Machine learning approach for optimizing usability of healthcare websites.

In today's digital era, hospital websites serve as crucial informational resources, providing patients with easy access to medical services. Ensuring the usability of these websites is essential, as it directly impacts users' ability to navigate and retrieve vital medical information. Despite the recognized importance of website usability in the healthcare sector, there is a notable lack of empirical studies leveraging machine learning to assess this usability. This study aims to fill this gap by evaluating the user-friendliness of hospital websites using machine learning models, including Decision Trees, Random Forests, Ridge Regression, and Support Vector Regression. The dataset used in this analysis was generated by a custom-built automated tool developed by the author, which assessed the usability of 100 hospital websites. Among the models, Random Forest Regression and Ridge Regression demonstrated exceptional performance, achieving an accuracy rate of 98% and 87% respectively. Key metrics such as R-square, Mean Square Error (MSE), Mean Absolute Error (MAE), and Explained Variance Score (EVS) confirmed the model's predictive accuracy. Cross-validation further highlighted the robustness of Ridge Regression exhibiting low overfitting. The importance rankings consistently underscored the critical role of overall usability in predicting website performance. The study recommends expanding the dataset to include a broader range of healthcare websites, integrating user interaction data, and exploring advanced analytical techniques like deep learning to enhance future usability assessments. These advancements could lead to optimized website design and improved digital healthcare experiences for a diverse range of users.