Machine Learning Classification of Pediatric Health Status Based on Cardiorespiratory Signals with Causal and Information Domain Features Applied—An Exploratory Study
Maciej Rosoł, Jakub S Gąsior, Kacper Korzeniewski, Jonasz Łaba, Robert Makuch, Bożena Werner, Marcel Młyńczak, Antonio Jorge Forte · 2024
Read Machine Learning Classification of Pediatric Health Status Based on Cardiorespiratory Signals with Causal and Information Domain Features Applied—An Exploratory Study by Maciej Rosoł, Jakub S Gąsior, Kacper Korzeniewski, Jonasz Łaba, Robert Makuch, Bożena Werner, Marcel Młyńczak, Antonio Jorge Forte (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11642896.txt.
Description
Heart and breathing signals carry clues about a child's health, and machine learning can sort those clues faster than a human reader. Maciej Rosoł and co-authors test whether such models can tell apart three groups of young people: heart patients, healthy children, and young athletes. They feed the models short, still recordings of heart and breathing signals, sliced into six feature sets.
The best model scored above 89 percent accuracy using the richest feature set. Features that capture how heart and breathing influence each other, drawn from causal and information-based measures, clearly raised the accuracy. Tools that explain the models' choices confirmed those linked features mattered for each group. The authors propose the winning feature set as a base for tracking training or recovery progress.
Catalog record
| CREATOR | Maciej Rosoł, Jakub S Gąsior, Kacper Korzeniewski, Jonasz Łaba, Robert Makuch, Bożena Werner, Marcel Młyńczak, Antonio Jorge Forte |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 67 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |