Explainable ensemble machine learning models for revenue forecasting in multidisciplinary dental clinics: The role of orthodontic production variables

Ergin Kalkan; İbrahim Budak

doi:10.66235/kumj.1894369

Explainable ensemble machine learning models for revenue forecasting in multidisciplinary dental clinics: The role of orthodontic production variables

Abstract

Aims: Accurate revenue forecasting is essential for effective financial planning in dental healthcare services; however, increasing variability in multidisciplinary clinical workload limits the adequacy of traditional linear approaches. This study aimed to develop and compare explainable machine learning–based models for forecasting monthly revenue in a multidisciplinary public dental clinic and to evaluate the specific contribution of orthodontic production within this framework.

Methods: Monthly aggregate data covering 48 months (2021–2024) from dental clinics affiliated with the Kastamonu Provincial Health Directorate were analyzed. Independent variables consisted of monthly procedure volumes in endodontics, restorative treatment, prosthodontics, periodontology, orthodontics, pedodontics, and oral surgery, while total monthly sales constituted the dependent variable. Six regression models were developed using the scikit-learn library: ExtraTreesRegressor, HistGradientBoostingRegressor, ElasticNet, KNeighborsRegressor, MLPRegressor, and a Stacking Regressor combining ExtraTrees and HistGradientBoosting with a Ridge meta-learner. A preprocessing pipeline including RobustScaler and log1p transformation was applied where appropriate. Model performance was evaluated using R², mean absolute error (MAE), root mean square error (RMSE), and mean absolute percentage error (MAPE). Model interpretability was assessed using SHapley Additive exPlanations (SHAP).

Results: All models achieved acceptable predictive performance; however, the Stacking model provided the best overall fit (R² ≈ 0.95) and the lowest MAE, RMSE, and MAPE (≈18%). Tree-based ensemble methods consistently outperformed distance-based and neural network approaches. ElasticNet demonstrated competitive performance (R² ≈ 0.91), indicating a strong linear component in revenue dynamics. SHAP analysis revealed that prosthodontic and restorative procedure volumes were the dominant drivers of monthly revenue, whereas orthodontic production had a comparatively modest short-term contribution.

Conclusion: Ensemble-based machine learning models, particularly stacking approaches, can accurately forecast monthly revenue in multidisciplinary dental clinics using clinical production indicators. Prosthodontic and restorative services represent the primary drivers of short-term revenue fluctuations, while orthodontic activity contributes more modestly within a monthly time frame. These findings support the integration of explainable machine learning models into financial planning and operational decision-making processes in dental healthcare institutions.

Keywords

References

Homauni A, Markazi-Moghaddam N, Mosadeghkhah A, Noori M, Abbasiyan K, Jame SZB. Budgeting in healthcare systems and organizations: a systematic review. Iran J Public Health. 2023;52(9):1889-1901. doi:10.18502/ijph.v52i9.13571
Zouo SJC, Olamijuwon J. Financial data analytics in healthcare: a review of approaches to improve efficiency and reduce costs. Open Access Res J Sci Technol. 2024;12(02):010–019. doi:10.53022/oarjst.2024.12.2.0129
Farrokhi F, Farrokhi F, Mohebbi SZ, Khami MR. A scoping review of the impact of COVID-19 on dentistry: financial aspects. BMC Oral Health. 2024;24(1):945. doi:10.1186/s12903-024-04726-4
Łaganowski K, Ortarzewska M, Czajka-Jakubowska A, Surdacka A, Nijakowski K. Long-term impact of the COVID-19 pandemic on dental care delivery in Poland: a single-center retrospective analysis. Int Dent J. 2025;75(3):1544-1553. doi:10.1016/j.identj.2025.02.024
Patharkar A, Cai F, Al-Hindawi F, Wu T. Predictive modeling of biomedical temporal data in healthcare applications: review and future directions. Front Physiol. 2024;15,1386760. doi:10.3389/fphys.2024.1386760
Atalan A, Şahin H. Forecasting of the dental workforce with machine learning models. J Eng Sci Res. 2024;6(1):125-132. doi:10.46387/bjesr.1455345
Şahap M, Özaslan NG, Veizi E. An artificial intelligence chatbot as a substitute for physician-patient counselling on perioperative anaesthesia in knee-related surgeries. Kastamonu Med J. 2026;6(1):34–43. doi:10.66235/kumj.1906313
Bansal RK, Arya A, Singh B, Singla M, Gupta S. Role of artificial intelligence and machine learning in conservative dentistry and endodontics: a review. Cureus. 2025;17(7):e88515. doi: 10.7759/cureus.88515

Almutairi TH, Olatunji SO. The utilization of AI in healthcare to predict no-shows for dental appointments: a case study conducted in Saudi Arabia. Inform Med Unlocked. 2024;46: 101472. doi:10.1016/j.imu.2024.101472
Tello M, Reich ES, Puckey J, et al. Machine learning based forecast for the prediction of inpatient bed demand. BMC Med Inform Decis Mak. 2022;22(1):55. doi:10.1186/s12911-022-01787-9
Cece O, Gençtürk M. Net profit margin forecasting with machine learning methods in hospital finance management. J Health Syst Policies. 2023;5(2):103-119. doi:10.52675/jhesp.1335249
Robinson JW. Regression tree boosting to adjust health care cost predictions for diagnostic mix. Health Serv Res. 2008;43(2):755-772. doi:10.1111/j.1475-6773.2007.00761.x
Scikit-learn. Hist Gradient Boosting Regressor. Available from: https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.HistGradientBoostingRegressor.html?utm=, (2025).
Zou H, Hastie T. Regularization and variable selection via the elastic net. J R Stat Soc Series B Stat Methodol. 2005;67(2):301-320. doi:10.1111/j.1467-9868.2005.00503.x
Altelbany SI. Evaluation of ridge, elastic net and lasso regression methods in precedence of multicollinearity problem: a simulation study. J Appl Econ Bus Stud. 2021;5(1):131-142. doi:10.34260/jaebs.517
Amangeldy B, Tasmurzayev N, Imankulov T, Imanbek B, Wójcik W, Nurakhov Y. A hybrid machine learning approach for high-accuracy energy consumption prediction using indoor environmental quality sensors. Energies. 2025;18(15):4164. doi:10.3390/en18154164
Reza AF, Singh R, Verma RK, Singh A, Ahn YH, Ray SS. An integral and multidimensional review on multi-layer perceptron as an emerging tool in the field of water treatment and desalination processes. Desalination. 2024;586:117849. doi:10.1016/j.desal.2024.117849
Hussain A, Giangrande P, Franchini G, Fenili L, Messi S. Analyzing the effect of error estimation on random missing data patterns in mid-term electrical forecasting. Electronics. 2025;14(7):1383. doi:10.3390/electronics14071383
Chicco D, Warrens MJ, Jurman G. The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation. Peerj Comput Sci. 2021;7:e623. doi:10.7717/peerj-cs.623
Willmott CJ, Matsuura K. Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Clim Res. 2005;30(1):79-82. doi:10.3354/cr030079
Aidoni A, Kofidis K, Urse C, Stoica A. Predictive modeling for natural gas prices in Romania using time series data and average temperature. Proc Int Conf Bus Excell. 2025;19(1):2505-2515. doi:10.2478/picbe-2025-0194
Magalhães B, Bento P, Pombo J, Calado MDR, Mariano S. Short-term load forecasting based on optimized random forest and optimal feature selection. Energies. 2024;17(8):1926. doi:10.3390/en17081926
Zou W, Yao X, Chen Y, Li X, Huang J, Zhang Y. An elastic net regression model for predicting the risk of ICU admission and death for hospitalized patients with COVID-19. Sci Rep. 2024;14(1),14404. doi:10.1038/s41598-024-64776-0
Seyghaly R, Garcia J, Masip-Bruin X, Kuljanin J. SBNNR: small‐size bat‐optimized KNN regression. Future Internet. 2024;16(11):422. doi:10.3390/fi16110422
Spicker D, Nazemi A, Hutchinson J, et al. Challenges for predictive modeling with neural network techniques using error‐prone dietary intake data. Stat Med. 2025;44(5):e70013. doi:10.1002/sim.70013
Chu J, Liu X, Zhang Z, Zhang Y, He M. A novel method overcoming overfitting of artificial neural network for accurate prediction: application on thermophysical property of natural gas. Case Stud Therm Eng. 2021;28,101406. doi:10.1016/j.csite.2021.101406
Efthimiou O, Seo M, Chalkou K, Debray T, Egger M, Salanti G. Developing clinical prediction models: a step-by-step guide. BMJ. 2024;386:e078276. doi:10.1136/bmj-2023-078276
Riley RD, Collins GS. Stability of clinical prediction models developed using statistical or machine learning methods. Biometr J. 2023;65(8):e2200302. doi:10.1002/bimj.202200302
Musharaf S, Kumar SS, Reddy BM, Sahoo B. A predictive approach for healthcare expenditure using ensemble techniques. In Proceedings of the 3rd International Conference on Futuristic Technology. 2025;2:41-48. doi:10.5220/0013586300004664
Piccialli F, Giampaolo F, Salvi A, Cuomo S. A robust ensemble technique in forecasting workload of local healthcare departments. Neurocomputing. 2021;444:69-78. doi:10.1016/j.neucom.2020.02.138
Tsichlaki A, Chin SY, Pandis N, Fleming PS. How long does treatment with fixed orthodontic appliances last? a systematic review. Am J Orthod Dentofacial Orthop. 2016;149(3):308–318. doi:10.1016/j.ajodo.2015.09.020

Details

Primary Language

English

Subjects

Clinical Sciences (Other)

Journal Section

Research Article

Authors

Ergin Kalkan ^*
0000-0002-5544-1271
Türkiye

İbrahim Budak
0000-0001-7762-6114
Türkiye

Publication Date

September 27, 2026

Submission Date

February 20, 2026

Acceptance Date

June 22, 2026

Published in Issue

Year 2026 Volume: 6 Number: 3

DOI

https://doi.org/10.66235/kumj.1894369

IZ

https://izlik.org/JA95RK89KU

Cite

RIS / Bibtex

APA

Kalkan, E., & Budak, İ. (2026). Explainable ensemble machine learning models for revenue forecasting in multidisciplinary dental clinics: The role of orthodontic production variables. Kastamonu Medical Journal, 6(3), 243-253. https://doi.org/10.66235/kumj.1894369

AMA

1.Kalkan E, Budak İ. Explainable ensemble machine learning models for revenue forecasting in multidisciplinary dental clinics: The role of orthodontic production variables. Kastamonu Medical Journal. 2026;6(3):243-253. doi:10.66235/kumj.1894369

Chicago

Kalkan, Ergin, and İbrahim Budak. 2026. “Explainable Ensemble Machine Learning Models for Revenue Forecasting in Multidisciplinary Dental Clinics: The Role of Orthodontic Production Variables”. Kastamonu Medical Journal 6 (3): 243-53. https://doi.org/10.66235/kumj.1894369.

EndNote

Kalkan E, Budak İ (September 1, 2026) Explainable ensemble machine learning models for revenue forecasting in multidisciplinary dental clinics: The role of orthodontic production variables. Kastamonu Medical Journal 6 3 243–253.

IEEE

[1]E. Kalkan and İ. Budak, “Explainable ensemble machine learning models for revenue forecasting in multidisciplinary dental clinics: The role of orthodontic production variables”, Kastamonu Medical Journal, vol. 6, no. 3, pp. 243–253, Sept. 2026, doi: 10.66235/kumj.1894369.

ISNAD

Kalkan, Ergin - Budak, İbrahim. “Explainable Ensemble Machine Learning Models for Revenue Forecasting in Multidisciplinary Dental Clinics: The Role of Orthodontic Production Variables”. Kastamonu Medical Journal 6/3 (September 1, 2026): 243-253. https://doi.org/10.66235/kumj.1894369.

JAMA

1.Kalkan E, Budak İ. Explainable ensemble machine learning models for revenue forecasting in multidisciplinary dental clinics: The role of orthodontic production variables. Kastamonu Medical Journal. 2026;6:243–253.

MLA

Kalkan, Ergin, and İbrahim Budak. “Explainable Ensemble Machine Learning Models for Revenue Forecasting in Multidisciplinary Dental Clinics: The Role of Orthodontic Production Variables”. Kastamonu Medical Journal, vol. 6, no. 3, Sept. 2026, pp. 243-5, doi:10.66235/kumj.1894369.

Vancouver

1.Ergin Kalkan, İbrahim Budak. Explainable ensemble machine learning models for revenue forecasting in multidisciplinary dental clinics: The role of orthodontic production variables. Kastamonu Medical Journal. 2026 Sep. 1;6(3):243-5. doi:10.66235/kumj.1894369