University of Michigan

Adnan Tahir

Ira H Schachar

Kanishka T Jayasundera

Matthew K Johnson-Roberson

Daniel L Albertus

Nathan T Patel

Christopher R Ranella

Jillian T Huang

Naheed W Khan

Sarwar Zahid

Amani Al-Tarouti

Zhao Huang

Andrew M Lynch

Gail Hohner

Carla S Kaspar

A method for automatically diagnosing inherited retinal disease includes receiving a plurality of dissimilar types of data and pre-processing at least one of the plurality of dissimilar types of data to generate a feature vector descriptive of a patient. Further, the method includes, for each of the plurality of dissimilar types of data: (i) comparing portions of the respective type of data or a corresponding feature vector to data in a mutation proven database; (ii) generating a ranked list of matches between the patient and the plurality of patients with known diagnoses; and (iii) storing the ranked list of matches in an output database. A diagnosis routine then aggregates a plurality of ranked lists of matches in the output database to generate a ranked list of genetic diagnoses corresponding to the patient and sends an indication of the ranked list of genetic diagnoses to the end user device.

Systems and methods for diagnosing inherited retinal diseases

Growing community of inventors

Ann Arbor, MI, United States of America

Adnan Tahir