{"id":"21bc11bc-70e4-4adf-ac3f-fc582a39d451","arxiv_id":"2611.17053","paper_version":1,"verdict":"ACCEPT","confidence":"HIGH","novelty_score":6.0,"correctness_risk":"low","formal_verification":"none","parameter_count":5,"one_line_summary":"tEHR adapts LLMs to EHR prediction by converting medical codes to text descriptions, using continued pretraining and discriminative fine-tuning, achieving strong results on MIMIC-IV and CPRD tasks.","lead":"This paper introduces tEHR, a method that converts structured electronic health records into natural language descriptions and adapts large language models to predict patient outcomes. The approach achieves strong performance across multiple clinical tasks and datasets, and systematic experiments reveal that the semantic meaning of medical events is a key driver of this performance.","discovery_kind":"new_method","skeptic_critique":{"model":"deepseek/deepseek-v4-flash","headline":"The ablation 'scrambled concepts' may not fully isolate the contribution of pretrained lexical semantics from the model's ability to exploit syntactic and distributional patterns in the text stream.","rationale":"The reader's weakest_assumption focuses on whether the natural language descriptions are a faithful and sufficient representation, and notes that the paper does not compare against using code hierarchies. My concern is related but distinct: it targets the internal validity of the key ablation that is used to support the central claim about pretrained language semantics. The 'scrambled concepts' ablation is the primary evidence that lexical grounding matters, but it may not fully isolate the contribution of pretrained semantics from other linguistic features. This is a load-bearing concern because the paper's main contribution is demonstrating the importance of pretrained language semantics. However, the paper does provide other supporting evidence (e.g., atomic codes ablation, hashed concepts, alternative semantic injection methods) that collectively strengthen the claim. The concern is real but not fatal; the paper's overall conclusion is still well-supported. Therefore, I recommend UNCHANGED verdict. I partially agree with the reader because my concern is about the interpretation of a specific ablation rather than the overall assumption about description faithfulness.","tokens_in":22519,"tokens_out":641,"duration_ms":6953,"concrete_test":"Replace each clinical code's description with a description of a semantically unrelated concept from a non-medical domain (e.g., legal terms, financial instruments) that preserves the same part-of-speech distribution and sentence structure. If performance drops to near the 'hashed concepts' level, the original ablation's interpretation is supported. If performance remains closer to the full tEHR level, then the model is leveraging general linguistic patterns rather than specific clinical semantics.","verdict_should_be":"UNCHANGED","load_bearing_attack":"The paper's central claim is that pretrained language semantics are a key contributor to tEHR's performance. The key ablation is 'scrambled concepts' (Section 3.3), where concept descriptions are deterministically permuted within event categories for each patient. The authors argue this 'breaks the correspondence between each concept and its true clinical meaning' while preserving 'plausible medical language and broad event type'. However, this ablation may not fully isolate lexical semantics from other cues. The scrambled descriptions still form coherent English text, and the LLM's pretrained knowledge of syntax, grammar, and general medical terminology (e.g., 'pancreatitis' vs 'diabetes') could still provide signal. The model might exploit distributional patterns in the scrambled text that correlate with outcomes, even if individual concept-description mappings are wrong. The ablation does not control for the possibility that the LLM is using general linguistic patterns rather than specific semantic knowledge of each code. A stronger test would be to compare against a condition where descriptions are replaced with semantically unrelated but syntactically similar text from a different domain (e.g., legal or financial descriptions), which would preserve linguistic structure while removing clinical semantics. The paper acknowledges limitations but does not address this specific confound.","agreement_with_reader":"partial"},"referee_report":null,"author_rebuttal":null,"desk_editor":{"model":"deepseek/deepseek-v4-flash","letter":"Hey,\n\nThis is a well-executed empirical paper. The core idea is straightforward: convert structured EHR events into natural-language descriptions and adapt a causal LLM through continued pretraining + discriminative fine-tuning. The main contribution is the systematic ablation study that isolates the contribution of pretrained language semantics. The paper does this cleanly, with multiple baselines, three seeds, and honest reporting of limitations.\n\nWhat's new: The two-stage framework (continued pretraining then LoRA fine-tuning) applied to textualised EHR is not entirely novel—there are prior works doing pieces of this—but the thorough ablations are the value add. The finding that lexical grounding matters more than elapsed-time descriptions, and that the atomic-code variant underperforms despite same backbone, is genuinely informative for the field.\n\nThe paper is sound. The experiments are well-designed, the results are clear, and the authors acknowledge the main limitations: CPRD evaluation is only one task, the ablation suite is only on MIMIC-IV, computational cost is high, and the CLMBR-T comparison is incomplete due to vocabulary mapping issues. They also note that clustering does not establish causality.\n\nSoft spots: The stress-test concern about the scrambled-concepts ablation is real. The authors argue that scrambling 'breaks the correspondence between each concept and its true clinical meaning' while preserving 'plausible medical language and broad event type.' But scrambled descriptions still form coherent English, and the LLM could exploit general linguistic patterns (syntax, distributional cues) that correlate with outcomes. The ablation does not fully isolate lexical semantics from these other signals. A stronger control would be to replace descriptions with semantically unrelated but syntactically similar text from a different domain (e.g., legal or financial). The paper does not address this confound. That said, the atomic-code variant (which removes all lexical semantics) also shows a large drop, which partially mitigates the concern—but the scrambled condition is still ambiguous.\n\nAnother minor point: the paper claims tEHR 'avoids dataset-specific preprocessing,' but the textualisation still requires mapping codes to descriptions via official coding-system metadata, which is itself a form of preprocessing. This is a minor overstatement.\n\nWho is this for: Researchers working on clinical AI, especially those building EHR foundation models. The paper provides practical guidance on what matters (lexical grounding, continued pretraining) and what doesn't (elapsed-time descriptions). It deserves a serious referee.\n\nRecommendation: Accept with minor revisions. The scrambled-concepts ablation should be discussed more carefully, and the authors should either add a stronger control or explicitly acknowledge the confound. The paper is otherwise solid.\n\nBest,\n[Your name]","headline":"Solid empirical paper on using LLMs for EHR prediction; the central claim about lexical grounding holds up, but the stress-test concern about the scrambled-concepts ablation is real and not fully addressed.","tokens_in":23353,"tokens_out":649,"duration_ms":8054},"pith_extraction":null,"created_at":"2026-11-13T10:50:32.986817+00:00","model_set":{"reader":"deepseek/deepseek-v4-flash"},"pipeline_version":"pith-pipeline@v1.4.1-daily-deepseek-or-medium","input_kind":null,"input_chars":null,"input_total_chars":null,"passes_missing":null,"published_standing":null,"published_confidence":null,"objection_audit":null,"run_record":null,"basis":{"kind":"not_recorded","source":null,"chars_given":null,"chars_total":null},"receipt":null,"falsifier":null,"supporting_citations":[],"lane_accuracy":{"status":"not yet measured","lane":{"model":"deepseek/deepseek-v4-flash","input_kind":null},"url":"https://pith.science/accuracy"},"review_version":1}