Snizhko Ye.M., Palamarchuk Yu.A., Botsva T.O.

Dnipropetrovsk national university named after O.Honchar

 

WIRELESS SENSOR NETWORK SOLUTIONS FOR HEALTHCARE

 

         Wireless sensor networks (WSN) are being widely applied in medical domains. Wearable WSN nodes work for constant monitoring of vital signs, gathering and transmision of physiological data.

         Continuous health monitoring with wearable or clothing-embedded transducers and implantable body sensor networks will allow to detect emergency conditions. Also, these systems provide useful methods to remotely acquire and monitor the physiological signals without interruption of the patient’s normal life [1]. Although traditional hospital systems allow continuous monitoring of patient vital signs, these systems require the sensors to be placed bedside monitors and limit the patient`s free moving to his bed. But now, there is no relation between the sensors and the bedside equipment due to the wireless devices and wireless networks. In most cases, health monitoring will be done by infrastructure-oriented wireless networks. But, the coverage of the infrastructure-oriented networks changes with time or location. Sometimes, the coverage of wireless network is not available, or the coverage is available but we cannot access to the network due to a lack of available bandwidth. So, with these problems and restrictions, continuous health monitoring is not possible and emergency signals may not be transmitted from a patient to healthcare providers.[2] As a possible example, we can solve the problem of continuous health monitoring by ad hoc wireless network architecture that can transmit vital signs over a short-range.

                In an emergency or disaster scenario, the same solution would help clinical staff to more effectively care for large numbers of casualties. Medics could receive immediate notifications on any critical changes in patient condition, such as respiratory failure or cardiac arrest. Wireless sensors could possibly replace existing wired telemetry systems for many specific clinical applications, such as rehabilitation or long-term out-ward monitoring.

         Meeting the potential of WSNs inhealthcare requires addressing many of technical challenges. These challenges include more than just the resource limitations that all WSNs have: network capacity, processing, battery life and memory constraints. Specifically, unlike applications in other domains, healthcare applications must meet strict requirements on system reliability, quality of service, and particularly privacy and security.[3]

         Most medical sensors have traditionally been too costly and complex to be used outside of clinical environments. But recent inventions in microelectronics and computing have made medical sensing available to individuals at their living spaces. Medical sensors have become interconnected with other devices. Earlier medical sensors were isolated modules with integrated user interfaces for displaying their measurements. Now sensors became capable of interfacing to external devices via wired interfaces such as RS 232, USB, and Ethernet. More recently, medical sensors have incorporated wireless connections, both short range, such as Bluetooth, Zigbee, and near-field radios to communicate wirelessly to nearby computers, smartphones, and long range, such as WiFi to communicate directly with cloud computing services.

         Critical points in WSNs for clinical use

Interoperability. As a result of multiple types of nodes (i.e. different types  of physiological data require different sensing nodes, alocated on different areas of human body) present in the system, communication between devices — motes, mplanted medical devices etc. - may occupy multiple bands and use different protocols. The WSN designed for out-ward care must provide middleware interoperability between disparate devices, and support unique relationships among devices, such as implants and their outside controllers.

Real-time data gathering and analysis. The rate of collection of data is higher in this type of network than in WSNs used, for example, in environmental studies. Efficient communication and processing become critical. Event ordering, time-stamping, synchronization, and quick response in emergency situations will  required here as in any healthcare IT product.

Robustness. Sensors and other devices must operate with enough reliability to yield

high-confidence data suitable for medical diagnosis and treatment. Since the out-ward care network will not be maintained within a controlled clinic, devices must have long enougth time of autonomous work.

Patient and object tracking. Tracking can be considered at three levels: symbolic (e.g., ward or X-Ray Lab); geographical (GPS coordinates); relational/associational. It is complicated by the presence of multiple patients, periodical leaving the network zone.

Multi-modal interconnection and energy conservation. Limited computational and radio communication capabilities require algorithms with energy-aware communication. Heterogeneous devices will be on very different duty-cycles, from always-on wired-power units to tiny, wearable units, making calculation of comunication time-range a difficult algorithm task.

Multi-level data processing. Data may be gathered at multiple levels, from simple on-body filtering to compression in storage nodes. Embedded real-time databases store data of interest and allow to query them.

Privacy and security. Data collected by the network is sensitive, and personnel access issues are not always clear from the very first sight. Data must be available to any involved doctor during emergencies, but all access attempts should be trailed. WSN should not “leak” information when even a fact that data are obtained may violate patient's privacy. When dealing with an out-ward monitoring system, patients should have a read-only access to their physiological data to avoid fraud.

 

References:

1. Carl Falcon. Wireless medical devices: Satisfying radio requirements. Medical Device & Diagnostic Industry, Sept.2004.

2. J. A. Stankovic and others. Wireless Sensor Networks for In-Home Healthcare: Potential and Challenges

3. JeongGil Ko, Chenyang Lu, Mani B. Srivastava,John A. Stankovic. Wireless Sensor Networks for Healthcare - Proceedings of the IEEE, ol. 98, No. 11, Nov. 2010