Buchumschlag

Using Natural Language Processing and Machine Learning to classify the status of kidney allograft in Electronic Medical Records written in Spanish

Gespeichert in:
Veröffentlicht in:PLoS One vol. 20, no. 5 (May 2025), p. e0322587
1. Verfasser: Garcia-Lopez, Andrea
Weitere Verfasser: Cuervo-Rojas, Juliana, Garcia-Lopez, Juan, Giron-Luque, Fernando
Veröffentlicht:
Public Library of Science
Schlagworte:
Colombia
Medical records
Accuracy
Datasets
Classification
Models
Test sets
Data mining
Regression analysis
Regression models
Neural networks
Data processing
Feature selection
Machine learning
Codes
Kidneys
Electronic medical records
Electronic health records
Learning algorithms
Performance measurement
Artificial intelligence
Sensitivity
Kidney transplantation
Kidney transplants
Natural language processing
Unstructured data
Algorithms
Large language models
Allografts
Social
Online-Zugang:Citation/Abstract
Full Text
Full Text - PDF
Tags: Tag hinzufügen
Keine Tags, Fügen Sie das erste Tag hinzu!
Abstract:IntroductionAccurate identification of graft loss in Electronic Medical Records of kidney transplant recipients is essential but challenging due to inconsistent and not mandatory International Classification of Diseases (ICD) codes. We developed and validated Natural Language Processing (NLP) and machine learning models to classify the status of kidney allografts in unstructured text in EMRs written in Spanish.MethodsWe conducted a retrospective cohort of 2712 patients transplanted between July 2008 and January 2023, analyzing 117,566 unstructured medical records. NLP involved text normalization, tokenization, stopwords removal, spell-checking, elimination of low-frequency words and stemming. Data was split in training, validation and test sets. Data balance was performed using undersampling technique. Feature selection was performed using LASSO regression. We developed, validated and tested Logistic Regression, Random Forest, and Neural Networks models using 10-fold cross-validation. Performance metrics included area under the curve, F1 Score, accuracy, sensitivity, specificity, Negative Predictive Value, and Positive Predictive Value.ResultsThe test performance results showed that the Random Forest model achieved the highest AUC (0.98) and F1 score (0.65). However, it had a modest sensitivity (0.76) and a relatively low PPV (0.56), implying a significant number of false positives. The Neural Network model also performed well with a high AUC (0.98) and reasonable F1 score (0.61), but its PPV (0.49) was lower, indicating more false positives. The Logistic Regression model, while having the lowest AUC (0.91) and F1 score (0.49), showed the highest sensitivity (0.83) with the lowest PPV (0.35).ConclusionWe developed and validated three machine learning models combined with NLP techniques for unstructured texts written in Spanish. The models performed well on the validation set but showed modest performance on the test set due to data imbalance. These models could be adapted for clinical practice, though they may require additional manual work due to high false positive rates.
ISSN:1932-6203
DOI:10.1371/journal.pone.0322587
Quelle:Health & Medical Collection