Use of machine learning to assess the prognostic utility of radiomic features for in-hospital COVID-19 mortality.

As portable chest X-rays are an efficient means of triaging emergent cases, their use has raised the question as to whether imaging carries additional prognostic utility for survival among patients with COVID-19. This study assessed the importance of known risk factors on in-hospital mortality and investigated the predictive utility of radiomic texture features using various machine learning approaches. We detected incremental improvements in survival prognostication utilizing texture features derived from emergent chest X-rays, particularly among older patients or those with a higher comorbidity burden. Important features included age, oxygen saturation, blood pressure, and certain comorbid conditions, as well as image features related to the intensity and variability of pixel distribution. Thus, widely available chest X-rays, in conjunction with clinical information, may be predictive of survival outcomes of patients with COVID-19, especially older, sicker patients, and can aid in disease management by providing additional information.

Portable Breath-Based Volatile Organic Compound Monitoring for the Detection of COVID-19 During the Circulation of the SARS-CoV-2 Delta Variant and the Transition to the SARS-CoV-2 Omicron Variant.

Importance: Breath analysis has been explored as a noninvasive means to detect COVID-19. However, the impact of emerging variants of SARS-CoV-2, such as Omicron, on the exhaled breath profile and diagnostic accuracy of breath analysis is unknown. Objective: To evaluate the diagnostic accuracies of breath analysis on detecting patients with COVID-19 when the SARS-CoV-2 Delta and Omicron variants were most prevalent. Design, Setting, and Participants: This diagnostic study included a cohort of patients who had positive and negative test results for COVID-19 using reverse transcriptase polymerase chain reaction between April 2021 and May 2022, which covers the period when the Delta variant was overtaken by Omicron as the major variant. Patients were enrolled through intensive care units and the emergency department at the University of Michigan Health System. Patient breath was analyzed with portable gas chromatography. Main Outcomes and Measures: Different sets of VOC biomarkers were identified that distinguished between COVID-19 (SARS-CoV-2 Delta and Omicron variants) and non-COVID-19 illness. Results: Overall, 205 breath samples from 167 adult patients were analyzed. A total of 77 patients (mean [SD] age, 58.5 [16.1] years; 41 [53.2%] male patients; 13 [16.9%] Black and 59 [76.6%] White patients) had COVID-19, and 91 patients (mean [SD] age, 54.3 [17.1] years; 43 [47.3%] male patients; 11 [12.1%] Black and 76 [83.5%] White patients) had non-COVID-19 illness. Several patients were analyzed over multiple days. Among 94 positive samples, 41 samples were from patients in 2021 infected with the Delta or other variants, and 53 samples were from patients in 2022 infected with the Omicron variant, based on the State of Michigan and US Centers for Disease Control and Prevention surveillance data. Four VOC biomarkers were found to distinguish between COVID-19 (Delta and other 2021 variants) and non-COVID-19 illness with an accuracy of 94.7%. However, accuracy dropped substantially to 82.1% when these biomarkers were applied to the Omicron variant. Four new VOC biomarkers were found to distinguish the Omicron variant and non-COVID-19 illness (accuracy, 90.9%). Breath analysis distinguished Omicron from the earlier variants with an accuracy of 91.5% and COVID-19 (all SARS-CoV-2 variants) vs non-COVID-19 illness with 90.2% accuracy. Conclusions and Relevance: The findings of this diagnostic study suggest that breath analysis has promise for COVID-19 detection. However, similar to rapid antigen testing, the emergence of new variants poses diagnostic challenges. The results of this study warrant additional evaluation on how to overcome these challenges to use breath analysis to improve the diagnosis and care of patients.

COVID-19 Transmission to Health Care Personnel During Tracheostomy Under a Multidisciplinary Safety Protocol.

BACKGROUND: Tracheostomies are highly aerosolizing procedures yet are often indicated in patients with COVID-19 who require prolonged intubation. Robust investigations of the safety of tracheostomy protocols and provider adherence and evaluations are limited. OBJECTIVES: To determine the rate of COVID-19 infection of health care personnel involved in COVID-19 tracheostomies under a multidisciplinary safety protocol and to investigate health care personnel's attitudes and suggested areas for improvement concerning the protocol. METHODS: All health care personnel involved in tracheostomies in COVID-19-positive patients from April 9 through July 11, 2020, were sent a 22-item electronic survey. RESULTS: Among 107 health care personnel (80.5%) who responded to the survey, 5 reported a positive COVID-19 test result (n = 2) or symptoms of COVID-19 (n = 3) within 21 days of the tracheostomy. Respondents reported 100% adherence to use of adequate personal protective equipment. Most (91%) were familiar with the tracheostomy protocol and felt safe (92%) while performing tracheostomy. Suggested improvements included creating dedicated tracheostomy teams and increasing provider choices surrounding personal protective equipment. CONCLUSIONS: Multidisciplinary engagement in the development and implementation of a COVID-19 tracheostomy protocol is associated with acceptable safety for all members of the care team.

Asthma and coronavirus disease 2019-related outcomes in hospitalized patients: A single-center experience.

BACKGROUND: Several chronic conditions have been associated with a higher risk of severe coronavirus disease 2019 (COVID-19), including asthma. However, there are conflicting conclusions regarding risk of severe disease in this population. OBJECTIVE: To understand the impact of asthma on COVID-19 outcomes in a cohort of hospitalized patients and whether there is any association between asthma severity and worse outcomes. METHODS: We identified hospitalized patients with COVID-19 with confirmatory polymerase chain reaction testing with (n = 183) and without asthma (n = 1319) using International Classification of Diseases, Tenth Revision, codes between March 1 and December 30, 2020. We determined asthma maintenance medications, pulmonary function tests, highest historical absolute eosinophil count, and immunoglobulin E. Primary outcomes included death, mechanical ventilation, intensive care unit (ICU) admission, and ICU and hospital length of stay. Analysis was adjusted for demographics, comorbidities, smoking status, and timing of illness in the pandemic. RESULTS: In unadjusted analyses, we found no difference in our primary outcomes between patients with asthma and patients without asthma. However, in adjusted analyses, patients with asthma were more likely to have mechanical ventilation (odds ratio, 1.58; 95% confidence interval [CI], 1.02-2.44; P = .04), ICU admission (odds ratio, 1.58; 95% CI, 1.09-2.29; P = .02), longer hospital length of stay (risk ratio, 1.30; 95% CI, 1.09-1.55; P < .003), and higher mortality (hazard ratio, 1.53; 95% CI, 1.01-2.33; P = .04) compared with the non-asthma cohort. Inhaled corticosteroid use and eosinophilic phenotype were not associated with considerabledifferences. Interestingly, patients with moderate asthma had worse outcomes whereas patients with severe asthma did not. CONCLUSION: Asthma was associated with severe COVID-19 after controlling for other factors.

Early identification of patients admitted to hospital for covid-19 at risk of clinical deterioration: model development and multisite external validation study.

OBJECTIVE: To create and validate a simple and transferable machine learning model from electronic health record data to accurately predict clinical deterioration in patients with covid-19 across institutions, through use of a novel paradigm for model development and code sharing. DESIGN: Retrospective cohort study. SETTING: One US hospital during 2015-21 was used for model training and internal validation. External validation was conducted on patients admitted to hospital with covid-19 at 12 other US medical centers during 2020-21. PARTICIPANTS: 33 119 adults (≥18 years) admitted to hospital with respiratory distress or covid-19. MAIN OUTCOME MEASURES: An ensemble of linear models was trained on the development cohort to predict a composite outcome of clinical deterioration within the first five days of hospital admission, defined as in-hospital mortality or any of three treatments indicating severe illness: mechanical ventilation, heated high flow nasal cannula, or intravenous vasopressors. The model was based on nine clinical and personal characteristic variables selected from 2686 variables available in the electronic health record. Internal and external validation performance was measured using the area under the receiver operating characteristic curve (AUROC) and the expected calibration error-the difference between predicted risk and actual risk. Potential bed day savings were estimated by calculating how many bed days hospitals could save per patient if low risk patients identified by the model were discharged early. RESULTS: 9291 covid-19 related hospital admissions at 13 medical centers were used for model validation, of which 1510 (16.3%) were related to the primary outcome. When the model was applied to the internal validation cohort, it achieved an AUROC of 0.80 (95% confidence interval 0.77 to 0.84) and an expected calibration error of 0.01 (95% confidence interval 0.00 to 0.02). Performance was consistent when validated in the 12 external medical centers (AUROC range 0.77-0.84), across subgroups of sex, age, race, and ethnicity (AUROC range 0.78-0.84), and across quarters (AUROC range 0.73-0.83). Using the model to triage low risk patients could potentially save up to 7.8 bed days per patient resulting from early discharge. CONCLUSION: A model to predict clinical deterioration was developed rapidly in response to the covid-19 pandemic at a single hospital, was applied externally without the sharing of data, and performed well across multiple medical centers, patient subgroups, and time periods, showing its potential as a tool for use in optimizing healthcare resources.

Augmenting existing deterioration indices with chest radiographs to predict clinical deterioration.

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.

Comprehensive evaluation of COVID-19 patient short- and long-term outcomes: Disparities in healthcare utilization and post-hospitalization outcomes.

BACKGROUND: Understanding risk factors for short- and long-term COVID-19 outcomes have implications for current guidelines and practice. We study whether early identified risk factors for COVID-19 persist one year later and through varying disease progression trajectories. METHODS: This was a retrospective study of 6,731 COVID-19 patients presenting to Michigan Medicine between March 10, 2020 and March 10, 2021. We describe disease progression trajectories from diagnosis to potential hospital admission, discharge, readmission, or death. Outcomes pertained to all patients: rate of medical encounters, hospitalization-free survival, and overall survival, and hospitalized patients: discharge versus in-hospital death and readmission. Risk factors included patient age, sex, race, body mass index, and 29 comorbidity conditions. RESULTS: Younger, non-Black patients utilized healthcare resources at higher rates, while older, male, and Black patients had higher rates of hospitalization and mortality. Diabetes with complications, coagulopathy, fluid and electrolyte disorders, and blood loss anemia were risk factors for these outcomes. Diabetes with complications, coagulopathy, fluid and electrolyte disorders, and blood loss were associated with lower discharge and higher inpatient mortality rates. CONCLUSIONS: This study found differences in healthcare utilization and adverse COVID-19 outcomes, as well as differing risk factors for short- and long-term outcomes throughout disease progression. These findings may inform providers in emergency departments or critical care settings of treatment priorities, empower healthcare stakeholders with effective disease management strategies, and aid health policy makers in optimizing allocations of medical resources.

Racial Bias in Pulse Oximetry Measurement Among Patients About to Undergo Extracorporeal Membrane Oxygenation in 2019-2020: A Retrospective Cohort Study.

BACKGROUND: Pulse oximeters may produce less accurate results in non-White patients. RESEARCH QUESTION: Do pulse oximeters detect arterial hypoxemia less effectively in Black, Hispanic, and/or Asian patients than in White patients in respiratory failure and about to undergo extracorporeal membrane oxygenation (ECMO)? STUDY DESIGN AND METHODS: Data on adult patients with respiratory failure readings 6 h before ECMO were provided by the Extracorporeal Life Support Organization registry. Data was collected from 324 centers between January 2019 and July 2020. Our primary analysis was of rates of occult hypoxemia-low arterial oxygen saturation (Sao2 ≤ 88%) on arterial blood gas measurement despite a pulse oximetry reading in the range of 92% to 96%. RESULTS: The rate of pre-ECMO occult hypoxemia, that is, arterial oxygen saturation (Sao2) ≤ 88%, was 10.2% (95% CI, 6.2%-15.3%) for 186 White patients with peripheral oxygen saturation (Spo2) of 92% to 96%; 21.5% (95% CI, 11.3%-35.3%) for 51 Black patients (P = .031 vs White); 8.6% (95% CI, 3.2%-17.7%) for 70 Hispanic patients (P = .693 vs White); and 9.2% (95% CI, 3.5%-19.0%) for 65 Asian patients (P = .820 vs White). Black patients with respiratory failure had a statistically significantly higher risk of occult hypoxemia with an OR of 2.57 (95% CI, 1.12-5.92) compared with White patients (P = .026). The risk of occult hypoxemia for Hispanic and Asian patients was equivalent to that of White patients. In a secondary analysis of patients with Sao2 ≤ 88% despite Spo2 > 96%, Black patients had more than three times the risk compared with White patients (OR, 3.52; 95% CI, 1.12-11.10; P = .032). INTERPRETATION: Compared with White patients, the prevalence of occult hypoxemia was higher in Black patients than in White patients about to undergo ECMO for respiratory failure, but it was comparable in Hispanic and Asian patients compared with White patients.

Tracheostomy for COVID-19 respiratory failure: timing, ventilatory characteristics, and outcomes.

BACKGROUND: Whereas data from the pre-pandemic era have demonstrated that tracheostomy can accelerate liberation from the ventilator, reduce need for sedation, and facilitate rehabilitation, concerns for healthcare worker safety have led to disagreement on tracheostomy placement in COVID-19 patients. Data on COVID-19 patients undergoing tracheostomy may inform best practices. Thus, we report a retrospective institutional cohort experience with tracheostomy in ventilated patients with COVID-19, examining associations between time to tracheostomy and duration of mechanical ventilation in relation to patient characteristics, clinical course, and survival. METHODS: Clinical data were extracted for all COVID-19 tracheostomies performed at a quaternary referral center from April-July 2020. Outcomes studied included mortality, adverse events, duration of mechanical ventilation, and time to decannulation. RESULTS: Among 64 COVID-19 tracheostomies (13% of COVID-19 hospitalizations), patients were 64% male and 42% African American, with a median age of 54 (range, 20-89). Median time to tracheostomy was 22 (range, 7-60) days and median duration of mechanical ventilation was 39.4 (range, 20-113) days. Earlier tracheostomy was associated with shortened mechanical ventilation (R2=0.4, P<0.01). Median decannulation time was 35.3 (range, 7-79) days. There was 19% mortality and adverse events in 45%, mostly from bleeding in therapeutically anticoagulated patients. CONCLUSIONS: Tracheostomy was associated with swifter liberation from the ventilator and acceptable safety for physicians in this series of critically ill COVID-19 patients. Patient mortality was not increased relative to historical data on acute respiratory distress syndrome (ARDS). Future studies are required to establish conclusions of causality regarding tracheostomy timing with mechanical ventilation, complications, or mortality in COVID-19 patients.

Automated detection of acute respiratory distress syndrome from chest X-Rays using Directionality Measure and deep learning features.

Acute respiratory distress syndrome (ARDS) is a life-threatening lung injury with global prevalence and high mortality. Chest x-rays (CXR) are critical in the early diagnosis and treatment of ARDS. However, imaging findings may not result in proper identification of ARDS due to a number of reasons, including nonspecific appearance of radiological features, ambiguity in a patient's case due to the pathological stage of the disease, and poor inter-rater reliability from interpretations of CXRs by multiple clinical experts. This study demonstrates the potential capability of methodologies in artificial intelligence, machine learning, and image processing to overcome these challenges and quantitatively assess CXRs for presence of ARDS. We propose and describe Directionality Measure, a novel feature engineering technique used to capture the "cloud-like" appearance of diffuse alveolar damage as a mathematical concept. This study also examines the effectiveness of using an off-the-shelf, pretrained deep learning model as a feature extractor in addition to standard features extracted from the histogram and gray-level co-occurrence matrix (GLCM). Data was collected from hospitalized patients at Michigan Medicine's intensive care unit and the cohort's inclusion criteria was specifically designed to be representative of patients at risk of developing ARDS. Multiple machine learning models were used to evaluate these features with 5-fold cross-validation and the final performance was reported on a hold-out, temporally distinct test set. With AdaBoost, Directionality Measure achieved an accuracy of 78% and AUC of 74% - outperforming classification results using features from the histogram (75% accuracy and 73% AUC), GLCM (76% accuracy and 73% AUC), and ResNet-50 (77% accuracy and 73% AUC). Further experimental results demonstrated that using all feature sets in combination achieved the best overall performance, yielding an accuracy of 83% and AUC of 79% with AdaBoost. These results demonstrate the potential capability of using the proposed methodologies to complement current clinical analysis for detection of ARDS from CXRs.

Predicting Intensive Care Transfers and Other Unforeseen Events: Analytic Model Validation Study and Comparison to Existing Methods.

BACKGROUND: COVID-19 has led to an unprecedented strain on health care facilities across the United States. Accurately identifying patients at an increased risk of deterioration may help hospitals manage their resources while improving the quality of patient care. Here, we present the results of an analytical model, Predicting Intensive Care Transfers and Other Unforeseen Events (PICTURE), to identify patients at high risk for imminent intensive care unit transfer, respiratory failure, or death, with the intention to improve the prediction of deterioration due to COVID-19. OBJECTIVE: This study aims to validate the PICTURE model's ability to predict unexpected deterioration in general ward and COVID-19 patients, and to compare its performance with the Epic Deterioration Index (EDI), an existing model that has recently been assessed for use in patients with COVID-19. METHODS: The PICTURE model was trained and validated on a cohort of hospitalized non-COVID-19 patients using electronic health record data from 2014 to 2018. It was then applied to two holdout test sets: non-COVID-19 patients from 2019 and patients testing positive for COVID-19 in 2020. PICTURE results were aligned to EDI and NEWS scores for head-to-head comparison via area under the receiver operating characteristic curve (AUROC) and area under the precision-recall curve. We compared the models' ability to predict an adverse event (defined as intensive care unit transfer, mechanical ventilation use, or death). Shapley values were used to provide explanations for PICTURE predictions. RESULTS: In non-COVID-19 general ward patients, PICTURE achieved an AUROC of 0.819 (95% CI 0.805-0.834) per observation, compared to the EDI's AUROC of 0.763 (95% CI 0.746-0.781; n=21,740; P<.001). In patients testing positive for COVID-19, PICTURE again outperformed the EDI with an AUROC of 0.849 (95% CI 0.820-0.878) compared to the EDI's AUROC of 0.803 (95% CI 0.772-0.838; n=607; P<.001). The most important variables influencing PICTURE predictions in the COVID-19 cohort were a rapid respiratory rate, a high level of oxygen support, low oxygen saturation, and impaired mental status (Glasgow Coma Scale). CONCLUSIONS: The PICTURE model is more accurate in predicting adverse patient outcomes for both general ward patients and COVID-19 positive patients in our cohorts compared to the EDI. The ability to consistently anticipate these events may be especially valuable when considering potential incipient waves of COVID-19 infections. The generalizability of the model will require testing in other health care systems for validation.

Deep learning to detect acute respiratory distress syndrome on chest radiographs: a retrospective study with external validation.

BACKGROUND: Acute respiratory distress syndrome (ARDS) is a common, but under-recognised, critical illness syndrome associated with high mortality. An important factor in its under-recognition is the variability in chest radiograph interpretation for ARDS. We sought to train a deep convolutional neural network (CNN) to detect ARDS findings on chest radiographs. METHODS: CNNs were pretrained on 595 506 radiographs from two centres to identify common chest findings (eg, opacity and effusion), and then trained on 8072 radiographs annotated for ARDS by multiple physicians using various transfer learning approaches. The best performing CNN was tested on chest radiographs in an internal and external cohort, including a subset reviewed by six physicians, including a chest radiologist and physicians trained in intensive care medicine. Chest radiograph data were acquired from four US hospitals. FINDINGS: In an internal test set of 1560 chest radiographs from 455 patients with acute hypoxaemic respiratory failure, a CNN could detect ARDS with an area under the receiver operator characteristics curve (AUROC) of 0·92 (95% CI 0·89-0·94). In the subgroup of 413 images reviewed by at least six physicians, its AUROC was 0·93 (95% CI 0·88-0·96), sensitivity 83·0% (95% CI 74·0-91·1), and specificity 88·3% (95% CI 83·1-92·8). Among images with zero of six ARDS annotations (n=155), the median CNN probability was 11%, with six (4%) assigned a probability above 50%. Among images with six of six ARDS annotations (n=27), the median CNN probability was 91%, with two (7%) assigned a probability below 50%. In an external cohort of 958 chest radiographs from 431 patients with sepsis, the AUROC was 0·88 (95% CI 0·85-0·91). When radiographs annotated as equivocal were excluded, the AUROC was 0·93 (0·92-0·95). INTERPRETATION: A CNN can be trained to achieve expert physician-level performance in ARDS detection on chest radiographs. Further research is needed to evaluate the use of these algorithms to support real-time identification of ARDS patients to ensure fidelity with evidence-based care or to support ongoing ARDS research. FUNDING: National Institutes of Health, Department of Defense, and Department of Veterans Affairs.

Comparing Clinical Features and Outcomes in Mechanically Ventilated Patients with COVID-19 and Acute Respiratory Distress Syndrome.

Rationale: Patients with severe coronavirus disease (COVID-19) meet clinical criteria for the acute respiratory distress syndrome (ARDS), yet early reports suggested they differ physiologically and clinically from patients with non-COVID-19 ARDS, prompting treatment recommendations that deviate from standard evidence-based practices for ARDS. Objectives: To compare respiratory physiology, clinical outcomes, and extrapulmonary clinical features of severe COVID-19 with non-COVID-19 ARDS. Methods: We performed a retrospective cohort study, comparing 130 consecutive mechanically ventilated patients with severe COVID-19 with 382 consecutive mechanically ventilated patients with non-COVID-19 ARDS. Initial respiratory physiology and 28-day outcomes were compared. Extrapulmonary manifestations (inflammation, extrapulmonary organ injury, and coagulation) were compared in an exploratory analysis. Results: Comparison of patients with COVID-19 and non-COVID-19 ARDS suggested small differences in respiratory compliance, ventilatory efficiency, and oxygenation. The 28-day mortality was 30% in patients with COVID-19 and 38% in patients with non-COVID-19 ARDS. In adjusted analysis, point estimates of differences in time to breathing unassisted at 28 days (adjusted subdistributional hazards ratio, 0.98 [95% confidence interval (CI), 0.77-1.26]) and 28-day mortality (risk ratio, 1.01 [95% CI, 0.72-1.42]) were small for COVID-19 versus non-COVID-19 ARDS, although the confidence intervals for these estimates include moderate differences. Patients with COVID-19 had lower neutrophil counts but did not differ in lymphocyte count or other measures of systemic inflammation. Conclusions: In this single-center cohort, we found no evidence for large differences between COVID-19 and non-COVID-19 ARDS. Many key clinical features of severe COVID-19 were similar to those of non-COVID-19 ARDS, including respiratory physiology and clinical outcomes, although our sample size precludes definitive conclusions. Further studies are needed to define COVID-19-specific pathophysiology before a deviation from evidence-based treatment practices can be recommended.

Improving Prone Positioning for Severe Acute Respiratory Distress Syndrome during the COVID-19 Pandemic. An Implementation-Mapping Approach.

Rationale: Prone positioning reduces mortality in patients with severe acute respiratory distress syndrome (ARDS), a feature of severe coronavirus disease 2019 (COVID-19). Despite this, most patients with ARDS do not receive this lifesaving therapy.Objectives: To identify determinants of prone-positioning use, to develop specific implementation strategies, and to incorporate strategies into an overarching response to the COVID-19 crisis.Methods: We used an implementation-mapping approach guided by implementation-science frameworks. We conducted semistructured interviews with 30 intensive care unit (ICU) clinicians who staffed 12 ICUs within the Penn Medicine Health System and the University of Michigan Medical Center. We performed thematic analysis using the Consolidated Framework for Implementation Research. We then conducted three focus groups with a task force of ICU leaders to develop an implementation menu, using the Expert Recommendations for Implementing Change framework. The implementation strategies were adapted as part of the Penn Medicine COVID-19 pandemic response.Results: We identified five broad themes of determinants of prone positioning, including knowledge, resources, alternative therapies, team culture, and patient factors, which collectively spanned all five Consolidated Framework for Implementation Research domains. The task force developed five specific implementation strategies, including educational outreach, learning collaborative, clinical protocol, prone-positioning team, and automated alerting, elements of which were rapidly implemented at Penn Medicine.Conclusions: We identified five broad themes of determinants of evidence-based use of prone positioning for severe ARDS and several specific strategies to address these themes. These strategies may be feasible for rapid implementation to increase use of prone positioning for severe ARDS with COVID-19.

Evaluating a Widely Implemented Proprietary Deterioration Index Model among Hospitalized Patients with COVID-19.

Rationale: The Epic Deterioration Index (EDI) is a proprietary prediction model implemented in over 100 U.S. hospitals that was widely used to support medical decision-making during the coronavirus disease (COVID-19) pandemic. The EDI has not been independently evaluated, and other proprietary models have been shown to be biased against vulnerable populations. Objectives: To independently evaluate the EDI in hospitalized patients with COVID-19 overall and in disproportionately affected subgroups. Methods: We studied adult patients admitted with COVID-19 to units other than the intensive care unit at a large academic medical center from March 9 through May 20, 2020. We used the EDI, calculated at 15-minute intervals, to predict a composite outcome of intensive care unit-level care, mechanical ventilation, or in-hospital death. In a subset of patients hospitalized for at least 48 hours, we also evaluated the ability of the EDI to identify patients at low risk of experiencing this composite outcome during their remaining hospitalization. Results: Among 392 COVID-19 hospitalizations meeting inclusion criteria, 103 (26%) met the composite outcome. The median age of the cohort was 64 (interquartile range, 53-75) with 168 (43%) Black patients and 169 (43%) women. The area under the receiver-operating characteristic curve of the EDI was 0.79 (95% confidence interval, 0.74-0.84). EDI predictions did not differ by race or sex. When exploring clinically relevant thresholds of the EDI, we found patients who met or exceeded an EDI of 68.8 made up 14% of the study cohort and had a 74% probability of experiencing the composite outcome during their hospitalization with a sensitivity of 39% and a median lead time of 24 hours from when this threshold was first exceeded. Among the 286 patients hospitalized for at least 48 hours who had not experienced the composite outcome, 14 (13%) never exceeded an EDI of 37.9, with a negative predictive value of 90% and a sensitivity above this threshold of 91%. Conclusions: We found the EDI identifies small subsets of high-risk and low-risk patients with COVID-19 with good discrimination, although its clinical use as an early warning system is limited by low sensitivity. These findings highlight the importance of independent evaluation of proprietary models before widespread operational use among patients with COVID-19.