Predicting hypertension using machine learning: Findings from Qatar Biobank Study

Abstract

Background and objective Hypertension, a global burden, is associated with several risk factors and can be treated by lifestyle modifications and medications. Prediction and early diagnosis is important to prevent related health complications. The objective is to construct and compare predictive models to identify individuals at high risk of developing hypertension without the need of invasive clinical procedures. Methods This is a cross-sectional study using 987 records of Qataris and long-term residents aged 18 + years from Qatar Biobank. Percentages were used to summarize data and chi-square tests to assess associations. Predictive models of hypertension were constructed and compared using three supervised machine learning algorithms: decision tree, random forest, and logistics regression using 5-fold cross-validation. The performance of algorithms was assessed using accuracy, positive predictive value (PPV), sensitivity, F-measure, and area under the receiver operating characteristic curve (AUC). Stata and Weka were used for analysis. Results Age, gender, education level, employment, tobacco use, physical activity, adequate consumption of fruits and vegetables, abdominal obesity, history of diabetes, history of high cholesterol, and mother's history high blood pressure were important predictors of hypertension. All algorithms showed more or less similar performances:

Routine blood biomarkers for the detection of multiple myeloma using machine learning

“…F‐measure is the geometric mean of sensitivity and PPV and is used to determine the trade‐off between sensitivity and PPV 13 . The Matthews correlation coefficient (MCC) is favored over the F‐measure and accuracy when handling an unbalanced data set 14 . We also included the F‐measure and MCC to assess the performance of the algorithms.…”

“…We also included the F‐measure and MCC to assess the performance of the algorithms. Table shows the definitions of the different evaluation indices 14–16 …”

“…13 The Matthews correlation coefficient (MCC) is favored over the Fmeasure and accuracy when handling an unbalanced data set. 14 We also included the F-measure and MCC to assess the performance of the algorithms. Table S1 shows the definitions of the different evaluation indices.…”

“…Table S1 shows the definitions of the different evaluation indices. [14][15][16] Categorical data were represented as counts and percentages, and chi-square tests were used to assess associations. Numerical data were reported as median (interquartile range, IQR).…”

Challenges Experienced by Public Higher Education Institutions of Learning in the Implementation of Training and Development: A Case Study of Saudi Arabian Higher Education

“…It is possible that teachers are not familiar enough with the latest training techniques, such as group discussions and case study reviews, or that trainees cannot agree that these new methods have any real value, and therefore the introduction of new training methods is seen as time-consuming and wasteful(Llorent-Bedmar et al, 2020). Traditional and predictable training methods are most commonly used in Arab organizations, according to Atiyyah(AlKaabi et al, 2020). They are very limited in scope, with lectures being the most prevalent mode of information dissemination.…”