A Protocol For Developing A Machine Learning Model To Forecast Healthcare Treatment Resource Utilization

Despite spending a significant number of resources and years developing a medical system, Patients with underlying comorbidities who have SARS-nCoV-2 carry a heavy financial burden that necessitates significant medical expenditures and resources for patient care. Clinical management cost uncertainty paralyzes the healthcare system and causes deficits in annual national budgets. This research will be focusing the necessary steps in developing the protocol. Overall, this article will include intervention logic mapping, questionnaires, recorded consultations, in-depth interviews, focus group discussions, and contextual data recording will be used as methods. The best effective AI-based technique for medical expense prediction and estimation for COVID-19 patients with comorbidities was identified. Regarding medical perspective and user acceptance, a better grasp of the issues and barriers confronting Malaysia's healthcare system. Deep learning techniques created a CNN-based model for predicting medical costs. Validation of the proposed model using real-world data and demonstration of its capacity to appropriately anticipate expenses. Using a relevant performance indicator such as RMSE, compare the constructed model to existing cost prediction approaches. Insights about the economic impact of COVID-19 on patients with comorbidities and healthcare practitioners in Malaysia. This research on the economic impact of COVID-19 on patients with comorbidities and healthcare practitioners, along with the development of a CNN-based cost prediction model, has significant implications for healthcare management, policy-making, and AI advancement in healthcare. The findings will inform more efficient resource allocation, guide public health policies, and contribute to the ongoing development of AI applications in healthcare.