Telemedicine against CoVID-19 crisis

Diagnosis of Coronary Artery Disease based on Machine Learning algorithms Support Vector Machine, Artificial Neural Network, and Random Forest

Background

Coronary artery disease (CAD) is known as the most common cardiovascular disease. The development of CAD is influenced by several risk factors. Diagnostic and therapeutic methods of this disease have many and costly side effects. Therefore, researchers are looking for cost-effective and accurate methods to diagnose this disease. Machine learning algorithms can help specialists diagnose the disease early. The aim of this study is to detect CAD using machine learning algorithms.

Materials and Methods

In this study, three data mining algorithms support vector machine (SVM), artificial neural network (ANN), and random forest were used to predict CAD using the Isfahan Cohort Study dataset of Isfahan Cardiovascular Research Center. 19 features with 11495 records from this dataset were used for this research.

Results

All three algorithms achieved relatively close results. However, the SVM had the highest accuracy compared to the other techniques. The accuracy was calculated as 89.73% for SVM. The ANN algorithm also obtained the high area under the curve, sensitivity and accuracy and provided acceptable performance. Age, sex, Sleep satisfaction, history of stroke, history of palpitations, and history of heart disease were most correlated with target class. Eleven rules were also extracted from this dataset with high confidence and support.

Conclusion

In this study, it was shown that machine learning algorithms can be used with high accuracy to detect CAD. Thus, it allows physicians to perform timely preventive treatment in patients with CAD.

An Integrated Community-Based Blood Pressure Telemonitoring Program - A Population-Based Observational Study

BACKGROUND

Home blood pressure telemonitoring (BPT) has been shown to improve blood pressure control. A community-based BPT program (the Health+ program) was launched in 2015 in an urban area around a medical center.

OBJECTIVES

To examine the impact of the BPT program on the use of medical resources.

METHODS

We conducted a retrospective propensity-score (PS)-matched observational cohort study using the National Health Insurance Research Database (NHIRD) 2013-2016 in Taiwan. A total of 9,546 adults with a high risk of cardiovascular disease participated in the integrated BPT program, and 19,082 PS-matched controls were identified from the NHIRD. The primary and secondary outcome measures were changes in 1-year emergency department visit rate, hospitalization rate, duration of hospital stay, and healthcare costs.

RESULTS

The number of emergency department visits in the Health+ group significantly reduced (0.8 to 0.6 per year vs. 0.8 to 0.9 per year, p < 0.0001) along with a significant decrease in hospitalization rate (43.7% to 21.3% vs. 42.7% to 35.3%, p < 0.001). The duration of hospital stay was also lower in the Health+ group (4.3 to 3.3 days vs. 5.3 to 6.5 days, p < 0.0001). The annual healthcare costs decreased more in the Health+ group (USD 1642 to 1169 vs. 1466 to 1393 per year, p < 0.001), compared with the controls. Subgroup analysis of the Health+ group revealed that the improvements in outcomes were significantly greater among those who were younger and had fewer comorbidities, especially without diabetes or hypertension.

CONCLUSIONS

A community-based integrated BPT program may improve patients' health outcomes and reduce healthcare costs.