Background: The American Medical Association recommends that electronic health record (EHR) notes, often dense and written in nuanced language, be made readable for patients and laypeople, a practice we refer to as the simplification of discharge notes. Our approach to achieving the simplification of discharge notes involves a process of incremental simplification steps to achieve the ideal note. In this paper, we present the first step of this process. Large language models (LLMs) have demonstrated considerable success in text summarization. Such LLM summaries represent the content of EHR notes in an easier-to-read language. However, LLM summaries can also introduce inaccuracies. Objective: This study aims to test the hypothesis that summaries generated by LLMs from highlighted discharge notes will achieve increased accuracy compared to those generated from the original notes. For this purpose, we aim to prove a hypothesis that summaries generated by LLMs of discharge notes in which detailed information is highlighted are likely to be more accurate than summaries of the original notes. Methods: To test our hypothesis, we randomly sampled 15 discharge notes from the MIMIC III database and highlighted their detailed information using an interface terminology we previously developed with machine learning. This interface terminology was curated to encompass detailed information from the discharge notes. The highlighted discharge notes distinguished detailed information, specifically the concepts present in the aforementioned interface terminology, by applying a blue background. To calibrate the LLMs’ summaries for our simplification goal, we chose GPT-4o and used prompt engineering to ensure high-quality prompts and address issues of output inconsistency and prompt sensitivity. We provided both highlighted and unhighlighted versions of each EHR note along with their corresponding prompts to GPT-4o. Each generated summary was manually evaluated to assess its quality using the following evaluation metrics: completeness, correctness, and structural integrity. Results: We used the study sample of 15 discharge notes. On average, summaries from highlighted notes (H-summaries) achieved 96% completeness, 8% higher than the summaries from unhighlighted notes (U-summaries). H-summaries had higher completeness in 13 notes, and U-summaries had higher or equal completeness in 2 notes, resulting in P=.01, which implied statistical significance. Moreover, H-summaries demonstrated better correctness than U-summaries, with fewer instances of erroneous information (2 vs 3 errors, respectively). The number of improper headers was smaller for H-summaries for 11 notes and U-summaries for 4 notes (P=.03; implying statistical significance). Moreover, we identified 8 instances of misplaced information in the U-summaries and only 2 in the H-summaries. We showed that our findings supported the hypothesis that summarizing highlighted discharge notes improves the accuracy of the summaries. Conclusions: Feeding LLMs with highlighted discharge notes, combined with prompt engineering, results in higher-quality summaries in terms of correctness, completeness, and structural integrity compared to unhighlighted discharge notes.

This study investigates whether incorporating highlighted information in discharge notes improves the quality of the summaries generated by Large Language Models (LLMs). Specifically, it evaluates the effect of using highlighted versus unhighlighted inputs for fine-tuning LLaMA2-13B model for summarization tasks. We fine-tuned LlaMA2-13B in two variants using MIMIC-IV-Ext-BHC dataset: one variant fine-tuned with the highlighted discharge notes (H-LLaMA), and the other on the same set of notes without highlighting (U-LLaMA). Highlighting was performed automatically using a Cardiology Interface Terminology (CIT) presented in our previous work. H-LLaMA and U-LLaMA were evaluated on a randomly selected test set of 100 discharge notes using multiple metrics (including BERTScore, ROUGE-L, BLEU, and SummaC_CONV). Additionally, LLM-based judgment via ChatGPT-4o rated coherence, fluency, conciseness, and correctness, alongside a manual completeness evaluation on a random sample of 40 notes. H-LLaMA consistently outperformed U-LLaMA across all metrics. H-summaries, generated using H-LLaMA, in comparison to U-summaries, generated using U-LLaMA, achieved higher BERTScore (63.75 vs. 59.61), ROUGE-L (23.43 vs. 21.82), BLEU (10.4 vs. 8.41), and SummaC_CONV (67.7 vs. 40.2). Manual review also showed improved completeness for H-summaries (54.8% vs. 47.6%). All improvements were statistically significant (p < 0.05). Moreover, LLM-based evaluation indicated higher average ratings across coherence, correctness, and conciseness.

Battery-powered sensors must sample sparingly to conserve energy while still reconstructing the signal faithfully between measurements, and the decision logic must fit microcontroller-class hardware. We use a large language model (LLM) as an offline policy compiler: given a natural-language task description and a compact rule grammar, it returns policies as a few numeric thresholds and integer periods, under 100 bytes. No weights are fitted and the model never sees the raw series, only eight summary statistics: the approach is training-free but statistics-informed. Policies come from an agentic loop: a generator LLM proposes candidates, a deterministic evaluator scores each exactly on the recorded trace, and an optimizer LLM refines them over eight rounds. We evaluate Claude Opus 4.8, Claude Fable 5, ChatGPT 5.4 and ChatGPT 5.5, five seeds each, on the Beijing PM2.5 series against classical baselines, a budget-matched random search, and NSGA-II and ParEGO over the identical grammar. The loop improves on zero-shot generation and random search (pooled Wilcoxon p < 10−5): within a 0.20 duty-cycle budget the best model’s mean across five seeds reaches an RMSE of 21.79 against 25.09 for random search, and 15.98 against 20.57 within 0.30. The gain narrows at the tightest subsampling, which an interpolation-error bound explains through the signal’s curvature.

Discharge notes contain complex clinical language that patients often struggle to understand. We investigate the impact of automatic highlighting and multi-step prompting on discharge note simplification using in-context learning with large language models. Highlighting is performed using a domain-specific Cardiology Interface Terminology. We used 28 MIMIC-III discharge notes paired with physician-authored summaries and evaluated four configurations (U1, U2, H1, H2): one-step and two-step simplification applied to either highlighted or unhighlighted notes. In one-step simplification (U1 or H1), the model generated a structured, patient-friendly summary directly from the note. In two-step simplification (U2 or H2), the model first generated a structured summary and then simplified it to a 6th-grade reading level. Manual evaluation showed that completeness improved from U1 to H2 (U1 < H1 < U2 < H2), with H2 achieving the highest completeness (92.45%) and the fewest errors (1) compared to U1 (79.05%, 5 errors). Improvements were statistically significant (p < 0.001), except between H1 and U1. Readability improves across all methods (e.g., FKGL reduced from 11 to 7.7 in U2). LLM-based evaluation using both ChatGPT and Gemini shows strong agreement (ρ = 0.88) and favors H2. This pilot study shows combining highlighting with two-step prompting yields more patient-comprehensible summaries.

BACKGROUND The American Medical Association recommends that electronic health record (EHR) notes, often dense and written in nuanced language, be made readable for patients and laypeople, a practice we refer to as the simplification of discharge notes. Our approach to achieving the simplification of discharge notes involves a process of incremental simplification steps to achieve the ideal note. In this paper, we present the first step of this process. Large language models (LLMs) have demonstrated considerable success in text summarization. Such LLM summaries represent the content of EHR notes in an easier-to-read language. However, LLM summaries can also introduce inaccuracies. OBJECTIVE This study aims to test the hypothesis that summaries generated by LLMs from highlighted discharge notes will achieve increased accuracy compared to those generated from the original notes. For this purpose, we aim to prove a hypothesis that summaries generated by LLMs of discharge notes in which detailed information is highlighted are likely to be more accurate than summaries of the original notes. METHODS To test our hypothesis, we randomly sampled 15 discharge notes from the MIMIC III database and highlighted their detailed information using an interface terminology we previously developed with machine learning. This interface terminology was curated to encompass detailed information from the discharge notes. The highlighted discharge notes distinguished detailed information, specifically the concepts present in the aforementioned interface terminology, by applying a blue background. To calibrate the LLMs’ summaries for our simplification goal, we chose GPT-4o and used prompt engineering to ensure high-quality prompts and address issues of output inconsistency and prompt sensitivity. We provided both highlighted and unhighlighted versions of each EHR note along with their corresponding prompts to GPT-4o. Each generated summary was manually evaluated to assess its quality using the following evaluation metrics: completeness, correctness, and structural integrity. RESULTS We used the study sample of 15 discharge notes. On average, summaries from highlighted notes (H-summaries) achieved 96% completeness, 8% higher than the summaries from unhighlighted notes (U-summaries). H-summaries had higher completeness in 13 notes, and U-summaries had higher or equal completeness in 2 notes, resulting in P=.01, which implied statistical significance. Moreover, H-summaries demonstrated better correctness than U-summaries, with fewer instances of erroneous information (2 vs 3 errors, respectively). The number of improper headers was smaller for H-summaries for 11 notes and U-summaries for 4 notes (P=.03; implying statistical significance). Moreover, we identified 8 instances of misplaced information in the U-summaries and only 2 in the H-summaries. We showed that our findings supported the hypothesis that summarizing highlighted discharge notes improves the accuracy of the summaries. CONCLUSIONS Feeding LLMs with highlighted discharge notes, combined with prompt engineering, results in higher-quality summaries in terms of correctness, completeness, and structural integrity compared to unhighlighted discharge notes.