Citations

Objective We aimed to use machine learning (ML) models to investigate the impact of clinical, social and behavioural factors on 1-year progression from pre-diabetes to type 2 diabetes mellitus (DM). Design A retrospective cohort study. Setting A large health system including eight sites in southeast Michigan. Participants Adults with haemoglobin A1c (HbA1c) between 5.7% and 6.4% for two consecutive years between 1 January 2008 and 31 December 2023, and no prior history of type 2 DM or metformin use. Primary outcome measure New-onset type 2 DM (HbA1c ≥6.5%) in 1 year. Results Among 11 809 individuals, 815 (6.9%) progressed to type 2 DM within 1 year. CatBoost demonstrated the best performance (average area under the curve 0.78). Prior-year HbA1c was the most influential covariate (SHapley Additive exPlanations 1.02). Traditional metabolic factors (high-density lipoprotein, body mass index (BMI), white blood cell, age, gender, triglycerides) also contributed. Lastly, while inclusion of social and behavioural determinants of health (SBDH) did not significantly improve the overall model performance, depression emerged as the prominent SBDH covariate. Depression was a stronger predictor of diabetes progression in individuals with higher baseline BMI and lower baseline HbA1c. Conclusions Inclusion of social and behavioural covariates provided no incremental value for prediction of diabetes progression from pre-diabetes. However, machine learning revealed that depression may play a role in progression to type 2 DM.

Abstract RATIONALE: The American Thoracic Society (ATS) recently recommended using “race-neutral” GLI-Global prediction equations to interpret spirometry results. However, the unintended consequences for workers have not been fully evaluated. METHODS: We analyzed the impact of adopting GLI-Global on 24 hypothetical subjects, using on-line calculators to examine the effects on 1) larger vs. smaller predicted values; 2) Black, Southeast Asian, Northeast Asian, and White races; and 3) 80%, 100%, and 120% of race-specific predicted forced vital capacity (FVC). RESULTS: Race-specific predicted FVCs decline by group: White > NE Asian > SE Asian > Black, with a difference of 0.84 L between Blacks and Whites. GLI-Global Predicteds are midway between Blacks’ and Whites’. Workers at 80% of race-specific Predicted change the most when GLI-Global is employed: Blacks and SE Asians show declining %Predicted values and Z-scores and an increase in FVCs<LLN, while Whites and NE Asians show increasing %Predicted and Z-scores and a decrease in FVCs<LLN. CONCLUSIONS: Choice of prediction equation for use in occupational health practice differentially affects individuals in several groups: a) When fixed criteria are used for job placement and retention decisions, Black and SE Asian persons may be particularly adversely affected, while Whites and NE Asians will more likely exceed the fixed criteria; b) When fixed criteria are used for disability decisions, Black and SE Asian persons may look increasingly disabled, while White and NE Asian persons may now fail to qualify for disability; and c) Disparate effects are most prominent for persons with lung function measures in the lower portion of the normal range. Since occupational criteria are unlikely to change quickly, clinicians and policymakers should consider the real-world implications of mandating or recommending specific equations.

AbstractBackgroundPrevious studies have demonstrated low first‐time donor return rates (DRR) following catastrophic events. Little is known, however, about the influence of demographic factors on the DRR of first‐time donors during the COVID‐19 pandemic, including the unique motivation of COVID‐19 convalescent plasma (CCP) donors as compared to non‐CCP donors.Study Design and MethodsThirteen blood collection organizations submitted deidentified data from first‐time CCP and non‐CCP donors returning for regular (non‐CCP) donations during the pandemic. DRR was calculated as frequencies. Demographic factors associated with returning donors: race/ethnicity, gender, and generation (Gen Z: 19–24, Millennial: 25–40, Gen X: 41–56, and Boomer: ≥57 years old), within the CCP and non‐CCP first‐time cohorts were compared using chi‐square test at p < .05 statistical significance.ResultsFrom March 2020 through December 2021, there were a total of 44,274 first‐time CCP and 980,201 first‐time non‐CCP donors. DRR were 14.6% (range 11.9%–43.3%) and 46.6% (range 10.0%–76.9%) for CCP and non‐CCP cohorts, respectively. Age over 40 years (Gen X and Boomers), female gender, and White race were each associated with higher return in both donor cohorts (p < .001). For the non‐CCP return donor cohort, the Millennial and Boomers were comparable.ConclusionThe findings demonstrate differences in returning donor trends between the two donor cohorts. The motivation of a first‐time CCP donor may be different than that of a non‐CCP donor. Further study to improve first‐time donor engagement would be worthwhile to expand the donor base with a focus on blood donor diversity emphasizing engagement of underrepresented minorities and younger donors.

AbstractBackgroundAlthough the safety and therapeutic efficacy of COVID‐19 convalescent plasma (CCP) has been extensively evaluated, the safety of CCP donation has not been explored in a multi‐institutional context.Study design and methodsNine blood collection organizations (BCOs) participated in a multi‐institutional donor hemovigilance effort to assess the safety of CCP donation. Donor adverse events (DAEs) were defined according to the Standard for Surveillance of Complications Related to Blood Donation, and severity was assessed using the severity grading tool. Multivariate analysis was performed to determine attributes associated with DAE severity.ResultsThe overall DAE rate was 37.7 per 1000 donations. Repeat apheresis and apheresis‐naïve donors experienced adverse event rates of 19.9 and 49.8 per 1000 donations, respectively. Female donors contributed 51.9% of CCP donations with a DAE rate of 49.4 per 1000 donations. The DAE rate for male donors was 27.4 per 1000 donations. Vasovagal reactions accounted for over half of all reported DAEs (51.1%). After adjustment, volume of CCP donated was associated with vasovagal reaction severity (odds ratio [OR] 6.5, 95% confidence interval [CI] 2.5–17.1). Donor age and donation history were also associated with DAE severity. Considerable differences in DAE types and rates were observed across the participating BCOs despite the use of standardized hemovigilance definitions.ConclusionThe safety of CCP donation appears comparable to that of conventional apheresis plasma donation with similar associated risk factors for DAE types and severity.