MD-Manifold: A Medical Distance Based Manifold Learning Approach for Heart Failure Readmission Prediction

dc.contributor.author Wang, Shaodong
dc.contributor.author Li, Qing
dc.contributor.author Zhang, Wenli
dc.date.accessioned 2020-12-24T20:00:55Z
dc.date.available 2020-12-24T20:00:55Z
dc.date.issued 2021-01-05
dc.description.abstract Dimension reduction is considered as a necessary technique in Electronic Healthcare Records (EHR) data processing. However, no existing work addresses both of the two points: 1) generating low-dimensional representations for each patient visit; and 2) taking advantage of the well-organized medical concept structure as the domain knowledge. Hence, we propose a new framework to generate low-dimensional representations for medical data records by combining the concept-structure based distance with manifold learning. To demonstrate the efficacy, we generated low-dimensional representations for hospital visits of heart failure patients, which was further used for a 30-day readmission prediction. The experiments showed a great potential of the proposed representations (AUC = 60.7%) that has comparative predictive power of the state-of-the-art methods, including one hot encoding representations (AUC = 60.1%) and PCA representations (AUC = 58.3%), with much less training time (improved by 99%). The proposed framework can also be generalized to various healthcare-related prediction tasks, such as mortality prediction.
dc.format.extent 10 pages
dc.identifier.doi 10.24251/HICSS.2021.591
dc.identifier.isbn 978-0-9981331-4-0
dc.identifier.uri http://hdl.handle.net/10125/71209
dc.language.iso English
dc.relation.ispartof Proceedings of the 54th Hawaii International Conference on System Sciences
dc.rights Attribution-NonCommercial-NoDerivatives 4.0 International
dc.rights.uri https://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subject Augmented Intelligence
dc.subject dimension reduction
dc.subject electronic healthcare records
dc.subject heart failure
dc.subject manifold learning
dc.subject readmission
dc.title MD-Manifold: A Medical Distance Based Manifold Learning Approach for Heart Failure Readmission Prediction
prism.startingpage 4869
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
0478.pdf
Size:
989.31 KB
Format:
Adobe Portable Document Format
Description: