Delgado AF, Díaz GEJ, Rodríguez WFL

Language: Spanish
References: 13
Page: 323-328
PDF size: 269.32 Kb.

ABSTRACT

Introduction: we demonstrate the ease and potential of machine learning in enhancing the detection and prevention of cardiovascular risk factors. Our study emphasizes the analysis of continuous numerical variables, often overlooked in research, highlighting the innovative approach of our investigation. Objective: to assess, using Python and performance metrics, the applicability of predictive methods (decision tree, random forest, and K-Nearest Neighbors [KNN]). Material and methods: a search was conducted on PubMed and Google Scholar, covering 1995 to 2023. Terms included "aprendizaje automático" and "machine learning prediction model". Additional literature was sourced through supplementary online searches and physical media. The study includes somatometric and laboratory data from a population of hospital workers in Mexico. Results and conclusion: the Random Forest model exhibited superior performance for numerical and categorical variables. Numerical variables were evaluated using root mean square error (RMSE), mean absolute error (MAE), mean square error (MSE), and coefficient of determination (R²). In contrast, categorical variables were assessed with accuracy, precision, sensitivity, F1-score, and ROC/AUC. This proves the Random Forest's robustness in handling diverse data types, suggesting its significant potential for early risk detection and intervention strategies in clinical settings.

REFERENCES

1. Deo RC. Machine Learning in Medicine. Circulation. 2015; 132 (20): 1920-1930. doi: 10.1161/CIRCULATIONAHA.115.001593.

2. Géron A. Hands-on machine learning with scikit-learn, keras, and tensorflow. Third. In: Butterfield N, Taché N, Cronin M, Kelly B, Cofer K, Head R, et al., editors. Sebastopol: O'Reilly Media; 2023.

3. McKinney W. Python for Data Analysis. Third. In: Haberman J, Rufino A, Faucher C, Saruba S, Klefstad S, Futato D, et al., editors. Sebastopol: O'Reilly; 2022.

4. Heo J, Yoon JG, Park H, Kim YD, Nam HS, Heo JH. Machine learning-based model for prediction of outcomes in acute stroke. Stroke. 2019; 50 (5): 1263-1265. doi: 10.1161/STROKEAHA.118.024293.

5. Uddin S, Khan A, Hossain ME, Moni MA. Comparing different supervised machine learning algorithms for disease prediction. BMC Med Inform Decis Mak. 2019; 19 (1): 281. doi: 10.1186/s12911-019-1004-8.

6. Theng D, Theng M. Machine learning algorithms for predictive analytics: a review and new perspectives. High Technology Letters. 2020; 26 (6): 537-345.

7. Park DJ, Park MW, Lee H, Kim YJ, Kim Y, Park YH. Development of machine learning model for diagnostic disease prediction based on laboratory tests. Sci Rep. 2021; 11 (1): 7567. doi: 10.1038/s41598-021-87171-5.

8. Wei C, Zhang L, Feng Y, Ma A, Kang Y. Machine learning model for predicting acute kidney injury progression in critically ill patients. BMC Med Inform Decis Mak. 2022; 22 (1): 17. doi: 10.1186/s12911-021-01740-2.

9. Rodríguez-Rivas JG, Rodríguez-Castillo S. Uso de Python para el análisis de datos aplicado en la investigación. Revista Incaing. 2022, 33-40.

10. Bhaskar H, Hoyle DC, Singh S. Machine learning in bioinformatics: a brief survey and recommendations for practitioners. Comput Biol Med. 2006; 36 (10): 1104-1125.

11. Martínez Montaño M del LC, Briones Rojas R, Cortés Riveroll JGR. Metodología de la investigación para el área de la salud. 2nd ed. de León Fraga J, Guerrero Aguilar. Héctor F., Manjarrez de la Vega JJ, editores. México: McGraw-Hill; 2013.

12. Rule A, Birmingham A, Zuniga C, Altintas I, Huang SC, Knight R et al. Ten simple rules for writing and sharing computational analyses in Jupyter Notebooks. PLoS Comput Biol. 2019; 15 (7): e1007007. doi: 10.1371/journal.pcbi.1007007.

13. Perez-Riverol Y, Gatto L, Wang R, Sachsenberg T, Uszkoreit J et al. Ten simple rules for taking advantage of git and GitHub. PLoS Comput Biol. 2016; 12 (7): e1004947. doi: 10.1371/journal.pcbi.1004947.