Papers › Context Clues: Evaluating Long Context Models for Clinical Prediction Tasks on EHRs

Context Clues: Evaluating Long Context Models for Clinical Prediction Tasks on EHRs

9 Dec 2024arXiv:2412.16178archive 2025-07-28

Michael Wornow, Suhana Bedi, Miguel Angel Fuentes Hernandez, Ethan Steinberg, Jason Alan Fries, Christopher Re, Sanmi Koyejo, Nigam H. Shah

Foundation Models (FMs) trained on Electronic Health Records (EHRs) have achieved state-of-the-art results on numerous clinical prediction tasks. However, most existing EHR FMs have context windows of <1k tokens. This prevents them from modeling full patient EHRs which can exceed 10k's of events. Recent advancements in subquadratic long-context architectures (e.g., Mamba) offer a promising solution. However, their application to EHR data has not been well-studied. We address this gap by presenting the first systematic evaluation of the effect of context length on modeling EHR data. We find that longer context models improve predictive performance -- our Mamba-based model surpasses the prior state-of-the-art on 9/14 tasks on the EHRSHOT prediction benchmark. For clinical applications, however, model performance alone is insufficient -- robustness to the unique properties of EHR is crucial. Thus, we also evaluate models across three previously underexplored properties of EHR data: (1) the prevalence of "copy-forwarded" diagnoses which creates artificial repetition of tokens within EHR sequences; (2) the irregular time intervals between EHR events which can lead to a wide range of timespans within a context window; and (3) the natural increase in disease complexity over time which makes later tokens in the EHR harder to predict than earlier ones. Stratifying our EHRSHOT results, we find that higher levels of each property correlate negatively with model performance, but that longer context models are more robust to more extreme levels of these properties. Our work highlights the potential for using long-context architectures to model EHR data, and offers a case study for identifying new challenges in modeling sequential data motivated by domains outside of natural language. We release our models and code at: https://github.com/som-shahlab/long_context_clues

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 13 code samples harvested from 1 repository linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 13 samples from 1 repository, 11 ran (11 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

som-shahlab/long_context_clues officialmentioned in papermentioned on GitHubjaxApache-2.0Syntology: 13 samples, 11 ran (0 instrument-failed) · 2 unverified report
reAIM-Lab/ehr_foundation_model_benchmark mentioned on GitHubSyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

13 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

11ran
2unverified

Licence: 0 of the 13 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from som-shahlab/long_context_clues. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

som-shahlab/long_context_clues official repository 13 samples, 11 ran (0 instrument-failed) · 2 unverified
apply_rotary_pos_emb in 393 papers
census: 14 implementations from 15 papers, 8 distinct outputs across 7 buckets, one shared input per bucket
hf_ehr/models/gpt.py ran Apache-2.0 (permissive) · f9e894cf5a449ee8 · report fixture: signature x:Tensor/3/float, sincos:tuple/1/Tensor · returned Tensor · level recorded 2026-09-24
calculate_flops_per_token hf_ehr/models/base.py ran Apache-2.0 (permissive) · 21a3f67d0b51467a · report fixture: signature model:callable/0/?, vocab_size:int/0/int · returned int · level recorded 2026-09-24
convert_lab_value_to_token_from_quantiles hf_ehr/utils.py ran Apache-2.0 (permissive) · aa28b86e19662530 · report fixture: signature code:str/0/str, unit:str/0/str, value:float/0/float, quantiles:list/1/float, is_tokenize_out_of_range:bool/0/bool · returned str · level recorded 2026-09-24
convert_lab_value_to_token_from_ranges hf_ehr/utils.py ran Apache-2.0 (permissive) · 4f65e9aa2f2807bc · report fixture: signature code:str/0/str, unit:str/0/str, value:float/0/float, ranges:list/1/tuple, is_tokenize_out_of_range:bool/0/bool · returned str · level recorded 2026-09-24
fixed_pos_embedding in 16 papers hf_ehr/models/gpt.py ran Apache-2.0 (permissive) · 5bef41387946c6d0 · report fixture: signature ages:Tensor/1/float, dim:int/0/int, dtype:dtype/0/? · returned tuple · level recorded 2026-09-24
get_ckpt_name hf_ehr/eval/ehrshot.py ran fingerprinted Apache-2.0 (permissive) · de4c6427b0f8e92f · report fixture: signature path_to_ckpt:str/0/str · returned str · level recorded 2026-09-24
get_rel_path hf_ehr/utils.py ran Apache-2.0 (permissive) · 45234ce476272614 · report fixture: returned str · level recorded 2026-09-24
hyena_forward hf_ehr/models/hyena.py ran Apache-2.0 (permissive) · bd7e025fc2906fa1 · report fixture: signature self:callable/0/?, input_ids:Tensor/2/int, inputs_embeds:NoneType/0/?, labels:Tensor/2/int, output_hidden_states:bool/0/bool, return_dict:bool/0/bool, pad_token_id:NoneType/0/? · returned CausalLMOutput · level recorded 2026-09-24
load_tokenizer_config_from_path hf_ehr/config.py ran Apache-2.0 (permissive) · a83875c130d6fc07 · report fixture: signature path_to_tokenizer_config:str/0/str, is_return_metadata:bool/0/bool · returned list · level recorded 2026-09-24
rewrite_paths_for_carina_from_config hf_ehr/config.py ran Apache-2.0 (permissive) · ffe7a6c2e6531674 · report fixture: signature config:DictConfig/0/? · returned DictConfig · level recorded 2026-09-24
rotate_every_two_v2 hf_ehr/models/gpt.py ran fingerprinted Apache-2.0 (permissive) · 0cd434a489251043 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-25
compute_feature_matrix hf_ehr/eval/ehrshot.py unverified Apache-2.0 (permissive) · 01d6a16e787ea3e1 · report
load_tokenizer_config_and_metadata_from_path hf_ehr/config.py unverified Apache-2.0 (permissive) · e35d31a309d54e00 · report

Tasks

Mamba

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections