OtherJournal of neuroengineering and rehabilitation2025

A time-efficient continuous ramp protocol for data-driven walking energy expenditure estimation across multiple speeds.

Jeong Hyunho, Park Sukyung

PMID 41034972

WHAT IT FOUND

Correcting for delayed breathing let a continuous treadmill ramp measure walking energy expenditure as well as steady-speed testing in healthy young men.

A model trained on that shorter testing estimated energy expenditure with similar overall accuracy to the conventional model and better than a smartwatch.

Key findings

01With time-delay compensation, the continuous ramp protocol produced energy expenditure values close to the discrete protocol, with a mean percentage difference of 0.13 ± 11.37%.

02A deep learning model trained on the continuous dataset estimated energy expenditure with an average error of 10.66 ± 2.41%, which was not statistically different from the discrete dataset model.

03The continuous-dataset model had significantly lower errors than the smartwatch across all walking speeds.

STILL TO COME

How it was doneWhat they found

Read the rest of this summary

You get three full summaries a month, free, and we do not ask for a card. Search, the TL;DRs and your library stay unlimited either way.

Already have one?

What it does not show

The study included only healthy young men, so it does not show how the method performs in patients or people with different ages, fitness levels, or walking abilities. All walking was on a treadmill in a laboratory, not during ordinary daily activity. The continuous protocol depended on a mathematical correction for delayed breathing measurements; without that correction, energy expenditure was underestimated. The sample was small, so some differences between protocols and sensor sets may not have been detected. The model was not tested on clinical populations or outside the laboratory. At high exercise intensities, anaerobic metabolism can change energy cost, which limits the continuous ramp protocol.

The easy way to misread this

Do not treat this as a validated clinical tool for estimating energy expenditure in patients. It was tested only in healthy young men walking on a treadmill, and the model was trained using laboratory gas measurements.

Summarised by AI from the full paper, without a clinician reviewing it. Check it against the source before it changes what you do. Read it on PubMed →


The study

Participants
27 healthy young male subjects
Certainty of evidence
Low

Browse

    Cite

    Jeong Hyunho, Park Sukyung A time-efficient continuous ramp protocol for data-driven walking energy expenditure estimation across multiple speeds. Journal of neuroengineering and rehabilitation. 2025.

    Read the original — we summarise, we never replace the paper.