Machine learning classification analysis for a hypertensive population as a function of several risk factors
作者：
Highlights：
• Best AUC 0.73 (95% CI [0.70–0.76]) showing fair result with the final diagnosis.
• This model predicts correctly hypertensive individuals 73% better than a randomly selected individual.
• According to the model Kidney disease and smoking habits do not affect odds of the outcome.
• According to the model odds of having hypertension is higher for female individuals than for male.
• Non-Hispanic black have higher odds of having hypertension than the rest of ethnics groups.
摘要
•Best AUC 0.73 (95% CI [0.70–0.76]) showing fair result with the final diagnosis.•This model predicts correctly hypertensive individuals 73% better than a randomly selected individual.•According to the model Kidney disease and smoking habits do not affect odds of the outcome.•According to the model odds of having hypertension is higher for female individuals than for male.•Non-Hispanic black have higher odds of having hypertension than the rest of ethnics groups.
论文关键词：Logistic regression,Hypertension,Artificial intelligence,Diabetes,Blood pressure,Cardiovascular disease,NHANES
论文评审过程：Received 12 December 2017, Revised 21 March 2018, Accepted 3 June 2018, Available online 4 June 2018, Version of Record 18 June 2018.
论文官网地址：https://doi.org/10.1016/j.eswa.2018.06.006
