Towards neonatal mortality risk classification: A data-driven approach using neonatal, maternal, and social factors

A case-based reasoning system for neonatal survival and LOS prediction in neonatal intensive care units: a development and validation study

Early prediction of neonates' survival and Length of Stay (LOS) in Neonatal Intensive Care Units (NICU) is effective in decision-making. We developed an intelligent system to predict neonatal survival and LOS using the "Case-Based Reasoning" (CBR) method. We developed a web-based CBR system based on K-Nearest Neighborhood (KNN) on 1682 neonates and 17 variables for mortality and 13 variables for LOS and evaluated the system with 336 retrospectively collected data. We implemented the system in a NICU to externally validate the system and evaluate the system prediction acceptability and usability. Our internal validation on the balanced case base showed high accuracy (97.02%), and F-score (0.984) for survival prediction. The root Mean Square Error (RMSE) for LOS was 4.78 days. External validation on the balanced case base indicated high accuracy (98.91%), and F-score (0.993) to predict survival. RMSE for LOS was 3.27 days. Usability evaluation showed that more than half of the issues identified were related to appearance and rated as a low priority to be fixed. Acceptability assessment showed a high acceptance and confidence in responses. The usability score (80.71) indicated high system usability for neonatologists. This system is available at http://neonatalcdss.ir/ . Positive results of our system in terms of performance, acceptability, and usability indicated this system can be used to improve neonatal care.

Prediction of neonatal deaths in NICUs: development and validation of machine learning models

BACKGROUND

Prediction of neonatal deaths in NICUs is important for benchmarking and evaluating healthcare services in NICUs. Application of machine learning techniques can improve physicians' ability to predict the neonatal deaths. The aim of this study was to present a neonatal death risk prediction model using machine learning techniques.

METHODS

This study was conducted in Tehran, Iran in two phases. Initially, important risk factors in neonatal death were identified and then several machine learning models including Artificial Neural Network (ANN), decision tree (Random Forest (RF), C5.0 and CHART tree), Support Vector Machine (SVM), Bayesian Network and Ensemble models were developed. Finally, we prospectively applied these models to predict neonatal death in a NICU and followed up the neonates to compare the outcomes of these neonates with real outcomes.

RESULTS

17 factors were considered important in neonatal mortality prediction. The highest Area Under the Curve (AUC) was achieved for the SVM and Ensemble models with 0.98. The best precision and specificity were 0.98 and 0.94, respectively for the RF model. The highest accuracy, sensitivity and F-score were achieved for the SVM model with 0.94, 0.95 and 0.96, respectively. The best performance of models in prospective evaluation was for the ANN, C5.0 and CHAID tree models.

CONCLUSION

Using the developed machine learning models can help physicians predict the neonatal deaths in NICUs.