Tanveer Syeda-Mahmood plenary talk: The Role of Machine Learning in Clinical Decision Support
In this keynote presentation, Tanveer Syeda-Mahmood of IBM Almaden Research Center discusses the role of learning techniques in decision support by giving examples from practical multimodal decision support systems. She also describes the IBM Medical Sieve Radiology Grand Challenge, a worldwide collaborative research effort across IBM research labs that is expanding patient data and knowledge-driven learning methods to define new clinical decision support systems for radiologists.
The IBM AALIM system pioneered a new direction in evidence-based medicine using the concept of patient similarity and exploiting consensus opinions of other physicians who have looked at similar patients. It proposed the fundamental idea that similar clinical data points to similar patients and therefore to similar recommendations for diagnosis, treatment, and outcome. This led to a scalable learning-driven way of doing clinical decision support where associations between diseases and their manifestations in modality data were learned automatically through patient similarity methods. With the advent of deep learning methods, learning-based decision support can now be combined with clinical knowledge-driven techniques to define the next generation of clinical decision support systems.
Tanveer Syeda-Mahmood is a Senior Manager at IBM Research, Almaden, and the Chief Scientist/overall lead for the research-wide Medical Sieve Radiology Grand Challenge project at IBM Research. Dr. Syeda-Mahmood has been involved in building healthcare informatics systems based on multimodal data for the last 10 years and pioneered the idea of patient similarity for clinical decision support through her work on AALIM, the first multimodal cardiac clinical decision support system.
Dr. Syeda-Mahmood graduated from the MIT AI Lab in 1993 with a PhD in Computer Science. She has over 200 refereed publications and over 80 filed patents.