{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T19:34:40Z","timestamp":1785526480000,"version":"3.56.0"},"reference-count":54,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2024,6,15]],"date-time":"2024-06-15T00:00:00Z","timestamp":1718409600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>This study assesses the predictive performance of six machine learning models and a 1D Convolutional Neural Network (CNN) in forecasting tumor dynamics within three months following Gamma Knife radiosurgery (GKRS) in 77 brain metastasis (BM) patients. The analysis meticulously evaluates each model before and after hyperparameter tuning, utilizing accuracy, AUC, and other metrics derived from confusion matrices. The CNN model showcased notable performance with an accuracy of 98% and an AUC of 0.97, effectively complementing the broader model analysis. Initial findings highlighted that XGBoost significantly outperformed other models with an accuracy of 0.95 and an AUC of 0.95 before tuning. Post-tuning, the Support Vector Machine (SVM) demonstrated the most substantial improvement, achieving an accuracy of 0.98 and an AUC of 0.98. Conversely, XGBoost showed a decline in performance after tuning, indicating potential overfitting. The study also explores feature importance across models, noting that features like \u201ccontrol at one year\u201d, \u201cage of the patient\u201d, and \u201cbeam-on time for volume V1 treated\u201d were consistently influential across various models, albeit their impacts were interpreted differently depending on the model\u2019s underlying mechanics. This comprehensive evaluation not only underscores the importance of model selection and hyperparameter tuning but also highlights the practical implications in medical diagnostic scenarios, where the accuracy of positive predictions can be crucial. Our research explores the effects of staged Gamma Knife radiosurgery (GKRS) on larger tumors, revealing no significant outcome differences across protocols. It uniquely considers the impact of beam-on time and fraction intervals on treatment efficacy. However, the investigation is limited by a small patient cohort and data from a single institution, suggesting the need for future multicenter research.<\/jats:p>","DOI":"10.3390\/diagnostics14121268","type":"journal-article","created":{"date-parts":[[2024,6,17]],"date-time":"2024-06-17T04:48:12Z","timestamp":1718599692000},"page":"1268","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Predicting Tumor Dynamics Post-Staged GKRS: Machine Learning Models in Brain Metastases Prognosis"],"prefix":"10.3390","volume":"14","author":[{"given":"Ana-Maria","family":"Trofin","sequence":"first","affiliation":[{"name":"University of Medicine and Pharmacy \u201cGrigore T. Popa\u201d Ia\u0219i, 700115 Iasi, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"C\u0103lin Gh.","family":"Buzea","sequence":"additional","affiliation":[{"name":"Clinical Emergency Hospital \u201cProf. Dr. Nicolae Oblu\u201d Ia\u0219i, 700309 Iasi, Romania"},{"name":"National Institute of Research and Development for Technical Physics, IFT Ia\u0219i, 700050 Iasi, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"R\u0103zvan","family":"Buga","sequence":"additional","affiliation":[{"name":"University of Medicine and Pharmacy \u201cGrigore T. Popa\u201d Ia\u0219i, 700115 Iasi, Romania"},{"name":"Clinical Emergency Hospital \u201cProf. Dr. Nicolae Oblu\u201d Ia\u0219i, 700309 Iasi, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maricel","family":"Agop","sequence":"additional","affiliation":[{"name":"Physics Department, Technical University \u201cGheorghe Asachi\u201d Iasi, 700050 Iasi, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6447-0958","authenticated-orcid":false,"given":"L\u0103cr\u0103mioara","family":"Ochiuz","sequence":"additional","affiliation":[{"name":"University of Medicine and Pharmacy \u201cGrigore T. Popa\u201d Ia\u0219i, 700115 Iasi, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dragos Teodor","family":"Iancu","sequence":"additional","affiliation":[{"name":"University of Medicine and Pharmacy \u201cGrigore T. Popa\u201d Ia\u0219i, 700115 Iasi, Romania"},{"name":"Regional Institute of Oncology, 700483 Iasi, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lucian","family":"Eva","sequence":"additional","affiliation":[{"name":"Clinical Emergency Hospital \u201cProf. Dr. Nicolae Oblu\u201d Ia\u0219i, 700309 Iasi, Romania"},{"name":"University Apollonia, 700511 Iasi, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2024,6,15]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"e000024","DOI":"10.1136\/esmoopen-2015-000024","article-title":"Descriptive statistical analysis of a real life cohort of 2419 patients with brain metastases of solid cancers","volume":"1","author":"Berghoff","year":"2016","journal-title":"ESMO Open"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"754","DOI":"10.1001\/archneur.1978.00500350058012","article-title":"Treatment for patients with cerebral metastases","volume":"35","author":"Markesbery","year":"1978","journal-title":"Arch. Neurol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"427","DOI":"10.1016\/S0360-3016(99)00198-4","article-title":"Stereotactic radiosurgery plus whole brain radiotherapy versus radiotherapy alone for patients with multiple brain metastases","volume":"45","author":"Kondziolka","year":"1999","journal-title":"Int. J. Radiat. Oncol. Biol. Phys."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"494","DOI":"10.1056\/NEJM199002223220802","article-title":"A Randomized trial of surgery in the treatment of single metastases to the brain","volume":"322","author":"Patchell","year":"1990","journal-title":"N. Engl. J. Med."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1159\/000066718","article-title":"Gamma knife radiosurgery for metastatic brain tumors","volume":"76","author":"Park","year":"2001","journal-title":"Ster. Funct. Neurosurg."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"134","DOI":"10.1200\/JCO.2010.30.1655","article-title":"Adjuvant whole-brain radiotherapy versus observation after radiosurgery or surgical resection of one to three cerebral metastases: Results of the EORTC 22952-26001 study","volume":"29","author":"Kocher","year":"2011","journal-title":"J. Clin. Oncol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"483","DOI":"10.1016\/j.ijrobp.2010.05.033","article-title":"Single-dose versus fractionated stereotactic radiotherapy for brain metastases","volume":"81","author":"Kim","year":"2011","journal-title":"Int. J. Radiat. Oncol. Biol. Phys."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"56","DOI":"10.14791\/btrt.2014.2.2.56","article-title":"Fractionated gamma knife radiosurgery for benign perioptic tumors: Outcomes of 38 patients in a single institute","volume":"2","author":"Jee","year":"2014","journal-title":"Brain Tumor Res. Treat."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1016\/j.radonc.2006.08.024","article-title":"Phase II trial of hypofractionated stereotactic radiotherapy for brain metastases: Results and toxicity","volume":"81","author":"Ganslandt","year":"2006","journal-title":"Radiother. Oncol."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Kim, J.W., Park, H.R., Lee, J.M., Kim, J.W., Chung, H.T., Kim, D.G., and Paek, S.H. (2016). Fractionated stereotactic gamma knife radiosurgery for large brain metastases: A retrospective, single center study. PLoS ONE, 11.","DOI":"10.1371\/journal.pone.0163304"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"S66","DOI":"10.1227\/01.NEU.0000182739.84734.6E","article-title":"Current treatment paradigms for the management of patients with brain metastases","volume":"57","author":"Ewend","year":"2005","journal-title":"Neurosurgery"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1007\/s11060-015-1915-x","article-title":"Outcome of gamma knife radiosurgery for metastatic brain tumors derived from non-small cell lung cancer","volume":"125","author":"Cho","year":"2015","journal-title":"J. Neuro-Oncol."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1243","DOI":"10.1097\/JTO.0000000000000630","article-title":"The 2015 World Health Organization classification of lung tumors: Impact of genetic, clinical and radiologic advances since the 2004 classification","volume":"10","author":"Travis","year":"2015","journal-title":"J. Thorac. Oncol."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1240","DOI":"10.1097\/JTO.0000000000000663","article-title":"Introduction to The 2015 World Health Organization classification of tumors of the lung, pleura, thymus, and heart","volume":"10","author":"Travis","year":"2015","journal-title":"J. Thorac. Oncol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1007\/s11912-011-0203-y","article-title":"Epidemiology of Brain Metastases","volume":"14","author":"Nayak","year":"2012","journal-title":"Curr. Oncol. Rep."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Jablonska, P.A., Bosch-Barrera, J., Serrano, D., Valiente, M., Calvo, A., and Aristu, J. (2021). Challenges and Novel Opportunities of Radiation Therapy for Brain Metastases in Non-Small Cell Lung Cancer. Cancers, 13.","DOI":"10.3390\/cancers13092141"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1016\/j.ctrv.2016.03.009","article-title":"The impact of brain metastasis on quality of life, resource utilization and survival in patients with non-small-cell lung cancer","volume":"45","author":"Peters","year":"2016","journal-title":"Cancer Treat. Rev."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1332","DOI":"10.1016\/j.annonc.2021.07.016","article-title":"EANO\u2013ESMO Clinical Practice Guidelines for diagnosis, treatment and follow-up of patients with brain metastasis from solid tumours","volume":"32","author":"Guckenberger","year":"2021","journal-title":"Ann. Oncol."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"492","DOI":"10.1200\/JCO.21.02314","article-title":"Treatment for Brain Metastases: ASCO-SNO-ASTRO Guideline","volume":"40","author":"Vogelbaum","year":"2022","journal-title":"J. Clin. Oncol."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"863","DOI":"10.1093\/annonc\/mdy474","article-title":"Metastatic non-small cell lung cancer: ESMO Clinical Practice Guidelines for diagnosis, treatment and follow-up","volume":"30","author":"Planchard","year":"2019","journal-title":"Ann. Oncol."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"88","DOI":"10.3389\/fonc.2018.00088","article-title":"Brain Metastases in Oncogene-Addicted Non-Small Cell Lung Cancer Patients: Incidence and Treatment","volume":"8","author":"Remon","year":"2018","journal-title":"Front. Oncol."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"772789","DOI":"10.3389\/fonc.2021.772789","article-title":"Modern Radiation Therapy for the Management of Brain Metastases From Non-Small Cell Lung Cancer: Current Approaches and Future Directions","volume":"11","author":"Mantovani","year":"2021","journal-title":"Front. Oncol."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"544","DOI":"10.1080\/00207454.2021.1935929","article-title":"Pathology of breast cancer metastasis and a view of metastasis to the brain","volume":"133","author":"Sakibuzzaman","year":"2023","journal-title":"Int. J. Neurosci."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"20200951","DOI":"10.1259\/bjr.20200951","article-title":"Brain metastases from primary colorectal cancer: Is radiosurgery an effective treatment approach? Results of a multicenter study of the radiation and clinical oncology Italian association (AIRO)","volume":"93","author":"Navarria","year":"2020","journal-title":"Br. J. Radiol."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"311","DOI":"10.21873\/anticanres.16165","article-title":"Radiotherapy in Prostate Brain Metastases: A Review of the Literature","volume":"43","year":"2023","journal-title":"Anticancer. Res."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"E445","DOI":"10.1016\/j.wneu.2020.02.152","article-title":"Prostate Cancer Brain Metastases: A Single -Institution Experience","volume":"138","author":"Bhambhvani","year":"2020","journal-title":"World Neurosurg."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Karpathiou, G., Camy, F., Chauleur, C., Dridi, M., Col, P.D., and Peoc\u2019h, M. (2022). Brain Metastases from Gynecologic Malignancies. Medicina, 58.","DOI":"10.3390\/medicina58040548"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"103600","DOI":"10.1016\/j.critrevonc.2022.103600","article-title":"Global management of brain metastasis from renal cell carcinoma","volume":"171","author":"Pierrard","year":"2022","journal-title":"Crit. Rev. Oncol."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Intern\u00f2, V., Sergi, M.C., Metta, M.E., Guida, M., Trerotoli, P., Strippoli, S., Circelli, S., Porta, C., and Tucci, M. (2023). Melanoma Brain Metastases: A Retrospective Analysis of Prognostic Factors and Efficacy of Multimodal Therapies. Cancers, 15.","DOI":"10.3390\/cancers15051542"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"445","DOI":"10.1023\/A:1016409317640","article-title":"Decision trees: An overview and their use in medicine","volume":"26","author":"Podgorelec","year":"2002","journal-title":"J. Med. Syst."},{"key":"ref_31","unstructured":"Salzberg, S.L. (1993). C4.5: Programs for Machine Learning by J. Ross Quinlan, Morgan Kaufmann Publishers."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"104313","DOI":"10.1016\/j.ijmedinf.2020.104313","article-title":"Comparison of nomogram with machine learning techniques for prediction of overall survival in patients with tongue cancer","volume":"145","author":"Alabi","year":"2020","journal-title":"Int. J. Med. Inform."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"638","DOI":"10.1109\/TMI.2017.2774044","article-title":"Convolutional Invasion and Expansion Networks for Tumor Growth Prediction","volume":"37","author":"Zhang","year":"2018","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1200\/JCO.1984.2.3.187","article-title":"Karnofsky performance status revisited: Reliability, validity, and guidelines","volume":"2","author":"Schag","year":"1984","journal-title":"J. Clin. Oncol."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"234","DOI":"10.1016\/j.semradonc.2008.04.004","article-title":"the linear-quadratic model is an appropriate methodology for determining isoeffective doses at large doses per fraction","volume":"18","author":"Brenner","year":"2008","journal-title":"Semin. Radiat. Oncol."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"679","DOI":"10.1259\/0007-1285-62-740-679","article-title":"The linear-quadratic formula and progress in fractionated radiotherapy","volume":"62","author":"Fowler","year":"1989","journal-title":"Br. J. Radiol."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"1543","DOI":"10.1016\/j.ijrobp.2008.10.035","article-title":"Three-staged stereotactic radiotherapy without whole brain irradiation for large metastatic brain tumors","volume":"74","author":"Higuchi","year":"2009","journal-title":"Int. J. Radiat. Oncol. Biol. Phys."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1016\/j.imavis.2018.04.004","article-title":"Beyond one-hot encoding: Lower dimensional target embedding","volume":"75","author":"Bautista","year":"2018","journal-title":"Image Vis. Comput."},{"key":"ref_39","first-page":"42","article-title":"A systematic study of the class imbalance problem in convolutional 642 neural networks","volume":"110","author":"Tan","year":"2019","journal-title":"Neural Netw."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Raschka, S., Patterson, J., and Nolet, C. (2020). machine learning in python: Main developments and technology trends in data science, machine learning, and artificial intelligence. Information, 11.","DOI":"10.3390\/info11040193"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Thanh Noi, P., and Kappas, M. (2018). Comparison of Random Forest, k-Nearest Neighbor, and Support Vector Machine Classifiers for Land Cover Classification Using Sentinel-2 Imagery. Sensors, 18.","DOI":"10.3390\/s18010018"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Saberioon, M., C\u00edsa\u0159, P., Labb\u00e9, L., Sou\u010dek, P., Pelissier, P., and Kerneis, T. (2018). Comparative Performance Analysis of Support Vector Machine, Random Forest, Logistic Regression and k-Nearest Neighbours in Rainbow Trout (Oncorhynchus mykiss) Classification Using Image-Based Features. Sensors, 18.","DOI":"10.3390\/s18041027"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Chen, T., and Guestrin, C. (2016, January 13\u201317). XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"1340","DOI":"10.1093\/bioinformatics\/btq134","article-title":"Permutation importance: A corrected feature importance measure","volume":"26","author":"Altmann","year":"2010","journal-title":"Bioinformatics"},{"key":"ref_45","first-page":"377","article-title":"Adapting the Predictive Power of the Gamma Knife Radiosurgery for Brain Metastases: Can Machine Learning Improve Outcomes?","volume":"96","author":"Sneed","year":"2016","journal-title":"Int. J. Radiat. Oncol."},{"key":"ref_46","first-page":"1435","article-title":"Deep Learning Predictive Models for Patient Survival Prediction in Brain Metastasis after Gamma Knife Radiosurgery","volume":"20","author":"Smith","year":"2018","journal-title":"Neuro-Oncol."},{"key":"ref_47","first-page":"999","article-title":"MRI Features Predict Survival and Molecular Markers in Brain Metastases from Lung Cancer: A Machine Learning Approach","volume":"37","author":"Zhou","year":"2019","journal-title":"J. Clin. Oncol."},{"key":"ref_48","first-page":"e391","article-title":"Machine Learning Algorithms in Radiation Therapy Planning and Delivery","volume":"44","author":"Pater","year":"2017","journal-title":"Med. Phys."},{"key":"ref_49","first-page":"58","article-title":"Machine Learning for Improved Decision-Making in Gamma Knife Radiosurgery Planning","volume":"15","author":"Gupta","year":"2020","journal-title":"Radiat. Oncol."},{"key":"ref_50","unstructured":"Liu, Y., Stojadinovic, S., Hrycushko, B., Wardak, Z., Lau, S., Lu, W., Yan, Y., Timmerman, R., Nedzi, L., and Jiang, S. (2021). Machine Learning-Based Treatment Margin Optimization for Gamma Knife Radiosurgery. Phys. Med. Biol., 66."},{"key":"ref_51","first-page":"1029","article-title":"The Future of Personalized Medicine in Oncology: A Digital Revolution for the Development of Precision Therapies","volume":"80","author":"Mayinger","year":"2020","journal-title":"Cancer Res."},{"key":"ref_52","first-page":"22","article-title":"Integrating Machine Learning and Genomics in Precision Oncology: Current Status and Future Directions","volume":"27","author":"Kessler","year":"2021","journal-title":"Nat. Med."},{"key":"ref_53","first-page":"620","article-title":"Neurocognition in Patients with Brain Metastases Treated with Radiosurgery or Radiosurgery Plus Whole-Brain Irradiation: A Randomised Controlled Trial","volume":"23","author":"Chang","year":"2022","journal-title":"Lancet Oncol."},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1007\/s11060-023-04374-8","article-title":"Fractionated versus staged gamma knife radiosurgery for mid-to-large brain metastases: A propensity score-matched analysis","volume":"164","author":"Noda","year":"2023","journal-title":"J. Neuro-Oncol."}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/14\/12\/1268\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T14:59:19Z","timestamp":1760108359000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/14\/12\/1268"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,15]]},"references-count":54,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2024,6]]}},"alternative-id":["diagnostics14121268"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics14121268","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,15]]}}}