Is respiratory rate estimation not poorly developed for clinical application and difficult implement?

In the following Nature scientific report from 02 January 2024: «Open-source software for respiratory rate estimation using single-lead electrocardiograms» https://scholar.google.com/scholar?hl=de&as_sdt=0%2C5&q=Open-source+software+for+respiratory+rate+estimation+using+single-lead+electrocardiograms&btnG= It says: “«Contact-based RR measurement methods are more clinically developed. These methods estimate RR by measuring respiratory sounds, carbon dioxide levels in exhaled gases, respiratory gas flow, or changes in blood oxygen saturation (SpO2)»“ But …