{"title":"从医学数据中半自动提取预测和临床有意义的时间特征用于预测建模的路线图","authors":"Gang Luo","doi":"10.1016/j.glt.2018.11.001","DOIUrl":null,"url":null,"abstract":"<div><p>Predictive modeling based on machine learning with medical data has great potential to improve healthcare and reduce costs. However, two hurdles, among others, impede its widespread adoption in healthcare. First, medical data are by nature longitudinal. Pre-processing them, particularly for feature engineering, is labor intensive and often takes 50–80% of the model building effort. Predictive temporal features are the basis of building accurate models, but are difficult to identify. This is problematic. Healthcare systems have limited resources for model building, while inaccurate models produce suboptimal outcomes and are often useless. Second, most machine learning models provide no explanation of their prediction results. However, offering such explanations is essential for a model to be used in usual clinical practice. To address these two hurdles, this paper outlines: 1) a data-driven method for semi-automatically extracting predictive and clinically meaningful temporal features from medical data for predictive modeling; and 2) a method of using these features to automatically explain machine learning prediction results and suggest tailored interventions. This provides a roadmap for future research.</p></div>","PeriodicalId":33615,"journal":{"name":"Global Transitions","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/j.glt.2018.11.001","citationCount":"15","resultStr":"{\"title\":\"A roadmap for semi-automatically extracting predictive and clinically meaningful temporal features from medical data for predictive modeling\",\"authors\":\"Gang Luo\",\"doi\":\"10.1016/j.glt.2018.11.001\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Predictive modeling based on machine learning with medical data has great potential to improve healthcare and reduce costs. However, two hurdles, among others, impede its widespread adoption in healthcare. First, medical data are by nature longitudinal. Pre-processing them, particularly for feature engineering, is labor intensive and often takes 50–80% of the model building effort. Predictive temporal features are the basis of building accurate models, but are difficult to identify. This is problematic. Healthcare systems have limited resources for model building, while inaccurate models produce suboptimal outcomes and are often useless. Second, most machine learning models provide no explanation of their prediction results. However, offering such explanations is essential for a model to be used in usual clinical practice. To address these two hurdles, this paper outlines: 1) a data-driven method for semi-automatically extracting predictive and clinically meaningful temporal features from medical data for predictive modeling; and 2) a method of using these features to automatically explain machine learning prediction results and suggest tailored interventions. This provides a roadmap for future research.</p></div>\",\"PeriodicalId\":33615,\"journal\":{\"name\":\"Global Transitions\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2019-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://sci-hub-pdf.com/10.1016/j.glt.2018.11.001\",\"citationCount\":\"15\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Global Transitions\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2589791819300015\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"Social Sciences\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Global Transitions","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2589791819300015","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"Social Sciences","Score":null,"Total":0}
A roadmap for semi-automatically extracting predictive and clinically meaningful temporal features from medical data for predictive modeling
Predictive modeling based on machine learning with medical data has great potential to improve healthcare and reduce costs. However, two hurdles, among others, impede its widespread adoption in healthcare. First, medical data are by nature longitudinal. Pre-processing them, particularly for feature engineering, is labor intensive and often takes 50–80% of the model building effort. Predictive temporal features are the basis of building accurate models, but are difficult to identify. This is problematic. Healthcare systems have limited resources for model building, while inaccurate models produce suboptimal outcomes and are often useless. Second, most machine learning models provide no explanation of their prediction results. However, offering such explanations is essential for a model to be used in usual clinical practice. To address these two hurdles, this paper outlines: 1) a data-driven method for semi-automatically extracting predictive and clinically meaningful temporal features from medical data for predictive modeling; and 2) a method of using these features to automatically explain machine learning prediction results and suggest tailored interventions. This provides a roadmap for future research.