Predicting Patient Satisfaction in Indian Healthcare Using Artificial Intelligence: A Data-Driven Approach to Patient Relationship Management
Main Article Content
Keywords
Patient satisfaction, Artificial intelligence, Predictive analytics, Healthcare technology, SHAP, Patient relationship management
Abstract
Background: Patient satisfaction serves as a vital measure of healthcare quality, especially in regions with limited resources, such as Chhattisgarh, India—a state characterized by its tribal populations and underdeveloped medical infrastructure. This research employs Artificial Intelligence (AI) to forecast patient satisfaction levels, specifically the overall satisfaction, with the goal of improving patient relationship management (PRM) in a public hospital setting in Chhattisgarh. Methods: Data from 107 patient surveys were examined, encompassing demographic factors (e.g., age group, gender, income level, and frequency of visits), service quality aspects (e.g., timeliness, accessibility, communication, system efficiency), and views on technology (e.g., technology quality and usability). An XGBoost regression model was developed to predict the overall satisfaction, complemented by SHapley Additive exPlanations (SHAP) for model interpretability. Additional analyses involved Pearson correlations, multiple linear regression, and t-tests. Missing values (under 5%) were handled through k-Nearest Neighbors (k-NN) imputation. The study did not involve preregistration or animal testing. Results: The XGBoost model yielded a root mean squared error (RMSE) of 0.39 and a coefficient of determination, R² of 0.90. SHAP highlighted communication (mean SHAP value = 0.72, p < 0.001), system efficiency (0.48, p < 0.01), and technology usability (0.35, p < 0.05) as primary influencers. Correlations revealed strong links, such as between communication and the overall satisfaction (correlation coefficient, r = 0.82, p < 0.001). Regression analysis supported the significance of communication (β = 0.70, p < 0.001) and system efficiency (β = 0.45, p < 0.01). Patients with very frequent visits showed reduced satisfaction (mean = 3.5 vs. 4.0 for occasional visitors, p < 0.001). Conclusions: Artificial Intelligence demonstrates strong potential for predicting patient satisfaction, emphasizing the roles of communication and operational efficiency. These insights could guide targeted PRM interventions in Chhattisgarh to better serve tribal and low-income groups. However, given the modest sample size from a single site, results should be viewed as preliminary, warranting larger-scale validation.
Downloads
Abstract 36 | PDF Downloads 17
References
2. Registrar General and Census Commissioner. Census of India. Chhattisgarh State Profile. Government of India: New Delhi, India; 2011. Available online: https://censusindia.gov.in/2011census/c-01.html.
3. Ministry of Health and Family Welfare. Health Infrastructure Statistics. Government of India: New Delhi, India; 2022. Available online: https://cbhidghs.mohfw.gov.in/index4.php?lang=1&level=0&linkid=930&lid=3774.
4. Dunsch, F., Evans, D.K., Macis, M., et al. Bias in patient satisfaction surveys: a threat to measuring healthcare quality. BMJ Glob Health. 2018;3(2):e000694. https://doi.org/10.1136/bmjgh-2017-000694.
5. Ministry of Health and Family Welfare. National Health Policy 2017. Government of India, New Delhi, India; 2017. Available online: https://main.mohfw.gov.in/sites/default/files/9147562941489753121.pdf.
6. Chen, T. and Guestrin, C. XGBoost: a scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, California, USA. August 13-17, 2022:785–794. https://doi.org/10.1145/2939672.2939785.
7. Lundberg, S.M. and Lee, S.I. A unified approach to interpreting model predictions. Adv Neural Inf Process Syst. 2017;30:4765–4774. https://doi.org/10.48550/arXiv.1705.07874.
8. Rajkomar, A., Dean, J. and Kohane, I. Machine learning in medicine. N Engl J Med. 2019;380(14):1347–1358. https://doi.org/10.1056/NEJMra1814259.
9. Zolnierek, K.B.H. and DiMatteo, M.R. Physician communication and patient adherence to treatment: a meta-analysis. Med Care. 2009;47(8):826–834. https://doi.org/10.1097/MLR.0b013e31819a5acc.
10. Ministry of Tribal Affairs. Tribal Health Report 2021. Government of India: New Delhi, India; 2021. Available online: https://tribal.nic.in/downloads/Statistics/AnnualReport/AREnglish2021.pdf.
11. Ministry of Statistics and Programme Implementation. National Sample Survey. Health in India: NSS 75th round. Government of India: New Delhi, India; 2018. Available online: https://mospi.gov.in/sites/default/files/publication_reports/Report_586_75th_Round.pdf.
12. National Health Authority. Ayushman Bharat Digital Mission: Progress Report. Government of India: New Delhi, India; 2022.
13. Kruse, C.S., Krowski, N., Rodriguez, B., et al. Telehealth and patient satisfaction: a systematic review and narrative analysis. BMJ Open. 2017;7(8):e016242. https://doi.org/10.1136/bmjopen-2017-016242.
14. Pennsylvania State University News. Penn State researchers use AI to analyze patient satisfaction. Published May 20, 2021. Available online: https://www.psu.edu/news/research/story/penn-state-researchers-use-ai-analyze-patient-satisfaction.
15. Jabbar, M.A., Iqbal, H., Chawla, U. Patient satisfaction: the role of artificial intelligence in healthcare. J Health Manag. 2024;26(2):1–15. https://doi.org/10.1177/09720634241246331.
16. Ogundare, O., Owadokun, T., Ogundare, T., et al. Integrated artificial intelligence in healthcare and the patient’s experience of care. Sci Rep. 2025;15(1):21879. https://doi.org/10.1038/s41598-025-07581-7.
17. Dixon, D., Sattar, H., Moros, N., et al. Unveiling the influence of AI predictive analytics on patient outcomes. Cureus. 2024;16(5):e59973. https://doi.org/10.7759/cureus.59954.
18. Villanueva-Miranda I, Xie Y, Xiao G. Sentiment analysis in public health: a systematic review of the current state, challenges, and future directions. Front Public Health. 2025 Jun 20;13:1609749. https://doi.org/10.3389/fpubh.2025.1609749.
19. NYU Langone News. New “AI Doctor” predicts hospital readmission & other health outcomes. Available online: https://nyulangone.org/news/new-ai-doctor-predicts-hospital-readmission-other-health-outcomes.
20. Parry M.W., Markowitz J.S., Nordberg C.M., et al. Patient perspectives on artificial intelligence in healthcare decision making: A Multi-Center Comparative Study. Indian J Orthop. 2023;57(4):653-665. https://doi.org/10.1007/s43465-023-00845-2.
Article Sidebar
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
Author(s) must obtain all parties consent [co-author(s), others if applicable] and submit the acceptance of Copyright Agreement with their paper. Written permission must be obtained by the author for material that has been published in copyrighted material; this includes tables, figures, and quoted text that exceeds 150 words. A copy of all permissions must accompany the manuscript when published in copyrighted material. The author(s) hereby represents and warrants that the paper is original and that he/she is the author of the paper, except for material that is clearly identified as to its original source, with permission notices from the copyright owners where required. Author(s) must clearly indicate that approval for publication has been received in cases of institutional ownership.
In all submitted material authors retain all copyrights; however, the GlobalCE Journal reserve the right to reprint all or portions of the article and to post all or part of the article online. GlobalCE Journal reserves the right to edit manuscripts as required to publish in the journal. Authors are responsible for obtaining any and all clearances as appropriate. Unless stated otherwise, all articles are open-access and distributed under the terms of the Creative Commons Attribution License (CC BY 4.0) which permits unrestricted use, distribution, and reproduction in any medium, provided the original author(s) and original work (e.g. first published in the Global Clinical Engineering Journal) is properly cited with the original URL and bibliographic citation information. The complete bibliographic information, a link to the original publication on www.Globalce.org well as the copyright and license information must be included. No use, distribution or reproduction is permitted which does not comply with these terms.
