rasmodev/Sepsis_Prediction_App_Streamlit

1import streamlit as st2import pickle3import pandas as pd4import numpy as np5 6# Page Title with Style7st.markdown(8    f"""9    <div style="text-align: center;">10        <h1 style="color: #800000;">🩸 Sepsis Prediction App</h1>11    </div>12    """,13    unsafe_allow_html=True14)15 16# Welcome Message with Style (Centered)17st.markdown(18    f"""19    <div style="text-align: center;">20        <p>👋 Welcome to the Sepsis Prediction App!</p>21    </div>22    """,23    unsafe_allow_html=True24)25 26# Sepsis Information27st.markdown(28    """29    **Sepsis** is a critical medical condition triggered by the body's extreme response to an infection. It can lead to organ failure and, if not detected early, poses a serious threat to life.30    """31)32 33# Link to WHO Fact Sheet on Sepsis34st.markdown("🔗 **Learn more about sepsis from [World Health Organization (WHO)](https://www.who.int/news-room/fact-sheets/detail/sepsis#:~:text=Overview,problems%20are%20at%20higher%20risk.)**")35 36st.markdown("---")37 38st.image("https://dinizululawgroup.com/wp-content/uploads/2020/07/news.jpg", width=700)39 40# Additional Information for Sample Prediction41st.write("📊 To make a sample prediction, you can refer to the training dataset information available in the sidebar.")42st.write("💉 Enter the medical data in the input fields below, then click 'Predict Sepsis', and get the patient's Sepsis status prediction.")43 44 45# About Section with Style46st.sidebar.title("ℹ️ About")47st.sidebar.info(48    "This app predicts sepsis onset using machine learning on medical data, aiding timely intervention by healthcare professionals. "49    "It utilizes a model trained on a sepsis dataset."50)51 52# Load The Train Dataset53train_df = pd.read_csv("Train.csv", index_col=None)54 55# Training Dataset Information in the sidebar56st.sidebar.markdown("📊 **Training Dataset Information:**")57st.sidebar.write("The model is trained on a sepsis dataset. Here's an overview of the dataset:")58st.sidebar.write(train_df.head())59 60# Auto-expand sidebar code61st.markdown(62    """63    <style>64        [data-testid="stSidebar"][aria-expanded="false"] > div:first-child {65            width: 100%;66        }67    </style>68    """,69    unsafe_allow_html=True70)71 72# Load the model and key components73with open('model_and_key_components.pkl', 'rb') as file:74    loaded_components = pickle.load(file)75 76loaded_model = loaded_components['model']77loaded_scaler = loaded_components['scaler']78 79# Data Fields80data_fields = {81    "**PRG**": "**Number of Pregnancies (applicable only to females)**\n   - The total number of pregnancies a female patient has experienced.",82    "**PL**": "**Plasma Glucose Concentration (mg/dL)**\n   - The concentration of glucose in the patient's blood). It provides insights into the patient's blood sugar levels.",83    "**PR**": "**Diastolic Blood Pressure (mm Hg)**\n   - The diastolic blood pressure, representing the pressure in the arteries when the heart is at rest between beats.",84    "**SK**": "**Triceps Skinfold Thickness (mm)**\n   - The thickness of the skinfold on the triceps, measured in millimeters (mm). This measurement is often used to assess body fat percentage.",85    "**TS**": "**2-hour Serum Insulin (mu U/ml)**\n   - The level of insulin in the patient's blood two hours after a meal, measured in micro international units per milliliter (mu U/ml).",86    "**M11**": "**Body Mass Index (BMI) (weight in kg / {(height in m)}^2)**\n   - BMI provides a standardized measure that helps assess the degree of body fat and categorizes individuals into different weight status categories, such as underweight, normal weight, overweight, and obesity.",87    "**BD2**": "**Diabetes pedigree function (mu U/ml)**\n   - The function provides information about the patient's family history of diabetes.",88    "**Age**": "**Age of the Patient (years)**\n   - Age is an essential factor in medical assessments and can influence various health outcomes."89}90# Organize input fields into two columns91col1, col2 = st.columns(2)92 93# Initialize input_data dictionary94input_data = {}95 96# Function to preprocess input data97def preprocess_input_data(input_data):98    numerical_cols = ['PRG', 'PL', 'PR', 'SK', 'TS', 'M11', 'BD2', 'Age']99    input_data_scaled = loaded_scaler.transform([list(input_data.values())])100    return pd.DataFrame(input_data_scaled, columns=numerical_cols)101 102# Function to make predictions103def make_predictions(input_data_scaled_df):104    y_pred = loaded_model.predict(input_data_scaled_df)105    sepsis_mapping = {0: 'Negative', 1: 'Positive'}106    return sepsis_mapping[y_pred[0]]107 108# Input Data Fields in two columns109with col1:110    input_data["PRG"] = st.slider("PRG: Number of Pregnancies", 0, 20, 0)111    input_data["PL"] = st.number_input("PL: Plasma Glucose Concentration (mg/dL)", value=0.0)112    input_data["PR"] = st.number_input("PR: Diastolic Blood Pressure (mm Hg)", value=0.0)113    input_data["SK"] = st.number_input("SK: Triceps Skinfold Thickness (mm)", value=0.0)114 115with col2:116    input_data["TS"] = st.number_input("TS: 2-Hour Serum Insulin (mu U/ml)", value=0.0)117    input_data["M11"] = st.number_input("M11: Body Mass Index (BMI)", value=0.0)118    input_data["BD2"] = st.number_input("BD2: Diabetes Pedigree Function (mu U/ml)", value=0.0)119    input_data["Age"] = st.slider("Age: Age of the patient (years)", 0, 100, 0)120 121# Predict Button with Style122if st.button("🔮 Predict Sepsis"):123    try:124        input_data_scaled_df = preprocess_input_data(input_data)125        sepsis_status = make_predictions(input_data_scaled_df)126        127        # Display the sepsis prediction and risk128        if sepsis_status == 'Negative':129            st.success(f"The patient is at **low risk** of developing sepsis. The predicted sepsis status is: **{sepsis_status}**")130        elif sepsis_status == 'Positive':131            st.error(f"**The patient is at **high risk** of developing sepsis. The predicted sepsis status is: **{sepsis_status}**")132 133        # Add the sepsis prediction to the input DataFrame134        input_data['Sepsis'] = sepsis_status135 136        # Convert the input data to a pandas DataFrame137        input_df = pd.DataFrame([input_data])138 139        # Display the input DataFrame140        st.markdown(141            f"""142            <div style="text-align: center; font-size: 18px; font-weight: bold;">143                <p>Input Data with Sepsis Prediction</p>144            </div>145            """,146            unsafe_allow_html=True147        )148        st.table(input_df)149 150    except Exception as e:151        st.error(f"An error occurred: {e}")152 153# Display Data Fields and Descriptions154st.sidebar.title("🔍 Data Fields")155for field, description in data_fields.items():156    st.sidebar.markdown(f"{field}: {description}")157 158# Copyright statement at the bottom159st.markdown(160    """161    <div style="text-align:center">162        Developed by <a href="https://www.linkedin.com/in/rasmo-/" style="font-style:italic">Rasmo Wanyama</a>.163    </div>164    """,165    unsafe_allow_html=True166)167 168st.stop()169