Pattern Recognition in Biomedical Data for Discovery

Motivation

“Biomedical data” refers to the increasingly large corpus of machine-mineable data encompassing two similar, yet pointedly distinct fields: biology and medicine. In recent years, experimental and technological advancements in these fields have resulted in an unprecedented diversity of molecular omics data and longitudinal health record data available for analysis. Moreover, entirely new data sources such as social networking data, wearable technologies and environmental measurements have emerged and are relevant indicators of phenomena observed across both biology and medicine. Creative and sophisticated integration of these datasets promises the opportunity to further biological knowledge and understanding of disease and ultimately to advance our ability to more holistically detect and treat disease and improve patient care. However, challenges stemming from limited data quality and standardization coupled with a dramatic increase in data size and required computational resources arise in pursuit of these goals. In this session, we are particularly interested in innovative approaches that utilize new or new combinations of biomedical data sources to address previously intractable questions. We will focus specifically on cutting-edge methods aimed at pattern discovery in biomedical data.

Mauna Kea Mauna Kea Mauna Kea

Session Topics

Topics within the scope of this session include:

Pattern discovery enabled by integration of multiple, distinct data modalities, including unlabeled data sources, such as:
  • Molecular omics data (e.g., sequencing, transcriptomics)
  • Medical imaging data
  • Natural language text (e.g., published articles, databases, clinical notes)
  • Longitudinal medical insurance claims records/li>
Addressing previously intractable questions by utilizing new data sources such as:
  • Annotated environmental data sources
  • Social networking data
  • Wearable technology
  • Patient-provided behavioral patterns
Identifying and overcoming inherent limits to biomedical data labels
  • Assigning confidence to discoveries where gold-standard truth assessments (i.e., from manual chart review) are extremely limited
  • Imputing data or accounting for missing data in sparse, noisy, and unlabeled or weakly-labeled datasets
  • Generating useful tools, including data visualization or metadata, for enabling human analyses of imperfect data
Evaluation and discovery of potential data biases stemming from external factors or the data generating process.
  • Batch effects
  • Institutional discrepancies
  • Dataset shift
    • Newly curated, integrated, or standardized datasets or computational resources to enable pattern discovery in biomedical data
  • Reproducibility frameworks
  • Cloud computing
    • Other related topics.

    Session Organizers

    Dokyoon Kim

    University of Pennsylvania
    dokyoon.kim@pennmedicine.upenn.edu

    Shilpa Kobren

    Harvard Medical School
    shilpa_kobren@hms.harvard.edu

    Submission Information

    Paper Submission Deadline: August 3, 2020 (THIS IS AN ABSOLUTE DEADLINE, THERE WILL BE NO EXTENSIONS)
    Notification of Acceptance: September 14, 2020
    Poster/Abstract Submission Deadline: November 15, 2020
    Conference Date: January 3 - 7, 2021

    Papers must be submitted to the PSB paper management system. Please note that the submitted papers are reviewed and accepted on a competitive basis. At least three reviewers will be assigned to each submitted manuscript.

    The accepted file formats are: postscript (*.ps) and Adobe Acrobat (*.pdf). Attached files should be named with the last name of the first author (e.g., altman.ps or altman.pdf). Hardcopy submissions, unprocessed TeX or LaTeX files, or electronic submissions not submitted through the paper management system will be rejected without review.

    Each paper must be accompanied by a cover letter. The cover letter should be the first page of your paper submission. The cover letter must state the following:

    • The email address of the corresponding author
    • The specific PSB session that should review the paper or abstract
    • The submitted paper contains original, unpublished results, and is not currently under consideration elsewhere
    • All co-authors concur with the contents of the paper

    Submitted papers are limited to twelve (12) pages (not including the cover letter) in our publication format. Please format your paper according to these instructions. If figures cannot be easily resized and placed precisely in the text, then it should be clear that with appropriate modifications, the total manuscript length would be within the page limit.