Call for Papers

We invite contributions from both industry and academia to share their research and experience in using artificial intelligence and machine learning methods in pharmaceutical and healthcare research and development. PharML will be held at the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD) on 13th - 17th of September 2021 (virtually).

Submission Guidelines

We invite authors to submit their work in either one of the following two formats:

• Research abstracts: describe preliminary results and are meant to foster discussion of emerging topics. Maximum of 6 pages.

• Long papers: present mature work, published or unpublished. Maximum of 16 pages.

Additional guidelines

• All manuscripts will be peer-reviewed, double-blinded.

• Authors should commit to present their work at the workshop in case it is accepted for an oral presentation.

• Abstracts and papers should be in PDF format, following the Springer Lecture Notes in Computer Science style (see link for LaTeX template)

• Submissions should be done via the workshop EasyChair page.

Paper publication

• Only unpublished work or extended versions of the abstracts are eligible for publication in the workshop proceedings.

• The proceedings of the workshop will be published either by Springer as a Lecture Notes volume or by CEUR in their workshop proceedings series .

Topics of Interest

• Survival Machine Learning (thematic session 1)

  • Deep Learning and Survival Modelling

  • Random Forest-based Survival Modelling

  • Regularized Regression for Survival

  • Longitudinal Survival Modelling

• Causal Inference (thematic session 2)

  • Subgroup discovery and targeted learning.

  • Estimating treatment effect in randomized and/or observational studies.

  • Causal structure learning from real world data.

• Domain Adaptation and Domain Generalization (thematic session 3)

  • Unsupervised Domain Adaptation

  • Supervised/Semi-supervised Domain Adaptation

  • Domain Generalization

  • Generalizability between models for Real World Data and Randomized Control Trials

  • Generalizability across diseases and demographic groups

  • Other applications for better generalizability

• Federated Learning (thematic session 4)

  • Centralized Federated Learning

  • De-centralized Federated Learning

  • Differential privacy and encryption

• Other topics

  • Multimodal Machine Learning (e.g. combining genomics, pathology reports, clinical data)

  • Medical Imaging

  • Natural Language Processing for health records.

  • Medical decision support

  • Digital biomarker development

  • Machine Learning for Personalized Healthcare

  • Generative Chemistry and Machine Learning for Drug Discovery

  • Learning on Graphs: Generative models, modelling dynamic graphs, transfer learning in graphs, limitations of traditional node/edge/graph embeddings

Workshop Programme

The workshop will feature:

• Invited keynote speakers

  • From academia: Lee Cooper (Northwestern University) and Vince Calhoun (Georgia Tech)

  • From industry: David Ohlssen (Novartis) and Ryan Copping (Roche).

• Presentations of long papers and short abstracts.

The full programme will be posted on the workshop's website in due course.

Important dates

• Submission Deadline: July 2nd, 2021

• Notification: August 2nd, 2021

• Workshop date: Monday 13th of September or Friday 17th of September (tbd)

• Workshop format: Virtual (online) event