Prognostic modeling of adverse outcomes of knee joint injury treatment in patients with diabetes mellitus

Purpose of research. The objectives of the study are to identify key risk factors and create a mathematical model for predicting treatment outcomes for knee injuries in patients with diabetes mellitus.

Methods. To solve this problem, a set of methods was used to take into account many factors affecting the risk of knee injury in patients with diabetes mellitus. These include descriptive statistics for sample characteristics (such as mean, standard deviation, median, quartiles), correlation analysis of Spearman and Pearson coefficients to identify relationships between variables, as well as logistic regression and machine learning methods (Random Forest and SVM) for building and evaluating predictive models. This approach provides an in-depth study of the relationships between clinical and functional indicators, which makes it possible to create accurate and reliable predictive models. As a result, this contributes to improved risk assessment and the development of individual preventive approaches, as well as personalized therapies, which significantly increases the effectiveness of treatment.

Results. A correlation was found between the level of HbA1c and the frequency of infectious complications (r = 0,68, p < 0,01). A mathematical model was developed that allows predicting an unfavorable treatment outcome with an accuracy of 89 % (AUC = 0,89). The prognostic model identified key risk factors for adverse treatment outcomes, including HbA1c levels exceeding 7,5 %, BMI over 30 kg/m² and age over 60 years.

Conclusion. In this work the predictive model works with an accuracy of 86 %, which is a good diagnostic indicator and a risk assessment tool for solving the important task of medical forecasting and prevention of complications.

1. Tarabichi M., Shohat N., Kheir M.M., et al. Determining the Threshold for HbA1c as a Predictor for Adverse Outcomes After Total Joint Arthroplasty: A Multicenter, Retrospective Study. The Journal of Arthroplasty. 2017;32(9):S263-S267.e1. https://doi.org/10.1016/j.arth.2017.04.065.

2. Bondar I.A., Shabelnikova O. Yu. Features of the clinical course and frequency of complications in patients with type 2 diabetes mellitus of various clusters in the Novosibirsk region. Problemy endokrinologii = Problems of Endocrinology. 2023;69(5):84-92. (In Russ.) https://doi.org/10.14341/probl13259.

3. Yaara Berkovich, Ela Cohen Nissan, David Maman, Michael Tobias Hirschmann, Yaniv Yonai, Yaniv Steinfeld, Yaron Berkovich. Diabetes and total knee arthroplasty: A nationwide analysis of short-term complications, healthcare utilization and costs. Knee Surgery, Sports Traumatology, Arthroscopy. 2025;33(9):3250-3260. https://doi.org/10.1002/ksa.12696.

4. Groot O.Q., Ogink P.T., Lans A., et al. Machine learning prediction models in orthopedic surgery: A systematic review in transparent reporting. Journal of Orthopaedic Research. 2022;40(2): 475-483. https://doi.org/10.1002/jor.25036.

5. Gimm G., Shin D.-W., Lee J., et al. A development of machine learning models to preoperatively predict insufficient clinical improvement after total knee arthroplasty. J. Orthop. Surg. Res. 2025;(20):778. https://doi.org/10.1186/s13018-025-06206-z.

6. Lyubimova L.V., Mikishanina E.A., Nikolaev N.S., Lyubimov E.A., Preobrazhenskaya E.V. Indices of systemic inflammation for predicting early in-fections after arthroplasty of large joints. Travmatologiya i ortopediya Rossii = Traumatology and Orthopedics of Russia. 2025;31(4):41-52. (In Russ.) https://doi.org/10.17816/2311-2905-17754.

7. Kuo Ren Tan, Jun Jie Benjamin Seng, Yu Heng Kwan, Ying Jie Chen, Sueziani Binte Zainudin, Dionne Hui Fang Loh, Nan Liu, Lian Leng Low. Evaluation of Machine Learning Methods Developed for Prediction of Diabetes Complications: A Systematic Review. Journal of Diabetes Science and Technology. 2021;17(2):474-489. https://doi.org/10.1177/19322968211056917.

8. Vaishya R., Patralekh M.K., Misra A., Vaish A. Outcomes of total knee arthroplasty in people with diabetes: An overview of systematic reviews and meta-analysis. Journal of Orthopaedics. 2025;65:336-345. https://doi.org/10.1016/j.jor.2025.06.023.

9. Seok Ho Hong, Seung Cheol Kwon, Jong Hwa Lee, Shinje Moon, Joong Il Kim. Influence of Diabetes Mellitus on Postoperative Complications After Total Knee Arthroplasty: A Systematic Review and Meta-Analysis. Medicina. 2024;60(11):1757. https://doi.org/10.3390/medicina60111757.

10. Andrea Baldini, Damiano Ardiri, Lorenzo Benvenuti, Mattia Chirico, Enrico Fiorilli, Alessandro Singlitico, Filippo Leggieri. What Are the Game Changers in Total Knee Arthroplasty? A Narrative Review of Evidence-Based Interventions That Transform Patient Outcomes. Journal of Personalized Medicine. 2025;15(8):389. https://doi.org/10.3390/jpm15080389.

11. Groot O.Q., Ogink P.T., Lans A., et al. Machine learning prediction models in orthopedic surgery: A systematic review in transparent reporting. Journal of Orthopaedic Research. 2022;40(2):475-483. https://doi.org/10.1002/jor.25036.

12. Geunwu Gimm, Byoungjun Jeon, Sung Eun Kim, Byeong Soo Kim, Hyuk-Soo Han, Sungwan Kim. A development of machine learning models to preoperatively predict insufficient clinical improvement after total knee arthroplasty. J. Orthop. Surg. Res. 2025;20:778. https://doi.org/10.1186/s13018-025-06206-z.

13. Bondar I.A., Shabelnikova O. Yu. Risks of deaths in case of individual clinical phenotypes in patients with type 2 diabetes mellitus in the Novosi-Birsk region. Sakharnyi diabet = Diabetes Mellitus. 2024;27(6):580-588. (In Russ.) https://doi.org/10.14341/DM13195.

14. Vasiliev V.A., Marchenkova L.A., Osvetchikova D.I., Rozhkova E.A., Fesyun A.D. Medical rehabilitation after injuries of the lower extremities in patients with diabetes mellitus: a review of the literature. Vestnik vosstanovitel'noi meditsiny = Bulletin of Restorative Medicine. 2024;23(3):61-68. (In Russ.)