Health Care Cost Reductions with Machine Learning-Directed Evaluations during Radiation Therapy - An Economic Analysis of a Randomized Controlled Study.

BACKGROUND: Machine learning (ML) may cost-effectively direct health care by identifying patients most likely to benefit from preventative interventions to avoid negative and expensive outcomes. System for High-Intensity Evaluation During Radiation Therapy (SHIELD-RT; NCT04277650) was a single-institution, randomized controlled study in which electronic health record-based ML accurately identified patients at high risk for acute care (emergency visit or hospitalization) during radiotherapy (RT) and targeted them for supplemental clinical evaluations. This ML-directed intervention resulted in decreased acute care utilization. Given the limited prospective data showing the ability of ML to direct interventions cost-efficiently, an economic analysis was performed. METHODS: A post hoc economic analysis was conducted of SHIELD-RT that included RT courses from January 7, 2019, to June 30, 2019. ML-identified high-risk courses (≥10% risk of acute care during RT) were randomized to receive standard of care weekly clinical evaluations with ad hoc supplemental evaluations per clinician discretion versus mandatory twice-weekly evaluations. The primary outcome was difference in mean total medical costs during and 15 days after RT. Acute care costs were obtained via institutional cost accounting. Physician and intervention costs were estimated via Medicare and Medicaid data. Negative binomial regression was used to estimate cost outcomes after adjustment for patient and disease factors. RESULTS: A total of 311 high-risk RT courses among 305 patients were randomized to the standard (n=157) or the intervention (n=154) group. Unadjusted mean intervention group supplemental visit costs were $155 per course (95% confidence interval, $142 to $168). The intervention group had fewer acute care visits per course (standard, 0.47; intervention, 0.31; P=0.04). Total mean adjusted costs were $3110 per course for the standard group and $1494 for the intervention group (difference in means, $1616 [95% confidence interval, $1450 to $1783]; P=0.03). CONCLUSIONS: In this economic analysis of a randomized controlled, health care ML study, mandatory supplemental evaluations for ML-identified high-risk patients were associated with both reduced total medical costs and improved clinical outcomes. Further study is needed to determine whether economic results are generalizable. (Funded in part by The Duke Endowment, The Conquer Cancer Foundation, the Duke Department of Radiation Oncology, and the National Cancer Institute of the National Institutes of Health [R01CA277782]; ClinicalTrials.gov number, NCT04277650.).

U.S. Adult Perspectives on Facial Images, DNA, and Other Biometrics.

Applications of biometrics in various societal contexts have been increasing in the United States, and policy debates about potential restrictions and expansions for specific biometrics (such as facial recognition and DNA identification) have been intensifying. Empirical data about public perspectives on different types of biometrics can inform these debates. We surveyed 4048 adults to explore perspectives regarding experience and comfort with six types of biometrics; comfort providing biometrics in distinct scenarios; trust in social actors to use two types of biometrics (facial images and DNA) responsibly; acceptability of facial images in eight scenarios; and perceived effectiveness of facial images for five tasks. Respondents were generally comfortable with biometrics. Trust in social actors to use biometrics responsibly appeared to be context specific rather than dependent on biometric type. Contrary to expectations given mounting attention to dataveillance concerns, we did not find sociodemographic factors to influence perspectives on biometrics in obvious ways. These findings underscore a need for qualitative approaches to understand the contextual factors that trigger strong opinions of comfort with and acceptability of biometrics in different settings, by different actors, and for different purposes and to identify the informational needs relevant to the development of appropriate policies and oversight.

COVID-19 Vaccine Administration, by Race and Ethnicity - North Carolina, December 14, 2020-April 6, 2021.

COVID-19 has disproportionately affected non-Hispanic Black or African American (Black) and Hispanic persons in the United States (1,2). In North Carolina during January-September 2020, deaths from COVID-19 were 1.6 times higher among Black persons than among non-Hispanic White persons (3), and the rate of COVID-19 cases among Hispanic persons was 2.3 times higher than that among non-Hispanic persons (4). During December 14, 2020-April 6, 2021, the North Carolina Department of Health and Human Services (NCDHHS) monitored the proportion of Black and Hispanic persons* aged ≥16 years who received COVID-19 vaccinations, relative to the population proportions of these groups. On January 14, 2021, NCDHHS implemented a multipronged strategy to prioritize COVID-19 vaccinations among Black and Hispanic persons. This included mapping communities with larger population proportions of persons aged ≥65 years among these groups, increasing vaccine allocations to providers serving these communities, setting expectations that the share of vaccines administered to Black and Hispanic persons matched or exceeded population proportions, and facilitating community partnerships. From December 14, 2020-January 3, 2021 to March 29-April 6, 2021, the proportion of vaccines administered to Black persons increased from 9.2% to 18.7%, and the proportion administered to Hispanic persons increased from 3.9% to 9.9%, approaching the population proportion aged ≥16 years of these groups (22.3% and 8.0%, respectively). Vaccinating communities most affected by COVID-19 is a national priority (5). Public health officials could use U.S. Census tract-level mapping to guide vaccine allocation, promote shared accountability for equitable distribution of COVID-19 vaccines with vaccine providers through data sharing, and facilitate community partnerships to support vaccine access and promote equity in vaccine uptake.

Gender representation in U.S. biomedical informatics leadership and recognition.

OBJECTIVE: This study sought to describe gender representation in leadership and recognition within the U.S. biomedical informatics community. MATERIALS AND METHODS: Data were collected from public websites or provided by American Medical Informatics Association (AMIA) personnel from 2017 to 2019, including gender of membership, directors of academic informatics programs, clinical informatics subspecialty fellowships, AMIA leadership (2014-2019), and AMIA awardees (1993-2019). Differences in gender proportions were calculated using chi-square tests. RESULTS: Men were more often in leadership positions and award recipients (P < .01). Men led 74.7% (n = 71 of 95) of academic informatics programs and 83.3% (n = 35 of 42) of clinical informatics fellowships. Within AMIA, men held 56.8% (n = 1086 of 1913) of leadership roles and received 64.1% (n = 59 of 92) of awards. DISCUSSION: As in other STEM fields, leadership and recognition in biomedical informatics is lower for women. CONCLUSIONS: Quantifying gender inequity should inform data-driven strategies to foster diversity and inclusion. Standardized collection and surveillance of demographic data within biomedical informatics is necessary.

Beyond the Genetic Information Nondiscrimination Act: ethical and economic implications of the exclusion of disability, long-term care and life insurance.

The Genetic Information Nondiscrimination Act (GINA) was intended to protect individuals in the USA from discrimination based on their genetic data, but does not apply to life, long-term care or disability insurance. Patient advocates and ethicists have argued that GINA does not go far enough. Others express concerns for the viability of insurance companies if millions of potential customers know more than professional actuaries. Here we discuss the exclusion of certain insurance types from GINA. We explore the ethical and economic implications of this distinction, and potential paths forward. We suggest that because long-term care and disability insurance can be essential for well-being, there is no good reason to place them in a class with life insurance and therefore beyond GINA's reach.