Soft Transducer for Patient's Vitals Telemonitoring with Deep Learning-Based Personalized Anomaly Detection.

Pasquale Arpaia,Giovanni Improta,Egidio De Benedetto,Francesco Serino,Federica Crauso,Luigi Duraccio

doi:10.3390/s22020536

Pasquale Arpaia, Giovanni Improta + Show 4 more

Open Access

https://doi.org/10.3390/s22020536

Copy DOI

Abstract

This work addresses the design, development and implementation of a 4.0-based wearable soft transducer for patient-centered vitals telemonitoring. In particular, first, the soft transducer measures hypertension-related vitals (heart rate, oxygen saturation and systolic/diastolic pressure) and sends the data to a remote database (which can be easily consulted both by the patient and the physician). In addition to this, a dedicated deep learning algorithm, based on a Long-Short-Term-Memory Autoencoder, was designed, implemented and tested for providing an alert when the patient’s vitals exceed certain thresholds, which are automatically personalized for the specific patient. Furthermore, a mobile application (EcO2u) was developed to manage the entire data flow and facilitate the data fruition; this application also implements an innovative face-detection algorithm that ensures the identity of the patient. The robustness of the proposed soft transducer was validated experimentally on five individuals, who used the system for 30 days. The experimental results demonstrated an accuracy in anomaly detection greater than 93%, with a true positive rate of more than 94%.

Highlights

The recent COVID-19 pandemic and the associated transition of patient care outside the hospital have boosted the development of systems for the remote monitoring of patient vitals signs [1,2,3], a task that has been favored by the advancement of wearable technologies [4,5,6,7,8,9] and the Internet of Things (IoT)
The data on the cloud are processed by means of a Deep Learning (DL) algorithm, which is trained on the basis of preliminary measurements of the patient vitals
The correct estimation of systolic and diastolic pressure, obtained by means of the multivariate linear regression algorithm, was verified after inserting the parameters required during the calibration phase

Summary

Introduction

The recent COVID-19 pandemic and the associated transition of patient care outside the hospital have boosted the development of systems for the remote monitoring of patient vitals signs [1,2,3], a task that has been favored by the advancement of wearable technologies [4,5,6,7,8,9] and the Internet of Things (IoT) These two technologies have contributed to the widespread adoption of smart healthcare solutions (soft transducer), deployed either at hospitals or at home [10,11]. Even a moderate increase in blood pressure is associated with reduced life expectancy In this regard, monitoring patient vitals represents an important aspect of patient care because these signs usually give early information about abnormal physiology. It is crucial for physicians to be able to monitor hypertensive patients regularly and to predict the evolution of this condition

Methods

Results

Conclusion