Call for Papers

Submissions are considered for two distinct tracks: the archival Proceedings track and the non-archival Findings track.

In response to the growing community, ML4H has transitioned from a NeurIPS-affiliated workshop into a standalone symposium. ML4H 2026 represents a continuation of prior ML4H events and will continue to be held in December directly before NeurIPS. ML4H 2026 will feature:

• Author, Reviewer and Career Mentorship Programs
• Best Paper Awards
• Top Reviewer Awards

If you are interested in being a reviewer, please reach out to us at ml4h@ahli.cc! We will be hosting a Reviewer Mentorship Program as well as Top Reviewer Awards.

---

Important Dates

All times are in AoE.

Aug 10	Submission site opens
Sep 10	Paper submission deadline (no separate abstract deadline)
Oct 5	Reviews available; author response period starts
Oct 12	Author response period ends
Oct 22	Decisions released
Oct 31	Early Career Travel Grant application deadline
Nov 7 (tentative)	Camera-ready deadline
Dec 6–7	In-person event

Quick Submission Instructions

Submission Site: https://openreview.net/group?id=ML4H/2026/Symposium

ML4H 2026 LaTeX template: Link will be provided soon.

Formatting and Anonymization: Submissions must be formatted using the ML4H 2026 LaTeX templates with proper anonymization. Gross violations of formatting guidelines, malformed, non-blinded, non-health-related, or grossly insufficient works may be desk rejected by the organizing committee without undergoing formal peer review.

Submission Form: All submissions will be managed through the OpenReview system. Authors are required to fill out a submission form on OpenReview that will be visible to reviewers. The form will indicate the submission track (Proceedings or Findings), which general area the submission should be considered under (Materials and Methods, Applications and Practice, or Impact and Society), and specific subject areas.

Required Information at Deadline: The paper submission deadline is September 10th 11:59 PM AoE. For this deadline, the title, author list, paper content, track, subject areas, and data modality should be submitted. Edits to these metadata will not be permitted past the paper submission deadline. Author lists cannot be changed after the submission deadline.

Data and Code: We encourage anonymized code and data submissions (if it can be made available with appropriate approval and guidelines) as supplemental materials during review. If you are not sharing code, you must explicitly state this in the paper. If your paper is accepted, we encourage public sharing of your code and/or data for the camera-ready version.

Ethics Board Approval: If your research requires IRB (or equivalent) approval or has been evaluated by your IRB as Not Human Subject Research, then for the camera-ready version you must provide relevant information. At the time of submission, to preserve anonymity, it suffices to include a statement that relevant ethics approval information will be provided if the paper is accepted. If your research does not require IRB approval, please explicitly state this and provide a justification in the paper.

---

Submission Tracks

ML4H 2026 will feature two main submission tracks. Accepted submissions to both tracks will be featured at the event’s poster session.

Submissions to the main tracks will undergo double-blind peer review, assessed based on their technical merit and contribution to the event. More details on how to write an excellent ML4H full paper or findings paper can be found here.

(A) Proceedings Track

Excellent ML4H Proceedings papers should be compelling, cohesive works with a high degree of technical sophistication as well as clear and high-impact relevance to health. Accepted proceedings papers will be published in the Proceedings for Machine Learning Research (PMLR). Past proceedings can be found here. Proceedings papers can be up to 8 pages at submission (excluding references and appendices). If your submission is accepted, you will be allowed 1 additional content page for the camera-ready version.

(B) Findings Track

An excellent findings paper is one that highlights new insights, valuable resources, or exciting preliminary directions that are broadly relevant to the community. The goal is to spark these insights at the event through interaction with other attendees — presenting new ideas or ways of thinking, leading to insightful discussion and feedback, dissemination of new valuable resources, or enabling new opportunities for collaboration. We especially solicit “non-traditional research artifacts” such as papers highlighting novel datasets, insightful negative results, exciting preliminary results that warrant rapid dissemination, reproducibility studies, and opinion pieces or critiques.

Findings papers can be up to 4 pages at submission (excluding references and appendices), though additional information not critical for understanding the work can be included in an appendix without penalty. Findings papers will not appear in the ML4H proceedings, but upon acceptance, we will make the accepted findings paper public on OpenReview. We also encourage (but do not require) authors to submit their findings as de-anonymized preprints (no page limit) to arXiv and mention ML4H in the comments.

Track Switching

Proceedings track submissions that are not accepted will automatically be considered for the Findings track. Findings track submissions cannot be considered for the Proceedings track. Decisions for both tracks will be released simultaneously.

Dual Submission Policy

Proceedings Track: Papers submitted to the ML4H Proceedings track cannot be already published in or simultaneously under review at any other archival venue. Similarly, papers accepted to and published in the ML4H Proceedings may not be published again later at any other archival venue.

Findings Track: Authors of accepted findings papers retain full copyright of their work, and acceptance of such a submission does not preclude publication of the same material in another archival venue (e.g. journal or conference). Findings submissions that are under review or have been recently published in a conference or journal are allowed; if this is the case, authors should clearly state any overlapping published or submitted work at the time of submission (in a confidential comment), and must ensure they are not violating any other venue’s dual submission policies.

FAQ about NeurIPS 2026 submissions:

• Papers under review at NeurIPS 2026 (Main, E&D, or Position Paper tracks) are not allowed to simultaneously submit to ML4H 2026 Proceedings track unless they are withdrawn from NeurIPS first. However, they could be submitted to ML4H 2026 Findings track.
• Papers submitted to NeurIPS 2026 workshops are allowed to simultaneously submit to ML4H 2026 (either track) if the workshop is non-archival and does not publish workshop proceedings.

Reciprocal Reviewing Requirement

To support a high-quality and equitable review process, AHLI is introducing a new author reviewing policy based on submission volume.

Every submission must include at least one author registered to review a minimum of three (3) papers. A qualified reviewer will have at least one prior archival publication at a comparable peer-reviewed venue (for example, a ML for health conference, or a health-focused paper at an ML venue).

If none of the authors meet this qualification, please reach out to the ML4H organizing team and the submission will be exempt from this requirement after evaluation. We welcome and encourage submissions from first-time contributors at ML4H. Papers co-authored by Area Chairs, Senior Area Chairs, or ML4H 2026 organizers are exempt from this requirement.

Authors of each submission must nominate at least one reciprocal reviewer at the time of submission. If an author is the nominated reciprocal reviewer for several papers, their reviewing load may increase accordingly.

Submission Areas

Submitted papers should describe innovative machine learning research focused on relevant problems in health-related disciplines. Past works have spanned data integration, temporal models, deep learning, semi-supervised learning, reinforcement learning, transfer learning, few/zero shot learning, learning from missing or biased data, learning from non-stationary data, causality, model biases, model evaluation, model criticism, model interpretability, model deployment, human-computer interaction, privacy/security, and many more topics. Submissions should be made to one of the following three general areas:

Area 1: Models and Methods — Algorithms, Inference, and Estimation

Advances in machine learning are critical for a better understanding of health. This area seeks technical contributions in modeling, inference, and estimation in health-focused or health-inspired settings. We welcome submissions that develop novel methods and algorithms, introduce relevant machine learning tasks, identify challenges with prevalent approaches, or learn from multiple sources of data (e.g. non-clinical and clinical data).

Our focus on health is broadly construed, including clinical healthcare, public health, and population health. While submissions should be primarily motivated by problems relevant to health, the contributions themselves are not required to be directly applied to real health data. For example, authors may use synthetic datasets to demonstrate properties of their proposed algorithms.

We welcome submissions from many perspectives, including but not limited to supervised learning, unsupervised learning, reinforcement learning, causal inference, representation learning, survival analysis, domain adaptation or generalization, interpretability, robustness, and algorithmic fairness. All kinds of health-relevant data types are in scope, including tabular health records, time series, text, images, videos, knowledge graphs, and more. We welcome all kinds of methodologies, from deep learning to probabilistic modeling to rigorous theory and beyond.

Example Papers

• Kim et al. “HeartMAE: Advancing Cardiac MRI Analysis through Optical Flow Guided Masked Autoencoding.” ML4H 2024.
• Khanna et al. “Learning Generalized Medical Image Representations Through Image-Graph Contrastive Pretraining.” ML4H 2023.
• Moor et al. “Med-Flamingo: A Multimodal Medical Few-Shot Learner.” ML4H 2023.
• Wang et al. “Interpretable Mechanistic Representations for Meal-Level Glycemic Control in the Wild.” ML4H 2023.
• Tang et al. “Modeling Multivariate Biosignals With Graph Neural Networks and Structured State Space Models.” CHIL 2023.
• Mao et al. “Towards Cross-Modal Causal Structure and Representation Learning.” ML4H 2022.
• Shalit et al. “Estimating individual treatment effect: generalization bounds and algorithms.” ICML 2017.

Area 2: Applications and Practice — Investigation, Evaluation, Interpretation, and Deployment

The goal of this area is to highlight works applying robust methods, models, or practices to identify, characterize, audit, evaluate, or benchmark ML approaches to healthcare problems. Additionally, we welcome unique deployments and datasets used to empirically evaluate these systems. Whereas Area 1 focuses on algorithmic novelty, submit your work here if the contribution is describing an emerging or established innovative application of ML in healthcare. Areas of interest include but are not limited to:

• Datasets and simulation frameworks for addressing gaps in ML healthcare applications
• Tools and platforms that facilitate integration of AI algorithms and deployment for healthcare applications
• Innovative ML-based approaches to solving practical problems grounded in a healthcare application
• Surveys, benchmarks, evaluations and best practices of using ML in healthcare
• Emerging applications of AI in healthcare

Introducing a new method is not prohibited for this area, but the focus should be on how the proposed ideas contribute to addressing a practical limitation (e.g., robustness, computational scalability, improved performance). We encourage submissions in both traditional clinical areas (e.g., EHR, medical image analysis) and emerging fields (e.g., remote and telehealth medicine, integration of omics).

Example Papers

• Gupta et al. “Multi-Modal Self-Supervised Learning for Surgical Feedback Effectiveness Assessment.” ML4H 2024.
• Goel et al. “LLMs Accelerate Annotation for Medical Information Extraction.” ML4H 2023.
• Gröger et al. “Towards Reliable Dermatology Evaluation Benchmarks.” ML4H 2023.
• Kocielnik et al. “Deep Multimodal Fusion for Surgical Feedback Classification.” ML4H 2023.
• Nguyen et al. “Pragmatic Radiology Report Generation.” ML4H 2023.
• Zhou et al. “Evaluating Model Performance in Medical Datasets Over Time.” CHIL 2023.
• Kinyanjui et al. “An Alzheimer’s disease simulator for benchmarking observational estimators of causal effects.” CHIL 2022.

Area 3: Impact and Society — Policy, Public Health, Social Outcomes, and Economics

Algorithms do not exist in a vacuum: instead, they often explicitly aim for important social outcomes. This area considers issues at the intersection of algorithms and the societies they seek to impact, specifically for health. Submissions could include methodological contributions such as algorithmic development and performance evaluation for policy and public health applications, large-scale or challenging data collection, combining clinical and non-clinical data, as well as detecting and measuring bias. Submissions could also include impact-oriented research such as determining how algorithmic systems for health may introduce, exacerbate, or reduce inequities and inequalities, discrimination, and unjust outcomes, as well as evaluating the economic implications of these systems. We invite submissions tackling the responsible design of AI applications for healthcare and public health. System design for the implementation of such applications at scale is also welcome, which often requires balancing various tradeoffs in decision-making. Submissions related to understanding barriers to the deployment and adoption of algorithmic systems for societal-level health applications are also of interest. In addressing these problems, insights from social sciences, law, clinical medicine, and the humanities can be crucial.

Example Papers

• Guerra-Adames et al. “Uncovering Judgment Biases in Emergency Triage: A Public Health Approach Based on Large Language Models.” ML4H 2024.
• Afzal et al. “Towards Equitable Kidney Tumor Segmentation: Bias Evaluation and Mitigation.” ML4H 2023.
• Khan et al. “How Fair Are Medical Imaging Foundation Models?” ML4H 2023.
• Merrill et al. “Homekit2020: A Benchmark for Time Series Classification on a Large Mobile Sensing Dataset with Laboratory Tested Ground Truth of Influenza Infections.” CHIL 2023.
• Cheng et al. “Meta-Analysis of Individualized Treatment Rules via Sign-Coherency.” ML4H 2022.
• Gupta et al. “An Extensive Data Processing Pipeline for MIMIC-IV.” ML4H 2022.
• Lopez-Martinez et al. “Instability in Clinical Risk Stratification Models Using Deep Learning.” ML4H 2022.

---

Author Response Period

Initial reviews will be released on October 5th. From October 5th to October 12th, 11:59 PM AoE, authors can submit responses to the reviews. Author responses may address any aspect of the reviews, including by adding specific types of new experimental results as requested by the reviewers, e.g. missing baselines. No conceptual changes to the original formulation are allowed beyond clarifications. After the author response period, the reviewers and meta-reviewer will discuss and reach a final decision for the papers. We reserve the right to solicit additional reviews after the author response period in the rare case that there are not sufficient high quality reviews to make a final decision.

Reviewer Discussion Period

During the reviewer discussion period, reviewers and meta-reviewers will discuss the paper, their reviews, and the author response. This process aims at seeking a consensus between reviewers and meta-reviewers. We ask reviewers to change their initially submitted review scores and recommendations during the discussion period, if applicable, and state this in the discussion along with justification. Discussions will take place within OpenReview by using the comment function in each respective submission and should remain double-blind.

In general, these discussions will be between reviewers and meta-reviewers only. However, when further clarifications from the authors are necessary, reviewers may reach out to authors through OpenReview comments. It is only in response to such direct questions that authors should add comments beyond their author response, and said comments should be limited to directly answering the asked question. The reviewer discussion period formally ends on October 17 11:59 PM AoE, but discussions may be finalized earlier.

Authorship Policy

To maintain the integrity and transparency of the submission process, the following authorship rules will be strictly enforced:

• No authors may be added after the submission deadline. This includes adding new authors to any version of the paper during the review, camera-ready, or archival preparation stages.
• Reordering of authors is permitted for accepted papers, provided that all listed authors agree to the change.
• Removal of authors after submission is only allowed with written permission from all authors, including the author being removed. Requests must be submitted to the program chairs and include a clear justification.

---

Policy on the Use of Large Language Models

We welcome authors to use any tool that is suitable for preparing high-quality papers and research. It is crucial to meet two primary expectations. Firstly, ensure methodological clarity to maintain scientific rigor and transparency. Detail the use of Large Language Models (LLMs) within the experimental setup (or equivalent) if they are a significant or innovative part of the approach. Note: standard editing tools like spell checkers or grammar suggestions do not require documentation. Secondly, authors bear full responsibility for all paper content, including text, figures, and references. While any tool can be used for preparation and writing, guaranteeing the accuracy and originality of all content is paramount.

All authors are fully responsible for understanding the pros and cons of any tools used in publications, especially regarding data retention and privacy. Be aware that some tools may use input for model training. High-level instructions can cause errors in plots, potentially harming scientific integrity. Authors must verify tools are used responsibly.

ML4H may conduct investigations regarding adherence to the Code of Conduct at any point, even after paper acceptance, publication, or the conference itself. In the event of a violation, ML4H retains the right to retract a paper’s publication. Violations can include, but are not limited to, scientifically unsound content, such as utilizing references produced by an LLM without verifying their accuracy, existence, or suitability within the manuscript’s context.

Data Use Policy

All AHLI-organized events, including ML4H 2026, are subject to AHLI’s Data Use Policy, which governs how submission and review data may be used for operational purposes.

Registration Requirement

To promote community interaction, at least one presenting author of accepted works must register for the event. Registration details are forthcoming.

Contact Us

Please direct questions to ml4h@ahli.cc and follow us on Twitter at @symposiumml4h.