Predictive model of mortality based on logistic regression of laboratory indicators
https://doi.org/10.34215/1609-1175-2025-2-45-49
Abstract
Objective. To develop and validate a mathematical model for predicting the risk of mortality based on patients’ laboratory indicators from blood and urine tests. Materials and methods. Clinical data of patients, including laboratory test results of blood and urine, were analyzed. Mathematical modeling and statistical analysis methods were used to develop the predictive model. Results. A predictive model demonstrating high accuracy in assessing the risk of adverse outcomes was developed. The model is based on readily available laboratory indicators and can be easily integrated into clinical practice. Conclusion. The proposed mathematical model represents an effective tool for early diagnosis of mortality risk. The practical significance of the study lies in the potential application of the developed model across various fields of clinical medicine to optimize the diagnostic and therapeutic process
About the Author
A. N. Mozol
Khasanskaya Central District Hospital
Russian Federation
Russian Federation
Andrei N. Mozol, Deputy Chief Physician for Medical Affairs
Molodezhnaya st., Slavyanka urban-type settlement, Khasansky MO, Primorsky Krai, 692701
References
1. Bahadori M, Soltani M, Soleimani M, Bahadori M Statistical modeling in healthcare: shaping the future of medical research and healthcare delivery. ResearchGate. 2023;9(25):431–446. doi: 10.4018/979-8-3693-0876-9.ch025
2. Toma M, Ong C Predictive modeling in medicine. MDPI. 2023;3(2):590–601. doi: 10.3390/encyclopedia3020042
3. Zavorotniy OO, Zinoviev EV, Kostyakov D.V. Predicting for mortality rate using regression analysis in patient with burn injury. Grekov's Bulletin of Surgery. 2020;179(5):21–29 (In Russ.) doi: 10.24884/0042-4625-2020-179-5-21-29
4. Hooft L, Schuit E, Debray TPA Prediction models for cardiovascular disease risk in the general population: systematic review damen. Center for health sciences and primary care, university medical center. 2016;353:i2416. doi: 10.1136/bmj.i2416
5. Chao HY, Wu CC, Singh A, Shedd A, Wolfshohl J, Chou EH, Huang YC, Chen KF Using machine learning to develop and validate an in-hospital mortality prediction model for patients with suspected sepsis. Biomedicines. 2022;10(4):802. doi: 10.3390/biomedicines10040802
6. Wendland Ph, Schmitt V, Zimmermann J Machine learning models for predicting severe COVID-19 outcomes in hospitals. Informatics in medicine unlocked. 2023;37:101188. doi: 10.1016/j.imu.2023.101188
7. Nassar AI., Madai DYu. Scoring models for the severity of combined craniofacial trauma (a review). Kuban Scientific Medical Bulletin. 2020;27(5):144–162 (In Russ.) doi: 10.25207/1608-6228-2020-27-5-144-162
Review
For citations:
Mozol A.N. Predictive model of mortality based on logistic regression of laboratory indicators. Pacific Medical Journal. 2025;(2):45-49. (In Russ.) https://doi.org/10.34215/1609-1175-2025-2-45-49
Views:
5
Email this article 