A computational approach to mortality prediction of alcohol use disorder inpatients. (1st August 2016)

• Record Type: Journal Article
• Authors: Calvert, Jacob; Mao, Qingqing; Rogers, Angela J.; Barton, Christopher; Jay, Melissa; Desautels, Thomas; Mohamadlou, Hamid; Jan, Jasmine; Das, Ritankar
• Is Part Of: Computers in biology and medicine. Volume 75(2016)
• Page Start: 74
• Page End: 79
• Publication Date: 2016-08-01
• Subjects: ICU Intensive Care Unit -- MICU Medical Intensive Care Unit -- EHR Electronic Health Records -- AUD Alcohol Use Disorder -- ICD-9 International Statistical Classification of Diseases version 9 -- MIMIC III Multiparameter Intelligent Monitoring in Intensive Care version III -- ROC Receiver Operating Characteristic -- AUROC Area Under Receiver Operating Characteristic -- CDSS Clinical Decision Support Systems -- MEWS Modified Early Warning Score -- SOFA Sepsis-Related Organ Failure Assessment -- SAPS II Simplified Acute Physiology Score -- WBC White Blood Cell count -- HIPAA Health Insurance Portability and Accountability Act -- BIDMC Beth Israel Deaconess Medical Center -- PPV Positive Predictive Value -- NPV Negative Predictive Value -- LR+ Positive Likelihood Ratio -- LR- Negative Likelihood Ratio -- OR Odds Ratio; Alcohol use disorder -- Clinical decision support systems -- Mortality prediction -- Electronic health records -- Medical informatics; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2016.05.015
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Background: Health information technologies can assist clinicians in the Intensive Care Unit (ICU) by providing additional analysis of patient stability. However, because patient diagnoses can be confounded by chronic alcohol use, the predictive value of existing systems is suboptimal. Through the use of Electronic Health Records (EHR), we have developed computer software called AutoTriage to generate accurate predictions through multi-dimensional analysis of clinical variables. We analyze the performance of AutoTriage on the Alcohol Use Disorder (AUD) subpopulation in this study, and build on results we reported for AutoTriage performance on the general population in previous work. Methods: AUD-related ICD-9 codes were used to obtain a patient population from MIMIC III ICU dataset for a retrospective study. Patient mortality risk score is generated through analysis of eight EHR-based clinical variables. The score is determined by combining weighted subscores, each of which are obtained from singlets, doublets or triplets of one or more of the eight continuous-valued clinical variable inputs. A temporally updating risk score is computed with a continuously revised 12-hour mortality prediction. Results: Among AUD patients, in a non-overlapping test set, AutoTriage outperforms existing systems with an Area Under Receiver Operating Characteristic (AUROC) value of 0.934 for 12-h mortality prediction. At a sensitivity of 90%, AutoTriage achieves a specificity of 80%, positive predictive value of 40%, negative predictive value of 89%, and an Odds Ratio of 36. Conclusions: For mortality prediction, AutoTriage demonstrates improvements in both the accuracy and the Odds Ratio over current systems among the AUD patient population. Highlights: AutoTriage algorithm predicts patient mortality in ICU among AUD patients. Multi-dimensional analysis of clinical inputs used to generate mortality risk scores. AutoTriage achieves sensitivity of 90% at a specificity of 80% with AUROC of 0.93. Mortality predicted 12 h in advance with an Odds Ratio of 36 and accuracy of 81%. Improvement of all metrics over MEWS, SAPS II, and SOFA for mortality prediction.