{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,26]],"date-time":"2026-10-26T18:00:58Z","timestamp":1793037658175,"version":"4.5.0"},"reference-count":38,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,10,9]],"date-time":"2024-10-09T00:00:00Z","timestamp":1728432000000},"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>Myasthenia Gravis (MG) is an autoimmune disease that causes muscle weakness in 80% of patients, most of whom test positive for anti-acetylcholine receptor (AChR) antibodies (AChR-Abs). Predicting and improving treatment outcomes are necessary due to varying responses, ranging from complete relief to minimal improvement.<\/jats:p><\/jats:sec><jats:sec><jats:title>Objective<\/jats:title><jats:p>Our study aims to develop and validate an interpretable machine learning (ML) model that integrates systemic inflammation indices with traditional clinical indicators. The goal is to predict the short-term prognosis (after 6\u2009months of treatment) of AChR-Ab+ generalized myasthenia gravis (GMG) patients to guide personalized treatment strategies.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>We performed a retrospective analysis on 202 AChR-Ab+ GMG patients, dividing them into training and external validation cohorts. The primary outcome of this study was the Myasthenia Gravis Foundation of America (MGFA) post-intervention status assessed after 6\u2009months of treatment initiation. Prognoses were classified as \u201cunchanged or worse\u201d for a poor outcome and \u201cimproved or better\u201d for a good outcome. Accordingly, patients were categorized into \u201cgood outcome\u201d or \u201cpoor outcome\u201d groups. In the training cohort, we developed and internally validated various ML models using systemic inflammation indices, clinical indicators, or a combination of both. We then carried out external validation with the designated cohort. Additionally, we assessed the feature importance of our most effective model using the Shapley Additive Explanations (SHAP) method.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>In our study of 202 patients, 28.7% (58 individuals) experienced poor outcomes after 6\u2009months of standard therapy. We identified 11 significant predictors, encompassing both systemic inflammation indexes and clinical metrics. The extreme gradient boosting (XGBoost) model demonstrated the best performance, achieving an area under the receiver operating characteristic (ROC) curve (AUC) of 0.944. This was higher than that achieved by logistic regression (Logit) (AUC: 0.882), random forest (RF) (AUC: 0.917), support vector machines (SVM) (AUC: 0.872). Further refinement through SHAP analysis highlighted five critical determinants\u2014two clinical indicators and three inflammation indexes\u2014as crucial for assessing short-term prognosis in AChR-Ab+ GMG patients.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>Our analysis confirms that the XGBoost model, integrating clinical indicators with systemic inflammation indexes, effectively predicts short-term prognosis in AChR-Ab+ GMG patients. This approach enhances clinical decision-making and improves patient outcomes.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fneur.2024.1459555","type":"journal-article","created":{"date-parts":[[2024,10,9]],"date-time":"2024-10-09T04:54:07Z","timestamp":1728449647000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Interpretable machine learning models for predicting short-term prognosis in AChR-Ab+ generalized myasthenia gravis using clinical features and systemic inflammation index"],"prefix":"10.3389","volume":"15","author":[{"given":"Yanan","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meng","family":"Pan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao","family":"Jia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenbin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiqi","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liqin","family":"Luan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2024,10,9]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1038\/s41572-019-0079-y","article-title":"Myasthenia gravis","volume":"5","author":"Gilhus","year":"2019","journal-title":"Nat Rev Dis Primers"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1016\/j.ncl.2018.01.002","article-title":"Generalized myasthenia gravis: classification, clinical presentation, natural history, and epidemiology","volume":"36","author":"Hehir","year":"2018","journal-title":"Neurol Clin"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"1054","DOI":"10.1212\/wnl.26.11.1054","article-title":"Antibody to acetylcholine receptor in myasthenia gravis. Prevalence, clinical correlates, and diagnostic value","volume":"26","author":"Lindstrom","year":"1976","journal-title":"Neurology"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1097\/cnd.0000000000000034","article-title":"Treatment-refractory myasthenia gravis","volume":"15","author":"Silvestri","year":"2014","journal-title":"J Clin Neuromuscul Dis"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"419","DOI":"10.1212\/wnl.0000000000002790","article-title":"International consensus guidance for management of myasthenia gravis: executive summary","volume":"87","author":"Sanders","year":"2016","journal-title":"Neurology"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"551","DOI":"10.1007\/s40120-024-00590-0","article-title":"Constructing and validating a nomogram model for short-term prognosis of patients with AChR-Ab+ GMG","volume":"13","author":"Liang","year":"2024","journal-title":"Neurol Ther"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1186\/s12967-021-02961-9","article-title":"Nomogram for short-term outcome assessment in AChR subtype generalized myasthenia gravis","volume":"19","author":"Zhao","year":"2021","journal-title":"J Transl Med"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"1785","DOI":"10.3389\/fimmu.2017.01785","article-title":"Immunopathogenesis in myasthenia gravis and neuromyelitis optica","volume":"8","author":"Wang","year":"2017","journal-title":"Front Immunol"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"366","DOI":"10.1111\/cei.13546","article-title":"Roles of cytokines and T cells in the pathogenesis of myasthenia gravis","volume":"203","author":"Uzawa","year":"2021","journal-title":"Clin Exp Immunol"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"841","DOI":"10.1007\/s10654-021-00752-6","article-title":"Systemic inflammation markers and cancer incidence in the UK Biobank","volume":"36","author":"N\u00f8st","year":"2021","journal-title":"Eur J Epidemiol"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"372","DOI":"10.3109\/14397595.2015.1091136","article-title":"Neutrophil to lymphocyte ratio (NLR) and platelet to lymphocyte ratio (PLR) were useful markers in assessment of inflammatory response and disease activity in SLE patients","volume":"26","author":"Qin","year":"2016","journal-title":"Mod Rheumatol"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"345","DOI":"10.3343\/alm.2019.39.4.345","article-title":"The platelet-to-lymphocyte ratio as an inflammatory marker in rheumatic diseases","volume":"39","author":"Gasparyan","year":"2019","journal-title":"Ann Lab Med"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1186\/s12883-021-02432-0","article-title":"Association of neutrophil-to-lymphocyte ratio (NLR) with the prognosis of first attack neuromyelitis optica spectrum disorder (NMOSD): a retrospective cohort study","volume":"21","author":"Xie","year":"2021","journal-title":"BMC Neurol"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"675","DOI":"10.1016\/j.beth.2020.05.002","article-title":"Supervised machine learning: a brief primer","volume":"51","author":"Jiang","year":"2020","journal-title":"Behav Ther"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"10473","DOI":"10.1007\/s00432-023-04956-z","article-title":"Machine learning and deep learning techniques for breast cancer diagnosis and classification: a comprehensive review of medical imaging studies","volume":"149","author":"Radak","year":"2023","journal-title":"J Cancer Res Clin Oncol"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"10760296241259784","DOI":"10.1177\/10760296241259784","article-title":"Interpretable machine learning models using peripheral immune cells to predict 90-day readmission or mortality in acute heart failure patients","volume":"30","author":"Chen","year":"2024","journal-title":"Clin Appl Thromb Hemost"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"17562864231154976","DOI":"10.1177\/17562864231154976","article-title":"Short-term outcome prediction for myasthenia gravis: an explainable machine learning model","volume":"16","author":"Zhong","year":"2023","journal-title":"Ther Adv Neurol Disord"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1002\/mus.27247","article-title":"Assessment of clinical factors affecting outcome of myasthenia gravis","volume":"64","author":"Yoshimoto","year":"2021","journal-title":"Muscle Nerve"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"197","DOI":"10.2147\/ijnrd.s461028","article-title":"Comparative analysis of logistic regression, gradient boosted trees, SVM, and random forest algorithms for prediction of acute kidney injury requiring dialysis after cardiac surgery","volume":"17","author":"Omar","year":"2024","journal-title":"Int J Nephrol Renovasc Dis"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"e20928","DOI":"10.1016\/j.heliyon.2023.e20928","article-title":"Application of machine learning algorithms to predict lymph node metastasis in gastric neuroendocrine neoplasms","volume":"9","author":"Liu","year":"2023","journal-title":"Heliyon"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"908","DOI":"10.1097\/j.pain.0000000000003089","article-title":"Machine learning study of the extended drug-target interaction network informed by pain related voltage-gated sodium channels","volume":"165","author":"Chen","year":"2024","journal-title":"Pain"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"e14848","DOI":"10.1111\/cns.14848","article-title":"Machine learning-based prediction of clinical outcomes after traumatic brain injury: hidden information of early physiological time series","volume":"30","author":"Ding","year":"2024","journal-title":"CNS Neurosci Ther"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"1451","DOI":"10.1007\/s00259-023-06513-9","article-title":"Prediction of therapy response of breast cancer patients with machine learning based on clinical data and imaging data derived from breast [18F]FDG-PET\/MRI","volume":"51","author":"Jannusch","year":"2024","journal-title":"Eur J Nucl Med Mol Imaging"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1109\/MIS.2020.2978066","article-title":"An evaluation of four resampling methods used in machine learning classification","volume":"36","author":"Nakatsu","year":"2020","journal-title":"IEEE Intell Syst"},{"key":"ref25","first-page":"4768","article-title":"A unified approach to interpreting model predictions","author":"Lundberg","year":"2017"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"362","DOI":"10.1016\/j.omtn.2020.08.022","article-title":"An interpretable prediction model for identifying N7-methylguanosine sites based on XGBoost and SHAP","volume":"22","author":"Bi","year":"2020","journal-title":"Mol Ther Nucleic Acids"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"106130","DOI":"10.1016\/j.intimp.2019.106130","article-title":"Comparison of peripheral blood B cell subset ratios and B cell-related cytokine levels between ocular and generalized myasthenia gravis","volume":"80","author":"Hu","year":"2020","journal-title":"Int Immunopharmacol"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1186\/s12911-019-1004-8","article-title":"Comparing different supervised machine learning algorithms for disease prediction","volume":"19","author":"Uddin","year":"2019","journal-title":"BMC Med Inform Decis Mak"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"128442","DOI":"10.1016\/j.conbuildmat.2022.128442","article-title":"Machine learning prediction models for compressive strength of calcined sludge-cement composites","volume":"346","author":"Zhang","year":"2022","journal-title":"Constr Build Mater"},{"key":"ref30","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":"ref31","doi-asserted-by":"publisher","first-page":"e212240","DOI":"10.1001\/jamanetworkopen.2021.2240","article-title":"Use of machine learning to develop and evaluate models using preoperative and intraoperative data to identify risks of postoperative complications","volume":"4","author":"Xue","year":"2021","journal-title":"JAMA Netw Open"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"1497","DOI":"10.1212\/wnl.41.9.1497","article-title":"Inflammation at the neuromuscular junction in myasthenia gravis","volume":"41","author":"Maselli","year":"1991","journal-title":"Neurology"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"102337","DOI":"10.1016\/j.jaut.2019.102337","article-title":"Risk factors associated with myasthenia gravis in thymoma patients: the potential role of thymic germinal centers","volume":"106","author":"Lefeuvre","year":"2020","journal-title":"J Autoimmun"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"314","DOI":"10.21037\/jtd.2016.03.03","article-title":"Increased frequency of thymic T follicular helper cells in myasthenia gravis patients with thymoma","volume":"8","author":"Song","year":"2016","journal-title":"J Thorac Dis"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"e0205464","DOI":"10.1371\/journal.pone.0205464","article-title":"MicroRNA and mRNA expression associated with ectopic germinal centers in thymus of myasthenia gravis","volume":"13","author":"Sengupta","year":"2018","journal-title":"PLoS One"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"3","DOI":"10.3390\/diagnostics12030593","article-title":"Systematic review of prognostic role of blood cell ratios in patients with gastric cancer undergoing surgery","volume":"12","author":"Schiefer","year":"2022","journal-title":"Diagnostics"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"692","DOI":"10.3390\/jpm12060992","article-title":"Blood cell count inflammatory markers as prognostic indicators of periodontitis: a systematic review and meta-analysis","volume":"12","author":"Alm\u0103\u0219an","year":"2022","journal-title":"J Pers Med"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"1223","DOI":"10.1007\/s10072-021-05420-x","article-title":"Increased systemic immune-inflammation index can predict respiratory failure in patients with Guillain\u2013Barr\u00e9 syndrome","volume":"43","author":"Wu","year":"2022","journal-title":"Neurol Sci"}],"container-title":["Frontiers in Neurology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2024.1459555\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,9]],"date-time":"2024-10-09T04:54:09Z","timestamp":1728449649000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2024.1459555\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,9]]},"references-count":38,"alternative-id":["10.3389\/fneur.2024.1459555"],"URL":"https:\/\/doi.org\/10.3389\/fneur.2024.1459555","relation":{},"ISSN":["1664-2295"],"issn-type":[{"value":"1664-2295","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,9]]},"article-number":"1459555"}}