CS Forum: Ole Winther

Topic: FindZebra - the search engine for rare diseases

Speaker: Prof. Ole Winther, Technical University of Denmark (DTU)

Host: Prof. Aki Vehtari

Time: 15:30-17:00 (coffee from 15:15)

Place: AS1 in TUAS Building

Abstract

The web has become a primary information resource about illnesses and treatments for both medical and non-medical users. Standard web search is by far the most common interface to this
information. It is therefore of interest to find out how well web search engines work for diagnostic queries and what factors contribute to successes and failures. Among diseases, rare (or orphan) diseases represent an especially challenging and thus interesting class to diagnose as each is rare, diverse in symptoms and usually has scattered resources associated with it. We design an evaluation approach for web search engines for rare disease diagnosis which includes 56 real life
diagnostic cases and around 500 Doctor Dilemma questions related to rare diseases, performance measures, information resources and guidelines for customising Google Search to this task. In addition, we introduce FindZebra available at findzebra.com, a specialized rare disease search engine. FindZebra is powered by open source search technology and uses curated freely available online medical information. FindZebra outperforms Google Search in both default set-up and customised to the resources used by FindZebra. Our results indicate that a specialized search engine can improve the diagnostic quality without compromising the ease of use of the currently widely popular standard web search. The proposed evaluation approach can be valuable for future development and benchmarking. The FindZebra search engine is available at findzebra.com. In the talk Prof. Ole Winther will present example cases and the basic as well as the latest added functionality.

Bio

Ole Winther is Professor in Data Science and Complexity at DTU Compute, Technical University of Denmark and group leader in Gene Regulation Bioinformatics at the Bioinformatics Centre, Dept. of Biology/BRIC, KU. The gene regulation group works on high throughput data analysis in tight
collaboration with experimental and clinical groups. Ole Winther has contributed to methodological aspects of machine learning most notably advanced variational methods for Bayesian inference. Ole Winther's current interests include clinical bioinformatics, information retrieval for diagnosis
(findzebra.com) and deep learning.