Comparison Metrics for Multi-Step Biomedical Signal Prediction

25 Pages Posted: 22 Feb 2022

See all articles by Pravinumar G. Kandhare

Pravinumar G. Kandhare

University of Alabama at Birmingham

Namasivayam Ambalavanan

University of Alabama at Birmingham

Colm P. Travers

University of Alabama at Birmingham

Waldemar A. Carlo

University of Alabama at Birmingham

Nikolay M. Sirakov

Texas A&M University Commerce

Arie Nakhmani

University of Alabama at Birmingham

Abstract

Prediction of changes in biomedical signals, such as vital signs, is useful for many clinical applications. Several signal prediction (forecasting) tools were developed, but their evaluation and applicability to a specific clinical use is context dependent. In this work, we propose a novel method for evaluation and comparison of vital sign predictors for intervention based clinical studies. Specifically, we study and compare nine deep learning and statistics based predictive models for multi-step prediction of bradycardia events in preterm infants, but the proposed method could be applied to other biomedical signals. Our results on testing sets with several days of vital sign recordings show that simple statistical predictors could outperform state-of-the-art deep learning architectures for low-dimensional signals.

Keywords: Deep learning, Biomedical Signal, Predictor Evaluation, Time Series Forecasting

Suggested Citation

Kandhare, Pravinumar G. and Ambalavanan, Namasivayam and Travers, Colm P. and Carlo, Waldemar A. and Sirakov, Nikolay M. and Nakhmani, Arie, Comparison Metrics for Multi-Step Biomedical Signal Prediction. Available at SSRN: https://ssrn.com/abstract=4040757 or http://dx.doi.org/10.2139/ssrn.4040757

Pravinumar G. Kandhare

University of Alabama at Birmingham ( email )

Birmingham, AL 35294-4460
United States

Namasivayam Ambalavanan

University of Alabama at Birmingham ( email )

Birmingham, AL 35294-4460
United States

Colm P. Travers

University of Alabama at Birmingham ( email )

Birmingham, AL 35294-4460
United States

Waldemar A. Carlo

University of Alabama at Birmingham ( email )

Birmingham, AL 35294-4460
United States

Nikolay M. Sirakov

Texas A&M University Commerce ( email )

2600 South Neal Street
Commerce, TX 75428
United States
903 886 5943 (Phone)

HOME PAGE: http://faculty.tamuc.edu/nsirakov/

Arie Nakhmani (Contact Author)

University of Alabama at Birmingham ( email )

Birmingham, AL 35294-4460
United States

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
57
Abstract Views
333
Rank
698,457
PlumX Metrics