Pith. sign in

REVIEW 4 major objections 6 minor 37 references

A general-domain large language model pipeline can surface thousands of candidate documentation inconsistencies in real-world discharge summaries, but judging them, the paper argues, requires a graded ontology, not a binary label.

Reviewed by Pith at T0; open to challenge. T0 means a machine referee read the full paper against a public rubric. the ladder, T0–T4 →

Challenge this review Re-run · record.json Download PDF Read on arXiv ↗

T0 review · deepseek-v4-flash

2026-08-01 04:00 UTC pith:DY7W23U3

load-bearing objection A genuinely honest formative study of LLM-based EHR inconsistency detection; the taxonomy and failure-mode analysis are useful, but the headline numbers are unadjudicated and the abstract overstates what is supported. the 4 major comments →

arxiv 2607.22954 v1 pith:DY7W23U3 submitted 2026-07-24 cs.CL stat.AP

Toward Automated Detection of Documentation Inconsistencies in Electronic Health Records

Jian Lu , Panyu Chen , Miriam Treggiari , Robert Blessing , Danyang Zhuo , Chunhua Weng , William W. Stead , Anru R. Zhang This is my paper
classification cs.CL stat.AP
keywords Electronic Health RecordsNatural Language ProcessingDischarge SummariesMedical ErrorsDocumentation QualityLarge Language ModelsClinical Inconsistency DetectionOntology
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved

The pith

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper tries to establish that a two-stage pipeline built from general-purpose large language models can, without task-specific training, pull candidate documentation inconsistencies out of real-world discharge summaries. Applied to 3,000 records, the pipeline flagged 3,460 statement pairs, touching demographics, allergies, procedures, diagnoses, labs, medications, and care planning, with at least one flag in about 70% of admissions. The authors are careful to call these candidates, not confirmed errors; expert review shows many apparent conflicts dissolve once timing, evolving diagnoses, or documentation conventions are taken into account. From those observations they propose a graded ontology of clinical inconsistency—strict contradiction versus ambiguity—and a schema for describing each flag by section, scope, domain, attribute, and contradiction axis. A reader should care because EHR documentation errors are a recognized patient-safety risk, and this is a concrete attempt to turn open-ended LLM scanning into a structured, testable framework for automated quality assurance.

Core claim

On the paper's own terms, the discovery is that a two-stage LLM architecture—open-ended candidate identification followed by context-grounded verification—can scan full-length discharge summaries and return a large pool of internally conflicting statement pairs, 3,460 across 3,000 sampled records, including pairs with plausible safety implications such as a documented allergy alongside a prescription of the same drug, conflicting dosing frequencies in one medication entry, and post-procedure instructions for a procedure the record says was not performed. The same study, however, demonstrates that most of the work lies in interpretation: flagged pairs are often reconciled by a timeline, a dia

What carries the argument

The load-bearing mechanism is the two-stage detection pipeline, where Stage 1 prompts a general-purpose large language model to scan an entire discharge summary and return candidate statement pairs, and Stage 2 feeds each candidate back to a second, cheaper model that must search the same document for any reconciling context before issuing a binary verdict. The verification stage uses an asymmetric burden of proof: a pair is retained only if no plausible timeline or clinical explanation reconciles it, which biases output toward precision. The paper's conceptual machinery is the graded ontology (which sorts flags into strict contradiction or ambiguity) and the normalization schema (which loca

Load-bearing premise

The study assumes that the pipeline outputs selected for expert chart review are representative of all 3,460 candidates, so the four failure modes and the ontology built from them generalize to the full corpus that was not adjudicated.

What would settle it

Build a clinician-labeled reference set covering all 3,460 candidates (or a random sample with pre-specified power), with at least two independent adjudicators and a measured inter-rater agreement; if a large majority of candidates are not confirmed as genuine inconsistencies, or if the ontology's expected categories cannot accommodate the confirmed cases, the paper's central framing would not survive.

Watch this falsifier — get emailed when new claim-graph text bears on it.

If this is right

  • If the pipeline's candidate pool is even partially accurate, discharge notes could be screened automatically at sign-out, with flagged statement pairs routed to a clinician for a quick check.
  • The four failure modes (temporal progression, clinical nuance, documentation conventions, actionable gaps) specify where engineering effort should go: explicit timeline extraction, clinical knowledge access, and template awareness.
  • The ontology and schema give a concrete label set, which is the prerequisite for building a clinician-annotated corpus and measuring sensitivity and precision.
  • The two-stage inverse-search design—divergent candidate generation followed by convergent verification—offers a general strategy for high-precision contradiction detection in other long, context-heavy documents.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • This framework likely transfers beyond discharge summaries to progress notes, consultation letters, or even cross-document reconciliation within a single hospital stay, since the section/phase schema generalizes to other note types.
  • The 'ambiguity' tier implies a dual-use application: even when a flag is not a true error, it can feed a documentation-improvement loop that prompts clinicians to clarify intended meaning, turning detectors into quality-of-documentation tools.
  • The temporal-progression failure mode strongly suggests a hybrid architecture—an LLM for candidate search plus a symbolic, graph-based timeline reasoner for verification—which could be tested against the current all-LLM design.
  • A concrete next experiment: use the schema as a labeling scheme to train a small supervised model to classify flags, and compare its labels against human adjudication—this would probe whether the ontology is learnable, not just descriptive.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit.

Referee Report

4 major / 6 minor

Summary. The paper presents a formative study of a two-stage LLM pipeline (Gemini 2.5 Pro for open-ended candidate identification, then Gemini 2.5 Flash for context-grounded verification) applied to 3,000 MIMIC-IV-Note discharge summaries. The pipeline produced 3,460 candidate inconsistencies, affecting 69.7% of admissions. A subset was informally reviewed by two clinical experts, yielding representative examples across demographics, allergies, procedures, diagnoses, laboratory, medications, and care planning, plus four recurring failure modes (temporal progression, clinical nuance, documentation conventions, actionable documentation gaps). The paper proposes a graded ontology of clinical inconsistency (strict contradiction vs. ambiguity) and a normalization schema (type, section, scope, domain, attribute, axis) as a framework for future curated-corpus development. The abstract, introduction, and conclusion describe the pipeline as surfacing inconsistencies 'many with direct implications for clinical reasoning, medication safety, and procedural care,' while the body repeatedly and correctly cautions that the outputs are unadjudicated candidates, not ground-truth inconsistencies.

Significance. If the findings are taken as formative and qualitative, the paper makes a useful contribution: it demonstrates that a general-domain LLM pipeline can produce clinically plausible inconsistency candidates from full-length real-world discharge summaries, and it provides a structured vocabulary (ontology and schema) for future labeling and adjudication. The two-stage design with an asymmetric 'no plausible reconciliation' burden of proof is a sensible response to the false-positive problem, and the explicit cataloging of failure modes—especially temporal reasoning and medication-course reasoning—is valuable for the field. The authors are appropriately transparent that sensitivity and Stage 2 precision are unanswered questions. However, the paper's quantitative-sounding claims ('many with direct implications') outrun the evidence, which consists of unadjudicated pipeline outputs and a non-randomly selected set of examples. The contribution is primarily conceptual and methodological, not an empirical demonstration of prevalence or reliability.

major comments (4)
  1. [Section 3.1 and Section 6] The central claim that the pipeline surfaces inconsistencies 'many with direct implications for clinical reasoning, medication safety, and procedural care' is not supported by the reported evidence. The 3,460 candidates are explicitly unadjudicated (Section 3.1), and Section 5.1 states that 'how frequently surfaced contradictions are clinically valid (Stage 2 precision)' remains unanswerable without a reference corpus. The expert-reviewed examples in Table 1 are 'selected through chart review' with no sampling plan, no inter-rater reliability statistic, and no adjudication protocol. This selection process does not license the word 'many.' Please either soften the conclusion to 'candidate inconsistencies, some of which, on informal expert review, appear clinically concerning,' or provide a randomized, independent adjudication of a prespecified sample of Stage-2 outputs with precision esti
  2. [Section 2.3] The method is defined entirely by the two prompts, yet neither prompt is included in the paper or an appendix. The description of Stage 1's exclusions and Stage 2's asymmetric burden of proof cannot be independently evaluated or reproduced without the exact prompt text, model parameters (temperature, max tokens, batching), and post-processing logic. Please provide the full prompts and inference configuration as supplementary material. This is a load-bearing reproducibility issue for an LLM-pipeline paper.
  3. [Abstract vs. Section 2.1] The abstract states the pipeline was applied to '3,000 randomly sampled MIMIC-IV-Note discharge summaries,' but the Methods say the sample was drawn as 'three contiguous 1,000-note batches from distinct positions in the corpus.' Contiguous batches are not a random sample and may be biased by temporal drift or documentation conventions. If the batches were selected by a pseudo-random mechanism, that mechanism is not described. Please correct the abstract or justify why contiguous batches are adequate for the qualitative claims, and report the corpus positions and date ranges of the batches.
  4. [Section 3.2] The four failure modes are presented as 'recurring,' but the paper gives no frequency information: no denominator for the number of candidates reviewed, no counts per failure mode, and no indication of whether the examples in Table 2 are exhaustive or illustrative. Since Section 5.2 prioritizes future work based on these failure modes (e.g., temporal-progression failures as the motivation for structured timeline reasoning), the absence of any distributional data weakens the roadmap. Please add a quantitative breakdown of the reviewed subset, or explicitly state that the four modes are illustrative and not prevalence-ranked.
minor comments (6)
  1. [Section 4.2] Typo: 'clinical reconcilation' should be 'clinical reconciliation.'
  2. [Section 3.1] The 'Procedure & device' narrative paragraph highlights laterality as a clinically distinctive subset, but the Table 1 procedure example is about a procedure that appears in discharge instructions but not in the procedure list—an absence/presence conflict, not laterality. Consider aligning the narrative with the example or adding a laterality example.
  3. [Figure 1 / Table 3] Naming is inconsistent: Figure 1 and Section 1 use 'care-planning domains,' while Table 3 and Section 3.1 use 'Disposition & care planning.' Standardize terminology.
  4. [Section 2.3] The phrase 'Stage 1 retained as Stage 1 in the final pipeline' is circular. Clarify that the original single-prompt design was kept unchanged as the first stage of the final two-stage pipeline.
  5. [Figure 2] The schema has no explicit 'temporal' dimension, even though temporal progression is a major failure mode and Table 4 lists 'timing' as a contradiction axis. Consider adding a 'when' field (e.g., phase pair) to the schema to make temporal context a first-class attribute.
  6. [Table 2] The heading 'T able 2' has a formatting artifact. Also, consider explicitly labeling the reconcilable pairs as Stage-2 false positives to make clear that they passed Stage 2 verification, and describe how they were identified (e.g., during expert review of the full candidate pool).

Circularity Check

0 steps flagged

No circularity: the pipeline is an independent LLM tool evaluated by expert review; the ontology is explicitly presented as a working vocabulary, not a derived prediction.

full rationale

The paper contains no fitted parameters, no equations, and no derivation whose output is wired back into its inputs. The central empirical claim—that a two-stage LLM pipeline can surface candidate inconsistencies in discharge summaries—is tested by applying an independently specified prompt pipeline to MIMIC-IV notes and reviewing a subset with clinical experts. The paper repeatedly and explicitly disclaims that the outputs are ground truth ('we treat them as pipeline-generated candidates rather than ground-truth inconsistencies,' Section 3.1; 'representative cases... should be interpreted as formative examples rather than as adjudicated prevalence estimates,' Section 3.1; 'without such a reference corpus key questions remain unanswerable—including... how frequently surfaced contradictions are clinically valid (Stage 2 precision),' Section 5.1). The ontology and schema are not used to prove the pipeline's accuracy; they are introduced as a 'working vocabulary to be tested and refined during corpus labeling' (Section 4.2). Deriving that vocabulary from the same qualitative cases it describes is an inductive limitation, not a circular reduction: the framework makes no quantitative claim that depends on its own construction. There are no load-bearing self-citations; references to MIMIC-IV, Gemini, and prior clinical NLP benchmarks are external. The main weaknesses—unadjudicated candidates, informal selection of examples, no inter-rater reliability statistics—are validity concerns, not circularity.

Axiom & Free-Parameter Ledger

0 free parameters · 3 axioms · 0 invented entities

The paper introduces no free parameters and no new physical or computational entities. Its conceptual framework—graded ontology and schema—is a labeling vocabulary rather than an invented mechanism. The load-bearing assumptions are about data representativeness, expert-review reliability, and treating unvalidated LLM outputs as a meaningful object of study.

axioms (3)
  • domain assumption MIMIC-IV-Note discharge summaries are representative of real-world EHR discharge documentation.
    All empirical findings are based on 3,000 notes from one tertiary academic center; no external corpus is used (Section 2.1).
  • domain assumption Clinical expert chart review of a selected subset is a reliable reference for adjudicating candidate inconsistencies.
    Representative cases and failure modes are derived from expert review of a subset without reported inter-rater reliability or a formal gold standard (Sections 3.1–3.2).
  • domain assumption LLM outputs (Gemini 2.5 Pro and Flash) can be treated as meaningful candidate pairs for qualitative study.
    The pipeline's outputs are not compared against a baseline or manually adjudicated in full; they are accepted as the object of study rather than validated measurements (Section 3.1).

pith-pipeline@v1.3.0-alltime-deepseek · 11922 in / 6736 out tokens · 62599 ms · 2026-08-01T04:00:23.452585+00:00 · methodology

0 comments
read the original abstract

Objective: To characterize the kinds of internal documentation inconsistencies a general-domain large language model (LLM) can surface from real-world discharge summaries, and to identify recurring failure modes that limit reliability at scale. Materials and Methods: We applied a two-stage LLM pipeline---open-ended candidate identification (Gemini 2.5 Pro) followed by context-grounded verification (Gemini 2.5 Flash)---to 3,000 randomly sampled MIMIC-IV-Note discharge summaries. A subset of the pipeline output was then reviewed manually by clinical experts. Results: Our pipeline surfaced 3,460 candidate inconsistencies, affecting 69.7% of admissions. Representative examples spanned demographics, allergies, procedures, diagnoses, laboratory, medications, and care-planning domains, with direct implications for clinical reasoning or patient safety. Expert review also revealed recurring failure modes that arise when verification requires temporal reasoning, evolving-diagnosis context, or knowledge of outpatient-prescribing conventions the model does not natively possess. Discussion: Detection is highly context-dependent: many flagged pairs require anchoring each statement to its source section and clinical domain, then assessing whether the conflict reflects a true contradiction or missing context. We propose a graded ontology spanning strict contradiction and ambiguity, with a schema characterizing each flagged case by category, section, domain, and inconsistency axis. Conclusion: This formative study establishes a methodological foundation and conceptual framework to guide subsequent validated, large-scale EHR-inconsistency analysis.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

37 extracted references · 7 canonical work pages · 1 internal anchor

  1. [1]

    The artificial intelligence clinician learns optimal treatment strategies for sepsis in inten- sive care

    Komorowski M, Celi LA, Badawi O, Gordon AC, Faisal AA. The artificial intelligence clinician learns optimal treatment strategies for sepsis in inten- sive care. Nature medicine. 2018;24(11):1716–1720. https://doi.org/10.1038/ s41591-018-0213-5

    2018

  2. [2]

    Multitask learning and benchmarking with clinical time series data

    Harutyunyan H, Khachatrian H, Kale DC, Galstyan A. Multitask learning and benchmarking with clinical time series data. Scientific data. 2017;6(1):96. https: //doi.org/10.1038/s41597-019-0103-9. 23

    doi:10.1038/s41597-019-0103-9 2017

  3. [3]

    Predicting hospital length of stay using neural networks on mimic iii data

    Gentimis T, Alnaser AJ, Durante A, Cook K, Steele R. Predicting hospital length of stay using neural networks on mimic iii data. In: 2017 IEEE 15th intl conf on dependable, autonomic and secure computing, 15th intl conf on pervasive intel- ligence and computing, 3rd intl conf on big data intelligence and computing and cyber science and technology congress...

    2017

  4. [4]

    Detection of medication mentions and medication change events in clinical notes using transformer-based models

    Guo Y, Ge Y, Sarker A. Detection of medication mentions and medication change events in clinical notes using transformer-based models. Medinfo. 2024;310:685. https://doi.org/10.3233/SHTI231052

    work page doi:10.3233/shti231052 2024

  5. [5]

    Enhancing phenotype recognition in clinical notes using large language models: PhenoBCBERT and PhenoGPT

    Yang J, Liu C, Deng W, Wu D, Weng C, Zhou Y, et al. Enhancing phenotype recognition in clinical notes using large language models: PhenoBCBERT and PhenoGPT. Clinical Natural Language Processing Workshop. 2023;5(1). https: //doi.org/10.48550/arXiv.2308.06294

    Pith/arXiv arXiv doi:10.48550/arxiv.2308.06294 2023

  6. [6]

    Methods and dimensions of electronic health record data quality assessment: enabling reuse for clinical research

    Weiskopf NG, Weng C. Methods and dimensions of electronic health record data quality assessment: enabling reuse for clinical research. J Am Medical Informatics Assoc. 2013;20(1):144–151. https://doi.org/10.1136/amiajnl-2011-000681

    doi:10.1136/amiajnl-2011-000681 2013

  7. [7]

    Preventable deaths due to problems in care in English acute hospitals: a retrospective case record review study

    Hogan H, Healey F, Neale G, Thomson R, Vincent C, Black N. Preventable deaths due to problems in care in English acute hospitals: a retrospective case record review study. BMJ Quality & Safety. 2012;21(9):737–745. https://doi.org/ 10.1136/bmjqs-2011-001159

    work page doi:10.1136/bmjqs-2011-001159 2012

  8. [8]

    Improving Diagnosis in Health Care

    Balogh EP, Miller BT, Ball JR, editors. Improving Diagnosis in Health Care. Washington, DC: National Academies Press; 2015. Committee on Diagnostic Error in Health Care, Board on Health Care Services, Institute of Medicine, National Academies of Sciences, Engineering, and Medicine. 24

    2015

  9. [9]

    The impact of electronic health records on diagnosis

    Graber ML, Byrne C, Johnston D. The impact of electronic health records on diagnosis. Diagnosis. 2017;4(4):211–223. https://doi.org/10.1515/dx-2017-0012

    work page doi:10.1515/dx-2017-0012 2017

  10. [10]

    The frequency of diagnostic errors in outpa- tient care: estimations from three large observational studies involving US adult populations

    Singh H, Meyer AND, Thomas EJ. The frequency of diagnostic errors in outpa- tient care: estimations from three large observational studies involving US adult populations. BMJ Quality & Safety. 2014;23(9):727–731. https://doi.org/10. 1136/bmjqs-2013-002627

    2014

  11. [11]

    Sentinel Event Alert 58

    The Joint Commission.: Safe use of health information technology. Sentinel Event Alert 58. Available from: https://digitalassets.jointcommission.org/api/public/ content/2dc4cad7bdc34451b85a2be5431f09ef?v=c9afdcd7

  12. [12]

    Georg Thieme Verlag KG

    The Joint Commission.: Safe Practices for Copy and Paste in the Electronic Health Record. Georg Thieme Verlag KG. Sentinel Event Alert, Issue 54

  13. [13]

    Direct Text Entry in Electronic Progress Notes: An Evaluation of Input Errors

    Weir CR, Hurdle JF, Felgar MA, Hoffman JM, Roth B, Nebeker JR. Direct Text Entry in Electronic Progress Notes: An Evaluation of Input Errors. Meth- ods of Information in Medicine. 2003;42(1):61–67. https://doi.org/10.1055/ s-0038-1634210

    2003

  14. [14]

    Unintended Consequences of Nation- wide Electronic Health Record Adoption: Challenges and Opportunities in the Transition to a Digital Health System

    Colicchio TK, Cimino JJ, Del Fiol G. Unintended Consequences of Nation- wide Electronic Health Record Adoption: Challenges and Opportunities in the Transition to a Digital Health System. Journal of Medical Internet Research. 2019;21(6):e13313. https://doi.org/10.2196/13313

    work page doi:10.2196/13313 2019

  15. [15]

    Unintended medication discrepancies at the time of hospital admission

    Cornish P, Knowles S, Marchesano R, Tam V, Shadowitz S, Juurlink D, et al. Unintended medication discrepancies at the time of hospital admission. Archives of Internal Medicine. 2005;165(4):424. https://doi.org/10.1001/archinte.165.4. 424. 25

    work page doi:10.1001/archinte.165.4 2005

  16. [16]

    Role of Computerized Physician Order Entry Systems in Facilitating Medication Errors

    Koppel R, Metlay JP, Cohen A, Abaluck B, Localio AR, Kimmel SE, et al. Role of Computerized Physician Order Entry Systems in Facilitating Medication Errors. JAMA. 2005;293(10):1197–1203. https://doi.org/10.1001/jama.293.10.1197

    work page doi:10.1001/jama.293.10.1197 2005

  17. [17]

    Patient- reported errors in electronic health record ambulatory visit notes

    Bell SK, Mejilla R, Anselmo M, Darer JD, Elmore JG, Leveille SG, et al. Patient- reported errors in electronic health record ambulatory visit notes. JAMA Network Open. 2020;3(2):e200275. https://doi.org/10.1001/jamanetworkopen.2020.0275

    arXiv 2020

  18. [18]

    LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models

    Guha N, Nyarko J, Ho DE, R´ e C, Chilton A, Narayana A, et al. LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models. arXiv preprint. 2023;ArXiv:2308.11462

    Pith/arXiv arXiv 2023

  19. [19]

    BloombergGPT: A Large Language Model for Finance

    Wu S, Irsoy O, Lu S, Dabravolski V, Dredze M, Gehrmann S, et al. BloombergGPT: A Large Language Model for Finance. arXiv preprint. 2023;ArXiv:2303.17564

    Pith/arXiv arXiv 2023

  20. [20]

    Large language models in medicine

    Thirunavukarasu AJ, Ting DSJ, Elangovan K, Gutierrez L, Tan TF, Ting DSW. Large language models in medicine. Nature Medicine. 2023;29(8):1930–1940. https://doi.org/10.1038/s41591-023-02448-8

    doi:10.1038/s41591-023-02448-8 2023

  21. [21]

    The future landscape of large language models in medicine

    Clusmann J, Kolbinger F, Muti H, Carrero ZI, Eckardt JN, Laleh NG, et al. The future landscape of large language models in medicine. Communications Medicine. 2023;3(1):141. https://doi.org/10.1038/s43856-023-00370-1

    doi:10.1038/s43856-023-00370-1 2023

  22. [22]

    Large language models encode clinical knowledge

    Singhal K, Azizi S, Tu T, Mahdavi S, Wei J, Chung HW, et al. Large language models encode clinical knowledge. Nature. 2022;620(7972):172–180. https://doi. org/10.1038/s41586-023-06291-2

    doi:10.1038/s41586-023-06291-2 2022

  23. [23]

    Toward expert- level medical question answering with large language models

    Singhal K, Tu T, Gottweis J, Sayres R, Wulczyn E, Amin M, et al. Toward expert- level medical question answering with large language models. Nature Medicine. 2025;31(3):943–950. https://doi.org/10.1038/s41591-024-03423-7. 26

    doi:10.1038/s41591-024-03423-7 2025

  24. [24]

    Large Language Models are Few-Shot Clinical Information Extractors

    Agrawal M, Hegselmann S, Lang H, Kim Y, Sontag D. Large Language Models are Few-Shot Clinical Information Extractors. In: Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics; 2022. p. 1998–2022. Available from: https://aclanthology.org/2022.emnlp-main.130/

    2022

  25. [25]

    A large language model for electronic health records

    Yang X, Chen A, Pournejatian NM, Shin HC, Smith KE, Parisien C, et al. A large language model for electronic health records. npj Digital Medicine. 2022;5(1):194. https://doi.org/10.1038/s41746-022-00742-2

    doi:10.1038/s41746-022-00742-2 2022

  26. [26]

    Adapted large language models can outperform medical experts in clinical text summarization

    Veen DV, Uden CV, Blankemeier L, Delbrouck JB, Aali A, Bl¨ uthgen C, et al. Adapted large language models can outperform medical experts in clinical text summarization. Nature Medicine. 2023;30(4):1134–1142. https://doi.org/10. 1038/s41591-024-02855-5

    2023

  27. [27]

    Overview of the MEDIQA-CORR 2024 Shared Task on Medical Error Detection and Correc- tion

    Abacha AB, Yim Ww, Fu Y, Sun Z, Xia F, Yetisgen M. Overview of the MEDIQA-CORR 2024 Shared Task on Medical Error Detection and Correc- tion. In: Clinical Natural Language Processing Workshop. Mexico City, Mexico: Association for Computational Linguistics; 2024. p. 596–603. Available from: https://aclanthology.org/2024.clinicalnlp-1.34

    2024

  28. [28]

    MEDEC: A Benchmark for Medical Error Detection and Correction in Clinical Notes

    Abacha AB, Yim Ww, Fu Y, Sun Z, Yetisgen M, Xia F, et al. MEDEC: A Benchmark for Medical Error Detection and Correction in Clinical Notes. In: Annual Meeting of the Association for Computational Linguistics; 2024. p. 22539– 22550

    2024

  29. [29]

    WangLab at MEDIQA-CORR 2024: Retrieval-Augmented and DSPy-Optimized LLM Programs for Medical Error Detection and Correction

    Toma A, Xie R, Palayew S, Lawler P, Wang B. WangLab at MEDIQA-CORR 2024: Retrieval-Augmented and DSPy-Optimized LLM Programs for Medical Error Detection and Correction. In: Proceedings of the 6th Clinical Natural Language Processing Workshop. Mexico City, Mexico: Association for Compu- tational Linguistics; 2024. p. 616–623. Available from: https://aclant...

    2024

  30. [30]

    PromptMind at MEDIQA-CORR 2024: Improving Clinical Text Correction with Error Categorization and LLM Ensembles

    Gundabathula SK, Kolar SR. PromptMind at MEDIQA-CORR 2024: Improving Clinical Text Correction with Error Categorization and LLM Ensembles. In: Clin- ical Natural Language Processing Workshop. Mexico City, Mexico: Association for Computational Linguistics; 2024. p. 367–373

    2024

  31. [31]

    Edinburgh Clinical NLP at MEDIQA-CORR 2024: Guiding Large Language Models with Hints

    Gema AP, Lee C, Minervini P, Daines L, Simpson TI, Alex B. Edinburgh clinical nlp at mediqa-corr 2024: Guiding large language models with hints. Clinical Natural Language Processing Workshop. 2024;p. 488–501. https://doi.org/10. 48550/arXiv.2405.18028

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.2405.18028 2024

  32. [32]

    Mimic-iv

    Johnson A, Bulgarelli L, Pollard T, Horng S, Celi LA, Mark R. Mimic-iv. Phy- sioNet Available online at: https://physionet org/content/mimiciv/10/(accessed August 23, 2021). 2020;p. 49–55

    2021

  33. [33]

    MIMIC-IV-Note: Deidentified Free-Text Clinical Notes

    Johnson A, Pollard T, Horng S, Celi LA, Mark R. MIMIC-IV-Note: Deidentified Free-Text Clinical Notes. PhysioNet. 2023;Version 2.2. https://doi.org/10.13026/ 1n74-ne17

    2023

  34. [34]

    Chain-of-Thought Prompting Elicits Reasoning in Large Language Models

    Wei J, Wang X, Schuurmans D, Bosma M, Chi EH, Xia F, et al. Chain-of-Thought Prompting Elicits Reasoning in Large Language Models. In: Neural Information Processing Systems (NeurIPS); 2022. p. 24824–24837

    2022

  35. [35]

    Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

    Comanici G, Bieber E, Schaekermann M, Pasupat I, Sachdeva N, Dhillon IS, et al. Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities. arXivorg. 2025

    2025

  36. [36]

    Logical Reasoning

    Dowden BH. Logical Reasoning. California State University, Sacramento; 2015. Open-access textbook. 28

    2015

  37. [37]

    SemEval-2017 Task 12: Clinical TempEval

    Bethard S, Savova G, Palmer M, Pustejovsky J. SemEval-2017 Task 12: Clinical TempEval. In: International Workshop on Semantic Evaluation. Association for Computational Linguistics; 2017. p. 565–572. 29

    2017