Incorporating a gastrointestinal failure score and a penalty function with the three latest SOFA scores into a machine learning model improved ICU mortality prediction, achieving an AUC of 0.9146.
Observational (n=4,500)
No
Does incorporating gastrointestinal failure parameters into SOFA score-based machine learning models improve ICU mortality prediction in critically ill patients?
Incorporating gastrointestinal failure parameters into SOFA-based machine learning models significantly improves the accuracy of ICU mortality prediction.
Absolute Event Rate: 0.9146% vs 0.9113%
BACKGROUND: The Sequential Organ Failure Assessment (SOFA) score is commonly used in ICUs around the world, designed to assess the severity of the patient's clinical state based on function/dysfunction of six major organ systems. The goal of this work is to build a computational model to predict mortality based on a series of SOFA scores. In addition, we examined the possibility of improving the prediction by incorporating a new component designed to measure the performance of the gastrointestinal system, added to the other six components. METHODS: In this retrospective study, we used patients' three latest SOFA scores recorded during an individual ICU stay as input to different machine learning models and ensemble learning models. We added three validated parameters representing gastrointestinal failure. Among others, we used classification models such as Support Vector Machines (SVMs), Neural Networks, Logistic Regression and a penalty function used to increase model robustness in regard to certain extreme cases, which may be found in ICU population. We used the Area under Curve (AUC) performance metric to examine performance. RESULTS: We found an ensemble model of linear and logistic regression achieves a higher AUC compared related works in past years. After incorporating the gastrointestinal failure score along with the penalty function, our best performing ensemble model resulted in an additional improvement in terms of AUC metrics. We implemented and compared 36 different models that were built using both the information from the SOFA score as well as that of the gastrointestinal system. All compared models have approximately similar and relatively large AUC (between 0.8645 and 0.9146) with the best results are achieved by incorporating the gastrointestinal parameters into the prediction models. CONCLUSIONS: Our findings indicate that gastrointestinal parameters carry significant information as a mortality predictor in addition to the conventional SOFA score. This information improves the predictive power of machine learning models by extending the SOFA to include information related to gastrointestinal organ system. The described method improves mortality prediction by considering the dynamics of the extended SOFA score. Although tested on a limited data set, the results' stability across different models suggests robustness in real-time use.
Aperstein et al. (Mon,) conduziram um estudo observacional em pacientes críticos de UTI (n=4.500). Modelos de aprendizado de máquina incorporando parâmetros gastrointestinais e escores SOFA vs. Modelos utilizando apenas os escores SOFA foram avaliados pela Área sob a curva (AUC) para previsão de mortalidade em UTI. Incorporar um escore de falência gastrointestinal e uma função de penalização com os três últimos escores SOFA em um modelo de aprendizado de máquina melhorou a previsão de mortalidade em UTI, atingindo uma AUC de 0,9146.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: