UP - logo
E-resources
Full text
Peer reviewed
  • 372-P: Predicting Real-Worl...
    RATZKI-LEEWING, ALEXANDRIA; HARRIS, STEWART B.; BLACK, JASON E.; ZOU, GUANGYONG; WEBSTER-BOGAERT, SUSAN; RYAN, BRIDGET L.

    Diabetes (New York, N.Y.), 06/2022, Volume: 71, Issue: Supplement_1
    Journal Article

    Most prediction models for diabetes-related iatrogenic severe hypoglycemia (SH) have derived from trial/administrative records subject to poor generalizability, ascertainment bias, and incomplete data capture. Redressing this gap, iNPHORM leveraged the clinical and methodological advantages of prospective self-report to develop and internally validate a 1-year SH prediction model for use in real-world clinical contexts. Adults (18-90 years old) with insulin- and/or secretagogue-treated type 1 or 2 diabetes (T1D, T2D) were recruited from a US-wide probability-based internet panel and followed for one year. Monthly emailed questionnaires assessed SH incidence and related factors. To model recurrent 1-year SH (daytime + nocturnal) , Andersen-Gill Cox proportional hazards regression was performed on participants completing ≥1 follow-up. Missing data were multiply imputed with chained equations. Machine learning penalized regression with lasso was used to select clinically plausible predictors. A total of 986 (T1D: 17%) participants were analyzed (retention rate: 86.2%) . The mean age was 51 (SD: 14.3) years, 49.6% were male, and the median duration of T1D/T2D was 12 (IQR: 14) years. Among T2D participants, 38% were on insulin (without secretagogues) , 38% on secretagogues (without insulin) , and 24% on insulin plus secretagogues. Across follow-up, 35.1% (95% CI: 32.2-38.1%) reported ≥1 SH, and the annual rate was 4.97 (95% CI: 4.13-5.99) . Combination insulin-secretagogue therapy; use of an insulin pump and continuous glucose monitoring; decreased age; increased previous SH requiring healthcare utilization; chronic kidney disease; and food insecurity predicted 1-year SH risk. The optimism adjusted c-statistic was 0.75. iNPHORM is the first long-term, prospective study on SH prediction in the general US population with T1D and T2D. Our 7-variable model can be used to identify patients at high-risk of SH, leading to more valid, cost-effective prevention strategies in the real world. Disclosure A.Ratzki-leewing: Consultant; Eli Lilly and Company, Other Relationship; Sanofi. S.B.Harris: Consultant; Abbott, AstraZeneca, Eli Lilly and Company, Novo Nordisk, Sanofi, Other Relationship; Abbott, AstraZeneca, Bayer Inc., Dexcom, Eli Lilly and Company, HLS Therapeutics, Janssen Pharmaceuticals, Inc., Novo Nordisk, Sanofi, Research Support; Applied Therapeutics Inc., AstraZeneca, Canadian Institutes of Health Research, Juvenile Diabetes Research Foundation (JDRF) , Novo Nordisk, Sanofi, The Lawson Foundation. J.E.Black: None. G.Zou: None. S.Webster-bogaert: None. B.L.Ryan: None. Funding Sanofi Global