REAL-WORLD UTILIZATION SHIFTS AND AI/NLP-DERIVED CLINICAL DRIVERS OF BIOLOGIC-TO-BIOSIMILAR SWITCHING IN INFLAMMATORY BOWEL DISEASE (IBD)
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, Shakir Khan, MBA9, Hitesh Khandelwal, BTech8, Satish Kumar, MBA8, Pankaj Bhardwaj, MBA, RPh8, Amit Kaushal, MBA, MD5, Kirti Batra, MBA10;
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 Lifesciences, Gurugram, India, 9Optum, United Health Group, Hyderabad, India, 10Optum Global Solutions, Noida, India
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 Lifesciences, Gurugram, India, 9Optum, United Health Group, Hyderabad, India, 10Optum Global Solutions, Noida, India
Presentation Documents
OBJECTIVES: To evaluate real‑world changes in healthcare resource utilization (HCRU) following switches from originator biologics to biosimilars among adults with inflammatory bowel disease (IBD) and to use AI‑enabled natural language processing (NLP) to identify clinician‑documented reasons for switching.
METHODS: A retrospective cohort study was conducted using de‑identified Optum® Market Clarity data (January 2017-June 2025). Adults aged ≥18 years with ≥1 inpatient or ≥2 outpatient IBD diagnoses who received an originator biologic and subsequently switched to a biosimilar were included. The index date was the first biosimilar claim following originator therapy. Continuous medical and pharmacy enrollment for ≥12 months before and after the index date was required. Baseline demographics, Charlson Comorbidity Index (CCI), and HCRU were compared between pre‑ and post‑switch periods. AI‑enabled NLP was applied to unstructured physician notes to extract clinician‑documented switching rationales.
RESULTS: A total of 18,499 patients met inclusion criteria; 51.7% were female, and most were commercially insured (78.6%), with lower representation from Medicaid (10.8%) and Medicare (10.3%). Comorbidity burden was low, with 64.5% having a CCI of 0. Significant reductions in HCRU were observed post‑switch. Emergency department visits decreased by 17.5% (0.15 vs. 0.19), inpatient stays by 7.7% (0.35 vs. 0.38), outpatient encounters by 4.1% (3.11 vs. 3.25), and diagnostic procedures by 39.5% (0.07 vs. 0.11). Therapeutic procedure utilization increased by 27.5% (0.11 vs. 0.09). All differences were statistically significant (p < 0.05). NLP analysis identified disease‑ and treatment‑related considerations, immunogenicity concerns, and payer coverage or reimbursement policies as the most frequently documented drivers of biosimilar switching.
CONCLUSIONS: Switching from originator biologics to biosimilars in IBD was associated with meaningful reductions in overall HCRU, supporting clinical and potential economic benefits. NLP‑derived insights highlighted clinical needs, immunogenicity, and payer policies as central drivers of switching, reinforcing biosimilars’ role in value‑based care.
METHODS: A retrospective cohort study was conducted using de‑identified Optum® Market Clarity data (January 2017-June 2025). Adults aged ≥18 years with ≥1 inpatient or ≥2 outpatient IBD diagnoses who received an originator biologic and subsequently switched to a biosimilar were included. The index date was the first biosimilar claim following originator therapy. Continuous medical and pharmacy enrollment for ≥12 months before and after the index date was required. Baseline demographics, Charlson Comorbidity Index (CCI), and HCRU were compared between pre‑ and post‑switch periods. AI‑enabled NLP was applied to unstructured physician notes to extract clinician‑documented switching rationales.
RESULTS: A total of 18,499 patients met inclusion criteria; 51.7% were female, and most were commercially insured (78.6%), with lower representation from Medicaid (10.8%) and Medicare (10.3%). Comorbidity burden was low, with 64.5% having a CCI of 0. Significant reductions in HCRU were observed post‑switch. Emergency department visits decreased by 17.5% (0.15 vs. 0.19), inpatient stays by 7.7% (0.35 vs. 0.38), outpatient encounters by 4.1% (3.11 vs. 3.25), and diagnostic procedures by 39.5% (0.07 vs. 0.11). Therapeutic procedure utilization increased by 27.5% (0.11 vs. 0.09). All differences were statistically significant (p < 0.05). NLP analysis identified disease‑ and treatment‑related considerations, immunogenicity concerns, and payer coverage or reimbursement policies as the most frequently documented drivers of biosimilar switching.
CONCLUSIONS: Switching from originator biologics to biosimilars in IBD was associated with meaningful reductions in overall HCRU, supporting clinical and potential economic benefits. NLP‑derived insights highlighted clinical needs, immunogenicity, and payer policies as central drivers of switching, reinforcing biosimilars’ role in value‑based care.
Conference/Value in Health Info
2026-05, ISPOR 2026, Philadelphia, PA, USA
Value in Health, Volume 29, Issue S6
Code
MSR47
Topic
Methodological & Statistical Research
Topic Subcategory
Artificial Intelligence, Machine Learning, Predictive Analytics
Disease
SDC: Gastrointestinal Disorders, STA: Biologics & Biosimilars