Year: 2020
Type: dissertation
Study design: Observational Study
Abstract: New methods and tools in the healthcare sector are growing gradually through the continuing innovation in medicine and technologies.Along with the scarcity of medical infrastructure and the speedy advancement in Information and Communication Technology (ICT), remote healthcare systems, such as eHealth, mHealth, telemedicine, and telemonitoring, are receiving paramount consideration worldwide.Because of the potential benefits and various eHealth initiatives in place, many studies have been conducted to determine the acceptance of eHealth technology.However, most were conducted in developed countries.Deployment of eHealth technology is essential for developing countries where access to quality healthcare is hindered by poor governmental policies, political crises, and lack of healthcare infrastructure, very few studies on eHealth consumer behavior were conducted.This research aims to understand the consumer behavior of eHealth among the urban corporate people of Bangladesh.The study has identified several specific objectives stated below: v questionnaire items among 47 items to be included in the model.By applying SEM, we found that the key factors to promoting the future use of a PHC system lie in the three most important factors: perceived usefulness (0.659), intention to use (0.454), and health awareness (0.447).These factors have a positive and direct influence on the use of PHC.Socio-demographic characteristics such as age, gender, education had no significant effect on accepting and using eHealth services.Second, the research predicted the blood uric acid value through machine learning approaches.The mean of uric acid measurement was 6.63 mg/dL.That means the uric acid of most of the people is close to the borderline (6.63 mg/dL whereas the normal range <7.0 mg/dL).Therefore, they need to check uric acid regularly.This study evaluated five machine learning approaches such as Boosted Decision Tree Regression, Decision Forest Regression, Bayesian Linear Regression, and Linear Regression.The Boosted Decision Tree Regression model showed the best performance among other models based on the Root Mean Squared Error (RMSE) 0.03, this RMSE is better than any other studies that predicted clinical measurements.Third, this research used the WHO guidelines and Design Science Research (DSR) framework to redesign the Portable Health Clinic (PHC), an RHS, for the containment of the spread of COVID-19 as well as proposed corona logic (C-Logic) for the main symptoms of COVID-19.We have modified the existing PHC model and proposed a Corona logic (c-logic) by following WHO guidelines and Design Science Research (DSR) framework.Using the distributed service platform of PHC, a trained healthcare worker with appropriate testing kits, can screen high-risk individuals, and help optimize triage to medical services.PHC with its new triage algorithm (C-Logic) classifies the patients whether the patient needs to move to a clinic for a PCR test or not.Through modified PHC service, we can help people to boost their knowledge, attitude (feelings/beliefs), and selfefficacy to execute preventing measures.The findings of this research are expected to offer proactively important and practical guidelines to service providers, implementers, and policymakers to promote the use of eHealth technology for regular health checkups.The findings can also contribute to the establishment of combined actions to improve NCDs management in the context of limited resources.Finally, the machine learning prediction model will assist for improving awareness among high-risk subjects.By predicting uric acid, this study can help to save medical costs.Our initial examination of the suitability of the PHC and its associated technologies as a key contributor to public health responses designed to " flatten the curve", particularly among unreached high-risk NCD populations in developing countries, indicate the strong possibility of affirmative impact.Theoretically, this study contributes to design science research by introducing a modified healthcare providing model.This study is limited by geographical scaling as the survey was conducted in one country and focused on only 18 institutions.Thus, the results may raise a concern over the generalizability of the findings, and scope exists to make the findings more generalized by examining additional countries and institutions.Given the cross-sectional design, the present study cannot determine the actual use.Hence, future studies should consider a longitudinal approach through which participants will be interviewed several over a period.Besides, a few variables could be added, such as trust in a PHC system and facilitating conditions, to understand additional insights into the use of eHealth technology by urban corporate people.A future study could include some additional features (e.g.income, work stress, everyday physical activity, alcohol intake, eating red meat, mental health factor, environmental factor, etc.).
Author: ベガン マスダ
Language: English
Field: Medicine
Domain: Health Sciences
Open Access status: green
OpenAlex ID: W3202783533