Dataset Information

Development and validation of predictive models for COVID-19 outcomes in a safety-net hospital population.

ABSTRACT:

Objective

To develop predictive models of coronavirus disease 2019 (COVID-19) outcomes, elucidate the influence of socioeconomic factors, and assess algorithmic racial fairness using a racially diverse patient population with high social needs.

Materials and methods

Data included 7,102 patients with positive (RT-PCR) severe acute respiratory syndrome coronavirus 2 test at a safety-net system in Massachusetts. Linear and nonlinear classification methods were applied. A score based on a recurrent neural network and a transformer architecture was developed to capture the dynamic evolution of vital signs. Combined with patient characteristics, clinical variables, and hospital occupancy measures, this dynamic vital score was used to train predictive models.

Results

Hospitalizations can be predicted with an area under the receiver-operating characteristic curve (AUC) of 92% using symptoms, hospital occupancy, and patient characteristics, including social determinants of health. Parsimonious models to predict intensive care, mechanical ventilation, and mortality that used the most recent labs and vitals exhibited AUCs of 92.7%, 91.2%, and 94%, respectively. Early predictive models, using labs and vital signs closer to admission had AUCs of 81.1%, 84.9%, and 92%, respectively.

Discussion

The most accurate models exhibit racial bias, being more likely to falsely predict that Black patients will be hospitalized. Models that are only based on the dynamic vital score exhibited accuracies close to the best parsimonious models, although the latter also used laboratories.

Conclusions

This large study demonstrates that COVID-19 severity may accurately be predicted using a score that accounts for the dynamic evolution of vital signs. Further, race, social determinants of health, and hospital occupancy play an important role.

SUBMITTER: Hao B

PROVIDER: S-EPMC9129120 | biostudies-literature | 2022 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Development and validation of predictive models for COVID-19 outcomes in a safety-net hospital population.

Hao Boran B Hu Yang Y Sotudian Shahabeddin S Zad Zahra Z Adams William G WG Assoumou Sabrina A SA Hsu Heather H Mishuris Rebecca G RG Paschalidis Ioannis C IC

Journal of the American Medical Informatics Association : JAMIA 20220601 7

<h4>Objective</h4>To develop predictive models of coronavirus disease 2019 (COVID-19) outcomes, elucidate the influence of socioeconomic factors, and assess algorithmic racial fairness using a racially diverse patient population with high social needs.<h4>Materials and methods</h4>Data included 7,102 patients with positive (RT-PCR) severe acute respiratory syndrome coronavirus 2 test at a safety-net system in Massachusetts. Linear and nonlinear classification methods were applied. A score based ...[more]

PMID: 35441692

Similar Datasets

Project description:Risk calculators can facilitate shared medical decision-making 1 . Demographics, comorbidities, medication use, geographic region, and other factors may increase the risk for COVID-19-related complications among patients with IBD 2,3 . Develop an individualized prognostic risk prediction tool for predicting the probability of adverse COVID-19 outcomes in patients with IBD. This study developed and validated prognostic penalized logistic regression models 4 using reports to Surveillance Epidemiology of Coronavirus Under Research Exclusion for Inflammatory Bowel Disease (SECURE-IBD) from March-October 2020. Model development was done using a training data set (85% of cases reported March 13 - September 15, 2020), and model validation was conducted using a test data set (the remaining 15% of cases plus all cases reported September 16-October 20, 2020). COVID-19 related:Hospitalization+: composite outcome of hospitalization, ICU admission, mechanical ventilation, or deathICU+: composite outcome of ICU admission, mechanical ventilation, or deathDeathWe assessed the resulting models' discrimination using the area under the curve (AUC) of the receiver-operator characteristic (ROC) curves and reported the corresponding 95% confidence intervals (CIs). We included 2709 cases from 59 countries (mean age 41.2 years [s.d. 18], 50.2% male). A total of 633 (24%) were hospitalized, 137 (5%) were admitted to the ICU or intubated, and 69 (3%) died. 2009 patients comprised the training set and 700 the test set.The models demonstrated excellent discrimination, with a test set AUC (95% CI) of 0.79 (0.75, 0.83) for Hospitalization+, 0.88 (0.82, 0.95) for ICU+, and 0.94 (0.89, 0.99) for Death. Age, comorbidities, corticosteroid use, and male gender were associated with higher risk of death, while use of biologic therapies was associated with a lower risk. Prognostic models can effectively predict who is at higher risk for COVID-19-related adverse outcomes in a population of IBD patients. A free online risk calculator ( https://covidibd.org/covid-19-risk-calculator/ ) is available for healthcare providers to facilitate discussion of risks due to COVID-19 with IBD patients. The tool numerically and visually summarizes the patient's probabilities of adverse outcomes and associated CIs. Helping physicians identify their highest-risk patients will be important in the coming months as cases rise in the US and worldwide. This tool can also serve as a model for risk stratification in other chronic diseases. Question: How well can a multivariable risk model predict the risk of hospitalization, intensive care unit (ICU) stay, or death due to COVID-19 in patients with inflammatory bowel disease (IBD)?Findings: Multivariable prediction models developed using data from an international voluntary registry of IBD patients and available for use online ( https://covidibd.org/ ) have very good discrimination for predicting hospitalization (Test set AUC 0.79) and excellent discrimination for ICU admission (Test set AUC 0.88) and death (Test set AUC 0.94). The models were developed with a training sample of 2009 cases and validated in an independent test sample of 700 cases comprised of a random sub-sample of cases and all cases entered in the registry during a one-month period after model development. Meaning: This risk prediction model may serve as an effective tool for healthcare providers to facilitate conversations about COVID-19-related risks with IBD patients.

Project description:BackgroundHospital admissions involving substance use disorders are increasing and represent an opportunity to engage patients in substance use treatment. Addiction medicine consultation services improve access to medications for opioid use disorder (MOUD) and patient outcomes. However, as hospitals continue to adopt addiction medicine consultation services it is important to identify where disparities may emerge in the process of care.ObjectiveTo describe addiction medicine consultation service use by race and ethnicity as well as substance to identify opportunities to reduce substance use treatment disparities.DesignRetrospective cohort study using 2016-2021 Electronic Health Record data from a large Midwest safety-net hospital.ParticipantsHospitalized adults aged 18 or older, with one or more substance use disorders.Main measuresConsultation orders placed, patient seen by consult provider, and receipt of MOUD by self-reported race.Key resultsBetween 2016 and 2021, we identified 16,895 hospitalized patients with a substance use disorder. Consultation orders were placed for 6344 patients and 2789 were seen by the consult provider. Black patients were less likely (aOR = 0.58; 95% CI: 0.53-0.63) to have an addiction medicine consultation order placed and, among patients with a consultation order, were less likely (aOR = 0.74; 95% CI: 0.65-0.85) to be seen by the consult provider than White patients. Overall, Black patients with OUD were also less likely to receive MOUD in the hospital (aOR = 0.63; 95% CI: 0.50-0.79) compared to White patients. However, there were no differences in MOUD receipt among Black and White patients seen by the consult provider.ConclusionsUsing Electronic Health Record data, we identified racial and ethnic disparities at multiple points in the inpatient addiction medicine consultation process. Addressing these disparities may support more equitable access to MOUD and other substance use treatment in the hospital setting.

Dataset Information

Development and validation of predictive models for COVID-19 outcomes in a safety-net hospital population.

Objective

Materials and methods

Results

Discussion

Conclusions

Publications

Development and validation of predictive models for COVID-19 outcomes in a safety-net hospital population.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets