Telemedicine – Hidden Markov Model for Patients Data in Wireless Body Area Networks

Telemedicine systems monitor vital signs in patients with chronic diseases and transmit the data electronically to healthcare providers. The system provides an alert mechanism for proactive diagnosis and timely treatment by physicians. This capability will be achieved with high bandwidth networks and devices, to deliver real-time analytics that can enhance health outcomes. Typically, patients in rural areas face challenges accessing specialized doctors for diagnosing and treating chronic illnesses like Tuberculosis (TB), heart-attack, cancer etc. The proposed telemedicine setup will facilitate rural patients to access expert doctor for obtaining diagnosing and treatment. When patients are in emergency condition in ambulatory service, the patient’s vital sign and diagnosis details which needs to reach nearby hospital doctor for quick start of treatment process, thereby saves diagnosis time and life of the patient. Hence, the proposed telemedicine setup will help in diagnosis and facilitate quick treatment of emergency patients. Patients undergoing post treatment of Tuberculosis (TB), cancer and heart-attack are unable to travel very often for long distance to consult doctor for reviewing their treatment progress in phased manner. In all cases, telemedicine routing path must have less average delay, low packet loss rate and high throughput for sending patients’ vital signs and diagnosis details when they are under critical emergency and delay-sensitive conditions. In THMM, through viterbi algorithm, the general patient probability accounts to 0.15, the probability of emergency patient accounts to 0.00585 and the probability of delay-tolerant patient accounts to 0.2115 for three clusters.