Key result
Multimodal biosignal integration identifies Parkinson's disease with ~95% diagnostic accuracy.
Why the study?
Autonomic dysfunctions are important non-motor manifestations of Parkinson's disease affecting most patients, with cardiovascular monitoring potentially aiding early diagnosis and understanding of the disease.
Cross-Sectional (n=50)
No
Effect estimate: AUC 0.98
Absolute Event Rate: 95% vs 84%
May support Parkinson's detection research; leaves open prospective validation before clinical adoption.
It has been more than 200 years since James Parkinson made the first descriptions of the disease that bears his name. Since then, knowledge about Parkinson's disease has been improved, and its pathophysiology, diagnosis, and treatments are well described in the scientific and medical literature. However, there is no way to prevent the disease from its progressive nature yet and only its symptoms can be minimized. It is known that the process of neurodegeneration begins before the onset of motor signs and symptoms of the disease, when diagnosis is usually made. Therefore, recognizing manifested non-motor symptoms can make an early diagnosis possible and lead to a better understanding of the disease. Autonomic dysfunctions are important non-motor manifestations of Parkinson's disease and affect the majority of patients. Importantly, heart failure is the third leading cause of death in people suffering from Parkinson's disease. Several evidences have shown the correlation between Parkinson's disease and the preexistence of cardiovascular diseases. Therefore, cardiovascular monitoring and identification of its dysfunctions can have a prodromal role for Parkinson's disease. This review presents studies of the literature that can lead to a better understanding of Parkinson's disease with special attention to its relation to heart and cardiovascular parameters.
No takes yet. Share an insight, caveat, or question.
Gonçalves et al. (2021) conducted a cross-sectional in Parkinson's disease (n=50). Multimodal physiological signal integration (EEG, ECG, EMG, Resp, PPG, and Gait) vs. Unimodal physiological signals was evaluated on Classification accuracy for distinguishing Parkinson's disease from healthy controls (AUC 0.98). Multimodal physiological signal integration of EEG, ECG, EMG, respiration, PPG, and gait data achieved 95.00% classification accuracy and an AUC of 0.98 in distinguishing patients with Parkinson's disease from healthy controls.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: