{"title":"BPPV治疗中机动次数的机器学习预测建模。","authors":"Mine Baydan-Aran, Kübra Binay-Bolat, Emre Söylemez, Orkun Tahir Aran","doi":"10.1177/09574271251351905","DOIUrl":null,"url":null,"abstract":"<p><p>ObjectiveSome patients with benign paroxysmal positional vertigo (BPPV) do not improve with a single maneuver and may require multiple maneuvers. This study aims to utilize machine learning (ML) to identify parameters predisposing multiple CRMs, thus enhancing the predictability of treatment requirements in BPPV patients.Study designRetrospective study.SettingHospital.PatientsThis study included 520 participants diagnosed with BPPV between 2018 and 2023, with a mean age of 56.2 ± 14.0 years.InterventionsAge, BPPV type, comorbid diseases, gender, and number of maneuvers that the patients recovered with were determined. The target outcome-\"number of maneuvers\"-was dichotomized as either one (0) or more than one (1). The models' success was evaluated using metrics such as precision, F1-score, accuracy, balanced accuracy, recall, area under the Receiver Operating Characteristic (ROC), and area under the curve (AUC).ResultsThe applied maneuver number to treat BPPV was 188 (36%) in one maneuver and 332 (67%) in more than one maneuvers. Gradient Boosting Machine (GBM) had the best AUC in maneuver number estimation. Also, logistic regression resulted the best precision score; XGBoost showed the best F1 and recall score while support vector classifier showed the best accuracy and balanced accuracy scores.ConclusionsMachine learning models with high predictive capabilities can help identify patients likely to need multiple maneuvers, allowing for more efficient treatment planning and enhanced patient outcomes.</p>","PeriodicalId":49960,"journal":{"name":"Journal of Vestibular Research-Equilibrium & Orientation","volume":" ","pages":"9574271251351905"},"PeriodicalIF":2.9000,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Predictive modeling of maneuver numbers in BPPV therapy using machine learning.\",\"authors\":\"Mine Baydan-Aran, Kübra Binay-Bolat, Emre Söylemez, Orkun Tahir Aran\",\"doi\":\"10.1177/09574271251351905\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>ObjectiveSome patients with benign paroxysmal positional vertigo (BPPV) do not improve with a single maneuver and may require multiple maneuvers. This study aims to utilize machine learning (ML) to identify parameters predisposing multiple CRMs, thus enhancing the predictability of treatment requirements in BPPV patients.Study designRetrospective study.SettingHospital.PatientsThis study included 520 participants diagnosed with BPPV between 2018 and 2023, with a mean age of 56.2 ± 14.0 years.InterventionsAge, BPPV type, comorbid diseases, gender, and number of maneuvers that the patients recovered with were determined. The target outcome-\\\"number of maneuvers\\\"-was dichotomized as either one (0) or more than one (1). The models' success was evaluated using metrics such as precision, F1-score, accuracy, balanced accuracy, recall, area under the Receiver Operating Characteristic (ROC), and area under the curve (AUC).ResultsThe applied maneuver number to treat BPPV was 188 (36%) in one maneuver and 332 (67%) in more than one maneuvers. Gradient Boosting Machine (GBM) had the best AUC in maneuver number estimation. Also, logistic regression resulted the best precision score; XGBoost showed the best F1 and recall score while support vector classifier showed the best accuracy and balanced accuracy scores.ConclusionsMachine learning models with high predictive capabilities can help identify patients likely to need multiple maneuvers, allowing for more efficient treatment planning and enhanced patient outcomes.</p>\",\"PeriodicalId\":49960,\"journal\":{\"name\":\"Journal of Vestibular Research-Equilibrium & Orientation\",\"volume\":\" \",\"pages\":\"9574271251351905\"},\"PeriodicalIF\":2.9000,\"publicationDate\":\"2025-06-13\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Vestibular Research-Equilibrium & Orientation\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1177/09574271251351905\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"NEUROSCIENCES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Vestibular Research-Equilibrium & Orientation","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1177/09574271251351905","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"NEUROSCIENCES","Score":null,"Total":0}
Predictive modeling of maneuver numbers in BPPV therapy using machine learning.
ObjectiveSome patients with benign paroxysmal positional vertigo (BPPV) do not improve with a single maneuver and may require multiple maneuvers. This study aims to utilize machine learning (ML) to identify parameters predisposing multiple CRMs, thus enhancing the predictability of treatment requirements in BPPV patients.Study designRetrospective study.SettingHospital.PatientsThis study included 520 participants diagnosed with BPPV between 2018 and 2023, with a mean age of 56.2 ± 14.0 years.InterventionsAge, BPPV type, comorbid diseases, gender, and number of maneuvers that the patients recovered with were determined. The target outcome-"number of maneuvers"-was dichotomized as either one (0) or more than one (1). The models' success was evaluated using metrics such as precision, F1-score, accuracy, balanced accuracy, recall, area under the Receiver Operating Characteristic (ROC), and area under the curve (AUC).ResultsThe applied maneuver number to treat BPPV was 188 (36%) in one maneuver and 332 (67%) in more than one maneuvers. Gradient Boosting Machine (GBM) had the best AUC in maneuver number estimation. Also, logistic regression resulted the best precision score; XGBoost showed the best F1 and recall score while support vector classifier showed the best accuracy and balanced accuracy scores.ConclusionsMachine learning models with high predictive capabilities can help identify patients likely to need multiple maneuvers, allowing for more efficient treatment planning and enhanced patient outcomes.
期刊介绍:
Journal of Vestibular Research is a peer-reviewed journal that publishes experimental and observational studies, review papers, and theoretical papers based on current knowledge of the vestibular system. Subjects of the studies can include experimental animals, normal humans, and humans with vestibular or other related disorders. Study topics can include the following:
Anatomy of the vestibular system, including vestibulo-ocular, vestibulo-spinal, and vestibulo-autonomic pathways
Balance disorders
Neurochemistry and neuropharmacology of balance, both at the systems and single neuron level
Neurophysiology of balance, including the vestibular, ocular motor, autonomic, and postural control systems
Psychophysics of spatial orientation
Space and motion sickness
Vestibular rehabilitation
Vestibular-related human performance in various environments