Real-time monitoring of patient data during medical operations can provide important diagnostic input that substantially improves the chances of success. With the growing speed of sensors, frameworks like Deep Neural Networks must execute computations under stringent time restrictions for real-time operation. The conventional computing platforms like CPU/GPU for running Deep learning algorithms incur a large overhead due to fixed architecture, communication protocols and memory accesses methods. However, the FPGA-based design can directly interface sensors, storage devices, display devices and even actuators, thus reducing the delays of data movement between ports and compute pipelines. In order to minimize human involvement and respond at an appropriate time, An FPGA accelerated healthcare monitoring system is proposed which can either monitor or measure three vital signs i.e. heart rate, respiratory rate and body temperature of human body. It will give the health report, health status and alerts to the concerned when required.

Project Proposal

1. High-level project introduction and performance expectation

The most precious concern for humans is their health. Due to the ongoing pandemic the health consciousness has increased in every individual, making people eager to know about their health status wherever and whenever they need. The primary goal of the proposed system is to  track heart conditions, respiratory system and body conditions by monitoring heart rate, breathe rate and body temperature. All the data that is tracked by various sensors are integrated into the system to process of health data. When the patient is at home, it is not possible for doctors and nurses to take care of him all the time so when we get the health report from the system we can take necessary measures or consult a relevant doctor based on emergencies. We analyze the data from sensors using an algorithm where the age of the patient is considered and determines whether vital parameters are in the specified range for the mentioned age. In a certain critical situation where people are mostly affected by some common disease in such scenarios analyzing the huge data manually for perdition and prioritizing patients becomes time consuming and error prone for individuals. Hence this process needs to be automated without human intervention to obtain accurate results and prioritize the patients according to their severity. The rapid growth of medical record, motivate and lead hospitals, primary care centers, and health organizations to use technology to reduce the effort, extract important information, and to speed up the process of analyzing and linking information to discover and predict diseases, drugs, and medical procedure for patients.

2. Block Diagram

3. Expected sustainability results, projected resource savings

In a time of social distancing and isolation, technology is enabling patients, caregivers, and clinicians to communicate and monitor health remotely. In pandemics time remote patient monitoring is a more valuable tool to assist healthcare professionals in triaging incoming cases that support each patient's condition. Starting sophisticated sensors to innovative algorithms and artificial intelligence (AI), a variety of fundamental technologies is out there to enable accurate wearable clinical gadgets that gather and transmit information to help remote patient checking. Expandable Today’s hospitals deploy numerous devices over wires for various medical applications such as monitoring, diagnosis, treatment, and alarms. In order to plug in more and more devices in hospitals, it is essential to replace wires with wireless technologies. This replacement not only reduces the deployment cost and time, but also gives patients an increased mobility and comfort by reducing the complexity of the network. The Internet of Things (IoT) can be described as connecting everyday objects like smartphones, Internet TVs, sensors and actuators to the Internet where the devices are intelligently linked together enabling new forms of communication between things and people, and between things themselves. The objective of the work is to develop a system for health care monitoring based on wireless networking.

4. Design Introduction

The heartbeat rate (HBR) is represented in beats per minute (BPM). For example, if 7 peak signals are detected within the duration of 6 seconds, then the heart rate is 70 BPM. Photoplethysmogram is one of the bio signals that are generated due to cardiac relaxation and contraction . A couple of photodiodes are clipped on the person’s finger or earlobe for Photoplethysmogram measurement. Commonly used in home care or sports medicine for heart rate monitoring is Photoplesthysmogram. Nowadays, the most popular noninvasive methods used for measuring heart rate is Photoplethysmogram. Advantages of PPG sensor are simple and easily wearable. Thermal convection flow meters generally employ sensing elements such as metal wires or films and thermistors electrically change resistances with temperature. Respiratory rate is usually represented in beats per minute (bpm). For example, if 2 respirations are detected in the span of 6 seconds then the respiratory rate is 20 BPM. The skin surface under the armpit or inside a body cavity (like mouth) are the two common areas for measuring the body temperature. There are several sensors for measuring skin as well as body temperature. Transducers like thermistors will change their resistance with respect to the temperature and they are usually made up of compressed sintered metal oxides such as nickel, manganese, or cobalt. Thermistors have a negative temperature coefficient and they will show a nonlinear relationship between temperature and resistance. Whenever the temperature increases then the resistance of the thermistor will decrease. The advantages of using thermistor as a temperature sensor are ease of use, high sensitivity in temperature change and its range. Various wearable sensors will measure the body temperature, heart rate and respiratory rate that analogue data is sent through an analogue to digital converter. Then the digital data from analogue to digital converter is sent to FPGA to get the processed health report. In the FPGA, Verilog code will take the vital parameters and age as inputs and gives the heart, body temperature and respiratory conditions as outputs. This health monitoring system gives a health report which tells us about normal heart, abnormal heart, normal temperature, fever, hypothermia, normal and abnormal respiration. It finally shows whether a person is healthy or Sick. So, based on this health report we can take necessary measures or consult a doctor in emergencies.

5. Functional description and implementation

FPGA based health monitoring system is portable and it can monitor health conditions all the time when we go for wearable sensors. It can be cheaper than existing solutions and simplifies health monitoring for the medical staff. It is multifunctional. Verilog HDL (Hardware Description Language) can be used for FPGA programming. Verilog HDL transmits data to the PC through a graphical user interface. Therefore, data transmission depends on the necessary clock oscillator and a clock period. An Health monitoring system using this technology will contain a low-cost, analogue to digital converter which is used to transform an analogue signal into a digital signal. This digitization allows users to connect the FPGA to the entire system. The main advantage of the FPGA is the ability to reconfigure it after it has been manufactured. This helps to fix bugs more quickly and easily.

The two phases of the development of the wireless network for health care monitoring are described below:

1. Hardware Development 
2. Software Development 

While implementing the system for health care monitoring, some safety regulations must be considered to provide protection against hazardous conditions.

Hardware part consists of two modules: 1. Sensing node. 2. Coordinator. The detailed discussion of their implementation is as follows:  Sensing Node  The main objective of the sensing node is to collect the data from the sensors, perform signal conditioning operation and then transmits the data to the coordinator. Sensing node consists of the following components:  FPGA, Sensors, Power supply. Coordinator: The function of the coordinator is to gather data and then display the data as per the requirements. Coordinator consists of the following components: FPGA, Internet,Display device.  Power supply.

6. Performance metrics, performance to expectation

The system takes patients age, heart_rate, respiratory_rate, and body_temperature as inputs to system.Health report and Health status as outputs where health report contains Body temperature conditions(fever, hypothermia and normal temperature),Heart conditions (normal_heart and abnormal_heart) and Respiratory conditions(normal_respirations and abnormal_respirations). Health status contains patient health status whether he is normal or sick.

7. Sustainability results, resource savings achieved

As illustrated in Fig.  medical data were collected using wearable devices in our proposed work, and the data were uploaded to smartphones using a mobile application. For the security of personal medical data, the person and associated doctor must register their names in the system and obtain unique identifcation numbers. The data are collected on the cloud using smartphones. Data required for the computation are transferred from the cloud to the FPGA device. The use of this device reduces the computational time required for the prediction of the pathological conditions of a given person. The report is uploaded to the cloud. If the pathological conditions of a person are severe, the report is sent from the cloud to the doctor. The doctor can send a recommendation via the mobile application through the cloud, and the person immediately receives a medical report on the smartphone. Similarly, if a person has a primary pathological condition, suggestions of home remedies can be provided.

8. Conclusion