Abstract 14107: Racial and Income Inequities in Cardiovascular Disease in Cancer versus Non-Cancer Patients: Propensity Score and Machine Learning Augmented Nationally Representative Case-Control Study of Mortality and Cost Among 30 Million Hospitalizations
Bibliographic record
Abstract
Introduction: We conducted the first known nationally representative propensity score analysis of racial and income inequities in cardiovascular disease (CVD) for patients with and without active cancer. Methods: Propensity score adjusted and backward propagation neural network machine learning augmented multivariable regression was performed by race and income (and their interaction) for the above outcomes in this case-control study of the United States’ largest and first ICD10-coded all-payer hospitalized dataset, the 2016 National Inpatient Sample (NIS). Models were stratified by active cancer and CVD (defined by the 2021 WHO). Results: Of the 30,195,722 adult hospitalized patients, 25.64% had CVD, and 7.11% had active cancer. In fully adjusted regression among patients without cancer, Hispanic (OR 1.34, 95%CI 1.03-1.25; p=0.012) and Asian (OR 1.22; 95%CI 1.11-1.34; p<0.001) had significantly increased mortality compared to Caucasian patients as did the lowest (OR 1.11; 95%CI 1.07-1.15; p<0.001) and second lowest (OR 1.05; 95%CI 1.01-1.08; p=0.006) income quartiles compared to the highest. Among patients with cancer, similar significant racial inequities were noted but without income disparities. Mortality was not significantly increased by the interaction in either strata. Among patients without cancer, Hispanics ($14,196.68; 95%CI 12,887.86-15,505.51; p<0.001) and Asians ($19,377.06; 95%CI 17,939.38-20,814.74; p<0.001) had significantly increased costs compared to Caucasians; African American, Hispanic, and Asian patients in the lowest and second lowest income quartiles had significantly increased costs compared to Caucasians in the highest quartile. Patients with cancer had comparable cost inequities by race but not by income or the interaction. Conclusions: This nationally representative study suggests that significant income and racial inequities exist in inpatient mortality and cost among patients with CVD, though these disparities are less pronounced among cancer versus non-cancer patients.
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 | 0.003 | 0.007 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".