A Machine Learning Study of 534,023 Medicare Beneficiaries with COVID-19: Implications for Personalized Risk Prediction

Walsh, Christi; Bae, Sunjae; Adalja, Amesh A.; Toner, Eric; Lash, Timothy A.; Hashim, Farah; Paturzo, Joseph Giuseppe R.; Segev, Dorry L.; Makary, Martin A.

doi:10.1101/2020.10.27.20220970

Cited by 15 publications

(18 citation statements)

References 28 publications

(43 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…(10) Persons with developmental disorders, congenital and acquired neurologic disabilities, cancers (especially lung cancer, leukemia and lymphoma), sickle cell disease, chronic kidney disease, heart failure, and diabetes appear to be at particularly high mortality risks. (10, 11) Hypertension, obesity, chronic lung diseases, and chronic liver diseases have also been associated with more severe COVID-19 disease. (12-15)…”

Section: Introductionmentioning

confidence: 99%

COVID-19 vaccine hesitancy among individuals with cancer, autoimmune diseases, and other serious comorbid conditions

Tsai

Hervey

Hoffman

et al. 2021

Preprint

View full text Add to dashboard Cite

Background: Individuals with comorbid conditions have been disproportionately affected by COVID-19. Since regulatory clinical trials with COVID-19 vaccines excluded those with immunocompromising conditions, few patients with cancer and autoimmune diseases were enrolled. With limited vaccine safety data available, vulnerable populations may have conflicted vaccine attitudes. Objective: To assess the incidence and reasons for COVID-19 vaccine hesitancy and to assess early vaccine safety. Design: Cross-sectional online survey, fielded January 15, 2021 through February 22, 2021 Setting: International participation (74% USA) Participants: Random sample of members of Inspire, an online health community of over 2.2 million individuals with comorbid conditions. Measurements: A 55-item online survey Results: 21,943 individuals completed the survey (100% with comorbidities including 27% cancer, 23% autoimmune diseases, 38% chronic lung diseases). 10% declared they would not, 4% stated they probably would not, and 5% were not sure they would agree to vaccination (hesitancy rate 19%). Factors associated with hesitancy included younger age, female gender, black-Pacific-Island-Native American heritage, less formal education, conservative political tendencies, resistance to masks or routine influenza vaccinations, and distrust of media coverage. 5501 (25%) had received at least one COVID-19 vaccine injection, including 29% of US participants. Following the first injection, 69% self-reported local and 40% systemic reactions, which increased following the second injection to 76% and 67%, respectively, with patterns mimicking clinical trials. Limitations: Study was performed early during vaccine availability. Attitudes may change. Conclusion: Nearly one in five individuals with serious comorbid conditions harbor COVID-19 hesitancy. Early safety experiences among those who have been vaccinated should be reassuring.

show abstract

Section: Introductionmentioning

confidence: 99%

COVID-19 vaccine hesitancy among individuals with cancer, autoimmune diseases, and other serious comorbid conditions

Tsai

Hervey

Hoffman

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Other COVID-19-related risk prediction tools have focused on predicting hospital course based on clinical data captured at the time of admission 9 and predicting mortality among US patients aged 65 years and older 8 . Our risk tool is unique in at least three ways.…”

Section: Discussionmentioning

confidence: 99%

“…The interactive application could provide a reliable basis for distinguishing between high- and low-risk patients to aid in personalizing clinical guidance on decisions about precautions, returning to normal activities, and vaccination. Other COVID-19-related risk prediction tools have focused on predicting hospital course based on clinical data captured at the time of admission 9 and predicting mortality among US patients aged 65 years and older 8 . Our risk tool is unique in at least three ways.…”

Section: Discussionmentioning

confidence: 99%

“…While the majority of cases are mild, patients with at least one comorbidity are at higher risk of adverse outcomes, including hospitalization, respiratory failure, or death 6,7 . Risk calculators can facilitate shared decision making between patients and healthcare providers 1 , and such tools have been created to predict death due to COVID-19 in US patients 65 years and older 8 , to determine hospitalization risk 9 , and to guide early vaccine allocation. Patients with inflammatory bowel disease (IBD) are prescribed immunosuppressive medications such as corticosteroids, immunomodulators, biologic therapies, and Janus-kinase inhibitors, which are linked with a higher risk of viral infection 10,11 .…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Development and validation of multivariable prediction models for adverse COVID-19 outcomes in IBD patients

Sperger

Shah

et al. 2021

Preprint

View full text Add to dashboard Cite

Structured AbstractImportanceRisk calculators can facilitate shared medical decision-making1. Demographics, comorbidities, medication use, geographic region, and other factors may increase the risk for COVID-19-related complications among patients with IBD2,3.ObjectivesDevelop an individualized prognostic risk prediction tool for predicting the probability of adverse COVID-19 outcomes in patients with IBD.Design, Setting, and ParticipantsThis study developed and validated prognostic penalized logistic regression models4 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).Main Outcomes and MeasuresCOVID-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).ResultsWe 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.Conclusions and RelevancePrognostic 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.Key PointsQuestionHow 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)?FindingsMultivariable 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.MeaningThis risk prediction model may serve as an effective tool for healthcare providers to facilitate conversations about COVID-19-related risks with IBD patients.

show abstract

“…Numerous groups have proposed individual risk models based on clinical outcomes in various populations studied early in the pandemic, but a consensus model has yet to emerge. (9)(10)(11) From a practical perspective, prediction models based on readily available administrative data (e.g., ICD-10 codes) will be most useful since more granular information extracted from clinical health records are neither universally available nor easy to obtain. Our primary goal was therefore to estimate excess riskspecific mortality in people with probable and confirmed Covid-19 infections.…”

Section: Introductionmentioning

confidence: 99%

Covid-19 and Excess Mortality in Medicare Beneficiaries

Greenwald¹,

Chamoun²,

Pj³

et al. 2021

Preprint

View full text Add to dashboard Cite

We estimated excess mortality in Medicare recipients with probable and confirmed Covid-19 infections in the general community and amongst residents of long-term care (LTC) facilities. We considered 28,389,098 Medicare and dual-eligible recipients from one year before February 29, 2020 through September 30, 2020, with mortality followed through November 30th, 2020. Probable and confirmed Covid-19 diagnoses, presumably mostly symptomatic, were determined from ICD-10 codes. We developed a Risk Stratification Index (RSI) mortality model which was applied prospectively to establish baseline mortality risk. Excess deaths attributable to Covid-19 were estimated by comparing actual-to-expected deaths based on historical comparisons and in closely matched cohorts with and without Covid-19. 677,100 (2.4%) beneficiaries had confirmed Covid-19 and 2,917,604 (10.3%) had probable Covid-19. 472,329 confirmed cases were community living and 204,771 were in LTC. Mortality following a probable or confirmed diagnosis in the community increased from an expected incidence of about 4% to actual incidence of 7.5%. In long-term care facilities, the corresponding increase was from 20.3% to 24.6%. The absolute increase was therefore similar at 3-4% in the community and in LTC residents. The percentage increase was far greater in the community (89%) than among patients in chronic care facilities (21%) who had higher baseline risk. The LTC population without probable or confirmed Covid-19 diagnoses experienced 38,932 excess deaths (35%) compared to historical estimates. Limitations in access to Covid-19 testing and disease under-reporting in LTC patients probably were important factors, although social isolation and disruption in usual care presumably also contributed. Remarkably, there were 31,360 fewer deaths than expected in community dwellers without probable or confirmed Covid-19 diagnoses, representing a 6% reduction. Disruptions to the healthcare system and avoided medical care were thus apparently offset by other factors, representing overall benefit. The Covid-19 pandemic had marked effects on mortality, but the effects were highly context-dependent.

show abstract

A Machine Learning Study of 534,023 Medicare Beneficiaries with COVID-19: Implications for Personalized Risk Prediction

Cited by 15 publications

References 28 publications

COVID-19 vaccine hesitancy among individuals with cancer, autoimmune diseases, and other serious comorbid conditions

COVID-19 vaccine hesitancy among individuals with cancer, autoimmune diseases, and other serious comorbid conditions

Development and validation of multivariable prediction models for adverse COVID-19 outcomes in IBD patients

Covid-19 and Excess Mortality in Medicare Beneficiaries

Contact Info

Product

Resources

About