Augmenting existing deterioration indices with chest radiographs to predict clinical deterioration

Abstract

Importance When hospitals are at capacity, accurate deterioration indices could help identify low-risk patients as potential candidates for home care programs and alleviate hospital strain. To date, many existing deterioration indices are based entirely on structured data from the electronic health record (EHR) and ignore potentially useful information from other sources. Objective To improve the accuracy of existing deterioration indices by incorporating unstructured imaging data from chest radiographs. Design, setting, and participants Machine learning models were trained to predict deterioration of patients hospitalized with acute dyspnea using existing deterioration index scores and chest radiographs. Models were trained on hospitalized patients without coronavirus disease 2019 (COVID-19) and then subsequently tested on patients with COVID-19 between January 2020 and December 2020 at a single tertiary care center who had at least one radiograph taken within 48 hours of hospital admission. Main outcomes and measures Patient deterioration was defined as the need for invasive or non-invasive mechanical ventilation, heated high flow nasal cannula, IV vasopressor administration or in-hospital mortality at any time following admission. The EPIC deterioration index was augmented with unstructured data from chest radiographs to predict risk of deterioration. We compared discriminative performance of the models with and without incorporating chest radiographs using area under the receiver operating curve (AUROC), focusing on comparing the fraction and total patients identified as low risk at different negative predictive values (NPV). Results Data from 6278 hospitalizations were analyzed, including 5562 hospitalizations without COVID-19 (training cohort) and 716 with COVID-19 (216 in validation, 500 in held-out test cohort). At a NPV of 0.95, the best-performing image-augmented deterioration index identified 49 more (9.8%) individuals as low-risk compared to the deterioration index based on clinical data alone in the first 48 hours of admission. At a NPV of 0.9, the EPIC image-augmented deterioration index identified 26 more individuals (5.2%) as low-risk compared to the deterioration index based on clinical data alone in the first 48 hours of admission. Conclusion and relevance Augmenting existing deterioration indices with chest radiographs results in better identification of low-risk patients. The model augmentation strategy could be used in the future to incorporate other forms of unstructured data into existing disease models.

The Problem of Pain in Rheumatology: Clinical Profiles Associated With Concomitant Diagnoses With Chronic Overlapping Pain Conditions

“…Using ICD codes to identify patients may lead to some misclassification; however, we required multiple visits within a specific time to reduce potential false positives. The complexity challenges of using ICD codes and other structured data for identifying cases are myriad, and one way to overcome these biases is to include unstructured data (or clinic notes) in developing computational phenotyping algorithms ( 22 , 23 ). We found that the prevalence of individual COPCs in our study is lower than other recently published studies.…”

Contrastive Transfer Learning for Prediction of Adverse Events in Hospitalized Patients

“…Epic’s Deterioration Index (DI) is one of the most widely used early warning systems deployed in hundreds of hospitals across the United States [1] , [2] . This system aims to detect patients who deteriorate and require higher levels of care.…”

“…The high-risk patients are at the greatest risk of encountering a composite adverse outcome which can be prevented by prompt interventions. This has been found to have fair performance and improve patient outcomes and reduce ICU admissions [2] .…”

“…Limited research has been conducted on the DI score and its relationship with adverse outcomes in clinical settings. DI scores were augmented with chest radiographs in [2] to predict clinical deterioration (death or the need for ICU-level therapies including invasive or non-invasive mechanical ventilation, heated high flow nasal cannula, or vasopressor support) for hospitalized patients with acute dyspnea. The general objective was to improve accuracy of the DI score by incorporating patients’ imaging data, who required supplemental oxygen during their hospitalization and had at least one chest radiograph performed during the first 48 hours.…”

Novel machine learning model to improve performance of an early warning system in hospitalized patients: a retrospective multisite cross-validation study

“…Epic’s Deterioration Index (EDI) is a proprietary algorithm and one of the most widely used EWS deployed in hundreds of hospitals across the US. 3 , 4 This system generates a patient risk score after hospital admission, and it is then regularly calculated based on most recent available data at 15-min intervals until discharge. A DI score value ranges between 0 and 100, defining low (<30 green), intermediate (30–60 orange), or high risk (>60 red) of a composite AE: all-cause mortality, cardiac arrest, transfer to intensive care, and evaluation by the rapid response team.…”