet]. [cited 2025 Jul 30]; Available from: https://ieeexplore.ieee.org/abstract/document/11013450/
31. Wahed M, Alzoubi A, … SW 2025 1st I, 2025 undefined. AI-Driven Approach to Predict High-Risk Newborns to Reduce NICU Admission Overcrowding. ieeexplore.ieee.orgMA Wahed, AE Alzoubi, SA Wahed, J Kursheva2025 1st International Conference on Computational Intelligence, 2025•ieeexplore.ieee.org [Internet]. [cited 2025 Jul 30]; Available from: https://ieeexplore.ieee.org/abstract/document/11013654/
32. Cheng J, Kuang H, Yang S, … HYBDM and, 2025 undefined. Segmentation-Guided Deep Learning for Glioma Survival Risk Prediction with Multimodal MRI. ieeexplore.ieee.orgJ Cheng, H Kuang, S Yang, H Yue, J Liu, J WangBig Data Mining and Analytics, 2025•ieeexplore.ieee.org [Internet]. [cited 2025 Jul 30]; Available from: https://ieeexplore.ieee.org/abstract/document/10856894/
33. Gonzalez N, Küper MP, Sciences MGFB, 2025 undefined. Integrated Workflow for Drug Repurposing in Glioblastoma: Computational Prediction and Preclinical Validation of Therapeutic Candidates. mdpi.comN Gonzalez, M Pérez Küper, M Garcia Fallit, JAP Agudelo, A Nicola CandiaBrain Sciences, 2025•mdpi.com [Internet]. [cited 2025 Jul 30]; Available from: https://www.mdpi.com/2076-3425/15/6/637
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Mutaz Abdel Wahed, Salma Abdel Wahed (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
The article is distributed under the Creative Commons Attribution 4.0 License. Unless otherwise stated, associated published material is distributed under the same licence.
