Prediction and Detection of Heart Attack using Ai and ML Technology

DOI : 10.17577/IJERTCONV7IS08012

Download Full-Text PDF Cite this Publication

Text Only Version

Prediction and Detection of Heart Attack using Ai and ML Technology

Shruti Jalapur, Vanishree Hatti, Sneha Jingade, Tahaseen Pinjar, Madhu Hippargi Dept of Computer Science and Engineering, Secab Institute of Engineering and Technology, Vijayapur, VTU Belgaum.

ABSTRACT

In recent years a wide range of wearable IOT healthcare application have been developed and deployed. The rapid increases wearable devices allows the transfer of patients health information between different devices, but the difficulty is in predicting and detecting of health status. The introduced system includes patients observing units, cloud for information maintenance and secure. By using some equipment units, different sensors and gadgets with networking association. The sensors that are used for sensing and monitoring will send the data; keep track of the regular health status of patients and we used ML and AI technology for predicting and detecting of heart attack.

Keywords: IOT, ML, Healthcare, ECG, Temperature, Sensors.

  1. INTRODUCTION

    Internet of things (IoT) has been a path breaking technology backed by many handshaking research areas to establish a high-end connectivity and communication between several mutually related devices to share information and interact, toward a better user experience. In the field of healthcare, the task of IoT is not only to offer a truly efficient and personalized healthcare to the users but also to redefine the healthcare system by connecting all the stakeholders and the state-of-art technologies making the most of the information shared across the closely communicating devices using the IoT platform.

    The internet of things in healthcare plays a major role in providing ease to patient and

    doctors. It consist of system that communicates between network connected system, applications and devices that can help patients and doctors to monitor, track and record patients vital data and medical information. Some of the devices include sensors, wifi modules that are connected to mobiles. Applications of smart phones also help to keeping a medical record with real time alerts and emergency services. These interconnected IoT devices produce large amount of data and information that should be dealt efficiently by the provider and so is a big challenge.

    The IoT technique is implemented to overcome the challenges of predicting, detecting, analysing and classifying the data. In this case, unlimited number of patients for a large period of time has become very fast and easy using the potential of IoT. The power of IoT for health and medical services are harnessed by sensors which accurately measures, monitors and analyze a variety of health status indicators. These can include basic vital health signs such as pulse rate and temperature.

  2. RELATED WORK

    In the year 2017 IoT Clinic-Internet based Patient Monitoring and Diagnosis

    System by Niharika Kumar[1]. They proposed a various components of a healthcare system and the different hardware architecture and the sensors being used to develop the ecosystem and provide treatment on time. Traditional healthcare system involves autonomous medical devices providing specific healthcare facilities. These Systems are generally installed at either healthcare centers or at the hospitals. Patients have to visit these medical centers to healthcare services.

    In the year 2018 IoT based Mobile Healthcare System for Human Activity Recognition by Abdulhamit Subasi, Mariam Radhwan, Rabea kurdi Kholoud Khateeb[2]. They proposed a accomplished through the help of introducing smart phones, health checking gadgets, smart IoT, and individual computerized collaborators in the health. In the modern healthcare application the usage of IoT technologies brings physicians and patients together for automated and intelligent daily activity monitoring for elderly people.

    In the year 2017 Complexity of Cyber Security Architecture for IoT Healthcare Industry: A Comparative Study by Aysha K, Alharam and Wael El-madany[3]. They proposed discuss the complexity issue of

    cyber security architecture for IoT based healthcare system. The objective of the study is for protecting healthcare industry from cyber attacks focusing on IoT based healthcare devices. The IP core architecture is considered to have more advantages compared to other architecture.

    In the year 2017 Modelling of Healthcare IoT using the Queuing Theory by Anastasiia, strielkina, Dmytro Uzun, Vyacheslav Kharchenko[4]. They proposed In this paper, we discussed opportunities and prospects for the IoT application in the field of healthcare. A healthcare IoT infrastructure with a brief description of each component is presented. These components are a device with a reader, cloud, healthcare provider and communication channel. Justification of applicability of the Queueing Theory.

    In the year 2017 A smart IoT platform for personalized healthcaremonitoring using semantic technologies by Ahmed Dridi, Salma Sassi, Sami Faiz [5]. They proposed a new IoT-based platform for personalized healthcare monitoring has been proposed, where, the problems of data interoperability, integration, visualization and confidentiality are addressed. The ultimate goal of achieving high quality of healthcare

    practices depends on the ability to effectively integrate data incoming from heterogeneous sources, share the collected data while keeping their security and privacy, use powerful data analytics tools to extract useful information from these data, and the ability to have an expressive and personalized visualization.

    ARDUINO:

    Arduino is an open source hardware and software company, project and user community that designs and manufactures single board microcontroller kits for building digital devices and interactive objects that seen and control objects in the physical and digital world. The board is equipped with sets of digital and analog input/output (I/O) Pins that may be interfaced to various expansion boards (shields) and other circuits. The boards has

    14 digital pins, 6 Analog pins, and programmable with the Arduino IDE (integrated development environment) via a type B USB cable. It can be powered by a USB cable or by an external 9 volt battery, though it accepts voltages between 7 and 20 volts

    DATA MINING:

    Data mining is that the method of discovering patterns in giant information sets involving strategies at the intersection of machine learning, statistics and information system. Data processing is associate knowledge domain subfield of engineering science associated statistics with an overall goal to extract data from a dataset and remodel the knowledge into a plain structure for any use.{Data mining | data method}is that the analysis step of the data discovery in information process or kdd. The distinction between information analysis and data processing is that information analysis is employed to check models and hypothesis on dataset example analysing the effectiveness of a promoting campaign, notwithstanding the quantity of information in distinction data processing uses machine learning and applied mathematics models to uncover clock- and-dagger or hidden patterns in an exceedingly giant volume of information. The term data processing is in fact a name as a result of the goal is that the extraction of patterns and data from and huge quantity of information not the extraction of information itself. It is also a buzzward and is usually applied to any type of giant scale information or

    informatics further as any application of pc call supporting system, as well as and business intelligence.

  3. PROPOSED METHODOLOGY

    In the proposed method we are acquiring the data from sensors and store it in mlab. This system is an IoT based health monitoring system which collect all the medical data of a patient including his heart rate, temperature and ECG and would send the data to the patients doctor regarding his full medical information, providing a reliable and fast healthcare service and also able to predict the heart attack using AI technology. There are three sensors in this system and they are:

    • Pulse sensor

    • Temperature sensor

    • ECG sensor

    These sensors are attached to the patients body and interfaced to the Arduino. The information are collected using sensors and then stored in the cloud and then the data transferred to the android system using wifi module.

    Fig 3.1 Architectural diagram

    Fig 3.2 Flow Chart

    ID3 Algorithm:

    1. Calculate the entropy of every attribute of the data set D.

    2. Partition the set D into subsets using the attribute for which the resulting entropy after splitting is minimized or equivalent information gain is maximum.

    3. Make decision tree node containing that attribute.

    4. Recur on subsets using remaining attributes.

    Bayesian Network:

    1. Bayesian network is a simple graphical notation for conditional independence assumption

    2. Each variable is represented by a node.

    3. The edges connecting the nodes show the dependency relation between the variables.

    4. The resultant graph is a DAG that represents the probability distribution of data over a set of variables.

      More precisely,

    5. If A1, A2… An are the random variables, where each variable Ai can take a set of values X (Ai).

    6. Each item corresponds to one of the possible assignments of values to the tuple of variables <A1,A2..AN>

    7. The probability distribution over this joint space is called the joint probability distribution

    Hence, a BBN describes the joint probability distribution over the set of variables. It is a graphical model of casual relationship cause and effect.

    Apriori Algorithm:

    Apriori(X, )

    Y1{large 1 item sets} k2

    While Yk-1

    Age

    Min

    Max

    1 month

    70

    190

    1 to 11 month

    80

    160

    1 to 2 year

    80

    130

    3 to 4 year

    80

    120

    5 to 6 year

    75

    115

    7 to 9 year

    70

    110

    Over 10 year

    60

    100

    Over 20 year

    100

    170

    Over 30 year

    95

    162

    Over 35 year

    93

    157

    Over 40 year

    90

    153

    Over 45 year

    88

    149

    Over 50 year

    85

    145

    Age

    Min

    Max

    1 month

    70

    190

    1 to 11 month

    80

    160

    1 to 2 year

    80

    130

    3 to 4 year

    80

    120

    5 to 6 year

    75

    115

    7 to 9 year

    70

    110

    Over 10 year

    60

    100

    Over 20 year

    100

    170

    Over 30 year

    95

    162

    Over 35 year

    93

    157

    Over 40 year

    90

    153

    Over 45 year

    88

    149

    Over 50 year

    85

    145

    Bk {b = {c}| Yk-1 c

    ,{s b||s|=k-1} Yk-1} for transaction xX Dx{b Bk| bx}

    for candidates bDx Count[b]count[b]+1

    Yk{bBk| count[b]>= }

    kk+1 return UYk

  4. RESULT AND ANALYSIS

    Detect as well as predict heart attack

    Helps old age people for regular checkups

    Working people can easily carry with themselves

    Status of the patients health is updated doctors and patients family regularly.

    Fig4.2 sign in page

    Table 4.1 heartbeat range according to age

    Fig4.3 registration page

    Result Analysis

    CP: Chest Pain

    Trestbps: Resting Blood Pressure Chol: Serum Cholesterol In Mg/Dl fbs: Fasting Blood Sugar

    restecg: Resting Electrocardiography thalach: Maximum Heart Rate Achieved exang: Exercise Induced Angina

    oldpeak = ST depression induced by exercise relative to rest

    thal: 3 = normal; 6 = fixed defect; 7 = reversible defect

  5. CONCLUSION

The paper reports an IOT based system for heart attack prediction and detection. We are using AI and ML technology to predict and detect heart attack. Arduino board is used which is a low cost solution for the possessing purpose. IOT technology integrates patients, doctor and is most useful for the people located in rural areas and do not have the resources to make frequent hospital visits.

REFERENCES

  1. Divakaran, Sindu, et al. "IOT clinic- Internet based patient monitoring and diagnosis system." 2017 IEEE International Conference on Power, Control, Signals and Instrumentation Engineering (ICPCSI). IEEE, 2017.

  2. Subasi, Abdulhamit, et al. "IoT based mobile healthcare system for human activity recognition." Learning and Technology Conference (L&T), 2018 15th. IEEE, 2018.

  3. Alharam, Aysha K., and Wael El- madany. "Complexity of Cyber Security Architecture for IoT Healthcare Industry: A Comparative Study." Future Internet of Things and Cloud Workshops (FiCloudW), 2017 5th International Conference on. IEEE, 2017.

  4. Strielkina, Anastasiia, Dmytro Uzun, and Vyacheslav Kharchenko. "Modelling of healthcare IoT using the queueing theory." Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS), 2017 9th IEEE International Conference on. Vol. 2. IEEE, 2017.

  5. Dridi, Ahmed, Salma Sassi, and Sami Faiz. "A Smart IoT platform for personalized healthcare monitoring using semantic technologies." Tools with Artificial Intelligence (ICTAI), 2017 IEEE 29th International Conference on. IEEE, 2017.

  6. Raj, Chanchal, Chaman Jain, and Wasim Arif. "HEMAN: Health monitoring and nous: An IoT based e-health care system for remote telemedicine." Wireless Communications, Signal Processing and Networking (WiSPNET), 2017 International Conference on. IEEE, 2017.

  7. Uddin, Mohammad Salah, Jannat Binta Alam, and Suraiya Banu. "Real time patient monitoring system based on Internet of Things." Advances in Electrical Engineering (ICAEE), 2017 4th International Conference on. IEEE, 2017.

  8. Patii, Niket, and Brijesh Iyer. "Health monitoring and tracking system for soldiers

    using Internet of Things (IoT)." Computing, Communication and Automation (ICCCA), 2017 International Conference on. IEEE, 2017.

  9. Prakashan, Kavyashree, et al. "Transformation of health care system using internet of things in villages." Industrial Engineering and Engineering Management (IEEM), 2017 IEEE International Conferene on. IEEE, 2017.

  10. https://www.semanticscholar.org/paper/I nternet-of-things-(IoT)-based-smart-health- care-Vippalapalli- Ananthula/38effa238d25b33254a5f05a4981 39b1ce8966fd

Leave a Reply