{"title":"睡眠阶段评分的智能助手","authors":"J. Bentrup","doi":"10.1109/CBMS.1992.244932","DOIUrl":null,"url":null,"abstract":"An intelligent assistant for sleep stage scoring is currently being developed. Due to the complexities and variations in the sleep signals, it is quite common that the system will initially be unable to correctly classify portions of the sleep signals. However, the system works in conjunction with somnologists, or human sleep stage scoring experts, and actively seeks their advice when it is unable to reliably decide on its own. The system incorporates the human guidance into its own knowledge base and continues with its scoring. The emphasis is on finding ways to produce reliable classifications in a domain that is at times very difficult to categorize. This reliability is critical if the physicians, in reaching their diagnoses and recommendations, are to rely on the machine's output. The system has successfully scored 156 test cases with an overall 92% epoch-by-epoch agreement with the human expert.<<ETX>>","PeriodicalId":197891,"journal":{"name":"[1992] Proceedings Fifth Annual IEEE Symposium on Computer-Based Medical Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1992-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"An intelligent assistant for sleep stage scoring\",\"authors\":\"J. Bentrup\",\"doi\":\"10.1109/CBMS.1992.244932\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"An intelligent assistant for sleep stage scoring is currently being developed. Due to the complexities and variations in the sleep signals, it is quite common that the system will initially be unable to correctly classify portions of the sleep signals. However, the system works in conjunction with somnologists, or human sleep stage scoring experts, and actively seeks their advice when it is unable to reliably decide on its own. The system incorporates the human guidance into its own knowledge base and continues with its scoring. The emphasis is on finding ways to produce reliable classifications in a domain that is at times very difficult to categorize. This reliability is critical if the physicians, in reaching their diagnoses and recommendations, are to rely on the machine's output. The system has successfully scored 156 test cases with an overall 92% epoch-by-epoch agreement with the human expert.<<ETX>>\",\"PeriodicalId\":197891,\"journal\":{\"name\":\"[1992] Proceedings Fifth Annual IEEE Symposium on Computer-Based Medical Systems\",\"volume\":\"1 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1992-06-14\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"[1992] Proceedings Fifth Annual IEEE Symposium on Computer-Based Medical Systems\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/CBMS.1992.244932\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"[1992] Proceedings Fifth Annual IEEE Symposium on Computer-Based Medical Systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CBMS.1992.244932","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
An intelligent assistant for sleep stage scoring is currently being developed. Due to the complexities and variations in the sleep signals, it is quite common that the system will initially be unable to correctly classify portions of the sleep signals. However, the system works in conjunction with somnologists, or human sleep stage scoring experts, and actively seeks their advice when it is unable to reliably decide on its own. The system incorporates the human guidance into its own knowledge base and continues with its scoring. The emphasis is on finding ways to produce reliable classifications in a domain that is at times very difficult to categorize. This reliability is critical if the physicians, in reaching their diagnoses and recommendations, are to rely on the machine's output. The system has successfully scored 156 test cases with an overall 92% epoch-by-epoch agreement with the human expert.<>