Distribution of Patients at Risk for Complications Related to COVID-19 in the United States: Model Development Study
Bibliographic record
Abstract
BACKGROUND: Coronavirus disease (COVID-19) has spread exponentially across the United States. Older adults with underlying health conditions are at an especially high risk of developing life-threatening complications if infected. Most intensive care unit (ICU) admissions and non-ICU hospitalizations have been among patients with at least one underlying health condition. OBJECTIVE: The aim of this study was to develop a model to estimate the risk status of the patients of a nationwide pharmacy chain in the United States, and to identify the geographic distribution of patients who have the highest risk of severe COVID-19 complications. METHODS: A risk model was developed using a training test split approach to identify patients who are at high risk of developing serious complications from COVID-19. Adult patients (aged ≥18 years) were identified from the Walgreens pharmacy electronic data warehouse. Patients were considered eligible to contribute data to the model if they had at least one prescription filled at a Walgreens location between October 27, 2019, and March 25, 2020. Risk parameters included age, whether the patient is being treated for a serious or chronic condition, and urban density classification. Parameters were differentially weighted based on their association with severe complications, as reported in earlier cases. An at-risk rate per 1000 people was calculated at the county level, and ArcMap was used to depict the rate of patients at high risk for severe complications from COVID-19. Real-time COVID-19 cases captured by the Johns Hopkins University Center for Systems Science and Engineering (CSSE) were layered in the risk map to show where cases exist relative to the high-risk populations. RESULTS: Of the 30,100,826 adults included in this study, the average age is 50 years, 15% have at least one specialty medication, and the average patient has 2 to 3 comorbidities. Nearly 28% of patients have the greatest risk score, and an additional 34.64% of patients are considered high-risk, with scores ranging from 8 to 10. Age accounts for 53% of a patient's total risk, followed by the number of comorbidities (29%); inferred chronic obstructive pulmonary disease, hypertension, or diabetes (15%); and urban density classification (5%). CONCLUSIONS: This risk model utilizes data from approximately 10% of the US population. Currently, this is the most comprehensive US model to estimate and depict the county-level prognosis of COVID-19 infection. This study shows that there are counties across the United States whose residents are at high risk of developing severe complications from COVID-19. Our county-level risk estimates may be used alongside other data sets to improve the accuracy of anticipated health care resource needs. The interactive map can also aid in proactive planning and preparations among employers that are deemed critical, such as pharmacies and grocery stores, to prevent the spread of COVID-19 within their facilities.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.009 | 0.015 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.003 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".