PreprintArticleVersion 1This version is not peer-reviewed
Development and Validation of a Logistic Regression Model to Predict Post-Operative Mortality in Emergency Cardiac Surgeries: A Comprehensive Analysis of Pre-Operative Factors and Model Performance
Version 1
: Received: 18 July 2024 / Approved: 19 July 2024 / Online: 25 July 2024 (09:39:22 CEST)
How to cite:
Patel, D.; Hofmann, J.; Bouras, A. Development and Validation of a Logistic Regression Model to Predict Post-Operative Mortality in Emergency Cardiac Surgeries: A Comprehensive Analysis of Pre-Operative Factors and Model Performance. Preprints2024, 2024072002. https://doi.org/10.20944/preprints202407.2002.v1
Patel, D.; Hofmann, J.; Bouras, A. Development and Validation of a Logistic Regression Model to Predict Post-Operative Mortality in Emergency Cardiac Surgeries: A Comprehensive Analysis of Pre-Operative Factors and Model Performance. Preprints 2024, 2024072002. https://doi.org/10.20944/preprints202407.2002.v1
Patel, D.; Hofmann, J.; Bouras, A. Development and Validation of a Logistic Regression Model to Predict Post-Operative Mortality in Emergency Cardiac Surgeries: A Comprehensive Analysis of Pre-Operative Factors and Model Performance. Preprints2024, 2024072002. https://doi.org/10.20944/preprints202407.2002.v1
APA Style
Patel, D., Hofmann, J., & Bouras, A. (2024). Development and Validation of a Logistic Regression Model to Predict Post-Operative Mortality in Emergency Cardiac Surgeries: A Comprehensive Analysis of Pre-Operative Factors and Model Performance. Preprints. https://doi.org/10.20944/preprints202407.2002.v1
Chicago/Turabian Style
Patel, D., Jonathan Hofmann and Andrew Bouras. 2024 "Development and Validation of a Logistic Regression Model to Predict Post-Operative Mortality in Emergency Cardiac Surgeries: A Comprehensive Analysis of Pre-Operative Factors and Model Performance" Preprints. https://doi.org/10.20944/preprints202407.2002.v1
Abstract
Objective:The primary objective of this study was to develop a logistic regression model to predictpost-operative in-hospital mortality rates for patients undergoing emergency cardiac surgeries, withthe aim of improving predictive accuracy over traditional risk assessment tools and enhancing patientoutcomes and clinical decision-making.Methods:Data were collected from 4,855 patients who underwent emergency cardiac surgeries ata tertiary hospital between 2008 and 2017.The analysis incorporated demographic, anthropomet-ric, and clinical factors, including the ASA classification, emergency status, and various preoperativelaboratory values. A logistic regression model was developed, and the Elixhauser Comorbidity Indexwas calculated using standard ICD-10 codes for its comprehensive assessment of comorbidities. Modelperformance was evaluated using metrics such as AUROC, AUPRC, accuracy, precision, recall, andF1 score.Results:The logistic regression model demonstrated strong predictive performance, with an AUROCof 0.939 and an AUPRC of 0.350. Key pre-operative factors identified included emergency operationstatus, ASA classification, and preoperative prothrombin time. The model significantly outperformedthe traditional ASA classification system, which showed an AUROC of 0.524 and an AUPRC of 0.010.These findings suggest a substantial improvement in predicting post-operative mortality.Conclusion:The logistic regression model significantly improves the prediction of post-operativemortality in emergency cardiac surgeries compared to the ASA classification system. These findingshighlight the potential of incorporating comprehensive pre-operative factors into predictive models toenhance clinical decision-making and patient outcomes. Implementing such models in routine clinicalpractice could lead to more accurate risk assessments, better resource allocation, and improved patientcare.
Keywords
Logistic Regression Model; Post-operative Mortality; Emergency Cardiac Surgeries; Predictive Accuracy; Clinical Decision-Making; ASA Classification; Elixhauser Comorbidity Index; Preoperative Factors; AUROC (Area Under the Receiver Operating Characteristic Curve); AUPRC (Area Under the Precision-Recall Curve); Model Performance Metrics; Preoperative Prothrombin Time; Traditional Risk Assessment Tools; Tertiary Hospital Data; Patient Outcomes
Subject
Medicine and Pharmacology, Cardiac and Cardiovascular Systems
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
