Clinical Machine Learning (Medial Research and Harvard Medical School)

We will have two lectures (approx. 35-40 minutes each) in Hebrew. Light refreshments will be served before the first lecture.

Estimated schedule:
1800 refreshments at the J&J conference hall (3rd floor)
1830 First lecture
1920 Second lecture

First lecture:

Lecturer: Dr. Moti Freiman, Staff Research Scientist at Philips Healthcare

Title: Reliable quantification of tissue micro-structure with Diffusion-Weighted MRI

Quantitative Diffusion-weighted MRI (DW-MRI) has the potential to provide important new insights into micro-structural properties of the body. However, DW-MRI signal decay analysis through commonly used models and fitting approaches is limited in providing a detailed and precise characterization of the tissue micro-structure. In this talk I'll present a motion-robust probabilistic signal decay model that explicitly characterize the multi-scale nature of diffusion inside the tissue, combined with a powerful combinatorial solver to achieve robust estimates of the model parameters. The proposed model and estimation approach enables a detailed and precise characterization of the tissue micro-structure. I'll demonstrate the potential clinical impact of the proposed approach in both improving the quality of DW-MRI images for visual assessment of Crohn's disease and in non-invasive characterization of active inflammation and fibrosis in Crohn's disease patients.

Moti Freiman is a staff research scientist at Philips Healthcare where he is developing advanced algorithms with the aim of improving the capacity of medical imaging devices to provide clinically meaningful information by leveraging machine learning, computer vision and image processing algorithms. Prior to Philips, Dr. Freiman was an Instructor in Radiology at Harvard Medical School where he developed advanced algorithms for quantitative analysis of diffusion-weighted MRI data. Dr. Freiman is the recipient of an NIH R01 research grant and the 2012 Crohn's and Colitis foundation of America research fellow award. He is the author and co-author of more than 40 journal and full-length conference papers and holds several patents and patent applications. The above mentioned lecture is part of his academic work in Harvard.

Second lecture:

Lecturer: Dr. Arturo Weschler, Chief Medical Officer at Medial Research

Title: When artificial intelligence meets the clinical laboratory: Enabling the value driven transformation of diagnostic testing

By applying machine learning algorithms to panels of laboratory tests, their history, basic demographics and complementary clinical data, Medial EarlySign creates algorithmic assays (AlgoMarkers) specifically crafted to improve clinical outcomes through improvement of clinical decisions. From early detection of patients at high risk for harboring Colorectal Cancer to identification of diabetic patients at high risk for developing cardiovascular or renal complications we will present how the clinical laboratory creates a unique opportunity for the seamless introduction of machine learning based clinical predictions into the clinical workflow and healthcare IT ecosystem in hospitals, ambulatory care and population health management.

Dr. Arturo Weschler serves as Executive Vice President of Product for Medial EarlySign. The company develops machine-learning-based tools designed to expose the hidden layer of information in standard medical data. Prior to joining Medial, he was co-founder and chief medical officer of Healarium, a startup in the field of digital health / self-management support. Until 2008, for more than a decade Dr Weschler was the CIO of the Tel Aviv Sourasky Medical Center, the second largest and one of the most progressive full-service healthcare institutions in Israel. He holds an MD (Cum Laude) from the Technion – Israel Institute of Technology, and served as lecturer in Medical Informatics in Tel Aviv and Bar Ilan Universities.