Researchers at MIT trained a neural network on nocturnal breathing patterns, collected either from a wearable belt or from radio waves bounced off a sleeping person's body, across data from about 7,700 individuals, with and without the disease.
The model identified Parkinson's from breathing alone and tracked how severe it was, all without a camera, a wire touching the patient, or the person being awake. The researchers point to breathing because the disease affects brainstem regions that control it early on.
Because breathing may shift before the classic tremor appears, the model raised the possibility of catching Parkinson's before a clinical diagnosis, though the study offered only initial evidence for that. Its main result was detecting disease already present, with an accuracy measure of 0.90.
Read the original study
Yang et al., Nature Medicine, 2022 · doi.org/10.1038/s41591-022-01932-x
No tremor needed, just the rhythm of breathing.
Source
- Yang, Y., Yuan, Y., Zhang, G., Wang, H., Chen, Y.-C., Liu, Y., Tarolli, C. G., Crepeau, D., Bukartyk, J., Junna, M. R., Videnovic, A., Ellis, T. D., Lipford, M. C., Dorsey, R., & Katabi, D. (2022). Artificial intelligence-enabled detection and assessment of Parkinson's disease using nocturnal breathing signals. Nature Medicine, 28(10), 2207–2215. https://doi.org/10.1038/s41591-022-01932-x