{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T22:26:30Z","timestamp":1790115990498,"version":"4.0.1"},"reference-count":38,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,8,4]],"date-time":"2025-08-04T00:00:00Z","timestamp":1754265600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurol."],"abstract":"<jats:sec><jats:title>Background<\/jats:title><jats:p>This study developed and validated an interpretable machine learning (ML) algorithm for predicting the risk of drug-resistant epilepsy (DRE) in children with Tuberous sclerosis (TSC).<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>To estimate the risk of DRE in pediatric TSC patients, an interpretable ML model was developed and validated. Clinical data were retrospectively collected from 88 pediatric patients with TSC-related epilepsy. 9 ML algorithms were applied, such as random forest (RF), to construct predictive models. To improve interpretability, SHapley Additive exPlanations (SHAP) were employed, providing both global and individualized feature importance explanations.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The RF model outperformed all other algorithms, yielding an AUC of 0.862 and a specificity of 0.930. Key predictors of DRE included a history of infantile epileptic spasms syndrome (IESS), multifocal discharges on EEG, three or more cortical tubers, and the use of three or more antiseizure medications (ASMs). The model was further evaluated using tenfold cross-validation and showed good calibration and clinical utility, as confirmed by decision curve analysis (DCA).<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>The RF-based prediction model provides a valuable tool for early identification of children with TSC at high risk for DRE, supporting individualized treatment decisions. The integration of SHAP improves model transparency and enhances clinical interpretability.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fneur.2025.1623212","type":"journal-article","created":{"date-parts":[[2025,8,4]],"date-time":"2025-08-04T05:26:30Z","timestamp":1754285190000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["An interpretable machine learning approach for predicting drug-resistant epilepsy in children with tuberous sclerosis complex"],"prefix":"10.3389","volume":"16","author":[{"given":"Jie","family":"Fu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Genfu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhixian","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiong","family":"Qin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,8,4]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1186\/s13023-018-0870-y","article-title":"Incidence of tuberous sclerosis and age at first diagnosis: new data and emerging trends from a national, prospective surveillance study","volume":"13","author":"Ebrahimi-Fakhari","year":"2018","journal-title":"Front Endocrinol"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"657","DOI":"10.1016\/S0140-6736(08)61279-9","article-title":"Tuberous sclerosis","volume":"372","author":"Curatolo","year":"2008","journal-title":"Lancet"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"733","DOI":"10.1016\/s1474-4422(15)00069-1","article-title":"Neurological and neuropsychiatric aspects of tuberous sclerosis complex","volume":"14","author":"Curatolo","year":"2015","journal-title":"Lancet Neurol"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1016\/j.ejpn.2015.12.005","article-title":"Early onset epileptic encephalopathy or genetically determined encephalopathy with early onset epilepsy? Lessons learned from TSC","volume":"20","author":"Curatolo","year":"2016","journal-title":"Eur J Paediatr Neurol"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"1181","DOI":"10.1586\/era.11.93","article-title":"Everolimus: An mTOR inhibitor for the treatment of tuberous sclerosis","volume":"11","author":"Franz","year":"2011","journal-title":"Expert Rev Anticancer Ther"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1002\/epi4.12286","article-title":"Epilepsy in tuberous sclerosis complex: findings from the TOSCA study","volume":"4","author":"Nabbout","year":"2019","journal-title":"Epilepsia Open"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"697467","DOI":"10.3389\/fneur.2021.697467","article-title":"Historical patterns of diagnosis, treatments, and outcome of epilepsy associated with tuberous sclerosis complex: results from TOSCA registry","volume":"12","author":"Nabbout","year":"2021","journal-title":"Front Neurol"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1016\/j.pediatrneurol.2021.07.011","article-title":"Updated international tuberous sclerosis complex diagnostic criteria and surveillance and management recommendations","volume":"123","author":"Northrup","year":"2021","journal-title":"Pediatr Neurol"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"304","DOI":"10.1002\/ana.25956","article-title":"Prevention of epilepsy in infants with tuberous sclerosis complex in the EPISTOP trial","volume":"89","author":"Kotulska","year":"2021","journal-title":"Ann Neurol"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1016\/j.seizure.2018.06.005","article-title":"Refractory epilepsy in preschool children with tuberous sclerosis complex: early surgical treatment and outcome","volume":"60","author":"Fohlen","year":"2018","journal-title":"Seizure"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1016\/j.yebeh.2017.02.007","article-title":"Influence of seizures on early development in tuberous sclerosis complex","volume":"70","author":"Capal","year":"2017","journal-title":"Epilepsy Behav"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"1092","DOI":"10.1177\/0883073817737446","article-title":"Predictors of drug-resistant epilepsy in tuberous sclerosis complex","volume":"32","author":"Jeong","year":"2017","journal-title":"J Child Neurol"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"5495","DOI":"10.3390\/jcm10235495","article-title":"Risk factors associated with refractory epilepsy in patients with tuberous sclerosis complex: a systematic review","volume":"10","author":"Miszewska","year":"2021","journal-title":"J Clin Med"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"1489","DOI":"10.1038\/s41436-020-0823-4","article-title":"TSC2 pathogenic variants are predictive of severe clinical manifestations in TSC infants: results of the EPISTOP study","volume":"22","author":"Og\u00f3rek","year":"2020","journal-title":"Genet Med"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1016\/j.ejpn.2023.08.005","article-title":"Updated clinical recommendations for the management of tuberous sclerosis complex associated epilepsy","volume":"47","author":"Specchio","year":"2023","journal-title":"Eur J Paediatr Neurol"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"107040","DOI":"10.1016\/j.eplepsyres.2022.107040","article-title":"Machine learning and statistic analysis to predict drug treatment outcome in pediatric epilepsy patients with tuberous sclerosis complex","volume":"188","author":"Zhao","year":"2022","journal-title":"Epilepsy Res"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"611","DOI":"10.1007\/s00234-021-02789-6","article-title":"Prediction of tuberous sclerosis-associated neurocognitive disorders and seizures via machine learning of structural magnetic resonance imaging","volume":"64","author":"Shrot","year":"2022","journal-title":"Neuroradiology"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"1373","DOI":"10.3174\/ajnr.A8053","article-title":"Predicting antiseizure medication treatment in children with rare tuberous sclerosis complex-related epilepsy using deep learning","volume":"44","author":"Wang","year":"2023","journal-title":"AJNR Am J Neuroradiol"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"1069","DOI":"10.1111\/j.1528-1167.2009.02397.x","article-title":"Definition of drug resistant epilepsy: consensus proposal by the ad hoc task force of the ILAE commission on therapeutic strategies","volume":"51","author":"Kwan","year":"2010","journal-title":"Epilepsia"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"102913","DOI":"10.1016\/j.eclinm.2024.102913","article-title":"Development and validation of an interpretable machine learning model for predicting the risk of distant metastasis in papillary thyroid cancer: a multicenter study","volume":"77","author":"Hou","year":"2024","journal-title":"EClinicalMedicine"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"100320","DOI":"10.1016\/j.labinv.2023.100320","article-title":"Union with recursive feature elimination: a feature selection framework to improve the classification performance of multicategory causes of death in colorectal cancer","volume":"104","author":"Deng","year":"2024","journal-title":"Lab Investig"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"565","DOI":"10.1177\/0272989X06295361","article-title":"Decision curve analysis: a novel method for evaluating prediction models","volume":"26","author":"Vickers","year":"2006","journal-title":"Med Decis Mak"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"106584","DOI":"10.1016\/j.cmpb.2021.106584","article-title":"Explanation of machine learning models using shapley additive explanation and application for real data in hospital","volume":"214","author":"Nohara","year":"2022","journal-title":"Comput Methods Prog Biomed"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13023-018-0764-z","article-title":"Early diagnosis of tuberous sclerosis complex: a race against time. How to make the diagnosis before seizures?","volume":"13","author":"S\u0142owi\u0144ska","year":"2018","journal-title":"Orphanet J Rare Dis"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"118","DOI":"10.1016\/j.yebeh.2018.10.013","article-title":"Predicting drug-resistant epilepsy\u2014a machine learning approach based on administrative claims data","volume":"89","author":"An","year":"2018","journal-title":"Epilepsy Behav"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"e213460","DOI":"10.1001\/jamanetworkopen.2021.3460","article-title":"Development of a machine learning model using electronic health record data to identify antibiotic use among hospitalized patients","volume":"4","author":"Moehring","year":"2021","journal-title":"JAMA Netw Open"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"613967","DOI":"10.3389\/fneur.2021.613967","article-title":"Diagnostic performance of MRI volumetry in epilepsy patients with hippocampal sclerosis supported through a random forest automatic classification algorithm","volume":"12","author":"Princich","year":"2021","journal-title":"Front Neurol"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1186\/s13195-023-01181-1","article-title":"Neural biomarker diagnosis and prediction to mild cognitive impairment and Alzheimer's disease using EEG technology","volume":"15","author":"Jiao","year":"2023","journal-title":"Alzheimer's Res Ther"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"1690","DOI":"10.1073\/pnas.1800256115","article-title":"Classification and interaction in random forests","volume":"115","author":"Denisko","year":"2018","journal-title":"Proc Natl Acad Sci USA"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"1208","DOI":"10.1111\/epi.16892","article-title":"Early epileptiform EEG activity in infants with tuberous sclerosis complex predicts epilepsy and neurodevelopmental outcomes","volume":"62","author":"De Ridder","year":"2021","journal-title":"Epilepsia"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"e1216","DOI":"10.1212\/wnl.0000000000200027","article-title":"Association of early MRI characteristics with subsequent epilepsy and neurodevelopmental outcomes in children with tuberous sclerosis complex","volume":"98","author":"Hulshof","year":"2022","journal-title":"Neurology"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1016\/j.pediatrneurol.2020.07.015","article-title":"Epilepsy risk prediction model for patients with tuberous sclerosis complex","volume":"113","author":"Farach","year":"2020","journal-title":"Pediatr Neurol"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1016\/j.pediatrneurol.2011.01.001","article-title":"Cortical tubers, cognition, and epilepsy in tuberous sclerosis","volume":"44","author":"Kassiri","year":"2011","journal-title":"Pediatr Neurol"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"704978","DOI":"10.3389\/fneur.2022.704978","article-title":"Antiepileptic effect and safety profile of rapamycin in pediatric patients with tuberous sclerosis complex","volume":"13","author":"Sadowski","year":"2022","journal-title":"Front Neurol"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"2153","DOI":"10.1016\/s0140-6736(16)31419-2","article-title":"Adjunctive everolimus therapy for treatment-resistant focal-onset seizures associated with tuberous sclerosis (EXIST-3): a phase 3, randomised, double-blind, placebo-controlled study","volume":"388","author":"French","year":"2016","journal-title":"Lancet"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"2408","DOI":"10.1212\/WNL.0000000000003400","article-title":"Long-term treatment of epilepsy with everolimus in tuberous sclerosis","volume":"87","author":"Krueger","year":"2016","journal-title":"Neurology"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"986","DOI":"10.1001\/jamaneurol.2022.2514","article-title":"Development and validation of a deep learning model for predicting treatment response in patients with newly diagnosed epilepsy","volume":"79","author":"Hakeem","year":"2022","journal-title":"JAMA Neurol"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"fcaf140","DOI":"10.1093\/braincomms\/fcaf140","article-title":"Leveraging interictal multimodal features and graph neural networks for automated planning of epilepsy surgery","volume":"7","author":"Nejedly","year":"2025","journal-title":"Brain Commun"}],"container-title":["Frontiers in Neurology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2025.1623212\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,4]],"date-time":"2025-08-04T05:26:31Z","timestamp":1754285191000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2025.1623212\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,4]]},"references-count":38,"alternative-id":["10.3389\/fneur.2025.1623212"],"URL":"https:\/\/doi.org\/10.3389\/fneur.2025.1623212","relation":{},"ISSN":["1664-2295"],"issn-type":[{"value":"1664-2295","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,4]]},"article-number":"1623212"}}