ML4H 2019 invites submissions describing innovative machine learning research focused on relevant problems in health and biomedicine. For the first time, ML4H 2019 will accept papers for a formal proceedings as well as accepting traditional, non-archival extended abstract submissions. Authors are invited to submit works for either track provided the work fits within the purview of Machine Learning for Health.
- Monday Sept 9, 2019: Submission deadline at 11:59pm
- Monday Sept 30, 2019: Acceptance notification
- Thursday Nov 28, 2019: NeurIPS deadline to cancel registration (with full refund)
- Friday Nov 29, 2019: Final papers posted online (with permission)
- One day: Friday or Saturday, Dec 13-14, 2019: Workshop
We invite submissions from all areas of machine learning for health and biomedicine but we especially encourage submissions that focus on this year’s theme: What makes machine learning in medicine different?
Example focus areas include, but are not limited to, the following:
Data and Labels are Noisy and/or Missing
Healthcare data suffers from very high rates of noise and missingness, both in terms of input data as well as in terms of labels. Therefore, methods such as noise-robust models, data imputation, semi-supervised learning, distant/weak supervision, and clinician in the loop learning, all have an important role to play in machine learning for healthcare.
Causality / Confounding
Causality is central to any interventional task within healthcare, and methods to learn causal structures from observational data or to account for additional confounding within data are critical in healthcare.
Do No Harm: Trust, Generalizability, Interpretability, & Reproducibility
Machine learning models in healthcare need to demonstrate robustness, pass a high bar of trust before deployment and be routinely validated. This places strong burdens on tests of generalizability (to assert the model will extend to novel patients), interpretability (to provide auxiliary arguments in favor of the models’ correctness), and reproducibility (to ensure the model can be trusted, audited, and debugged).
Deployment Challenges within Healthcare
Deploying a machine learning model in healthcare faces significant hurdles and requires additional socio-technical validation and control mechanisms. In addition, models models deployed in healthcare may face regulatory challenges.
Healthcare policy, new clinical knowledge or even the deployment of models to production can fundamentally change the process machine learning algorithms intend to model. For example, numerous examples have shown that when CMS increases the reimbursement for a particular diagnosis, the diagnosis is used in claims more frequently.
Fairness & Bias
Fairness concepts are important in healthcare, for example in ensuring all patients receive unbiased treatment, and especially difficult to respect, as protected subgroup information is often a valid causal link to clinical state.
Multi-modality, High-dimensionality, "p >> n"
Healthcare data is often highly multimodal, extremely high-dimensional, and can have many more features than samples (e.g., genomics). Each of these aspects requires specialized methodological innovation.
Healthcare data is extremely sensitive and is therefore protected by specialized laws such as HIPAA. A key goal of medical ML is therefore the development of algorithms that can verifiably preserve patient privacy with minimal tradeoffs in performance.
Researchers interested in contributing should upload anonymized papers in PDF format by Mon, Sept 9, 2019, 11:59 PM in the timezone of your choice. At the time of submission, authors will indicate whether they would like the submission to
1.) considered for inclusion in the official proceedings (up to 8 pages excluding references) or
2.) considered as a non-archival extended abstract for presentation at the workshop only (up to 4 pages excluding references). Additional pages containing only bibliographic references can be included without penalty.
A submission link and additional details regarding the two submission tracks will be provided on our website at least two weeks prior to the deadline: https://ml4health.github.io
Submissions should adhere to the NeurIPS conference paper format, via the NeurIPS LaTeX style file: https://nips.cc/Conferences/2019/PaperInformation/StyleFiles
Peer Review, Acceptance Criteria, & Registration/Attendance
All submissions will undergo double-blind peer review. It will be up to the authors to ensure the proper anonymization of their paper. Do not include any names or affiliations. Refer to your own past work in the third-person.
Accepted papers and extended abstracts will be chosen based on technical merit and suitability to the workshop's goals. All accepted works will be included in poster presentation sessions on the day of the workshop. Some accepted works will be invited to give short oral spotlight presentations at the workshop.
To promote community interaction, at least one presenting author should register for the workshop. Historically the main NeurIPS conference has sold out quickly, and this may extend to workshop registrations. If you plan to submit a paper, please register as soon as possible. Registration opens Sep. 6, 2019 (https://nips.cc/Register/view-registration), and registrations can be cancelled before November 28, 2019, 11:59 pacific time for a full refund (https://nips.cc/Help/CancellationPolicy). If you have already registered, confirm that you have a valid workshop registration.
Copyright for Accepted Papers
Authors of accepted extended abstracts (non-archival submissions) retain full copyright of their work, and acceptance of such a submission to NeurIPS ML4H 2019 does not preclude publication of the same material in another journal or conference.
Papers aimed for proceedings should follow the general NeurIPS dual submission policies. Extended abstract submissions that are under review or have been recently published in a conference or a journal are allowed for submission. Authors should clearly state any overlapping published or submitted work at the time of submission. Authors should ensure that they are not violating any other venue dual submission policies.
Please direct questions to: firstname.lastname@example.org