{"title":"人工,但它智能吗?","authors":"Michael R Levitt, Jan Vargas","doi":"10.1136/jnis-2024-022412","DOIUrl":null,"url":null,"abstract":"This editorial was not written by a chatbot, but it could have been.1 The expansion of abilities in artificial intelligence and machine learning (AI/ML) has led to a dramatic uptake in a variety of disciplines, with particular excitement in medical diagnosis and prognosis. Aside from its increasingly common use in the detection of large vessel occlusion for rapid stroke triage,2 recent applications of AI/ML in neurointervention have included patient selection3 and prediction of functional outcomes in mechanical thrombectomy,4–6 detection of catheter complications or undesirable embolization during endovascular intervention,7–9 and identification of patients with procedurally challenging arterial anatomy,10 among many others, employing AI/ML applications across large language models and computer vision. The state of the science of AI/ML in clinical outcome prediction in particular was recently summarized in the pages of this journal.11 A meta-analysis of 60 studies that used AI/ML to predict postoperative outcomes or complication after cerebrovascular or neuroendovascular surgery for stroke, aneurysm, or cerebral vascular malformation found relatively favorable performance compared with standard clinical prediction scales (area under the receiver operator characteristics curve (AUROC) >0.85 in most cases). Typically, such performance would be considered acceptable for clinical use. However, only 16.7% of such studies included external validation, and many had a high risk of bias. Given the rapid evolution of AI/ML in neurointervention, it is tempting for the clinician to lean more and more on this technology for diagnosis, prognosis, and clinical decision-making. However, we identify areas of concern that must be addressed in …","PeriodicalId":16411,"journal":{"name":"Journal of NeuroInterventional Surgery","volume":null,"pages":null},"PeriodicalIF":4.5000,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Artificial, but is it intelligent?\",\"authors\":\"Michael R Levitt, Jan Vargas\",\"doi\":\"10.1136/jnis-2024-022412\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This editorial was not written by a chatbot, but it could have been.1 The expansion of abilities in artificial intelligence and machine learning (AI/ML) has led to a dramatic uptake in a variety of disciplines, with particular excitement in medical diagnosis and prognosis. Aside from its increasingly common use in the detection of large vessel occlusion for rapid stroke triage,2 recent applications of AI/ML in neurointervention have included patient selection3 and prediction of functional outcomes in mechanical thrombectomy,4–6 detection of catheter complications or undesirable embolization during endovascular intervention,7–9 and identification of patients with procedurally challenging arterial anatomy,10 among many others, employing AI/ML applications across large language models and computer vision. The state of the science of AI/ML in clinical outcome prediction in particular was recently summarized in the pages of this journal.11 A meta-analysis of 60 studies that used AI/ML to predict postoperative outcomes or complication after cerebrovascular or neuroendovascular surgery for stroke, aneurysm, or cerebral vascular malformation found relatively favorable performance compared with standard clinical prediction scales (area under the receiver operator characteristics curve (AUROC) >0.85 in most cases). Typically, such performance would be considered acceptable for clinical use. However, only 16.7% of such studies included external validation, and many had a high risk of bias. Given the rapid evolution of AI/ML in neurointervention, it is tempting for the clinician to lean more and more on this technology for diagnosis, prognosis, and clinical decision-making. However, we identify areas of concern that must be addressed in …\",\"PeriodicalId\":16411,\"journal\":{\"name\":\"Journal of NeuroInterventional Surgery\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":4.5000,\"publicationDate\":\"2024-10-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of NeuroInterventional Surgery\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1136/jnis-2024-022412\",\"RegionNum\":1,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"NEUROIMAGING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of NeuroInterventional Surgery","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1136/jnis-2024-022412","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"NEUROIMAGING","Score":null,"Total":0}
This editorial was not written by a chatbot, but it could have been.1 The expansion of abilities in artificial intelligence and machine learning (AI/ML) has led to a dramatic uptake in a variety of disciplines, with particular excitement in medical diagnosis and prognosis. Aside from its increasingly common use in the detection of large vessel occlusion for rapid stroke triage,2 recent applications of AI/ML in neurointervention have included patient selection3 and prediction of functional outcomes in mechanical thrombectomy,4–6 detection of catheter complications or undesirable embolization during endovascular intervention,7–9 and identification of patients with procedurally challenging arterial anatomy,10 among many others, employing AI/ML applications across large language models and computer vision. The state of the science of AI/ML in clinical outcome prediction in particular was recently summarized in the pages of this journal.11 A meta-analysis of 60 studies that used AI/ML to predict postoperative outcomes or complication after cerebrovascular or neuroendovascular surgery for stroke, aneurysm, or cerebral vascular malformation found relatively favorable performance compared with standard clinical prediction scales (area under the receiver operator characteristics curve (AUROC) >0.85 in most cases). Typically, such performance would be considered acceptable for clinical use. However, only 16.7% of such studies included external validation, and many had a high risk of bias. Given the rapid evolution of AI/ML in neurointervention, it is tempting for the clinician to lean more and more on this technology for diagnosis, prognosis, and clinical decision-making. However, we identify areas of concern that must be addressed in …
期刊介绍:
The Journal of NeuroInterventional Surgery (JNIS) is a leading peer review journal for scientific research and literature pertaining to the field of neurointerventional surgery. The journal launch follows growing professional interest in neurointerventional techniques for the treatment of a range of neurological and vascular problems including stroke, aneurysms, brain tumors, and spinal compression.The journal is owned by SNIS and is also the official journal of the Interventional Chapter of the Australian and New Zealand Society of Neuroradiology (ANZSNR), the Canadian Interventional Neuro Group, the Hong Kong Neurological Society (HKNS) and the Neuroradiological Society of Taiwan.