MACHINE LEARNING IN HYPERTENSION DETECTION: A STUDY ON WORLD HYPERTENSION DAY DATA

Objective: Many modifiable and non-modifiable risk factors have been associated with hypertension. However, current screening programs are still failing in identifying individuals at higher risk of hypertension. Given the major impact of high blood pressure on cardiovascular events and mortality, there is an urgent need to find new strategies to improve hypertension detection. We aimed to explore whether a machine learning (ML) algorithm can help identifying individual predictors of hypertension. Design and method: We analysed the data set generated by the questionnaires administered during the World Hypertension Day from 2015 to 2019. Demographic information (age, sex, BMI), self-reported information on cardio- vascular risk factors (hypertension, diabetes, smoking, high cholesterol, kidney disease, family history of cardiovascular diseases), sleep complaints (snoring, witnessed apneas, daytime sleepiness) and prior cardiovascular diseases (previous cardio and cerebrovascular events, previous myocardial infarction) as well as information about the awareness of hypertension and its health consequences were collected through the questionnaire. We computed the performance (sensitivity and specificity) of standard screening programmes as recommended by World Health Organisation and of five different ML algorithms, exploiting different balancing techniques (oversampling and undersampling). Results: A total of 20206 individuals (mean age 50.89 years, 51.65% females) have been included for analysis. Results show that a gain of sensitivity reflects in a loss of specificity, bringing to a scenario where there is not an algorithm and a configuration which properly outperforms against the others (Table 1). However, Random Forest provides the most interesting balance between sensitivity and specificity with a greater Area Under the Curve compared to the standard screening programs (Table 1). Conclusions: Detection of hypertension at a population level still remains challenging and a machine learning approach could help in making screening programs more precise and cost effective, when based on accurate data collection. More studies are needed to identify new features to be acquired and to further improve the performances of ML models. Table 1: Performance in the test set of the three experimented schemes, original, oversampling and undersampling the training set, and of the medical protocol evaluation.