Cardiac Function Predicts Oxygen Uptake During Exercise In Adolescent Athletes: A Machine Learning Model Study
Bibliographic record
Abstract
PURPOSE: The relationship between cardiac function parameters and oxygen uptake (VO2) during exercise is not well understood beyond the contribution of stroke volume and heart rate (HR). Novel echocardiographic parameters of left (LV) and right ventricular (RV) function could aid in predicting cardiorespiratory performance in youth athletes. We aim to identify the cardiac function parameters best associated with concomitantly measured VO2 (ratio scaled to mass) during exercise testing in adolescent athletes. METHODS: Male adolescent football players (n = 97) underwent cardiopulmonary exercise testing and concomitant stress echocardiography on a recumbent cycle ergometer. Echocardiographic parameters of systolic and diastolic function, concomitant heart rate (HR) and VO2 were measured from rest to 150 W at 50 W increments. A supervised machine learning model (random forest) was trained with baseline characteristics, HR and each cardiac parameter sequentially to predict VO2, and then compared to a linear regression model. RESULTS: The best predictors of concomitant VO2 after adjusting for age, height, weight, gas exchange threshold and HR were LV circumferential strain, RV peak diastolic velocity, RV and LV longitudinal strain, RV peak systolic velocity and LV peak diastolic velocity (Figure 1A). Compared to a linear model, the random forest model including all cardiac parameters achieved better prediction accuracy, with an R2 = 0.86 vs 0.83, and also when considering individual cardiac parameters (Figure 1B). CONCLUSIONS: Cardiac function parameters improve VO2 prediction in addition to HR. In athletes LV circumferential function, and importantly, RV systolic and diastolic function contribute most to stroke volume increase. Machine learning approaches in evaluating and modelling exercise derived data was superior to conventional linear regression, we propose, by better addressing the non-linear relation of cardiac function parameters to HR and VO2Supported by: Canon Medical Systems and UKRI MRC #MR/N0137941/1
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".