About me
I am a final year Ph.D. student at the Technion in the Department of Data and Decision Sciences. My research has two primary objectives:
- Developing machine learning and causal inference methodologies which can be used in many scientific domains.
- Utilizing machine learning and causal inference techniques for healthcare applications to improve patient care.
I am experienced in various data modalities such as Electronic Health Records (EHRs), time series data, time-to-event data, tabular data, and imaging.
Some of my Ph.D. projects are presented here in short, with references to the full papers:
- Heterogeneous treatment effects in time-to-event data
- Discrete-time survival analysis with competing events: methods and tools
Prior to my Ph.D. journey, I was a researcher at Segal Lab, Weizmann Institute of Science (2020-2021). Throughout the COVID-19 pandemic, most of my effort was to develop strategic tools for public-health officials and policymakers. We devised national symptoms surveys for identifying virus spread clusters, developed machine-learning models for predicting the future number of hospitalized patients and deaths, analysed what-if scenarios that project the consequences of various national strategies, and provided real-time assessment of vaccine effectiveness at the national level.
Before that, I was a deep learning researcher at Zebra Medical Vision (2018-2019), where I developed deep-learning algorithms for the automated analysis of medical imaging, primarily CT scans and X-rays. These algorithms are now being employed by healthcare providers to enhance population health. For example, one of the main projects I worked on was the development of an automatic deep-learning-based system to identify vertebral compression fractures in computed tomography (CT) images.
I invite you to check out the dedicated pages for each of the main projects I worked on.