{"title":"Intracranial stenosis prediction using a small set of risk factors in the Tromsø Study.","authors":"Luca Bernecker, Liv-Hege Johnsen, Torgil Riise Vangberg","doi":"10.1186/s12911-025-02896-x","DOIUrl":null,"url":null,"abstract":"<p><p>Intracranial atherosclerotic stenosis (ICAS) refers to a narrowing of intracranial arteries due to plaque buildup on the inside of the vessel walls restricting blood flow. Early detection of ICAS is crucial to prevent serious consequences such as stroke. Here we apply three different machine learning methods, such as support vector machines, multi-layer perceptrons and Kolmogorov-Arnold Networks to predict ICAS according to sparse risk factors from blood lipids and demographic data, including smoking habits, age, sex, diabetes, blood pressure lowering and cholesterol-lowering drugs and high-density lipoprotein. We achieved similar performance on classification compared to modern detection algorithms for ICAS in TOF-MRA (time-of-flight magnetic resonance angiography). The prevalence of ICAS in the population is relatively low, which is often case in medicine. While in the medical research community, the issue of low prevalence is established, machine learning-based research in medicine often does not take into account a critical viewpoint of the prevalence in clinical settings of their methods. We showed that with a balanced training/test set an accuracy up to 81% was achievable, while with the inclusion of prevalence, the positive predictive value was at 19% to the prevalence data, changes the performance metrics. Therefore, we highlighted the discrepancy that can arise between the results reported by the models and their clinical relevance. Furthermore, the results demonstrate the predictive potential of limited risk factors, highlighting its potential contribution to a multi-modular classification algorithm based on MRAs.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"95"},"PeriodicalIF":3.3000,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11843764/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"BMC Medical Informatics and Decision Making","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1186/s12911-025-02896-x","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"MEDICAL INFORMATICS","Score":null,"Total":0}
引用次数: 0
Abstract
Intracranial atherosclerotic stenosis (ICAS) refers to a narrowing of intracranial arteries due to plaque buildup on the inside of the vessel walls restricting blood flow. Early detection of ICAS is crucial to prevent serious consequences such as stroke. Here we apply three different machine learning methods, such as support vector machines, multi-layer perceptrons and Kolmogorov-Arnold Networks to predict ICAS according to sparse risk factors from blood lipids and demographic data, including smoking habits, age, sex, diabetes, blood pressure lowering and cholesterol-lowering drugs and high-density lipoprotein. We achieved similar performance on classification compared to modern detection algorithms for ICAS in TOF-MRA (time-of-flight magnetic resonance angiography). The prevalence of ICAS in the population is relatively low, which is often case in medicine. While in the medical research community, the issue of low prevalence is established, machine learning-based research in medicine often does not take into account a critical viewpoint of the prevalence in clinical settings of their methods. We showed that with a balanced training/test set an accuracy up to 81% was achievable, while with the inclusion of prevalence, the positive predictive value was at 19% to the prevalence data, changes the performance metrics. Therefore, we highlighted the discrepancy that can arise between the results reported by the models and their clinical relevance. Furthermore, the results demonstrate the predictive potential of limited risk factors, highlighting its potential contribution to a multi-modular classification algorithm based on MRAs.
期刊介绍:
BMC Medical Informatics and Decision Making is an open access journal publishing original peer-reviewed research articles in relation to the design, development, implementation, use, and evaluation of health information technologies and decision-making for human health.