|
Activity Number:
|
254
- Digital Phenotyping
|
|
Type:
|
Invited
|
|
Date/Time:
|
Tuesday, August 4, 2020 : 1:00 PM to 2:50 PM
|
|
Sponsor:
|
Mental Health Statistics Section
|
|
Abstract #309227
|
|
|
Title:
|
Digital Phenotype of Patients with Major Depressive Disorder
|
|
Author(s):
|
Samprit Banerjee* and Jihui Lee
|
|
Companies:
|
Weill Medical College, Cornell University and Weill Cornell Medicine
|
|
Keywords:
|
digital phenotyping;
RNN;
forecasting
|
|
Abstract:
|
Smartphones provide an interactive interface that can passively measure various aspects of the user’s behavior from device sensors, as well as actively collect self-ratings (e.g. mood, stress etc.) obtained via daily ecological momentary assessment. Taken together with traditional clinical assessments, these measures have the potential to provide unique insight into the response trajectory of patients with major depressive disorder undergoing treatment. The potential to predict patient response in clinical trials of psychotherapy is a necessary step to modify future sessions in order to improve treatment efficacy. We present the challenges of predicting treatment response due to the noisy nature (missing or under-reporting) of such data and provide a pre-processing pipeline to address such challenges. We will then show and compare two approaches to predict treatment response – a prediction that utilizes an individual’s predictors alone (e.g. a time series or a recurrent neural network) and another where we borrow information from other individuals in our prediction model.
|
Authors who are presenting talks have a * after their name.
