Dimensions overall score 8.0

GitHub Code Pulse

No public code linked for this paper yet.

• PVminerLLM achieves up to 83.82% F1 score for Code prediction in structured extraction of patient voice from patient-generated text.result 95%
• PVminerLLM achieves up to 80.74% F1 score for Sub-code prediction in patient voice extraction.result 95%
• PVminerLLM achieves up to 87.03% F1 score for evidence Span extraction from patient-generated text.result 95%
• PVminerLLM substantially outperforms prompt-based baselines across multiple datasets and model sizes.result 90%
• Reliable patient voice extraction is feasible without extreme model scale, as strong performance is achieved even with smaller models.technical 85%
• The reliability of patient voice extraction could vary with different patient populations and linguistic styles.limitation 90%
• Patient-generated text contains critical information about patients' lived experiences, social circumstances, and engagement in care that strongly influence adherence, care coordination, and health equity.market 90%
• PVminerLLM is a supervised fine-tuned large language model tailored for structured extraction of patient voice from patient-generated text.method 95%

Competitive landscape

Competitor map is still being generated for this paper. Enable generation or check back soon.

Startup potential card