Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Apr 25;15(1):14450.
doi: 10.1038/s41598-025-99449-z.

Machine learning approach for optimizing usability of healthcare websites

Amandeep Kaur  1 , Jaswinder Singh  2 , Satinder Kaur  3
Affiliations

Machine learning approach for optimizing usability of healthcare websites

Amandeep Kaur et al. Sci Rep. .

Abstract

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.

Keywords: Healthcare; Machine learning; Regression algorithms; Usability; Website quality.

PubMed Disclaimer

Conflict of interest statement

Declarations. Competing interests: The authors declare no competing interests.

Figures

Fig. 1
Fig. 1
Graphical abstract illustrating the methodology, key findings, and conclusions of the hospital website usability assessment using machine learning models.
Fig. 2
Fig. 2
Plotting the predicted and observed data for random forest.
Fig. 3
Fig. 3
Prediction error for random forest regression.
Fig. 4
Fig. 4
Residuals for random forest regression.
Fig. 5
Fig. 5
Plotting the predicted and observed data for decision tree regression.
Fig. 6
Fig. 6
Plotting prediction errors for decision tree regression.
Fig. 7
Fig. 7
Plotting the residuals for decision tree regression.
Fig. 8
Fig. 8
Plotting the predicted and observed data for support vector regression.
Fig. 9
Fig. 9
Plotting the prediction error for support vector regression.
Fig. 10
Fig. 10
Residuals for SVR model.
Fig. 11
Fig. 11
Plotting the predicted and observed data for ridge regression.
Fig. 12
Fig. 12
Prediction error for ridge.
Fig. 13
Fig. 13
Plotting residuals for ridge.
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Jamal, A. et al. Association of online health information–seeking behavior and self-care activities among type 2 diabetic patients in Saudi Arabia. J. Med. Internet. Res.17(8), e4312. 10.2196/jmir.4312 (2015). - PMC - PubMed
    1. Moreno, J. M., del Morales, J. M., Porcel, C. & Herrera-Viedma, E. A quality evaluation methodology for health-related websites based on a 2-tuple fuzzy linguistic approach. Soft. Comput.14(8), 887–897 (2010).
    1. Amante, D. J., Hogan, T. P., Pagoto, S. L., English, T. M. & Lapane, K. L. Access to care and use of the internet to search for health information: results from the US National health interview survey. J. Med. Internet. Res.17(4), e106. 10.2196/jmir.4126 (2015). - PMC - PubMed
    1. Ranallo, P. A., Kilbourne, A. M., Whatley, A. S. & Pincus, H. A. Behavioral health information technology: from chaos to clarity. Health Aff.35(6), 1106–1113. 10.1377/hlthaff.2016.0013 (2016). - PubMed
    1. Carman, K. L. et al. Patient and family engagement: A framework for Understanding the elements and developing interventions and policies. Health Aff.32(2), 223–231. 10.1377/hlthaff.2012.1133 (2013). - PubMed

LinkOut - more resources