{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T22:34:42Z","timestamp":1789511682074,"version":"build-2803163510"},"reference-count":38,"publisher":"Journal of Neurosurgery Publishing Group (JNSPG)","issue":"4","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,1]]},"abstract":"<jats:sec>\n<jats:title>OBJECTIVE<\/jats:title>\n<jats:p>Cerebral infarction is a common complication in patients undergoing revascularization surgery for moyamoya disease (MMD). Although previous statistical evaluations have identified several risk factors for postoperative brain ischemia, the ability to predict its occurrence based on these limited predictors remains inadequately explored. This study aimed to assess the feasibility of machine learning algorithms for predicting cerebral infarction after revascularization surgery in patients with MMD.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title>METHODS<\/jats:title>\n<jats:p>This retrospective study was conducted across two centers and harnessed data from 512 patients with MMD who had undergone revascularization surgery. The patient cohort was partitioned into internal and external datasets. Using perioperative clinical data from the internal cohort, three distinct machine learning algorithms\u2014namely the support vector machine, random forest, and light gradient-boosting machine models\u2014were trained and cross-validated to predict the occurrence of postoperative cerebral infarction. Predictive performance validity was subsequently assessed using an external dataset. Shapley additive explanations (SHAP) analysis was conducted to augment the prediction model\u2019s transparency and to quantify the impact of each input variable on shaping both the aggregate and individual patient predictions.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title>RESULTS<\/jats:title>\n<jats:p>In the cohort of 512 patients, 33 (6.4%) experienced postrevascularization cerebral infarction. The cross-validation outcomes revealed that, among the three models, the support vector machine model achieved the largest area under the receiver operating characteristic curve (ROC-AUC) at mean \u00b1 SD 0.785 \u00b1 0.052. Notably, during external validation, the light gradient-boosting machine model exhibited the highest accuracy at 0.903 and the largest ROC-AUC at 0.710. The top-performing prediction model utilized five input variables: postoperative serum gamma-glutamyl transpeptidase value, positive posterior cerebral artery (PCA) involvement on preoperative MRA, infarction as the rationale for surgery, presence of an infarction scar on preoperative MRI, and preoperative modified Rankin Scale score. Furthermore, the SHAP analysis identified presence of PCA involvement, infarction as the rationale for surgery, and presence of an infarction scar on preoperative MRI as positive influences on postoperative cerebral infarction.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title>CONCLUSIONS<\/jats:title>\n<jats:p>This study indicates the usefulness of employing machine learning techniques with routine perioperative data to predict the occurrence of cerebral infarction after revascularization procedures in patients with MMD.<\/jats:p>\n<\/jats:sec>","DOI":"10.3171\/2024.1.jns232173","type":"journal-article","created":{"date-parts":[[2024,4,6]],"date-time":"2024-04-06T00:40:58Z","timestamp":1712364058000},"page":"927-935","source":"Crossref","is-referenced-by-count":9,"title":["Development and validation of machine learning models to predict postoperative infarction in moyamoya disease"],"prefix":"10.3171","volume":"141","author":[{"given":"Yutaro","family":"Fuse","sequence":"first","affiliation":[{"name":"Department of Neurosurgery, Nagoya University Graduate School of Medicine, Nagoya, Aichi;"},{"name":"Academia-Industry collaboration platform for cultivating Medical AI Leaders (AI-MAILs), Nagoya University Graduate School of Medicine, Nagoya, Aichi;"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kazuki","family":"Ishii","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, Nagoya University Graduate School of Medicine, Nagoya, Aichi;"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fumiaki","family":"Kanamori","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, Nagoya University Graduate School of Medicine, Nagoya, Aichi;"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shintaro","family":"Oyama","sequence":"additional","affiliation":[{"name":"Academia-Industry collaboration platform for cultivating Medical AI Leaders (AI-MAILs), Nagoya University Graduate School of Medicine, Nagoya, Aichi;"},{"name":"Innovative Research Center for Preventive Medical Engineering, Nagoya University, Nagoya, Aichi;"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takahiro","family":"Imaizumi","sequence":"additional","affiliation":[{"name":"Department of Advanced Medicine, Nagoya University Hospital, Nagoya, Aichi;"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yoshio","family":"Araki","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, Nagoya University Graduate School of Medicine, Nagoya, Aichi;"},{"name":"Department of Neurosurgery, Japanese Red Cross Aichi Medical Center Nagoya Daini Hospital, Nagoya, Aichi; and"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kinya","family":"Yokoyama","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, Nagoya University Graduate School of Medicine, Nagoya, Aichi;"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Syuntaro","family":"Takasu","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, Japan Community Health Care Organization Chukyo Hospital, Nagoya, Aichi, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yukio","family":"Seki","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, Japanese Red Cross Aichi Medical Center Nagoya Daini Hospital, Nagoya, Aichi; and"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ryuta","family":"Saito","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, Nagoya University Graduate School of Medicine, Nagoya, Aichi;"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1754","reference":[{"issue":"3","key":"b1","series-title":"Arch Neurol","first-page":"288","article-title":"Cerebrovascular \"moyamoya\" disease. Disease showing abnormal net-like vessels in base of brain","volume":"20","author":"Suzuki J","year":"1969","unstructured":"Suzuki J, Takaku A. Cerebrovascular \"moyamoya\" disease. Disease showing abnormal net-like vessels in base of brain. Arch Neurol. 1969;20(3):288\u2013299."},{"issue":"5","key":"b2","series-title":"Stroke","first-page":"1415","article-title":"Effects of extracranial-intracranial bypass for patients with hemorrhagic moyamoya disease: results of the Japan Adult Moyamoya Trial","volume":"45","author":"Miyamoto S","year":"2014","unstructured":"Miyamoto S, Yoshimoto T, Hashimoto N,  Effects of extracranial-intracranial bypass for patients with hemorrhagic moyamoya disease: results of the Japan Adult Moyamoya Trial. Stroke. 2014;45(5):1415\u20131421."},{"issue":"5","key":"b3","series-title":"J Neurosurg","first-page":"927","article-title":"Clinical outcome after 450 revascularization procedures for moyamoya disease. Clinical article","volume":"111","author":"Guzman R","year":"2009","unstructured":"Guzman R, Lee M, Achrol A,  Clinical outcome after 450 revascularization procedures for moyamoya disease. Clinical article. J Neurosurg. 2009;111(5):927\u2013935."},{"issue":"2","key":"b4","series-title":"J Neurosurg","first-page":"400","article-title":"Unstable moyamoya disease: clinical features and impact on perioperative ischemic complications","volume":"122","author":"Funaki T","year":"2015","unstructured":"Funaki T, Takahashi JC, Takagi Y,  Unstable moyamoya disease: clinical features and impact on perioperative ischemic complications. J Neurosurg. 2015;122(2):400\u2013407."},{"issue":"5 Suppl","key":"b5","series-title":"J Neurosurg","first-page":"433","article-title":"Risk factors for postoperative ischemic complications in patients with moyamoya disease","volume":"103","author":"Kim SH","year":"2005","unstructured":"Kim SH, Choi JU, Yang KH, Kim TG, Kim DS. Risk factors for postoperative ischemic complications in patients with moyamoya disease. J Neurosurg. 2005;103(5 Suppl):433-438."},{"issue":"2","key":"b6","series-title":"J Neurosurg","first-page":"1","article-title":"Risk factors for and outcomes of postoperative complications in adult patients with moyamoya disease","volume":"130","author":"Zhao M","year":"2018","unstructured":"Zhao M, Deng X, Zhang D,  Risk factors for and outcomes of postoperative complications in adult patients with moyamoya disease. J Neurosurg. 2018;130(2):1\u201312."},{"issue":"6","key":"b7","series-title":"Neurosurgery","first-page":"1120","article-title":"The relevance of hemodynamic factors to perioperative ischemic complications in childhood moyamoya disease","volume":"38","author":"Iwama T","year":"1996","unstructured":"Iwama T, Hashimoto N, Yonekawa Y. The relevance of hemodynamic factors to perioperative ischemic complications in childhood moyamoya disease. Neurosurgery. 1996;38(6):1120\u20131126."},{"issue":"1-3","key":"b8","series-title":"Acta Neurochir (Wien)","first-page":"26","article-title":"Peri-operative complications in adult moyamoya disease","volume":"132","author":"Iwama T","year":"1995","unstructured":"Iwama T, Hashimoto N, Tsukahara T, Murai B. Peri-operative complications in adult moyamoya disease. Acta Neurochir (Wien). 1995;132(1-3):26\u201331."},{"issue":"3","key":"b9","series-title":"Neurosurgery","first-page":"587","article-title":"Sex differences in clinical presentation and treatment outcomes in Moyamoya disease","volume":"71","author":"Khan N","year":"2012","unstructured":"Khan N, Achrol AS, Guzman R,  Sex differences in clinical presentation and treatment outcomes in Moyamoya disease. Neurosurgery. 2012;71(3):587\u2013593."},{"issue":"1","key":"b10","series-title":"BMC Neurol","first-page":"98","article-title":"Risk factors for postoperative stroke in adults patients with moyamoya disease: a systematic review with meta-analysis","volume":"19","author":"Wei W","year":"2019","unstructured":"Wei W, Chen X, Yu J, Li XQ. Risk factors for postoperative stroke in adults patients with moyamoya disease: a systematic review with meta-analysis. BMC Neurol. 2019;19(1):98."},{"issue":"1","key":"b11","series-title":"Cerebrovasc Dis","first-page":"41","article-title":"Proposal for a new grading of Moyamoya disease in adult patients","volume":"32","author":"Czabanka M","year":"2011","unstructured":"Czabanka M, Pe\u00f1a-Tapia P, Schubert GA,  Proposal for a new grading of Moyamoya disease in adult patients. Cerebrovasc Dis. 2011;32(1):41\u201350."},{"issue":"1","key":"b12","series-title":"Sci Rep","first-page":"5726","article-title":"Risk factors and a novel cerebral infarction extent scoring system for postoperative cerebral ischemia in patients with ischemic Moyamoya disease","volume":"13","author":"Chen Y","year":"2023","unstructured":"Chen Y, Gong X, Yang Z, Chen F, Wang J. Risk factors and a novel cerebral infarction extent scoring system for postoperative cerebral ischemia in patients with ischemic Moyamoya disease. Sci Rep. 2023;13(1):5726."},{"issue":"13","key":"b13","series-title":"N Engl J Med","first-page":"1216","article-title":"Predicting the future\u2014big data, machine learning, and clinical medicine","volume":"375","author":"Obermeyer Z","year":"2016","unstructured":"Obermeyer Z, Emanuel EJ. Predicting the future\u2014big data, machine learning, and clinical medicine. N Engl J Med. 2016;375(13):1216\u20131219."},{"issue":"3","key":"b14","series-title":"Intensive Care Med","first-page":"383","article-title":"Machine learning for the prediction of sepsis: a systematic review and meta-analysis of diagnostic test accuracy","volume":"46","author":"Fleuren LM","year":"2020","unstructured":"Fleuren LM, Klausch TLT, Zwager CL,  Machine learning for the prediction of sepsis: a systematic review and meta-analysis of diagnostic test accuracy. Intensive Care Med. 2020;46(3):383\u2013400."},{"issue":"1","key":"b15","series-title":"Nat Rev Mol Cell Biol","first-page":"40","article-title":"A guide to machine learning for biologists","volume":"23","author":"Greener JG","year":"2022","unstructured":"Greener JG, Kandathil SM, Moffat L, Jones DT. A guide to machine learning for biologists. Nat Rev Mol Cell Biol. 2022;23(1):40\u201355."},{"issue":"12","key":"b16","series-title":"J Clin Epidemiol","first-page":"1373","article-title":"A simulation study of the number of events per variable in logistic regression analysis","volume":"49","author":"Peduzzi P","year":"1996","unstructured":"Peduzzi P, Concato J, Kemper E, Holford TR, Feinstein AR. A simulation study of the number of events per variable in logistic regression analysis. J Clin Epidemiol. 1996;49(12):1373\u20131379."},{"issue":"3","key":"b17","series-title":"Perspect Clin Res","first-page":"148","article-title":"Common pitfalls in statistical analysis: logistic regression","volume":"8","author":"Ranganathan P","year":"2017","unstructured":"Ranganathan P, Pramesh CS, Aggarwal R. Common pitfalls in statistical analysis: logistic regression. Perspect Clin Res. 2017;8(3):148\u2013151."},{"key":"b18","series-title":"Int J Med Inform","first-page":"104484","article-title":"Comparison of machine learning and logistic regression models in predicting acute kidney injury: a systematic review and meta-analysis","volume":"151","author":"Song X","year":"2021","unstructured":"Song X, Liu X, Liu F, Wang C. Comparison of machine learning and logistic regression models in predicting acute kidney injury: a systematic review and meta-analysis. Int J Med Inform. 2021;151:104484."},{"key":"b19","series-title":"Mach Learn","first-page":"5","article-title":"Random forests","volume":"45","author":"Breiman L","year":"2001","unstructured":"Breiman L. Random forests. Mach Learn. 2001;45:5\u201332."},{"key":"b20","article-title":"LightGBM: a highly efficient gradient boosting decision tree","author":"Ke G","unstructured":"Ke G, Meng Q, Finley T,  LightGBM: a highly efficient gradient boosting decision tree. Paper presented at: 31st Conference on Neural Information Processing Systems (NIPS); December 4-9, 2017; Long Beach, CA. Accessed February 8, 2024. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/6449f44a102fde848669bdd9eb6b76fa-Paper.pdf"},{"key":"b21","series-title":"J Artif Intell Res","first-page":"321","article-title":"SMOTE: synthetic minority over-sampling technique","volume":"16","author":"Chawla NV","year":"2002","unstructured":"Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP. SMOTE: synthetic minority over-sampling technique. J Artif Intell Res. 2002;16:321\u2013357."},{"issue":"7","key":"b22","series-title":"Stroke","first-page":"2299","article-title":"Prediction of recurrent ischemic stroke using registry data and machine learning methods: the Erlangen Stroke Registry","volume":"53","author":"Vodencarevic A","year":"2022","unstructured":"Vodencarevic A, Weing\u00e4rtner M, Caro JJ,  Prediction of recurrent ischemic stroke using registry data and machine learning methods: the Erlangen Stroke Registry. Stroke. 2022;53(7):2299\u20132306."},{"issue":"6","key":"b23","series-title":"JAMA Netw Open","first-page":"e2319420","article-title":"Development of a deep learning model for retinal memorrhage detection on head computed tomography in young children","volume":"6","author":"Gunturkun F","year":"2023","unstructured":"Gunturkun F, Bakir-Batu B, Siddiqui A,  Development of a deep learning model for retinal memorrhage detection on head computed tomography in young children. JAMA Netw Open. 2023;6(6):e2319420."},{"key":"b24","series-title":"Comput Methods Programs Biomed","first-page":"107161","article-title":"Application of explainable artificial intelligence for healthcare: a systematic review of the last decade (2011-2022)","volume":"226","author":"Loh HW","year":"2022","unstructured":"Loh HW, Ooi CP, Seoni S, Barua PD, Molinari F, Acharya UR. Application of explainable artificial intelligence for healthcare: a systematic review of the last decade (2011-2022). Comput Methods Programs Biomed. 2022;226:107161."},{"key":"b25","series-title":"World Neurosurg","first-page":"e190","article-title":"Postoperative cerebral infarction risk factors and postoperative management of pediatric patients with moyamoya disease","volume":"113","author":"Muraoka S","year":"2018","unstructured":"Muraoka S, Araki Y, Kondo G,  Postoperative cerebral infarction risk factors and postoperative management of pediatric patients with moyamoya disease. World Neurosurg. 2018;113:e190\u2013e199."},{"key":"b26","series-title":"World Neurosurg","first-page":"e325","article-title":"Surgical designs of revascularization for moyamoya disease: 15 years of experience in a single center","volume":"139","author":"Araki Y","year":"2020","unstructured":"Araki Y, Uda K, Yokoyama K,  Surgical designs of revascularization for moyamoya disease: 15 years of experience in a single center. World Neurosurg. 2020;139:e325\u2013e334."},{"key":"b27","series-title":"Stroke Vasc Interv Neurol","first-page":"e000759","article-title":"Two-piece craniotomy is associated with improved postoperative outcomes of combined revascularization in patients with moyamoya disease","volume":"3","author":"Kanamori F","year":"2023","unstructured":"Kanamori F, Takasu S, Hatano N, Araki Y, Seki Y, Saito R. Two-piece craniotomy is associated with improved postoperative outcomes of combined revascularization in patients with moyamoya disease. Stroke Vasc Interv Neurol. 2023;3:e000759."},{"issue":"1","key":"b28","series-title":"Neurosurg Rev","first-page":"87","article-title":"Effects of superficial temporal artery to middle cerebral artery bypass on postoperative infarction rates among young children (\u2264 5 years old) with moyamoya disease","volume":"46","author":"Takasu S","year":"2023","unstructured":"Takasu S, Kanamori F, Hatano N, Seki Y, Saito R. Effects of superficial temporal artery to middle cerebral artery bypass on postoperative infarction rates among young children (\u2264 5 years old) with moyamoya disease. Neurosurg Rev. 2023;46(1):87."},{"issue":"2","key":"b29","series-title":"Neurosurgery","first-page":"324","article-title":"Surgical treatment for pediatric moyamoya disease: use of the superficial temporal artery for both areas supplied by the anterior and middle cerebral arteries","volume":"40","author":"Suzuki Y","year":"1997","unstructured":"Suzuki Y, Negoro M, Shibuya M, Yoshida J, Negoro T, Watanabe K. Surgical treatment for pediatric moyamoya disease: use of the superficial temporal artery for both areas supplied by the anterior and middle cerebral arteries. Neurosurgery. 1997;40(2):324\u2013330."},{"issue":"1","key":"b30","series-title":"Bioinformatics","first-page":"112","article-title":"MissForest\u2014non-parametric missing value imputation for mixed-type data","volume":"28","author":"Stekhoven DJ","year":"2012","unstructured":"Stekhoven DJ, B\u00fchlmann P. MissForest\u2014non-parametric missing value imputation for mixed-type data. Bioinformatics. 2012;28(1):112\u2013118."},{"issue":"2","key":"b31","series-title":"Pituitary","first-page":"237","article-title":"Machine learning models predict delayed hyponatremia post-transsphenoidal surgery using clinically available features","volume":"26","author":"Fuse Y","year":"2023","unstructured":"Fuse Y, Takeuchi K, Nishiwaki H,  Machine learning models predict delayed hyponatremia post-transsphenoidal surgery using clinically available features. Pituitary. 2023;26(2):237\u2013249."},{"key":"b32","series-title":"J Mach Learn Res","first-page":"2825","article-title":"Scikit-learn: machine learning in Python","volume":"12","author":"Pedregosa F","year":"2011","unstructured":"Pedregosa F, Varoquaux G, Gramfort A,  Scikit-learn: machine learning in Python. J Mach Learn Res. 2011;12:2825\u20132830."},{"issue":"1","key":"b33","series-title":"Cancer","first-page":"32","article-title":"Index for rating diagnostic tests","volume":"3","author":"Youden WJ","year":"1950","unstructured":"Youden WJ. Index for rating diagnostic tests. Cancer. 1950;3(1):32\u201335."},{"key":"b34","article-title":"A unified approach to interpreting model predictions","author":"Lundberg SM","unstructured":"Lundberg SM, Lee SI. A unified approach to interpreting model predictions. Paper presented at: 31st Conference on Neural Information Processing Systems (NIPS); December 4-9, 2017; Long Beach, CA. Accessed February 8, 2024. https:\/\/papers.nips.cc\/paper_files\/paper\/2017\/file\/8a20a8621978632d76c43dfd28b67767-Paper.pdf"},{"issue":"10","key":"b35","series-title":"Acta Neurochir (Wien)","first-page":"1895","article-title":"Grading of moyamoya disease allows stratification for postoperative ischemia in bilateral revascularization surgery","volume":"158","author":"Czabanka M","year":"2016","unstructured":"Czabanka M, Boschi A, Acker G,  Grading of moyamoya disease allows stratification for postoperative ischemia in bilateral revascularization surgery. Acta Neurochir (Wien). 2016;158(10):1895\u20131900."},{"issue":"7","key":"b36","series-title":"Neurol Med Chir (Tokyo)","first-page":"307","article-title":"Diagnostic criteria for moyamoya disease\u20142021 revised version","volume":"62","author":"Kuroda S","year":"2022","unstructured":"Kuroda S, Fujimura M, Takahashi J,  Diagnostic criteria for moyamoya disease\u20142021 revised version. Neurol Med Chir (Tokyo). 2022;62(7):307\u2013312."},{"issue":"2","key":"b37","series-title":"Neurosurgery","first-page":"E264","article-title":"Validation and application for the Berlin grading system of moyamoya disease in adult patients","volume":"87","author":"Yu J","year":"2020","unstructured":"Yu J, Zhang J, Chen J. Validation and application for the Berlin grading system of moyamoya disease in adult patients. Neurosurgery. 2020;87(2):E264."},{"issue":"6","key":"b38","series-title":"Neurosurgery","first-page":"986","article-title":"Berlin grading system can stratify the onset and predict peri-operative complications in adult moyamoya disease","volume":"81","author":"Kashiwazaki D","year":"2017","unstructured":"Kashiwazaki D, Akioka N, Kuwayama N,  Berlin grading system can stratify the onset and predict peri-operative complications in adult moyamoya disease. Neurosurgery. 2017;81(6):986\u2013991."}],"container-title":["Journal of Neurosurgery"],"original-title":[],"link":[{"URL":"https:\/\/thejns.org\/view\/journals\/j-neurosurg\/141\/4\/article-p927.xml","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/thejns.org\/downloadpdf\/journals\/j-neurosurg\/141\/4\/article-p927.xml","content-type":"text\/html","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/thejns.org\/downloadpdf\/journals\/j-neurosurg\/141\/4\/article-p927.xml","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T11:45:19Z","timestamp":1732621519000},"score":1,"resource":{"primary":{"URL":"https:\/\/thejns.org\/view\/journals\/j-neurosurg\/141\/4\/article-p927.xml"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,1]]},"references-count":38,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.3171\/2024.1.jns232173","relation":{},"ISSN":["0022-3085","1933-0693"],"issn-type":[{"value":"0022-3085","type":"print"},{"value":"1933-0693","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,1]]}}}