Novel Methodology for Triage and Prioritizing Using “Big Data” Patients with Chronic Heart Diseases Through Telemedicine Environmental

Abstract

Problem Statement: Improper triage and prioritization of big-data patients may result in erroneous strategic decisions. An example of such wrong decision making includes the triage of patients with chronic heart disease to low-priority groups. Incorrect decisions may jeopardize the patients’ health. Objective: This study aims to evaluate and score the big data of patients with chronic heart disease and of those who require urgent attention. The assessment is based on multicriteria decision making in a telemedical environment to improve the triage and prioritization processes. Methods: A hands-on study was performed. A total of 500 patients with chronic heart disease manifested in different symptoms and under various emergency levels were evaluated on the basis of the following four main measures. An electrocardiogram sensor was used to measure the electrical signals of the contractile activity of the heart over time. A SpO2 sensor was employed to determine the blood oxygen saturation levels of the patients. A blood pressure sensor was used to obtain the physiological data of the systolic and diastolic blood pressures of the patients. Finally, a non-sensory measurement (text frame) was conducted to assess chest pain and breathing. The patients were prioritized on the basis of a set of measurements by utilizing integrated back-forward adjustment for weight computation and technique for order performance by similarity to ideal solution. Discussion Results: Patients with the most urgent cases were given the highest priority level, whereas those with the least urgent cases were assigned with the lowest priority level among all patients’ scores. The first three patients assigned to the medical committee of doctors were proven to be the most critical emergency cases with the highest priority level on the basis of their clinical symptoms. By contrast, the last three patients were proven to be the least critical emergency cases and given the lowest priority levels relative to other patients. The throughput measurement in terms of scalability based on our proposed algorithm was more efficient than that of the benchmark algorithm. Finally, the new method for determining the “big data” patients characteristics based on “4Vs” was suggested.