COMPARATIVE VALIDITY OF ENERGY EXPENDITURE PREDICTION ALGORITHMS USING WEARABLE DEVICES FOR PEOPLE WITH SPINAL CORD INJURY

Spinal Cord, 2020 · DOI: 10.1038/s41393-020-0427-5 · Published: July 1, 2020

Spinal Cord Injury Rehabilitation Telehealth & Digital Health

Simple Explanation

This study evaluates how well existing energy expenditure (EE) prediction equations, designed for manual wheelchair users (MWUs) with spinal cord injury (SCI) and using ActiGraph activity monitors, perform on a new dataset. The researchers collected data from 29 MWUs with SCI, using a portable metabolic cart to measure their EE while they wore an ActiGraph. They then compared the EE values predicted by the existing equations with the measured EE values. The study found that none of the existing equations were accurate enough for clinical or research use, suggesting that more work is needed to develop better EE prediction models for this population.

Study Duration

Not specified

Participants

29 MWUs with chronic SCI

Evidence Level

Cross-sectional validation study

Key Findings

1
None of the five sets of predictive equations demonstrated equivalence within 20% of the criterion measure based on an equivalence test.
2
The mean absolute error for the five sets of predictive equations ranged from 0.87–6.41 kilocalories per minute (kcal·min−1) when compared with the criterion measure
3
The existing EE predictive equations based on ActiGraph monitors for MWUs with SCI showed varied performance when compared with the criterion measure.

Research Summary

This study examined the performance of five sets of published EE predictive equations for MWUs using an independent dataset from 29 MWUs with SCI. The out-of-sample validation showed that these predictive equations did not demonstrate statistical equivalence against the criterion measure based on 20% equivalence regions. Future work is needed to develop more accurate EE algorithms for MWUs with SCI.

Practical Implications

Need for Improved Accuracy

The study highlights the need for more accurate energy expenditure prediction models for manual wheelchair users with spinal cord injury, as existing equations are not sufficiently reliable for clinical or research applications.

Advancements in Technology

The findings suggest exploring the use of multi-sensor consumer devices and machine-learning techniques to improve the accuracy of EE prediction, especially by incorporating physiological signals and analyzing high-resolution raw acceleration signals.

Personalized Models

Future research should focus on developing personalized EE prediction models that consider individual factors, activity types, and intensities, as well as improving the accuracy of resting energy expenditure (REE) estimation for this population.

Study Limitations

1
The study attempted to follow a systematic review process, however, the search covered only three databases and limited effort has been made to locate unpublished work.
2
All 29 participants in the study had paraplegia. A larger sample size with various levels of diagnosis including tetraplegia could further improve our understanding of predictive equation performance.
3
The proportion of different types of activities in the protocol does not necessarily reflect the typical activity profile in everyday living.

Your Feedback

Was this summary helpful?

Back to Spinal Cord Injury