Abstract:Introduction: Early recognition of impending systemic failure with proper medical cares is critical for timely interventions. The Modified Early Warning Score (MEWS) is an essential tool for the identification of deteriorating patients. Considering the increasing complexity of patient conditions, the MEWS system does not take into account factors such as gender, age, chronic diseases, and other risk factors. This results in overly frequent alerts from the automated warning system, with a high number of false alarms that hinder healthcare professionals from making accurate clinical judgments. By the predictive model results, detect critical risk factors at an early stage, providing for clinical decision-making and enhancing the overall quality of patient care. Methods: Retrospective data of cases in the chest wards of a medical center about 4108 patients from January to June 2021. Features use the patient’s intervention measures and comorbidity parameters during hospitalization to understand the patient’s physical condition, and use machine learning to let the computer learn and judge, and then predict the patient’s final condition. Four model evaluation indicators were used, and XG Boost was the best prediction model, so it was adopted as the final model for prediction in this study. Results: The relationship between all feature values “‹”‹and the predicted target (death) is moderately correlated with signing DNR, the shift time of the nursing station, and the patient’s age. Among the comorbidities, diabetes, hypertension, heart failure, and renal failure have a greater impact.The staff accept the MEWS easily because of the clear design . The incidence of CPR was reduced from 2.42% to 1.58% after application of the MEWS in 2022. The MEWS helped the improvement of the clinical outcomes in our study. Conclusion: The establishment of the MEWS system is the basis for improvement. Comorbidities are graded according to disease severity to more accurately predict the impact of comorbidities.
Keywords: Artificial Intelligence and Healthcare, Machine Learning(ML)， MEWS
