Abstract
Teleconsultation is the use of electronic information and communication technology to assist and provide medical care to patients who are unable to go to a healthcare facility for treatment. Globally, teleconsultation is used to provide medical care in a variety of specialisations, for different ailments, and in a variety of ways. Over the past years, significant advancement in technology has improved the accessibility and standard of care that is received by patients through teleconsultation. Over time, researchers have examined the benefits and drawbacks of teleconsultation in comparison to conventional patients visit but still note that the benefits of teleconsultation outweigh its drawbacks as patients can easily have access to quality medical care attention remotely, easily, and timely. Recently, researchers have documented the use of machine-learning techniques to predict diseases and patient experiences like satisfaction, however, there are few papers on the prediction of experiences compared to the prediction of diseases. Therefore, this paper adopts the use of Supervised Machine Learning techniques in training and testing patients’ dataset and specifically used regression to predict patient satisfaction. Comparing the results gotten for Support Vector Regression (SVR) Model (using radial basis function kernel) with Decision Tree Regression, it is evident that SVR Model is the best-fit model for the dataset because it has a lower mean squared error of 1.061899561612261 for test data compared to the mean squared error value of DTR Model which is 2.6202531645569622. Hence, this paper concludes that SVR Model is the best-fit model to be used with teleconsultation in predicting patient satisfaction. However, the paper recommends that more machine learning algorithms should be explored and implemented with teleconsultation in treating patients and improving other healthcare services.