Scribd Logo
Upload

Welcome to Scribd!

  • 2 views

    05_AIHC_Exp04

    Uploaded by

    laxitac115

    Copyright:

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

    05_AIHC_Exp04

    Uploaded by

    laxitac115
    2 views8 pages

    Copyright

    © © All Rights Reserved

    Available Formats

    DOCX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd
    Download as docx, pdf, or txt
    2 views8 pages

    05_AIHC_Exp04

    Uploaded by

    laxitac115

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd
    Download as docx, pdf, or txt
    You are on page 1of 8

    Vidyavardhini’s College of Engineering & Technology

    Name: Durvesh Kajrekar


    Class: BE/CSE-DS
    Experiment No. 4

    AIfor Disease Prognosis


    Date of Performance: 23/8/24
    Date of Submission: 30/8/24

    HAIMLSBL701 AI&ML in Healthcare Lab


    Vidyavardhini’s College of Engineering & Technology

    Aim: To perform AI for prognosis of a diseases

    Objective: The objective of this experiment is to develop an AI-powered disease prognosis


    system that employs advanced machine learning algorithms, specifically convolutional neural
    networks (CNNs) for medical imaging and recurrent neural networks (RNNs) for time series
    data.

    Theory:
    The objective of using AI for the prognosis of diseases is to improve the accuracy and
    effectiveness of disease prediction, allowing for earlier and more precise diagnoses and
    treatment. AI can be a valuable tool in healthcare for a variety of purposes related to disease
    prognosis:

    1. Early Detection: Detects diseases or medical conditions at an earlier stage when


    treatment is more effective, potentially saving lives and reducing the severity of the
    disease's impact.

    2. Risk Assessment: Assess an individual's risk of developing a particular disease based


    on a range of factors, such as genetics, lifestyle, and medical history.

    3. Personalized Medicine: Tailor treatment plans to individual patients based on their


    unique characteristics and needs, improving the effectiveness of treatments and
    reducing side effects.

    4. Predictive Analytics: Use historical patient data to predict disease outcomes and
    recommend appropriate interventions or treatments.

    5. Resource Allocation: Optimize healthcare resource allocation by identifying patients


    at higher risk and allocating resources accordingly. This can be especially important
    in resource-constrained healthcare systems.

    6. Patient Engagement: Engage patients in their own healthcare by providing them with
    personalized health insights and recommendations.

    7. Reducing Healthcare Costs: Improve the efficiency of healthcare systems by reducing


    unnecessary tests and treatments through more accurate prognosis and diagnosis.

    8. Research and Drug Development: Assist researchers in identifying potential drug


    candidates or treatment strategies based on AI analysis of disease pathways and
    patient data.

    9. Public Health Planning: Help public health officials and organizations plan for disease
    outbreaks, resource allocation, and prevention strategies.

    10. Chronic Disease Management: Aid in the management of chronic diseases by


    providing ongoing monitoring and early warnings of potential complications.

    HAIMLSBL701 AI&ML in Healthcare Lab


    Vidyavardhini’s College of Engineering & Technology

    11. Telemedicine: Enable remote monitoring and diagnosis, particularly in underserved or


    remote areas.

    12. Quality of Life Improvement: Enhance the quality of life for patients by enabling
    proactive and preventive healthcare rather than just reactive treatment.

    In summary, the primary objective of using AI for disease prognosis is to improve healthcare
    outcomes, reduce costs, and enhance the overall quality of care by providing more accurate,
    personalized, and timely information to healthcare providers, researchers, and patients. AI
    has the potential to transform the healthcare industry by making disease prognosis and
    management more data-driven and patient-centric.

    Code:
    import pandas as pd
    import numpy as np
    import seaborn as sns
    import matplotlib.pyplot as plt
    from sklearn.metrics import confusion_matrix,accuracy_score
    %matplotlib inline

    HAIMLSBL701 AI&ML in Healthcare Lab


    Vidyavardhini’s College of Engineering & Technology

    #histogram
    df.hist(bins=10,figsize=(10,10))
    plt.show()

    HAIMLSBL701 AI&ML in Healthcare Lab


    Vidyavardhini’s College of Engineering & Technology

    #correlation
    sns.heatmap(df.corr())

    sns.countplot(y=df['Outcome'],palette='Set1')

    #box plot for outlier visualization

    HAIMLSBL701 AI&ML in Healthcare Lab


    Vidyavardhini’s College of Engineering & Technology

    sns.set(style="whitegrid")
    df.boxplot(figsize=(15,6))

    #box plot
    sns.set(style="whitegrid")
    sns.set(rc={'figure.figsize':(4,2)})
    sns.boxplot(x=df['Insulin'])
    plt.show()
    sns.boxplot(x=df['BloodPressure'])
    plt.show()
    sns.boxplot(x=df['DiabetesPedigreeFunction'])
    plt.show()

    #outlier remove
    Q1=df.quantile(0.25)

    HAIMLSBL701 AI&ML in Healthcare Lab


    Vidyavardhini’s College of Engineering & Technology

    Q3=df.quantile(0.75)
    IQR=Q3-Q1
    print("---Q1--- \n",Q1)
    print("\n---Q3--- \n",Q3)
    print("\n---IQR---\n",IQR)
    #print((df < (Q1 - 1.5 * IQR))|(df > (Q3 + 1.5 * IQR)))

    X=df_out.drop(columns=['Outcome'])
    y=df_out['Outcome']
    from sklearn.model_selection import train_test_split
    train_X,test_X,train_y,test_y=train_test_split(X,y,test_size=0.2)
    train_X.shape,test_X.shape,train_y.shape,test_y.shape

    HAIMLSBL701 AI&ML in Healthcare Lab


    Vidyavardhini’s College of Engineering & Technology

    Google Collaboratory Link:


    https://colab.research.google.com/drive/1cuVLZXp2-yyZS1mH4dv_qpo9hm5d9h7m?
    usp=sharing

    Conclusion:
    Comment on how useful it is to use AI for prognosis of a disease.
    AI may be used to find patterns in enormous volumes of medical data, aiding in disease
    prediction and prevention before symptoms appear. Diagnoses may reduce treatment costs by
    up to 50% and improve health outcomes by 40% and also reduce human errors.

    HAIMLSBL701 AI&ML in Healthcare Lab

    You might also like