Scribd Logo
Upload

Welcome to Scribd!

  • 8 views

    مشروع بيانات تخطيط القلب ويكا

    Uploaded by

    ابو العز
    The document describes using the Weka data mining tool to build a decision tree classification model to predict whether a patient will survive at least one year after a heart attack using echocardiogram data with 12 attributes. The data is discretized and the J48 decision tree algorithm is used to generate a model that can classify patients as surviving or not surviving at 1 year with an accuracy of 75.4% based on testing the model on the 61 instance dataset.

    Copyright:

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

    مشروع بيانات تخطيط القلب ويكا

    Uploaded by

    ابو العز
    8 views21 pages
    The document describes using the Weka data mining tool to build a decision tree classification model to predict whether a patient will survive at least one year after a heart attack using echocardiogram data with 12 attributes. The data is discretized and the J48 decision tree algorithm is used to generate a model that can classify patients as surviving or not surviving at 1 year with an accuracy of 75.4% based on testing the model on the 61 instance dataset.

    Original Description:

    الكشف عن الأمراض المختلفة في القلب

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    The document describes using the Weka data mining tool to build a decision tree classification model to predict whether a patient will survive at least one year after a heart attack using echocardiogram data with 12 attributes. The data is discretized and the J48 decision tree algorithm is used to generate a model that can classify patients as surviving or not surviving at 1 year with an accuracy of 75.4% based on testing the model on the 61 instance dataset.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    8 views21 pages

    مشروع بيانات تخطيط القلب ويكا

    Uploaded by

    ابو العز
    The document describes using the Weka data mining tool to build a decision tree classification model to predict whether a patient will survive at least one year after a heart attack using echocardiogram data with 12 attributes. The data is discretized and the J48 decision tree algorithm is used to generate a model that can classify patients as surviving or not surviving at 1 year with an accuracy of 75.4% based on testing the model on the 61 instance dataset.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 21

    ‫‪ ‬ا‪ ‬ا‪ ‬ا‪‬‬

    ‫ﺟﺎﻣﻌﺔ اﻟﻨﻴﻠﻴﻦ‬

    ‫ﻛﻠﻴﺔ ﻋﻠﻮم اﻟﺤﺎﺳﻮب وﺗﻘﺎﻧﺔ اﻟﻤﻌﻠﻮﻣﺎت‬

    ‫ﻣﺎﺟﺴﺘﻴﺮ ﺗﻘﺎﻧﺔ اﻟﻤﻌﻠﻮﻣﺎت‬

    ‫اﻟﻤﺠﻤﻮﻋﺔ اﻟﺜﺎﻧﻴﺔ‬

    ‫‪Model By Weka (Echocardiogram Data) Using‬‬


    ‫)‪Classification Model (Desion Tree‬‬
    ‫ﺑﻴﺎﻧﺎت ﺗﺨﻄﻴﻂ اﻟﻘﻠﺐ‬

    ‫إ‪‬اد ا‪:‬‬

    ‫ﺻﻔﻴﻪ ﻧﺎﺟﺢ ﻧﻮري اﻟﺒﺪري‬

    ‫إ‪‬اف ‪:‬‬

    ‫دﻛﺘﻮر ﻣﺤﻤﺪ ﻋﺜﻤﺎن ﻋﻠﻲ ﺣﺠﺎزي‬

    ‫‪1‬‬
    ‫ﻳﻮﺟﺪ اﻟﻜﺜﻴﺮ ﻣﻦ اﻟﻤﺮﺿﻰ اﻟﺬﻳﻦ ﻋﺎﻧﻮ ﻣﻦ اﻟﻨﻮﺑﺎت اﻟﻘﻠﺒﻴﻪ ﻓﻲ ﻣﺮﺣﻠﺔ ﻣﺎ ﻓﻲ‬
    ‫ﺣﻴﺎﺗﻬﻢ ‪ ،‬ﺑﻌﺾ اﻟﻤﺮﺿﻰ ﻻﻳﺰاﻟﻮن ﻋﻠﻰ ﻗﻴﺪ اﻟﺤﻴﺎة وﺑﻌﻀﻬﻢ ﻻ ‪ ،‬ﻓﺒﺄﺧﺬ اﻟﻌﺪﻳﺪ ﻣﻦ‬
    ‫اﻟﻤﺘﻐﻴﺮات ﻣﻊ ﺑﻌﻀﻬﺎ اﻟﺒﻌﺾ ﻳﻤﻜﻦ اﻟﺘﻨﺒﺆ إذا ﻛﺎن اﻟﻤﺮﻳﺾ ﺳﻴﺒﻘﻰ ﻋﻠﻰ ﻗﻴﺪ اﻟﺤﻴﺎة‬
    ‫ﻟﻤﺪة ﺳﻨﺔ واﺣﺪ ﻋﻠﻰ اﻷﻗﻞ ﺑﻌﺪ اﻟﻨﻮﺑﻪ اﻟﻘﻠﺒﻴﻪ أم ﻻ ‪.‬‬

    ‫اﻟﻤﺸﻜﻠﻪ اﻟﺘﻲ ﺗﻮاﺟﻪ اﻟﺒﺎﺣﺜﻮن ﻫﻲ اﻟﺘﺒﺆ ﻣﻦ اﻟﻤﺘﻐﻴﺮات اﻷﺧﺮى )ﻫﻞ ﺳﻴﺒﻘﻰ‬


    ‫ﻋﻠﻰ ﻗﻴﺪ اﻟﺤﻴﺎﻩ ﻣﺪة ﺳﻨﻪ واﺣﺪﻩ ﻋﻠﻰ اﻷﻗﻞ أم ﻻ ؟( ‪ ،‬أﺻﻌﺐ ﺟﺰء ﻣﻦ ﻫﺬﻩ‬
    ‫اﻟﻤﺸﻜﻠﻪ ﻫﻮ اﻟﺘﻨﺒﺆ ﺑﺸﻜﻞ ﺻﺤﻴﺢ ﺑﺄن اﻟﻤﺮﻳﺾ ﻟﻦ ﻳﻨﺠﻮ )وﺣﺠﻢ ﻣﺠﻤﻮﻋﺔ‬
    ‫اﻟﺒﻴﺎﻧﺎت ﻫﻮ ﺟﺰء ﻣﻦ اﻟﺼﻌﻮﺑﻪ( ‪.‬‬
    ‫‪DataSet : Echocardiogram Data‬‬

    ‫‪2‬‬
    Number of Attributes: 12
    Attribute Information:
    1. (survival) : the number of months patient survived (has survived, if
    patient is still alive). Because all the patients had their heart attacks at
    different times, it is possible that some patients have survived less than
    one year but they are still alive. Check the second variable to confirm
    this. Such patients cannot be used for the prediction task mentioned
    above.
    2. (still-alive) : a binary variable. D=dead at end of survival period, L
    means still alive .
    3. (age at heart attack) : age in years when heart attack occurred.
    4. (pericardial effusion) : binary. Pericardial effusion is fluid. around
    the heart. 0=no luid, 1= luid .
    5.( fractional shortening ) : a measure of contracility around the heart
    lower numbers are increasingly abnormal .
    6. (epss) : E-point septal separation, another measure of contractility.
    Larger numbers are increasingly abnormal.
    7. (lvdd) : left ventricular end-diastolic dimension. This is a measure of
    the size of the heart at end-diastole. Large hearts tend to be sick hearts.
    8. (wall motion score) : a measure of how the segments of the left
    ventricle are moving .
    9.( wall motion index) : equals wall-motion-score divided by number
    of segments seen. Usually 12-13 segments are seen in an
    echocardiogram. Use this variable INSTEAD of the wall motion score.
    10. (mult) : a derivate var which can be ignored .
    11. (group) : meaningless, ignore it .
    12. (alive at one)(class) : Derived from the first two attributes.
    (N) means patient was either dead after 1 year or had
    been followed for less than 1 year. (Y) means patient
    was alive at 1 year.

    Distribution of attribute number 2: still-alive


    Value Number of instances with this value
    ---- -----------------------------------
    D 40 (dead)
    L 21 (alive)
    Total 61

    3
    Distribution of attribute number 13: alive-at-1
    Value Number of instances with this value
    ---- -----------------------------------
    N 44
    Y 17
    Total 61

    The Application :

    4
    5
    Visualize All:

    Discretize:

    6
    Apply Discretize:

    7
    Visualize All After Descrize :

    Classify Using Tree(J48) :

    8
    Select The Class Attribute :

    9
    Classify Output :

    10
    Visualize Tree:

    11
    Tree View :

    12
    Visualize Classifier Errors :

    13
    14
    Select Attributes :

    Visualize :

    15
    16
    Knowledge Flow :

    17
    18
    Model(1) :

    Result of Model(1) :

    19
    Model(2) :

    Result of Model(2) Using Text Viewer :

    20
    Result of Model(2) Using Graph Viewer :

    Result Of Model :
    Distribution of attribute number still-alive
    Value Number of instances with this value
    No = 24.0 .
    Yes = 14.0/2.0 .

    21

    You might also like