Predicting the Show-ups and No-shows Status of Patients: a CART Model of Machine Learning

Abstract

Patient attendance status (Show-ups and No-shows) is a significant problem that seriously impacts healthcare efficiency and resource planning. The primary objective of this study is to comprehensively evaluate the performance of the Classification and Regression Trees (CART) model, a highly interpretable machine learning algorithm, in predicting patient attendance. Four independent variables (Patient Age, Appointment Time, Gender, and Chronic Disease Status) were used to predict attendance status (show-up/no-show), and the CART model's hyperparameters were optimized using 10-fold cross-validation to select the optimal tree structure. The numerical results indicate that the model performed acceptably on the training dataset, with a sensitivity of 70.3% and an overall accuracy of 62.2%. The relative importance of the independent variables revealed that Appointment Time (AppTime) and Age were the strongest predictors, while Gender and Chronic Disease contributed significantly less to the model's predictions. In conclusion, the potential of the CART model in predicting patient absences has been demonstrated.

Keywords

• Show-ups and No-shows
• Machine Learning
• CART Model
• Classification
• Predictive Analytics
• Healthcare Management.

References

1. [1] A. Atalan, N. F. Kaplan DÖNMEZ, and C. C. Donmez, “Developing Optimization Models to Evaluate Healthcare Systems,” Sigma Journal of Engineering and Natural Sciences, vol. 38, no. 2, pp. 853–873, 2020.
2. [2] W.-J. Chang and Y.-H. Chang, “Design of a Patient-Centered Appointment Scheduling with Artificial Neural Network and Discrete Event Simulation,” Journal of Service Science and Management, vol. 11, no. 01, pp. 71–82, 2018, doi: 10.4236/jssm.2018.111007.
3. [3] A. Naidu, “Factors affecting patient satisfaction and healthcare quality,” Int J Health Care Qual Assur, vol. 22, no. 4, pp. 366–381, 2009.
4. [4] A. Martyushev-Poklad, D. Yankevich, and M. Petrova, “Improving the Effectiveness of Healthcare: Diagnosis-Centered Care Vs. Person-Centered Health Promotion, a Long Forgotten New Model,” Front Public Health, vol. 10, May 2022, doi: 10.3389/fpubh.2022.819096.
5. [5] H. T. A. Khan, K. M. Addo, and H. Findlay, “Public Health Challenges and Responses to the Growing Ageing Populations,” Public Health Challenges, vol. 3, no. 3, Sep. 2024, doi: 10.1002/puh2.213.
6. [6] A. Atalan, “Application of Linear Regression Model to Forecast Re-appointment Time of Patients in the Oncology Department,” in The Evaluations and Researches in Social Sciences and Humanities, Livre de Lyon, 2021, pp. 360–377.
7. [7] A. Leiva-Araos, C. Contreras, H. Kaushal, and Z. Prodanoff, “Predictive Optimization of Patient No-Show Management in Primary Healthcare Using Machine Learning,” J Med Syst, vol. 49, no. 1, p. 7, Jan. 2025, doi: 10.1007/s10916-025-02143-w. [8] J. B. Norris, C. Kumar, S. Chand, H. Moskowitz, S. A. Shade, and D. R. Willis, “An empirical investigation into factors affecting patient cancellations and no-shows at outpatient clinics,” Decis Support Syst, vol. 57, pp. 428–443, 2014. [9] J. Jones, “Reduction of Endoscopic Procedural Delays and Cancellations: A Quality Improvement Project,” 2024.
8. [10] A. Atalan, “Desirability Optimization Based on the Poisson Regression Model: Estimation of the Optimum Dental Workforce Planning,” International Journal of Health Management and Tourism, vol. 7, no. 2, pp. 200–216, Jul. 2022, doi: 10.31201/ijhmt.1123824.

9. [11] G. Leibner, S. Brammli-Greenberg, J. Mendlovic, and A. Israeli, “To charge or not to charge: reducing patient no-show,” Isr J Health Policy Res, vol. 12, no. 1, p. 27, Aug. 2023, doi: 10.1186/s13584-023-00575-8.
10. [12] A. Atalan, H. Şahin, and Y. A. Atalan, “Integration of Machine Learning Algorithms and Discrete-Event Simulation for the Cost of Healthcare Resources,” Healthcare, vol. 10, no. 10, p. 1920, Sep. 2022, doi: 10.3390/healthcare10101920.
11. [13] A. Atalan and C. Ç. Dönmez, “Dynamic Price Application to Prevent Financial Losses to Hospitals Based on Machine Learning Algorithms,” Healthcare, vol. 12, no. 13, p. 1272, Jun. 2024, doi: 10.3390/healthcare12131272.
12. [14] K. M. Toffaha, M. C. E. Simsekler, A. Alshehhi, and M. Atif Omar, “Predicting Hospital No-Shows: Interpretable Machine Learning Models Approach,” IEEE Access, vol. 12, pp. 166058–166067, 2024, doi: 10.1109/ACCESS.2024.3490662.
13. [15] D. Liu et al., “Machine learning approaches to predicting no-shows in pediatric medical appointment,” NPJ Digit Med, vol. 5, no. 1, Dec. 2022, doi: 10.1038/s41746-022-00594-w.
14. [16] Z. Ahmed, K. Mohamed, S. Zeeshan, and X. Dong, “Artificial intelligence with multi-functional machine learning platform development for better healthcare and precision medicine,” Database, vol. 2020, p. baaa010, 2020.
15. [17] V. Santamato, C. Tricase, N. Faccilongo, A. Marengo, and J. Pange, “Healthcare performance analytics based on the novel PDA methodology for assessment of efficiency and perceived quality outcomes: A machine learning approach,” Expert Syst Appl, vol. 252, p. 124020, 2024.
16. [18] G. Fan, Z. Deng, Q. Ye, and B. Wang, “Machine learning-based prediction models for patients no-show in online outpatient appointments,” Data Science and Management, vol. 2, pp. 45–52, 2021.
17. [19] J. Charoenpong, B. Pimpunchat, S. Amornsamankul, W. Triampo, and N. Nuttavut, “A Comparison of Machine Learning Algorithms and their Applications.,” International Journal of Simulation--Systems, Science & Technology, vol. 20, no. 4, 2019.
18. [20] M. C. Weinstein et al., “Principles of good practice for decision analytic modeling in health-care evaluation: Report of the ISPOR task force on good research practices—Modeling studies,” Value in health, vol. 6, no. 1, pp. 9–17, 2003.
19. [21] M. M. Ghiasi, S. Zendehboudi, and A. A. Mohsenipour, “Decision tree-based diagnosis of coronary artery disease: CART model,” Comput Methods Programs Biomed, vol. 192, p. 105400, 2020.
20. [22] P. R. Harper, “A review and comparison of classification algorithms for medical decision making,” Health Policy (New York), vol. 71, no. 3, pp. 315–331, 2005.
21. [23] P. R. Harper, “A review and comparison of classification algorithms for medical decision making,” Health Policy (New York), vol. 71, no. 3, pp. 315–331, 2005, doi: 10.1016/j.healthpol.2004.05.002.
22. [24] R. J. Lewis, “An Introduction to Classification and Regression Tree (CART) Analysis.” [Online]. Available: https://www.researchgate.net/publication/240719582
23. [25] L. Bel, D. Allard, J. M. Laurent, R. Cheddadi, and A. Bar-Hen, “CART algorithm for spatial data: Application to environmental and ecological data,” Comput Stat Data Anal, vol. 53, no. 8, pp. 3082–3093, Jun. 2009, doi: 10.1016/j.csda.2008.09.012.
24. [26] B. Choubin, H. Darabi, O. Rahmati, F. Sajedi-Hosseini, and B. Kløve, “River suspended sediment modelling using the CART model: A comparative study of machine learning techniques,” Science of The Total Environment, vol. 615, pp. 272–281, 2018, doi: https://doi.org/10.1016/j.scitotenv.2017.09.293.