Link to the University of Pittsburgh Homepage
Link to the University Library System Homepage Link to the Contact Us Form

Identification of Factors Associated with Subsequent Alzheimer's Disease Diagnosis Using Machine Learning Over Complex Large-scale Longitudinal Health Data

Boyce, Richard and Albert, Steven and Munro, Paul (2020) Identification of Factors Associated with Subsequent Alzheimer's Disease Diagnosis Using Machine Learning Over Complex Large-scale Longitudinal Health Data. In: Pitt Momentum Fund 2020, University of Pittsburgh, Pittsburgh, Pa. (Unpublished)

[img]
Preview
PDF (Showcase Poster)
Download (777kB) | Preview
[img]
Preview
PDF (Showcase Slide)
Download (230kB) | Preview

Abstract

We seek a Pitt Momentum Teaming Grant to support the data extraction, analysis, and planning needed to secure large-scale research funding for a new Alzheimer’s disease (AD) research initiative among faculty and trainees who have never worked together, most of whom have never worked on AD but whose skill set will support a novel approach to understanding this intractable disease. Because AD pathogenesis begins a decade or more before the onset of clinical symptoms, we seek to identify in electronic health records (EHRs) antecedents of disease that warrant additional scrutiny as possible contributors to or protectors against disease onset. We have identified over 37,000 unique patients in the UPMC EHR with a diagnosis of AD or dementia since 2016, almost 15,000 of whom have EHR data from visits 10 or more years before this diagnosis. With IRB approval, we will apply both case-control and machine learning approaches to the EHR datasets extracted (diagnoses, medications, test results). The results of these initial analyses will be used to plan larger scale studies that incorporate neuroimaging, genetics, neuropathology, lifestyle, and other types of data (including longitudinal causal time series modeling) combined with natural language processing and literature-based discovery to develop causal models of disease predictors, onset, and progression. We will seek funding from the National Institute on Aging to conduct these follow-on larger scale analyses with the guidance of an AD program officer, Suzana Petanceska, who has indicated her enthusiasm for helping us plan projects focused on secondary data analyses and causal discovery. Toward this goal, in October, our team of faculty and trainees from the Schools of Medicine (Boyce, Silverstein, Aizenstein, Malec, Karim, Ly), Public Health (Albert, Shaaban), and Computing and Information (Munro, Taneja) began weekly meetings to work on IRB protocols, analysis strategies, data interpretation, and manuscript and grant preparation.


Share

Citation/Export:
Social Networking:
Share |

Details

Item Type: Conference or Workshop Item (Poster)
Status: Unpublished
Creators/Authors:
CreatorsEmailPitt UsernameORCID
Boyce, Richardrdb20@pitt.edurdb200000-0002-2993-2085
Albert, Stevensmalbert@pitt.edusmalbert0000-0001-6786-9956
Munro, Paulpwm@pitt.edupwm0000-0003-2398-9248
Centers: Other Centers, Institutes, Offices, or Units > Office of Sponsored Research > Pitt Momentum Fund
Date: 2020
Event Title: Pitt Momentum Fund 2020
Event Type: Other
DOI or Unique Handle: 10.18117/0g8p-ff43
Schools and Programs: School of Medicine > Biomedical Informatics
Refereed: No
Date Deposited: 24 Feb 2020 16:39
Last Modified: 24 Feb 2020 18:13
URI: http://d-scholarship.pitt.edu/id/eprint/38208

Metrics

Monthly Views for the past 3 years

Plum Analytics

Altmetric.com


Actions (login required)

View Item View Item