The Influence of Social Determinants on Receiving Outpatient Treatment with Monoclonal Antibodies, Disease Risk, and Effectiveness for COVID-19.

BACKGROUND: Limited research has studied the influence of social determinants of health (SDoH) on the receipt, disease risk, and subsequent effectiveness of neutralizing monoclonal antibodies (nMAbs) for outpatient treatment of COVID-19. OBJECTIVE: To examine the influence of SDoH variables on receiving nMAb treatments and the risk of a poor COVID-19 outcome, as well as nMAb treatment effectiveness across SDoH subgroups. DESIGN: Retrospective observational study utilizing electronic health record data from four health systems. SDoH variables analyzed included race, ethnicity, insurance, marital status, Area Deprivation Index, and population density. PARTICIPANTS: COVID-19 patients who met at least one emergency use authorization criterion for nMAb treatment. MAIN MEASURE: We used binary logistic regression to examine the influence of SDoH variables on receiving nMAb treatments and risk of a poor outcome from COVID-19 and marginal structural models to study treatment effectiveness. RESULTS: The study population included 25,241 (15.1%) nMAb-treated and 141,942 (84.9%) non-treated patients. Black or African American patients were less likely to receive treatment than white non-Hispanic patients (adjusted odds ratio (OR) = 0.86; 95% CI = 0.82-0.91). Patients who were on Medicaid, divorced or widowed, living in rural areas, or living in areas with the highest Area Deprivation Index (most vulnerable) had lower odds of receiving nMAb treatment, but a higher risk of a poor outcome. For example, compared to patients on private insurance, Medicaid patients had 0.89 (95% CI = 0.84-0.93) times the odds of receiving nMAb treatment, but 1.18 (95% CI = 1.13-1.24) times the odds of a poor COVID-19 outcome. Age, comorbidities, and COVID-19 vaccination status had a stronger influence on risk of a poor outcome than SDoH variables. nMAb treatment benefited all SDoH subgroups with lower rates of 14-day hospitalization and 30-day mortality. CONCLUSION: Disparities existed in receiving nMAbs within SDoH subgroups despite the benefit of treatment across subgroups.

Artificial Intelligence for Improved Hepatosplenomegaly Diagnosis.

Hepatosplenomegaly is commonly diagnosed by radiologists based on single dimension measurements and heuristic cut-offs. Volumetric measurements may be more accurate for diagnosing organ enlargement. Artificial intelligence techniques may be able to automatically calculate liver and spleen volume and facilitate more accurate diagnosis. After IRB approval, 2 convolutional neural networks (CNN) were developed to automatically segment the liver and spleen on a training dataset comprised of 500 single-phase, contrast-enhanced CT abdomen and pelvis examinations. A separate dataset of ten thousand sequential examinations at a single institution was segmented with these CNNs. Performance was evaluated on a 1% subset and compared with manual segmentations using Sorensen-Dice coefficients and Pearson correlation coefficients. Radiologist reports were reviewed for diagnosis of hepatomegaly and splenomegaly and compared with calculated volumes. Abnormal enlargement was defined as greater than 2 standard deviations above the mean. Median Dice coefficients for liver and spleen segmentation were 0.988 and 0.981, respectively. Pearson correlation coefficients of CNN-derived estimates of organ volume against the gold-standard manual annotation were 0.999 for the liver and spleen (P < 0.001). Average liver volume was 1556.8 ± 498.7 cc and average spleen volume was 194.6 ± 123.0 cc. There were significant differences in average liver and spleen volumes between male and female patients. Thus, the volume thresholds for ground-truth determination of hepatomegaly and splenomegaly were determined separately for each sex. Radiologist classification of hepatomegaly was 65% sensitive, 91% specific, with a positive predictive value (PPV) of 23% and an negative predictive value (NPV) of 98%. Radiologist classification of splenomegaly was 68% sensitive, 97% specific, with a positive predictive value (PPV) of 50% and a negative predictive value (NPV) of 99%. Convolutional neural networks can accurately segment the liver and spleen and may be helpful to improve radiologist accuracy in the diagnosis of hepatomegaly and splenomegaly.