EveryQuery: A Promptable Foundation Model for Clinical Prediction Tasks over Electronic Health Records

Payal Chandak; Gregory Kondas; Liat Antwarg Friedman; Isaac Kohane; Matthew McDermott

cs.AIMar 9, 2026

EveryQuery: A Promptable Foundation Model for Clinical Prediction Tasks over Electronic Health Records

Authors: Payal Chandak, Gregory Kondas, Liat Antwarg Friedman, Isaac Kohane, Matthew McDermott

Organizations: Harvard-MIT HST · Columbia University · Harvard Medical School

Abstract

Autoregressive foundation models for electronic health records can make predictions for diverse clinical tasks without finetuning. These methods work by generating possible "synthetic futures" for patients, and then inferring downstream predictions over these simulated trajectories. Despite their strong capabilities, these methods have several flaws. (1) Inference is extremely computationally expensive, as each prediction requires simulating many trajectories, each with many observations. (2) Their performance is noisy due to the variance inherent to simulation, which in particular reduces efficacy on rare events, which are often of high importance clinically. (3) They are not promptable, as their only input is the patient's medical history, requiring indirect aggregation at inference time. We introduce EveryQuery, a promptable foundation model for structured EHR data. Building on the insight that clinical prediction tasks can be written in a structured query language, EveryQuery takes a query as a prompt alongside the patient's history and estimates the outcome directly. This allows EveryQuery to make predictions across diverse clinical tasks, such as classification and survival modeling, without simulation or finetuning. Across three EHR datasets, EveryQuery outperforms a competitive autoregressive baseline on clinically relevant classification and time-to-event tasks, with mean AUROC gains of 14.3% and 12.7% on MIMIC-IV and a large academic medical center and comparable performance on the smaller NWICU dataset. Its advantage is largest for rare outcomes, and it requires 580x less inference compute.

Figures & tables

Figure 1: Overview of EveryQuery. Both models answer a query

\mathbf{q}

during inference (§ 3.1 ), estimating whether a code occurs before a given time, for a patient history

\mathbf{x}

. (a) An autoregressive model generates

K

future trajectories of up to

T

events each, and estimates the probability as the fraction of trajectories in which the code occurs. This yields quantized, high-variance estimates. (b) EveryQuery takes

\mathbf{q}

as input alongside

\mathbf{x}

and predicts

p(y=1\mid\mathbf{x},\mathbf{q})

directly.

Task	Conditional Clauses $(q_{i},a_{i})$	Target $q_{n}$
In-hospital mortality	–	(death, (0, discharge))
30-day readmission	–	(admission, (discharge, 30d))
Post-discharge mortality	((death, (0, discharge)), 0)	(death, (discharge, 90d))

Table 1: Example prompts in the query language.

Figure 2: EveryQuery outperforms the autoregressive baseline across clinical prediction tasks. Each point is a task, comparing EveryQuery with the AR baseline on AUROC for classification tasks (a) and Harrell’s C for time-to-event tasks (b). Points above the diagonal favor EveryQuery.

Figure 3: EveryQuery’s advantage over the autoregressive baseline is largest for rare events. Each row is a category of clinical prediction tasks, and each dot shows the mean

\Delta

AUROC for the tasks in that category grouped by prevalence. ICU tasks (a) are evaluated on MIMIC-IV and NWICU; and longitudinal care tasks (b) on AMC. EveryQuery’s gains grow as outcomes become rarer.

Appendix figures & tables12 assets

Supplementary material from the paper’s appendix.

Appendix

Dataset	Train	Val	Test	Total Events	Vocab
	Subjects
MIMIC	200,773	25,059	15,059	779,733,629	11,476
AMC	1,651,030	291,538	27,019	2,250,292,868	21,289
NWICU	20,723	2,590	772	54,785,364	2,159

Appendix

Table 2: Dataset statistics per split after preprocessing.

Optimization
Hyperparameter	Value
Optimizer	AdamW
Learning rate	$5\times 10^{-4}$
Betas	$(0.9,0.98)$
Epsilon	$10^{-8}$
Weight decay	0.05

Appendix

Table 3: EveryQuery training and architecture hyperparameters.

Task	Prev.	AUROC
		EveryQuery	Autoregressive
Visit/OP within 365d \| no TIMELINE//END within 365d, no MEDS_DEATH within 365d	0.730	0.543	0.720
Visit/ER within 365d \| no TIMELINE//END within 365d, no MEDS_DEATH within 365d	0.114	0.728	0.821
MEDS_DEATH within 1825d	0.028	0.887	0.838
Visit/ER within 30d \| no TIMELINE//END within 30d, no MEDS_DEATH within 30d	0.025	0.662	0.762
MEDS_DEATH within 365d	0.010	0.921	0.855

Appendix

Table 4: AMC outpatient visit, general cohort (

n=5

tasks).

Task	Prev.	AUROC
		EveryQuery	Autoregressive
LOINC/2823-3//ANY within 90d \| no TIMELINE//END within 90d, no MEDS_DEATH within 90d	0.623	0.799	0.827
LOINC/2823-3//UCUM/mmol/L//value_[5.0,inf) within 365d \| no TIMELINE//END within 365d, no MEDS_DEATH within 365d	0.354	0.769	0.757
ICD10CM/I48.91 within 1095d \| no TIMELINE//END within 1095d	0.284	0.828	0.799
Visit/IP within 365d \| no TIMELINE//END within 365d, no MEDS_DEATH within 365d, no RxNorm/1373473 within 30d	0.222	0.741	0.697
Visit/IP within 365d \| no TIMELINE//END within 365d, no MEDS_DEATH within 365d, no RxNorm/1545658 within 30d	0.222	0.741	0.697

Appendix

Table 5: AMC outpatient visit, heart-failure codes (

n=36

tasks).

Task	Prev.	AUROC
		EveryQuery	Autoregressive
LOINC/4548-4//ANY within 180d \| no TIMELINE//END within 180d, no MEDS_DEATH within 180d	0.301	0.866	0.867
ICD10CM/I50.814 within 1095d \| no TIMELINE//END within 1095d	0.151	0.898	0.821
LOINC/2160-0//UCUM/mg/dL//value_[2.34,inf) within 730d \| no TIMELINE//END within 730d	0.137	0.930	0.841
MEDS_DEATH within 1825d	0.121	0.813	0.734
ICD10CM/E11.319 within 1095d \| no TIMELINE//END within 1095d	0.116	0.832	0.764

Appendix

Table 6: AMC outpatient visit, type 2 diabetes codes (

n=59

tasks).

Task	Prev.	AUROC
		EveryQuery	Autoregressive
ICU_DISCHARGE within 7d \| no TIMELINE//END within 7d, no MEDS_DEATH before ICU_DISCHARGE	0.882	0.782	0.710
ICU_DISCHARGE within 3d \| no TIMELINE//END within 3d, no MEDS_DEATH before ICU_DISCHARGE	0.712	0.796	0.629
ICU_DISCHARGE within 2d \| no TIMELINE//END within 2d, no MEDS_DEATH before ICU_DISCHARGE	0.599	0.798	0.595
ICU_DISCHARGE within 1d \| no TIMELINE//END within 1d, no MEDS_DEATH before ICU_DISCHARGE	0.390	0.798	0.564
MEDS_DEATH within 365d	0.293	0.831	0.727

Appendix

Table 7: MIMIC-IV ICU, 24h after admission (

n=38

tasks).

Task	Prev.	AUROC
		EveryQuery	Autoregressive
ICU_DISCHARGE within 7d \| no TIMELINE//END within 7d, no MEDS_DEATH before ICU_DISCHARGE	0.875	0.721	0.528
ICU_DISCHARGE within 3d \| no TIMELINE//END within 3d, no MEDS_DEATH before ICU_DISCHARGE	0.686	0.706	0.619
ICU_DISCHARGE within 2d \| no TIMELINE//END within 2d, no MEDS_DEATH before ICU_DISCHARGE	0.565	0.688	0.661
ICU_DISCHARGE within 1d \| no TIMELINE//END within 1d, no MEDS_DEATH before ICU_DISCHARGE	0.369	0.676	0.693
MEDS_DEATH within 365d	0.203	0.817	0.737

Appendix

Table 8: NWICU ICU, 24h after admission (

n=27

tasks).

Dataset	Target code
MIMIC-IV	MEDS_DEATH
	PROCEDURE//START//225792
	ICU_ADMISSION//Medical Intensive Care Unit (MICU)
	MEDICATION//START//Norepinephrine
	HOSPITAL_DISCHARGE//HOME
	INFUSION_START//221289//value_[0.35491893,inf)

Appendix

Table 9: Target codes for time-to-event evaluation. Codes are written as they appear in each dataset’s vocabulary.

Figure 4: Survival curves on MIMIC-IV. Each panel shows one target code (Table 9 ), comparing the Kaplan–Meier estimate on held-out patients (black, dashed) with the survival curves estimated by the autoregressive baseline (blue) and EveryQuery (orange) at each prediction horizon in days.

Figure 5: Survival curves on NWICU. Each panel shows one target code (Table 9 ), comparing the Kaplan–Meier estimate on held-out patients (black, dashed) with the survival curves estimated by the autoregressive baseline (blue) and EveryQuery (orange) at each prediction horizon in days.

Figure 6: Survival curves on AMC. Each panel shows one target code (Table 9 ), comparing the Kaplan–Meier estimate on held-out patients (black, dashed) with the survival curves estimated by the autoregressive baseline (blue) and EveryQuery (orange) at each prediction horizon in days.

Figure 7: On randomly sampled tasks, EveryQuery’s advantage over the autoregressive baseline grows as events become rarer. Each point is one randomly sampled task (§ 5.5 ), plotted by prevalence (log scale) against

\Delta

AUROC (EveryQuery minus autoregressive). Red lines show linear fits, and each panel reports the Spearman correlation between prevalence and

\Delta

AUROC.

Explore similar work

EHR-RAGp: Prototype-Guided Retrieval of Longitudinal Electronic Health Records for Clinical Prediction Models
May 12, 2026Saeed Shurrab, Mariam Al-Omari, Dana El Samad +1Long-Context Modeling Clinical Prediction
New York University · New York University Abu Dhabi
Pretraining EHR Foundation Models with Patient-Aware Sampling
Jul 24, 2026Joshua Placidi, Yuxuan Liu, Jinpei Han +2Longitudinal EHR Modeling Electronic Health Records
Dept. of Computing, Imperial College London, London, United Kingdom · Dept. of Bioengineering, Imperial College London, London, United Kingdom · UKRI Centres in AI for Health, United Kingdom +1
Sequence Composition in EHR Foundation Model Pretraining
Oct 12, 2026Joshua Placidi, Inigo Stibbe, Alfred J. Balston +2Electronic Health Records Longitudinal EHR Modeling
Department of Computing, Imperial College London

May 12, 2026J/K move · Enter open · S save

EHR-RAGp: Prototype-Guided Retrieval of Longitudinal Electronic Health Records for Clinical Prediction Models

Saeed Shurrab, Mariam Al-Omari, Dana El Samad, Farah E. Shamout

New York University · New York University Abu Dhabi

Long-Context Modeling Clinical Prediction Longitudinal EHR Modeling

Open paper AskPDF arXiv

Electronic Health Records (EHR) contain rich longitudinal patient information and are widely used in predictive modeling applications. However, effectively leveraging historical data remains challenging due to long trajectories, heterogeneous events, temporal irregularity, and the varying relevance of past clinical context. Existing approaches often rely on fixed windows or uniform aggregation, which can obscure clinically important signals. In this work, we introduce EHR-RAGp, a retrieval-based framework that dynamically integrates the most relevant patient history consisting of diverse clinical event types. We propose a prototype-guided retrieval module that acts as an alignment mechanism and estimates the relevance of retrieved historical chunks with respect to a given prediction task, guiding the model towards the most informative context. Across multiple clinical prediction tasks and two benchmark datasets, EHR-RAGp consistently outperforms state-of- the-art EHR-based and transformer-based baselines. Furthermore, EHR-RAGp is model-agnostic, as integrating it with various backbone models yields substantial performance gains. Overall, EHR-RAGp establishes a novel direction for modeling long-range clinical context to improve downstream performance via retrieval.

Abstract

Explore similar work

EHR-RAGp: Prototype-Guided Retrieval of Longitudinal Electronic Health Records for Clinical Prediction Models

Pretraining EHR Foundation Models with Patient-Aware Sampling

Sequence Composition in EHR Foundation Model Pretraining