# Development and Validation of the Provider Documentation Summarization Quality Instrument for Large Language Models

arXiv: https://arxiv.org/abs/2501.08977 · HTML: https://mlsanity.com/paper/2501.08977/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jan 2025.

## Built on by (most cited first, 9 of 9)

- [Document Summarization with Conformal Importance Guarantees](https://mlsanity.com/paper/2509.20461/) (2025)
- [Brittleness and Promise: Knowledge Graph Based Reward Modeling for Diagnostic Reasoning](https://mlsanity.com/paper/2509.18316/) (2025)
- [Augmenting Human Evaluation with LLM Judges: How Many Human Reviews Do You Need?](https://mlsanity.com/paper/2605.16354/) (2026)
- [Metric Match: A Subset Selection Approach to Evaluating LLM Judge Reliability](https://mlsanity.com/paper/2606.15029/) (2026)
- [One note in three: a verified census of three deployed AI scribes, and the instrument that counted it](https://mlsanity.com/paper/2608.31017/) (2026)
- [Dual-stage and Lightweight Patient Chart Summarization for Emergency Physicians](https://mlsanity.com/paper/2510.06263/) (2025)
- [CareTransition-Audit: A Benchmark to Audit Discharge Summaries for Efficient Care Transitions](https://mlsanity.com/paper/2604.05435/) (2026)
- [Evaluating Patient Safety Risks in Generative AI: Development and Validation of a FMECA Framework for Generated Clinical Content](https://mlsanity.com/paper/2605.04085/) (2026)
- [KnowBench: Effort Reduction as a Unified, Deployment-Grounded Benchmark for Clinical AI](https://mlsanity.com/paper/2609.15794/) (2026)

## Abstract (arXiv)

As Large Language Models (LLMs) are integrated into electronic health record (EHR) workflows, validated instruments are essential to evaluate their performance before implementation. Existing instruments for provider documentation quality are often unsuitable for the complexities of LLM-generated text and lack validation on real-world data. The Provider Documentation Summarization Quality Instrument (PDSQI-9) was developed to evaluate LLM-generated clinical summaries. Multi-document summaries were generated from real-world EHR data across multiple specialties using several LLMs (GPT-4o, Mixtral 8x7b, and Llama 3-8b). Validation included Pearson correlation for substantive validity, factor analysis and Cronbach's alpha for structural validity, inter-rater reliability (ICC and Krippendorff's alpha) for generalizability, a semi-Delphi process for content validity, and comparisons of high-versus low-quality summaries for discriminant validity. Seven physician raters evaluated 779 summaries and answered 8,329 questions, achieving over 80% power for inter-rater reliability. The PDSQI-9 demonstrated strong internal consistency (Cronbach's alpha = 0.879; 95% CI: 0.867-0.891) and high inter-rater reliability (ICC = 0.867; 95% CI: 0.867-0.868), supporting structural validity and generalizability. Factor analysis identified a 4-factor model explaining 58% of the variance, representing organization, clarity, accuracy, and utility. Substantive validity was supported by correlations between note length and scores for Succinct (rho = -0.200, p = 0.029) and Organized (ρ = -0.190, p = 0.037). Discriminant validity distinguished high- from low-quality summaries (p < 0.001). The PDSQI-9 demonstrates robust construct validity, supporting its use in clinical practice to evaluate LLM-generated summaries and facilitate safer integration of LLMs into healthcare workflows.