REAL-WORLD EPIDEMIOLOGY, CLINICAL OUTCOMES AND PATIENT SATISFACTION AMONG USERS OF ARTIFICIAL PANCREAS SYSTEMS IN TYPE 1 AND TYPE 2 DIABETES INSIGHTS FROM PHYSICIAN NOTES USING NLP

Author(s)

Vikash K. Verma, MBA, PharmD1, Louis Brooks Jr, MS2, Marissa Seligman, PharmD3, Abhimanyu Roy, MBA4, Abhinav Nayyar, MBA, MBBS5, Ankitkumar Arora, MPharm6, Anuj Gupta, MSc7, Vishan Khatavkar, MBA8, Arunima Sachdev, MA4, Tisha Sharma, BTech7, Trishala N. Amin, MA9, Khushboo -10, Pankaj Bhardwaj, MBA, RPh11, Ram K. Mishra, PhD12, Priyanka Chaubey, Sr., MBA7;
1Optum Lifesciences, Boston, MA, USA, 2Optum, Bloomsbury, NJ, USA, 3Optum, Winchester, MA, USA, 4Optum, Gurgaon, India, 5Optum Life Sciences, Gurugram, India, 6Optum Global Solutions, Gurgaon, India, 7Optum Lifesciences, Noida, India, 8Optum, Gurugram, India, 9Optum Life Sciences, Behrampur, India, 10Gurugram, India, 11Optum Lifesciences, Gurugram, India, 12Optum Global Solution, Gurugram, India
OBJECTIVES: Artificial pancreas systems (APS), which integrate continuous glucose monitoring with automated insulin delivery, offer promising benefits for improving glycemic control and reducing acute complications in both type 1 (T1D) and type 2 diabetes (T2D). This study examined real‑world APS utilization, clinical outcomes, and patient‑reported experience captured through unstructured physician notes using natural language processing (NLP).
METHODS: This retrospective cohort study used Optum® Market Clarity data (January 2021-June 2025). Patients aged ≥6 years with confirmed T1D or T2D who initiated APS between January 2022 and June 2024 were included. Continuous enrollment for ≥12 months pre‑ and ≥12 months post‑index (first APS initiation) was required. Outcomes included APS incidence, change in HbA1c from baseline to 12‑month follow‑up, and rates of severe hypoglycemia and diabetic ketoacidosis (DKA). Paired t‑tests assessed changes in glycemic outcomes. NLP techniques were applied to unstructured physician notes to extract sentiment, patient experience themes, and satisfaction indicators.
RESULTS: Among 1,626,752 individuals with T1D (19.5%) or T2D (80.5%), 91,472 initiated APS during the identification period. The final analytic cohort consisted of 47,882 APS users; mean±SD age was 62.85±14.07 years, and 52.76% were female; 34.72% were aged ≥65 years. Baseline HbA1c averaged 8.04%. Among patients with values available at both time points, mean HbA1c decreased from 8.04 to 7.73 at 12 months (p < 0.0001). For those with sequential 6‑month measurements, HbA1c improved from 7.79 to 7.62 (p < 0.0001). Severe hypoglycemia and DKA events remained infrequent throughout follow‑up. NLP of physician notes revealed overall positive sentiment regarding APS use, with increased documentation of improved glycemic stability, reduced burden of glucose management, and enhanced patient satisfaction.
CONCLUSIONS: The use of APS was associated with modest HbA1c improvement and a favorable safety profile in real-world practice. However, long-term studies are needed to evaluate sustained impact and broader outcomes.

Conference/Value in Health Info

2026-05, ISPOR 2026, Philadelphia, PA, USA

Value in Health, Volume 29, Issue S6

Code

CO9

Topic

Clinical Outcomes

Topic Subcategory

Clinical Outcomes Assessment

Disease

SDC: Diabetes/Endocrine/Metabolic Disorders (including obesity)

Your browser is out-of-date

ISPOR recommends that you update your browser for more security, speed and the best experience on ispor.org. Update my browser now

×