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

Simple item page
dc.contributor.authorWang, Shaodong
dc.contributor.authorLi, Qing
dc.contributor.authorZhang, Wenli
dc.date.accessioned2020-12-24T20:00:55Z
dc.date.available2020-12-24T20:00:55Z
dc.date.issued2021-01-05
dc.description.abstractDimension 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.extent10 pages
dc.identifier.doi10.24251/HICSS.2021.591
dc.identifier.isbn978-0-9981331-4-0
dc.identifier.urihttp://hdl.handle.net/10125/71209
dc.language.isoEnglish
dc.relation.ispartofProceedings of the 54th Hawaii International Conference on System Sciences
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 International
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subjectAugmented Intelligence
dc.subjectdimension reduction
dc.subjectelectronic healthcare records
dc.subjectheart failure
dc.subjectmanifold learning
dc.subjectreadmission
dc.titleMD-Manifold: A Medical Distance Based Manifold Learning Approach for Heart Failure Readmission Prediction
prism.startingpage4869

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
0478.pdf
Size:
989.31 KB
Format:
Adobe Portable Document Format
Download

Collections

Augmented Intelligence