RESUMO

BACKGROUND: The use of tools that allow estimation of the probability of progression of chronic kidney disease (CKD) to advanced stages has not yet achieved significant practical importance in clinical setting. This study aimed to develop and validate a machine learning-based model for predicting the need for renal replacement therapy (RRT) and disease progression for patients with stage 3-5 CKD. METHODS: This was a retrospective, closed cohort, observational study. Patients with CKD affiliated with a private insurer with five-year follow-up data were selected. Demographic, clinical, and laboratory variables were included, and the models were developed based on machine learning methods. The outcomes were CKD progression, a significant decrease in the estimated glomerular filtration rate (eGFR), and the need for RRT. RESULTS: Three prediction models were developed-Model 1 (risk at 4.5 years, n = 1446) with a F1 of 0.82, 0.53, and 0.55 for RRT, stage progression, and reduction in the eGFR, respectively,- Model 2 (time- to-event, n = 2143) with a C-index of 0.89, 0.67, and 0.67 for RRT, stage progression, reduction in the eGFR, respectively, and Model 3 (reduced Model 2) with C-index = 0.68, 0.68 and 0.88, for RRT, stage progression, reduction in the eGFR, respectively. CONCLUSION: The time-to-event model performed well in predicting the three outcomes of CKD progression at five years. This model can be useful for predicting the onset and time of occurrence of the outcomes of interest in the population with established CKD.

Assuntos

Inteligência Artificial , Progressão da Doença , Taxa de Filtração Glomerular , Insuficiência Renal Crônica , Terapia de Substituição Renal , Humanos , Masculino , Feminino , Insuficiência Renal Crônica/terapia , Insuficiência Renal Crônica/fisiopatologia , Pessoa de Meia-Idade , Estudos Retrospectivos , Aprendizado de Máquina , Idoso , Estudos de Coortes , Adulto

RESUMO

Introduction: Bipolar disorder (BD) is a chronically progressive mental condition, associated with a reduced quality of life and greater disability. Patient admissions are preventable events with a considerable impact on global functioning and social adjustment. While machine learning (ML) approaches have proven prediction ability in other diseases, little is known about their utility to predict patient admissions in this pathology. Aim: To develop prediction models for hospital admission/readmission within 5 years of diagnosis in patients with BD using ML techniques. Methods: The study utilized data from patients diagnosed with BD in a major healthcare organization in Colombia. Candidate predictors were selected from Electronic Health Records (EHRs) and included sociodemographic and clinical variables. ML algorithms, including Decision Trees, Random Forests, Logistic Regressions, and Support Vector Machines, were used to predict patient admission or readmission. Survival models, including a penalized Cox Model and Random Survival Forest, were used to predict time to admission and first readmission. Model performance was evaluated using accuracy, precision, recall, F1 score, area under the receiver operating characteristic curve (AUC) and concordance index. Results: The admission dataset included 2,726 BD patients, with 354 admissions, while the readmission dataset included 352 patients, with almost half being readmitted. The best-performing model for predicting admission was the Random Forest, with an accuracy score of 0.951 and an AUC of 0.98. The variables with the greatest predictive power in the Recursive Feature Elimination (RFE) importance analysis were the number of psychiatric emergency visits, the number of outpatient follow-up appointments and age. Survival models showed similar results, with the Random Survival Forest performing best, achieving an AUC of 0.95. However, the prediction models for patient readmission had poorer performance, with the Random Forest model being again the best performer but with an AUC below 0.70. Conclusion: ML models, particularly the Random Forest model, outperformed traditional statistical techniques for admission prediction. However, readmission prediction models had poorer performance. This study demonstrates the potential of ML techniques in improving prediction accuracy for BD patient admissions.