In the time series for health workshop, we will explore challenges when dealing with time series data to better understand and improve human health. Time series are highly diverse, spanning a variety of modalities including wearables, Electronic Health Record (EHR) data, medical time series (ECG, EEG, fMRI), and audio, amongst others. Submitted papers should discuss novel methods or perspectives, present preliminary results for promising future directions, or introduce resources, like datasets, that accelerate research in this area. All papers must clearly demonstrate or discuss their relevance to healthcare, and in particular, focus on challenges with health time series data. Potential topics can include, but are not limited to:
Unsupervised, semi-supervised, and supervised representation learning
Novel architecture or models for time series
Classification, regression, and forecasting
Bayesian models
Sequential decision making
Handling time series data challenges like missing values, noisy and irregular measurements, high-dimensionality, etc.
Multi-modal models including time series
Deployment and implementation challenges
Explainability, fairness, and privacy for time series models
Challenging applied problems (e.g., “dynamic treatment recommendation for sepsis from EHR time series”)
Where appropriate, we encourage authors to add discussions of any ethical considerations relevant to the presented work.
Authors are invited to submit short papers with up to 4 pages, but unlimited number of pages for references. Authors may use as many pages of appendices (after the bibliography) as they wish, but reviewers are not required to read the appendix. All accepted papers will be presented in person as posters and lightning talks. There are no formal proceedings generated from this workshop. Authors are encouraged to make their work publicly available through our online listing of presented work.
The reviewing process will be double-blind. Please submit anonymized versions of your paper that include no identifying information about any author identities or affiliations. Submitted papers must be new work that has not yet been published.
TS4H is collaborating with Machine Learning for Health, co-located at NeurIPS. If you would like your paper to be considered for their workshop as well, please follow their submission guidelines - this includes a submission deadline of September 1, 2022 and papers up to 4 pages, excluding references.
Submission format: Latex style files
Submission link: OpenReview
Submission Deadline: September 22nd September 30th, 2022 Anywhere on Earth (AoE)
Notifications: October 22nd, 2022
Workshop event: December 2nd, 2022, In-person in New Orleans, LA, USA
Authors will be asked to confirm that their submissions accord with the NeurIPS code of conduct.