Scribd Logo
Upload

Welcome to Scribd!

  • 68 views

    IOT Based Heart Disease Prediction

    Uploaded by

    IJRASETPublications
    In today's world cardiovascular disease is the leading cause of death. The disease strikes a person so quickly that they do not receive treatment. Properly diagnosing patients is therefore a daunting task for medical professionals. Misdiagnosis by a hospital leads to a bad reputation and a loss of dignity. At the same time the treatment of this disease is very high and not very expensive for patients especially in India.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    IOT Based Heart Disease Prediction

    Uploaded by

    IJRASETPublications
    68 views4 pages
    In today's world cardiovascular disease is the leading cause of death. The disease strikes a person so quickly that they do not receive treatment. Properly diagnosing patients is therefore a daunting task for medical professionals. Misdiagnosis by a hospital leads to a bad reputation and a loss of dignity. At the same time the treatment of this disease is very high and not very expensive for patients especially in India.

    Original Title

    IOT based Heart Disease Prediction

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    In today's world cardiovascular disease is the leading cause of death. The disease strikes a person so quickly that they do not receive treatment. Properly diagnosing patients is therefore a daunting task for medical professionals. Misdiagnosis by a hospital leads to a bad reputation and a loss of dignity. At the same time the treatment of this disease is very high and not very expensive for patients especially in India.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    68 views4 pages

    IOT Based Heart Disease Prediction

    Uploaded by

    IJRASETPublications
    In today's world cardiovascular disease is the leading cause of death. The disease strikes a person so quickly that they do not receive treatment. Properly diagnosing patients is therefore a daunting task for medical professionals. Misdiagnosis by a hospital leads to a bad reputation and a loss of dignity. At the same time the treatment of this disease is very high and not very expensive for patients especially in India.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 4

    9 II February 2021

    https://doi.org/10.22214/ijraset.2021.32976
    International Journal for Research in Applied Science & Engineering Technology (IJRASET)
    ISSN: 2321-9653; IC Value: 45.98; SJ Impact Factor: 7.429
    Volume 9 Issue II Feb 2021- Available at www.ijraset.com

    IOT based Heart Disease Prediction


    Mrs. Shital. P. Chattar1, Prathamesh Wadile2, Bhushan Saraf 3, Omkar Kardile4, Aditya Pawar5
    1
    Professor, 2, 3, 4, 5Student, Department Information Technology, Pimpri Chinchwad Polytechnic College, Pune

    Abstract: In today's world cardiovascular disease is the leading cause of death. The disease strikes a person so quickly that they
    do not receive treatment. Properly diagnosing patients is therefore a daunting task for medical professionals. Misdiagnosis by a
    hospital leads to a bad reputation and a loss of dignity. At the same time the treatment of this disease is very high and not very
    expensive for patients especially in India.
    The purpose of this paper is to improve the cost-effective treatment using data mining technology to simplify the decision support
    system. Almost all hospitals use a certain hospital management system to manage the health care of patients. Unfortunately most
    programs do not usually use large clinical data where important information is hidden.
    As these systems generate a large amount of data in various forms but this data is rarely visited and remains unused. Therefore,
    in this process much effort is required to make wise decisions.
    Diagnosing the disease using a variety of features or symptoms is a daunting task. This paper uses various data mining
    techniques in an effort to help diagnose the disease in question.
    Keywords: cardiovascular disease, data mining, intelligent decisions, symptoms

    I. INTRODUCTION
    Today, many hospitals manage health care data using a health information system; as the system contains a large amount of data,
    which is used to extract hidden information to make intelligent medical diagnoses. The value of machine learning in health care is
    its ability to process large data sets beyond human capacity, and to reliably translate that data into clinical data that assists
    physicians in planning and providing care, ultimately leading to better outcomes, lower cost of care. A system that provides a
    diagnosis of heart disease using a history heart database. To improve this program, medical terms such as sex, blood pressure, and
    cholesterol are used as 13 input signals. To get the right results, two other traits are used, namely obesity and smoking, as these traits
    are considered important symptoms of heart disease. Viz data separation techniques. Neural Networks, Tree Decisions. Random
    Forest, and the Naive Bayes are in use.
    The healthcare industry collects a large amount of health care information that is, unfortunately, not "mine" to find hidden
    information for effective decision-making. Hidden patterns and relationships are often overused. Advanced data mining methods
    can help rectify this situation. The study developed an Intelligent Heart Disease Prediction System (IHDPS) using data mining
    techniques, namely Decision Trees, Naïve Bayes and Neural Network.
    The results show that each process has its own unique capabilities in achieving the goals of the defined mining objectives. IHDPS
    can answer the complex questions of "what if" traditional decision-making systems cannot. Using medical profiles such as age, sex,
    blood pressure, and blood sugar can predict that patients may develop heart disease. Enables important information, e.g. patterns,
    relationships between medical aspects related to heart disease, which should be established. IHDPS is based, easy to use, awesome,
    reliable and flexible. Used on Java-Python platform via Random Forest Algo.

    II. LITERATURE SURVEY


    Very few programs use the available clinical information for predictive purposes and even if they do, they are limited by a large
    number of applicable organizational rules. Diagnosis of this condition is based solely on Doctors' intuitions and patient records.
    Finding is not possible in advance.
    In the present system, the effective use of various data is time consuming. There are only a handful of decision-making programs
    available in the medical industry with very limited effectiveness. As mentioned earlier, medical decisions are made on the basis of a
    physician's intuition and not on rich material from a medical database. Improper treatment due to poor diagnosis poses a serious
    threat to the medical profession. To address these issues a data mining solution was assisted with medical information was
    introduced.

    ©IJRASET: All Rights are Reserved 123


    International Journal for Research in Applied Science & Engineering Technology (IJRASET)
    ISSN: 2321-9653; IC Value: 45.98; SJ Impact Factor: 7.429
    Volume 9 Issue II Feb 2021- Available at www.ijraset.com

    The main cause of death and illness is heart disease


    1) Ahmed M. Alaa [2] et.al proposed a machine learning strategy for the risk of heart disease. But they have achieved a very high
    accuracy of 77%. Since the database is unbalanced, there is a need to use sample techniques. Instead, they used direct learning
    models in the database. Stephen F. Weng [3] et.al studied the use of machine learning algorithms to improve predicting heart
    risk. They have shown that machine learning algorithms are effective in improving the accuracy of the cardiovascular
    prediction, but the required number of patient records should be higher to achieve better results. Rine Nakanishi [4] et.al
    examined ML methods for improving the predictable rate of heart disease (CHD). They used electronic learning methods in
    6814 patient records and obtained a measure of accuracy. Senthilkumar Mohan [6] proposed a machine learning model that
    found key features to improve the predictive rate of heart disease. They have experimented with a combination of different
    factors and obtained 88.7% accuracy with a random hybrid forest.

    III. PROPOSED SYSTEM


    The proposed system has the advantage of detecting a heart attack with the help of monitoring the heartbeat based on the internet of
    the object. Our method uses a heartbeat sensor, Arduino board and Wi-Fi module. After setting the program, the heartbeat sensor
    will begin to hear the heartbeat readings and will display the human heartbeat on the LCD screen. Also, using a Wi-Fi module will
    transmit data over the Internet. The system allows a given point that can help determine if a person is healthy by checking his or her
    heart rate and comparing it to a set point. After setting these limits, the system will start monitoring the patient's heart rate and soon
    the heart rate will go above or below the specific limit and the system will send a warning message. As part of this project we are
    using an android app model that will track a patient's heart rate and monitor it and provide an urgent message about the risk of a
    heart attack.
    IV. CONCLUSION
    In this study we attempted to raise a comprehensive paper on the diagnosis of heart disease by monitoring a person's heartbeat. The
    heartbeat connected to the microcontroller is a human heartbeat sensor and transmits via the Internet using a Wi-Fi module. The
    system allows you to set the limits of your heartbeat. After setting these limits a person can begin to monitor the heartbeat and
    whenever a person's heart rate exceeds a certain level they can get a warning of high heart rate and the risk of heart attack. And
    warnings for a low heart rate.

    REFERENCES
    [1] J Thomas MR, Lip GY. Symptoms of a novel tragedy and a risk assessment for heart disease. Circular research. 2017; 120 (1): 133–149.
    https://doi.org/10.1161/CIRCRESAHA.116.309955 PMID: 28057790
    [2] Ahmed M. AlaaID1, Thomas Bolton, Emanuele Di Angelantonio, James HF RuddID, Mihaela van der Schaar, Cardiovascular Predictability Predictability
    using Automated Machine Learning: A prospective study of 423,604 UK participants in Biobankob, PLOS ONE 14 (5): e0213653.
    https://doi.org/10.1371/journal, May 15, 2019 Evil, History Hypertext History of Multiuser Dimensions, MUD History,
    http://www.ccs.neu.edu/home/pb/mudhistory.html . 1986. (URL link * include year)
    [3] Stephen F. Weng, Jenna Reps, Joe Kai1, Jonathan M. Garibaldi, Nadeem Qureshi, ―Configuration studies can improve the prediction of cardiovascular risk
    using standard clinical data? ‖, PLOS ONE | https://doi.org/10.1371/journal.pone. 0174944 April 4, 2017
    [4] Rine Nakanishi, Damini Dey, Frederic Commandeur, Piotr Slomka, achMachine Learning in Predicting Coronary Heart Disease and Cardiovascular Disease
    Events: Results from The Multi-Ethnic Study of Atherosclerosis (Mesa) ‖, JACC Mar- 20, 2018, Volume 71, Release 11
    [5] https://www.cdc.gov/heartdisease/facts.htm. Available [Online].
    [6] Senthilkumar Mohan, Chandrasegar Thirumalai, Gautam Srivastava ff Important Guidelines for Heart Disease Using Hybrid Machine Learning Techniques,
    Digital Identity Object 10.1109 / ACCESS.2019.2923707, IEEE Access, VOLUME 7, 2019 Compator Compatibility of Compact ‖ Process. The fourth is Ann.
    Allerton Conf. Circuits and Program Theory, pages 8-16, 1994. (Conference procedures)

    ©IJRASET: All Rights are Reserved 124

    You might also like