Optimizing Telemedicine Services for Rural Women: A Decision Tree-Based Heap Optimizer Approach for Predictive Healthcare Delivery

Women living in rural areas still have a great difficulty gaining access to healthcare especially in underdeveloped areas where the infrastructure for medical treatment is limited. By means of remotely available healthcare services, telemedicine has become a possibly useful solution to close this gap; still, the optimisation of these services to generate better outcomes is a continuous challenge. Even if telemedicine is becoming more and more popular, women living in rural areas still sometimes face challenges including limited health resources, socioeconomic problems, and poor internet access. Therefore, much sought for are effective optimisation models that can predict the needs of healthcare and enhance the provision of services to this particular group. This work attempts to provide a Decision Tree-based Heap Optimiser (DTHO) for use in rural women's telemedicine service prediction and optimisation. Using decision tree learning, the DTHO method classifies healthcare needs depending on past data. Moreover, used are heap-based approaches for effective resource distribution. Using data from surveys on telemedicine use and rural healthcare, the predictive model was developed by means of analysis. The model maximised resource allocation by 30%, so allowing a more efficient provision of telemedicine services. For identifying healthcare needs, it also attained an accuracy of 85%. Reducing service delays by 20–25 percent enabled the heap-based optimiser to increase patient satisfaction by 20%.