"Phenomics is the New Genomics"

Presented by Marzyeh Ghassemi, Visiting Researcher at Google's Verily & MIT CSAIL Post Doctoral Fellow

Talk Description: The explosion of clinical data provides an exciting new opportunity to use machine learning to discover new and impactful clinical information. Among the questions that can be addressed are establishing the value of treatments and interventions in heterogeneous patient populations, creating risk stratification for clinical endpoints, and investigating the benefit of specific practices or behaviors. However, there are many challenges to overcome. First, clinical data are noisy, sparse, and irregularly sampled. Second, many clinical endpoints (e.g., the time of disease onset) are ambiguous, resulting in ill-defined prediction targets.

We tackle these problems by learning "phenotypes" - abstractions that generalize across applications despite missing and noisy data. Dr. Ghassemi’s work spans coded records from administrative staff, vital signs recorded by monitors, lab results from ordered tests, notes taken by clinical staff, and accelerometer signals from wearable monitors. The learned representations capture higher-level structure and dependencies between multi-modal time series data and multiple time-varying targets. I focus on learning techniques that transform diverse data modalities into a consistent intermediate that improves prediction in clinical investigation.

In this talk, Dr. Ghassemi will discuss the need for practical, evidence-based medicine, and the challenges of creating multi-modal representations for prediction targets varying both spatially and temporally.

This video is part of IACS's 2018 Symposium on the Future of Computation in Science and Engineering. This year our annual symposium focused on how medicine and health care are being reshaped by computational science, big data, and information technology.

To learn more, visit our website at https://computefest.seas.harvard.edu/symposium

Видео "Phenomics is the New Genomics" канала Harvard Institute for Applied Computational Science