AI-Identified Reasons for Nonescalation of Lipid-Lowering Therapy for Secondary Prevention
Authors' conclusion
Results of this study show that after using a state-of-the art LLM, nearly 9 in 10 ASCVD encounters with above-goal LDL-C level did not have patient LLT escalated, most often because of adverse effects, patient preference, preference for lifestyle changes, therapeutic inertia (eg, repeat laboratory tests), and near-goal LDL-C level. These findings highlight an avenue for personalizing system-level digital health interventions to help discover and minimize guideline-discordant care gaps in secondary prevention of ASCVD.
Study context
- Population
- Adults aged 18 to 90 years with 2 or more clinician-billed encounters for atherosclerotic cardiovascular disease (ASCVD) and with low-density lipoprotein cholesterol (LDL-C) level greater than or equal to 70 mg/dL at the most recent encounter, in a large, integrated health system in Northern Californiaunique patients with ASCVD-related encounters, 13,810 (49.1%) had above-goal LDL-C level
- Participants
- 28,113 adults
- Index test or model
- Large language models (LLMs) against clinical annotations
- Target condition
- treat-to-target strategy use (LDL-C target documentation, LDL-C target value), LLT adjustment and reasons for LLT nonescalation documented in clinical notes
Performance
As reported in the abstract
Micro-weighted F1 scores ranged from
0.80 to 0.98
Further findings
Characteristics of patients with above-goal LDL-C level
- Patients with above-goal LDL-C level, of the 28 113 identified
- 13 810 (49.1%)
- Mean (SD) age of those with above-goal LDL-C level
- 70.9 [11.4] years
- Male, of those with above-goal LDL-C level
- 7904 male [57.2%]
Treat-to-target strategy (inference set)
- Treat-to-target strategy identified, of all relevant notes
- 3756 (28.1%)
- Targeting an LDL-C level less than 70 mg/dL
- 2280 [17.1%]
- Inference set: 13 394 patients with above-goal LDL-C level and 13 354 relevant notes
Lipid-lowering therapy (LLT) nonescalation and reasons (inference set)
- LLT not escalated, of all relevant notes
- 11 842 (88.7%)
- Of those not escalated, containing at least 1 LLT nonescalation reason
- 4788 (40.4%)
- Patient-reported adverse effects
- 1683 [12.6%]
- LDL-C level close to goal
- 922 [6.9%]
- Patient preference to avoid LLT
- 914 [6.8%]
- Preference for lifestyle changes
- 811 [6.1%]
- Deferral to repeat laboratory tests
- 617 [4.6%]
Original publication
Composed by AI from the published abstract and checked against it. How Briefs are made →