Subramanian, Suraj
(2020)
Recurrent Multitask-Learning for Irregular Clinical Time Series Forecasting.
Master's Thesis, University of Pittsburgh.
(Unpublished)
Abstract
Inflammatory Bowel Disease (IBD) is a group of chronic gastrointestinal disorders that are difficult to treat. Having no known cure, treatment courses can be long-term and expensive. IBD flare-ups can happen without warning and there exists no objective criteria to measure the disease's activity. Recently, Recurrent Neural Networks (RNN) have emerged as a state-of-the-art method in clinical time series analysis; building on recent work that apply RNNs to temporal patient data, this thesis explores methodologies for processing temporal clinical data, the feasibility of a deep RNN classifier to forecast the future healthcare utilization, and techniques to curb overfitting while training on a small dataset. This work shows that multitask learning is helpful to train stable models, and deep networks can be engineered to process small noisy datasets in the clinical domain.
Share
| Citation/Export: |
|
| Social Networking: |
|
Details
| Item Type: |
University of Pittsburgh ETD
|
| Status: |
Unpublished |
| Creators/Authors: |
|
| ETD Committee: |
|
| Date: |
5 June 2020 |
| Date Type: |
Publication |
| Defense Date: |
3 April 2020 |
| Approval Date: |
5 June 2020 |
| Submission Date: |
14 April 2020 |
| Access Restriction: |
No restriction; Release the ETD for access worldwide immediately. |
| Number of Pages: |
50 |
| Institution: |
University of Pittsburgh |
| Schools and Programs: |
School of Computing and Information > Information Science |
| Degree: |
MS - Master of Science |
| Thesis Type: |
Master's Thesis |
| Refereed: |
Yes |
| Uncontrolled Keywords: |
inflammatory bowel disease, crohn's disease, ulcerative colitis, recurrent neural networks, gated recurrent unit, clinical time series, electronic health records, risk stratification |
| References: |
1 Trend of research interest in EHR and DL . . . . . . . . . . . . . . . . . . . . 4
2 ANN Architecture . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8
3 LSTM Cell . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10
4 GRU Cell . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11
5 Histogram of annual charges . . . . . . . . . . . . . . . . . . . . . . . . . . . 24
6 Baseline Confusion Matrices . . . . . . . . . . . . . . . . . . . . . . . . . . . 32
7 GRUD Confusion Matrices . . . . . . . . . . . . . . . . . . . . . . . . . . . . 32
8 Training and Validation Loss Trend (50 epochs) - OL Data Split . . . . . . . 33
9 Training and Validation Loss Trend (50 epochs) - HO Data Split . . . . . . . 34 |
| Date Deposited: |
05 Jun 2020 21:21 |
| Last Modified: |
05 Jun 2020 21:21 |
| URI: |
http://d-scholarship.pitt.edu/id/eprint/38713 |
Metrics
Monthly Views for the past 3 years
Plum Analytics
Actions (login required)
 |
View Item |
![[feed]](/images/feed-icon-32x32.png){kind=icon}