|
|
JAIST Repository >
School of Information Science >
Conference Papers >
Conference Papers >
Please use this identifier to cite or link to this item:
http://hdl.handle.net/10119/18246
|
| Title: | Does Deep Learning REALLY Outperform Non-deep Machine Learning for Clinical Prediction on Physiological Time Series? |
| Authors: | Liao, Ke
Wang, Wei
Elibol, Armagan
Meng, Lingzhong
Zhao, Xu
Chong, Nak Young |
| Issue Date: | 2021-08 |
| Publisher: | Institute of Electrical and Electronics Engineers (IEEE) |
| Magazine name: | Proc. IEEE Int'l Conf. on Automation Science and Engineering, Lyon, France, August 23-27, 2021 |
| DOI: | 10.48550/arXiv.2211.06034 |
| Abstract: | Machine learning has been widely used in healthcare applications to approximate complex models, for clinical diagnosis, prognosis, and treatment. As deep learning has the outstanding ability to extract information from time series, its true capabilities on sparse, irregularly sampled, multivariate, and imbalanced physiological data are not yet fully explored. In this paper, we systematically examine the performance of machine learning models for the clinical prediction task based on the EHR, especially physiological time series. We choose Physionet 2019 challenge public dataset to predict Sepsis outcomes in ICU units. Ten baseline machine learning models are compared, including 3 deep learning methods and 7 non-deep learning methods, commonly used in the clinical prediction domain. Nine evaluation metrics with specific clinical implications are used to assess the performance of models. Besides, we sub-sample training dataset sizes and use learning curve fit to investigate the impact of the training dataset size on the performance of the machine learning models. We also propose the general pre-processing method for the physiology time-series data and use Dice Loss to deal with the dataset imbalanced problem. The results show that deep learning indeed outperforms non-deep learning, but with certain conditions: firstly, evaluating with some particular evaluation metrics (AUROC, AUPRC, Sensitivity, and FNR), but not others; secondly, the training dataset size is large enough (with an estimation of a magnitude of thousands). |
| Rights: | Copyright (C) 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. |
| URI: | http://hdl.handle.net/10119/18246 |
| Material Type: | author |
| Appears in Collections: | b11-1. 会議発表論文・発表資料 (Conference Papers)
|
Files in This Item:
| File |
Description |
Size | Format |
|---|
| N-CHONGーI-0428.pdf | | 632Kb | Adobe PDF | View/Open |
|
All items in DSpace are protected by copyright, with all rights reserved.
|
