#	Pagina
attuale pagina	/open-h2020/projects/208222/results.html

Report

Teaser, summary, work performed and final results

Periodic Reporting for period 1 - WECARMON (Wearable Cardiorespiratory Monitor)

Teaser

Summary

The WECARMONâ€™s main objective is to develop a novel system for monitoring patients suffering of cardiorespiratory diseases. This novel system will be based on a very comfortable wearable armband which can monitor some cardiorespiratory parameters during the patientsâ€™ normal life. Its innovative nature is based on two main tools: 1) a long-term (months) wearable ECG device which uses dry electrodes which causes no skin irritation and which are placed in a leadless armband, and 2) signal processing techniques for estimating respiratory rate and volumes from ECG which are robust against artefacts generated by movements during daily life.

This long-term wearable cardiorespiratory monitor has a wide range of applications, including monitoring of sleep, stress level, fitness level, and chronic respiratory patients. Among these applications, WECARMON will study the monitoring of chronic respiratory patients. Specifically, patients who are suffering obstructive sleep apnea syndrome (OSAS), and patients who are suffering of chronic obstructive respiratory disease (COPD) or asthma.

OSAS is characterized by an interruption of the airflow to the lungs produced by an upper airways occlusion during sleep. Then, arterial oxygen saturation goes down across time and mechanical respiratory efforts are intensified. If these efforts are not enough to reopen the upper airways, the hypercapnia level evolves dangerously and an arousal is generated to reactive all the peripheral systems restoring respiration. These episodes could occur hundreds of times in a single night producing serious health implications. The Gold Standard procedure for OSAS diagnosis is polysomnography, which consist of an overnight recording using a high number of sensors, being quite involved and difficult to use in ambulatory scenario. Application of different techniques for home sleep apnea monitoring has been extensively developed. Some of them are based on electrocardiogram and/or respiratory information derived from it. These alternatives could be applied using electrocardiogram recordings from the wearable armband, obtaining a very interesting device for OSAS screening.

An OSAS screening based on such a comfortable and wearable device would be an excellent alternative to the polysomnography, being more comfortable for the patient and economic for the society. Furthermore, depending on the results obtained when evaluating the armband device for OSAS screening, we could think of monitoring the patient during some weeks in order to assess the effectiveness of the treatment and to adapt it in case it is needed.

The other application on which WECARMON project will focus is monitoring of COPD and/or asthma patients. These patients are affected by destabilizations (or â€œexacerbationsâ€) which makes them to seek medical help and often lead to their hospitalization. Exacerbations can start quickly (in minutes to hours) and they are one of the main causes of mortality among patients with COPD and asthma which are the two most common chronic respiratory diseases, affecting millions of children and adults. The wearable armband may allow us to early detect COPD/asthma exacerbations and lead to a better prognosis of the patient and a reduction of financial costs to society.

Work performed

Different strategies for improving the quality of the ECG signal recorded by the armband were investigated, and different morphological features were studied for artefact detection. These features were used as inputs to different kind of classifiers, leading to an artifact detector based on machine learning. 24-hours recordings were analyzed, and obtained results suggest that the armband device is suitable for a daily life monitoring, obtaining usable data almost half of the non-bed time and almost all the bed time.

A study on deriving respiratory rate using the wearable armband was performed. The study included paced breathing stages at 10, 12, 18, 24, and 30 breaths per minute, as well as an stage during spontaneous breathing. Respiratory rate was estimated from the armband-ECG signals, and the estimates were compared to those obtained from the respiration signal. The obtained relative error that was not higher than 1.25% in median and not higher than 2.78% for all the studied stages. In addition, the methods were modified in order to reduce their computational time. The adaptation reduced the computational time up to a 82.05% assuming a lower accuracy, specifically, the highest median of relative error increased to -1.33%, and its highest IQR increased to 4.22%. These results are very promising and allow us to consider the armband wearable device as a potential wearable cardiorespiratory monitor.

The Fellow collaborated with a study about estimating the tidal volume from conventional ECG signals recorded during a treadmill exercise stress test, which constitutes a highly noisy and non-stationary environment. Subject-specific models for estimating tidal volume based on ECG derived features were proposed and calibrated during a maximal effort test. These models were validated for tidal volume estimation in a submaximal treadmill test, conducted by the same subject in a different day. The different proposed approaches led to fitting errors lower than 14% in most of the cases and than 6% in some of them, suggesting that tidal volume can be estimated from ECG in non-stationary conditions. Further studies are being elaborated in order to evaluate these methods using ECG signals recorded with the armband device.

The armband was evaluated as HRV monitor. Five traditional HRV parameters were derived from the armband-ECG signals and from a comercially-available Holter momnitor: SDNN, RMSSD, pNN50, and powers within low frequency and high frequency bands. The obtained Pearsonâ€™s correlation coefficient between the measurements from the armband device and the measures from the Holter were higher than 0.99, suggesting that the quality of armband-ECG signals is enough to estimate HRV parameters during stationary movement restricted conditions.

Final results

The WECARMON project has made some progress beyond the state of the art in the field of wearable devices for monitoring biomedical information. Specifically, methods for detecting artifacts in the ECG signals recorded by the armband device have been developed, as well as methods for minimizing these artefacts. In addition, methods for deriving respiratory rate from the armband device have been also developed. In addition, the wearable device demonstrated to be an accurate HRV, so it can also assess the autonomic nervous system.

Summarizing, WECARMON project has led to a long-term (months) wearable device that can provide cardiorespiratory information (including heart rate and respiratory rate, and a tidal volume estimation is currently being investigated), and.autonomic nervous system information. This has a big interest and possibilities for ambulatory environments (even without the tidal volume estimation) with its both economic and social advantages, especially in cases for which the conventional respiration monitors (plethysmographs, pneumographs, spirometersâ€¦) are not convenient such as OSAS, COPD, and epilepsy, among others. In addition, it allows a daily-basis monitoring of the patient providing a lot of data which can be used to adapt the treatment, so the wearable monitoring can be used for personalized medicine.