With the rise of medical foundation models and the growing availability of imaging data, scalable pretraining techniques offer a promising way to identify imaging biomarkers predictive of future disease risk. While current self-supervised methods for 3D medical imaging models capture local structural features like organ morphology, they fail to link pixel biomarkers with long-term health outcomes due to a missing context problem. Current approaches lack the temporal context necessary to identify biomarkers correlated with disease progression, as they rely on supervision derived only from images and concurrent text descriptions. To address this, we introduce time-to-event pretraining, a pretraining framework for 3D medical imaging models that leverages large-scale temporal supervision from paired, longitudinal electronic health records (EHRs). Using a dataset of 18,945 CT scans (4.2 million 2D images) and time-to-event distributions across thousands of EHR-derived tasks, our method improves outcome prediction, achieving an average AUROC increase of 23.7% and a 29.4% gain in Harrell’s C-index across 8 benchmark tasks. Importantly, these gains are achieved without sacrificing diagnostic classification performance. This study lays the foundation for integrating longitudinal EHR and 3D imaging data to advance clinical risk prediction.

Foundation Models (FMs) trained on Electronic Health Records (EHRs) have achieved state-of-the-art results on numerous clinical prediction tasks. However, prior EHR FMs typically have context windows of $<$1k tokens, which prevents them from modeling full patient EHRs which can exceed 10k's of events. For making clinical predictions, both model performance and robustness to the unique properties of EHR data are crucial. 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. Additionally, we measure robustness to three unique, previously underexplored properties of EHR data: (1) the prevalence of ``copy-forwarded" diagnoses which create artificial token repetition in 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 (e.g., a 14% higher Brier loss between the least and most irregular patients), 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 on how to identify and quantify new challenges in modeling sequential data motivated by domains outside of natural language. We release all of our model checkpoints and code.

Health AI suffers from a systemic reproducibility crisis that irreparably hinders research across both academia and industry [4,5].One key tool poised to solve this crisis is the Medical Event Data Standard (MEDS), a comprehensive data format and open-source ecosystem designed to enhance reproducibility and interoperability of AI research using longitudinal Electronic Health Records (EHR) [6].Currently adopted by over 15 institutions globally, MEDS encompasses various open-source tools, published models, and data processing pipelines, enabling streamlined model development and robust benchmarking.In this tutorial, participants will gain key hands-on experience in working with the MEDS format to perform efficient, reproducible, state-of-the-art AI research over real health data.Participants will transform data into the MEDS format, preprocess data, build predictive models, and contribute to the decentralized MEDS-DEV benchmarking platform.Interactive exercises using Jupyter notebooks will provide hands-on experience and practical skills for reproducible health AI research.Attendees will leave equipped

The ability of large language models (LLMs) to follow natural language instructions with human-level fluency suggests many opportunities in healthcare to reduce administrative burden and improve quality of care. However, evaluating LLMs on realistic text generation tasks for healthcare remains challenging. Existing question answering datasets for electronic health record (EHR) data fail to capture the complexity of information needs and documentation burdens experienced by clinicians. To address these challenges, we introduce MedAlign, a benchmark dataset of 983 natural language instructions for EHR data. MedAlign is curated by 15 clinicians (7 specialities), includes clinician-written reference responses for 303 instructions, and provides 276 longitudinal EHRs for grounding instruction-response pairs. We used MedAlign to evaluate 6 general domain LLMs, having clinicians rank the accuracy and quality of each LLM response. We found high error rates, ranging from 35% (GPT-4) to 68% (MPT-7B-Instruct), and 8.3% drop in accuracy moving from 32k to 2k context lengths for GPT-4. Finally, we report correlations between clinician rankings and automated natural language generation metrics as a way to rank LLMs without human review. MedAlign is provided under a research data use agreement to enable LLM evaluations on tasks aligned with clinician needs and preferences.

We present a self-supervised, time-to-event (TTE) foundation model called MOTOR (Many Outcome Time Oriented Representations) which is pretrained on timestamped sequences of events in electronic health records (EHR) and health insurance claims. TTE models are used for estimating the probability distribution of the time until a specific event occurs, which is an important task in medical settings. TTE models provide many advantages over classification using fixed time horizons, including naturally handling censored observations, but are challenging to train with limited labeled data. MOTOR addresses this challenge by pretraining on up to 55M patient records (9B clinical events). We evaluate MOTOR's transfer learning performance on 19 tasks, across 3 patient databases (a private EHR system, MIMIC-IV, and Merative claims data). Task-specific models adapted from MOTOR improve time-dependent C statistics by 4.6\% over state-of-the-art, improve label efficiency by up to 95\%, and are more robust to temporal distributional shifts. We further evaluate cross-site portability by adapting our MOTOR foundation model for six prediction tasks on the MIMIC-IV dataset, where it outperforms all baselines. MOTOR is the first foundation model for medical TTE predictions and we release a 143M parameter pretrained model for research use at https://huggingface.co/StanfordShahLab/motor-t-base.

Synthesizing information from various data sources plays a crucial role in the practice of modern medicine. Current applications of artificial intelligence in medicine often focus on single-modality data due to a lack of publicly available, multimodal medical datasets. To address this limitation, we introduce INSPECT, which contains de-identified longitudinal records from a large cohort of pulmonary embolism (PE) patients, along with ground truth labels for multiple outcomes. INSPECT contains data from 19,402 patients, including CT images, sections of radiology reports, and structured electronic health record (EHR) data (including demographics, diagnoses, procedures, and vitals). Using our provided dataset, we develop and release a benchmark for evaluating several baseline modeling approaches on a variety of important PE related tasks. We evaluate image-only, EHR-only, and fused models. Trained models and the de-identified dataset are made available for non-commercial use under a data use agreement. To the best our knowledge, INSPECT is the largest multimodal dataset for enabling reproducible research on strategies for integrating 3D medical imaging and EHR data.

While the general machine learning (ML) community has benefited from public datasets, tasks, and models, the progress of ML in healthcare has been hampered by a lack of such shared assets. The success of foundation models creates new challenges for healthcare ML by requiring access to shared pretrained models to validate performance benefits. We help address these challenges through three contributions. First, we publish a new dataset, EHRSHOT, which contains de-identified structured data from the electronic health records (EHRs) of 6,739 patients from Stanford Medicine. Unlike MIMIC-III/IV and other popular EHR datasets, EHRSHOT is longitudinal and not restricted to ICU/ED patients. Second, we publish the weights of CLMBR-T-base, a 141M parameter clinical foundation model pretrained on the structured EHR data of 2.57M patients. We are one of the first to fully release such a model for coded EHR data; in contrast, most prior models released for clinical data (e.g. GatorTron, ClinicalBERT) only work with unstructured text and cannot process the rich, structured data within an EHR. We provide an end-to-end pipeline for the community to validate and build upon its performance. Third, we define 15 few-shot clinical prediction tasks, enabling evaluation of foundation models on benefits such as sample efficiency and task adaptation. Our model and dataset are available via a research data use agreement from here: https://stanfordaimi.azurewebsites.net/. Code to reproduce our results is available here: https://github.com/som-shahlab/ehrshot-benchmark.

OBJECTIVE: Development of electronic health records (EHR)-based machine learning models for pediatric inpatients is challenged by limited training data. Self-supervised learning using adult data may be a promising approach to creating robust pediatric prediction models. The primary objective was to determine whether a self-supervised model trained in adult inpatients was noninferior to logistic regression models trained in pediatric inpatients, for pediatric inpatient clinical prediction tasks. MATERIALS AND METHODS: This retrospective cohort study used EHR data and included patients with at least one admission to an inpatient unit. One admission per patient was randomly selected. Adult inpatients were 18 years or older while pediatric inpatients were more than 28 days and less than 18 years. Admissions were temporally split into training (January 1, 2008 to December 31, 2019), validation (January 1, 2020 to December 31, 2020), and test (January 1, 2021 to August 1, 2022) sets. Primary comparison was a self-supervised model trained in adult inpatients versus count-based logistic regression models trained in pediatric inpatients. Primary outcome was mean area-under-the-receiver-operating-characteristic-curve (AUROC) for 11 distinct clinical outcomes. Models were evaluated in pediatric inpatients. RESULTS: When evaluated in pediatric inpatients, mean AUROC of self-supervised model trained in adult inpatients (0.902) was noninferior to count-based logistic regression models trained in pediatric inpatients (0.868) (mean difference = 0.034, 95% CI=0.014-0.057; P < .001 for noninferiority and P = .006 for superiority). CONCLUSIONS: Self-supervised learning in adult inpatients was noninferior to logistic regression models trained in pediatric inpatients. This finding suggests transferability of self-supervised models trained in adult patients to pediatric patients, without requiring costly model retraining.

OBJECTIVE: There are over 363 customized risk models of the American College of Cardiology and the American Heart Association (ACC/AHA) pooled cohort equations (PCE) in the literature, but their gains in clinical utility are rarely evaluated. We build new risk models for patients with specific comorbidities and geographic locations and evaluate whether performance improvements translate to gains in clinical utility. MATERIALS AND METHODS: We retrain a baseline PCE using the ACC/AHA PCE variables and revise it to incorporate subject-level information of geographic location and 2 comorbidity conditions. We apply fixed effects, random effects, and extreme gradient boosting (XGB) models to handle the correlation and heterogeneity induced by locations. Models are trained using 2 464 522 claims records from Optum©'s Clinformatics® Data Mart and validated in the hold-out set (N = 1 056 224). We evaluate models' performance overall and across subgroups defined by the presence or absence of chronic kidney disease (CKD) or rheumatoid arthritis (RA) and geographic locations. We evaluate models' expected utility using net benefit and models' statistical properties using several discrimination and calibration metrics. RESULTS: The revised fixed effects and XGB models yielded improved discrimination, compared to baseline PCE, overall and in all comorbidity subgroups. XGB improved calibration for the subgroups with CKD or RA. However, the gains in net benefit are negligible, especially under low exchange rates. CONCLUSIONS: Common approaches to revising risk calculators incorporating extra information or applying flexible models may enhance statistical performance; however, such improvement does not necessarily translate to higher clinical utility. Thus, we recommend future works to quantify the consequences of using risk calculators to guide clinical decisions.

OBJECTIVE: Ulcerative colitis (UC) is a chronic inflammatory disorder with limited effective therapeutic options for long-term treatment and disease maintenance. We hypothesized that a multi-cohort analysis of independent cohorts representing real-world heterogeneity of UC would identify a robust transcriptomic signature to improve identification of FDA-approved drugs that can be repurposed to treat patients with UC. MATERIALS AND METHODS: We performed a multi-cohort analysis of 272 colon biopsy transcriptome samples across 11 publicly available datasets to identify a robust UC disease gene signature. We compared the gene signature to in vitro transcriptomic profiles induced by 781 FDA-approved drugs to identify potential drug targets. We used a retrospective cohort study design modeled after a target trial to evaluate the protective effect of predicted drugs on colectomy risk in patients with UC from the Stanford Research Repository (STARR) database and Optum Clinformatics DataMart. RESULTS: Atorvastatin treatment had the highest inverse-correlation with the UC gene signature among non-oncolytic FDA-approved therapies. In both STARR (n = 827) and Optum (n = 7821), atorvastatin intake was significantly associated with a decreased risk of colectomy, a marker of treatment-refractory disease, compared to patients prescribed a comparator drug (STARR: HR = 0.47, P = .03; Optum: HR = 0.66, P = .03), irrespective of age and length of atorvastatin treatment. DISCUSSION & CONCLUSION: These findings suggest that atorvastatin may serve as a novel therapeutic option for ameliorating disease in patients with UC. Importantly, we provide a systematic framework for integrating publicly available heterogeneous molecular data with clinical data at a large scale to repurpose existing FDA-approved drugs for a wide range of human diseases.

Using a risk stratification model to guide clinical practice often requires the choice of a cutoff-called the decision threshold-on the model's output to trigger a subsequent action such as an electronic alert. Choosing this cutoff is not always straightforward. We propose a flexible approach that leverages the collective information in treatment decisions made in real life to learn reference decision thresholds from physician practice. Using the example of prescribing a statin for primary prevention of cardiovascular disease based on 10-year risk calculated by the 2013 pooled cohort equations, we demonstrate the feasibility of using real-world data to learn the implicit decision threshold that reflects existing physician behavior. Learning a decision threshold in this manner allows for evaluation of a proposed operating point against the threshold reflective of the community standard of care. Furthermore, this approach can be used to monitor and audit model-guided clinical decision making following model deployment.