Upload 25 files

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+static/images/back1.jpg filter=lfs diff=lfs merge=lfs -text
+static/images/back3.jpg filter=lfs diff=lfs merge=lfs -text
+static/images/back5.jpg filter=lfs diff=lfs merge=lfs -text
+static/images/back6.jpg filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,173 @@
+from flask import Flask, request, jsonify, render_template
+import torch
+from torchvision import transforms
+from PIL import Image
+import os
+import torch.nn as nn
+import timm
+from torchvision.models import swin_t, Swin_T_Weights, vit_b_16, ViT_B_16_Weights
+from transformers import GPT2LMHeadModel, GPT2Tokenizer
+
+app = Flask(__name__)
+
+# Set up directories for uploads and models
+UPLOAD_FOLDER = os.path.join('static', 'uploads')
+app.config['UPLOAD_FOLDER'] = UPLOAD_FOLDER
+
+# Device configuration
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+
+# Load the LLM model and tokenizer
+model = GPT2LMHeadModel.from_pretrained('models\\LLM').to(device)
+tokenizer = GPT2Tokenizer.from_pretrained('models\\LLM')
+separator_token = tokenizer.eos_token  # Separator token for the model
+
+# Define and load the pre-trained Swin models
+
+# Gastrointestinal Model (4 classes: Diverticulosis, Neoplasm, Peritonitis, Ureters)
+gastrointestinal_classes = ['Diverticulosis', 'Neoplasm', 'Peritonitis', 'Ureters']
+gastrointestinal_model = timm.create_model('swin_base_patch4_window7_224', pretrained=True)
+gastrointestinal_model.head = nn.Linear(gastrointestinal_model.head.in_features, len(gastrointestinal_classes))
+gastrointestinal_model = gastrointestinal_model.to(device)
+gastrointestinal_model.load_state_dict(torch.load('models\\gastrointestinal_model_swin.pth', map_location=device, weights_only=True), strict=False)
+gastrointestinal_model.eval()
+
+# Chest CT Model (4 classes: Adenocarcinoma, Large cell carcinoma, Normal, Squamous cell carcinoma)
+chest_ct_classes = ['Adenocarcinoma', 'Large Cell Carcinoma', 'Normal', 'Squamous Cell Carcinoma']
+chest_ct_model = swin_t(weights=Swin_T_Weights.IMAGENET1K_V1)
+chest_ct_model.head = nn.Linear(chest_ct_model.head.in_features, len(chest_ct_classes))
+chest_ct_model = chest_ct_model.to(device)
+chest_ct_model.load_state_dict(torch.load('models\\best_model.pth', map_location=device, weights_only=True), strict=False)
+chest_ct_model.eval()
+
+# Chest X-ray Model (2 classes: Normal, Pneumonia)
+chest_xray_classes = ['Normal', 'Pneumonia']
+chest_xray_model = vit_b_16(weights=ViT_B_16_Weights.IMAGENET1K_V1)
+chest_xray_model.heads.head = nn.Linear(chest_xray_model.heads.head.in_features, len(chest_xray_classes))
+chest_xray_model = chest_xray_model.to(device)
+chest_xray_model.load_state_dict(torch.load('models\\best_model_vit_chest_xray.pth', map_location=device, weights_only=True), strict=False)
+chest_xray_model.eval()
+
+# Image transformation (same for all models)
+transform = transforms.Compose([
+    transforms.Resize((224, 224)),
+    transforms.ToTensor(),
+    transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
+])
+
+
+# Helper function to load and transform images
+def process_image(image_path):
+    image = Image.open(image_path).convert('RGB')
+    return transform(image).unsqueeze(0).to(device)
+
+# LLM helper function to generate answers
+def generate_answer(question, max_length=1024):
+    model.eval()  # Set the model to evaluation mode
+    input_text = question + separator_token
+    input_ids = tokenizer.encode(input_text, return_tensors='pt').to(device)
+
+    output = model.generate(input_ids, max_length=max_length, pad_token_id=tokenizer.eos_token_id)
+    answer = tokenizer.decode(output[:, input_ids.shape[-1]:][0], skip_special_tokens=True)
+    return answer
+
+# Prediction routes for each model
+@app.route('/predict_gastrointestinal', methods=['POST'])
+def predict_gastrointestinal():
+    if 'file' not in request.files:
+        return jsonify({"error": "No file uploaded"}), 400
+    
+    file = request.files['file']
+    file_path = os.path.join(app.config['UPLOAD_FOLDER'], file.filename)
+    file.save(file_path)
+
+    # Preprocess the image
+    image_tensor = process_image(file_path)
+
+    # Make prediction using the gastrointestinal model
+    with torch.no_grad():
+        output = gastrointestinal_model(image_tensor)
+        
+        # Ensure the output tensor has the right shape and handle it
+        
+        # If the output has extra dimensions, flatten it
+        if len(output.shape) > 2:
+            output = output.view(output.size(0), -1)
+
+        # Check if output is for a batch or single sample
+        if output.size(0) != 1:
+            return jsonify({"error": "Unexpected output size"}), 500
+        
+        # Get the predicted class (ensure it's scalar)
+        _, predicted = torch.max(output, 1)
+        predicted_class = gastrointestinal_classes[predicted.item()]
+
+    return jsonify({'prediction': predicted_class})
+
+
+@app.route('/predict_chest_ct', methods=['POST'])
+def predict_chest_ct():
+    if 'file' not in request.files:
+        return jsonify({"error": "No file uploaded"}), 400
+    
+    file = request.files['file']
+    file_path = os.path.join(app.config['UPLOAD_FOLDER'], file.filename)
+    file.save(file_path)
+
+    # Preprocess the image
+    image_tensor = process_image(file_path)
+
+    # Make prediction using the chest CT model
+    with torch.no_grad():
+        output = chest_ct_model(image_tensor)
+        _, predicted = torch.max(output, 1)
+        predicted_class = chest_ct_classes[predicted.item()]
+
+    return jsonify({'prediction': predicted_class})
+
+
+@app.route('/predict_chest_xray', methods=['POST'])
+def predict_chest_xray():
+    if 'file' not in request.files:
+        return jsonify({"error": "No file uploaded"}), 400
+    
+    file = request.files['file']
+    file_path = os.path.join(app.config['UPLOAD_FOLDER'], file.filename)
+    file.save(file_path)
+
+    # Preprocess the image
+    image_tensor = process_image(file_path)
+
+    # Make prediction using the chest X-ray model
+    with torch.no_grad():
+        output = chest_xray_model(image_tensor)
+        _, predicted = torch.max(output, 1)
+        predicted_class = chest_xray_classes[predicted.item()]
+
+    return jsonify({'prediction': predicted_class})
+
+
+# New LLM route for asking questions
+@app.route('/ask_llm', methods=['POST'])
+def ask_llm():
+    user_question = request.json.get('question', None)
+    
+    if not user_question:
+        return jsonify({"error": "No question provided"}), 400
+    
+    try:
+        # Generate answer using the fine-tuned GPT-2 model
+        answer = generate_answer(user_question)
+    except Exception as e:
+        return jsonify({"error": f"An error occurred: {str(e)}"}), 500
+
+    return jsonify({'answer': answer})
+
+
+# Main route for the homepage
+@app.route('/')
+def index():
+    return render_template('index.html')
+
+if __name__ == "__main__":
+    app.run(debug=True)

models/LLM/config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "distilgpt2",
+  "_num_labels": 1,
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 6,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

models/LLM/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.44.2"
+}

models/LLM/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be1dd397ce1983f5a553f6c5f9aa65f22260e75a8ba77ebf91ee75c6dcac2118
+size 327657928

models/LLM/special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

models/LLM/tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

models/chest_ct_model_swin.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:789bda3e8a7908341b793cff4d88dc01b823953a076eab42ba9c8fc26018d9cc
+size 110386359

models/chest_xray_vit.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc43ca56aeb7922c689380f34c020f1bb88859511e159c4b47a5a7155b4a48be
+size 343263994

models/gastrointestinal_model_swin.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc0180d6a9c4bc375fa20cf52adbecffeb274c8f285768fe96e31985532b47c8
+size 347124772

static/styles.css

@@ -0,0 +1,184 @@
+/* General Styles */
+body {
+    margin: 0;
+    font-family: Arial, sans-serif;
+    background-color: #f0f8ff;
+    background-image: url('/static/images/back3.jpg');
+    background-size: cover;
+    background-position: center;
+    animation: backgroundChange 15s infinite;
+}
+
+button, .research-link, .case-report-link, input[type="file"] {
+    background-color: #4682b4; 
+    color: white; 
+    padding: 10px 20px;
+    border: none;
+    border-radius: 5px;
+    cursor: pointer;
+    font-size: 16px;
+    transition: background-color 0.3s ease;
+}
+
+button:hover, .research-link:hover, .case-report-link:hover, input[type="file"]:hover {
+    background-color: #03355e;
+}
+
+.container {
+    text-align: center;
+    padding: 50px;
+}
+
+h1 {
+    font-size: 2.5em;
+    color: #00000022;
+    margin-bottom: 20px;
+}
+
+/* Tab Styles */
+.tabs {
+    display: flex;
+    justify-content: center;
+    margin-bottom: 20px;
+}
+
+.tab-button {
+    background-color: #4682b4;
+    color: rgb(0, 0, 0);
+    border: none;
+    padding: 10px 20px;
+    margin: 0 5px;
+    cursor: pointer;
+    font-size: 1.1em;
+    transition: background-color 0.3s ease;
+}
+
+.tab-button:hover {
+    background-color: #03355e;
+}
+
+.tab-button.active {
+    background-color: #ffffff;
+}
+
+.tab-content {
+    display: none;
+}
+
+.tab-content.active {
+    display: block;
+}
+
+form {
+    margin-bottom: 20px;
+}
+
+label {
+    font-size: 1.2em;
+}
+
+input[type="file"], input[type="text"] {
+    margin: 10px 0;
+    padding: 10px;
+    width: 100%;
+    max-width: 500px;
+    border: 1px solid #ccc;
+    border-radius: 5px;
+}
+
+button[type="submit"], button[type="button"] {
+    background-color: #5a9bd4;
+    color: white;
+    padding: 10px 20px;
+    border: none;
+    font-size: 1.1em;
+    cursor: pointer;
+    transition: background-color 0.3s ease;
+}
+
+button:hover {
+    background-color: #03355e;
+}
+
+/* Prediction Result */
+.prediction-result {
+    margin-top: 20px;
+    font-size: 1.5em;
+    color: #000000;
+    opacity: 1;
+}
+
+/* Dropdown Links Styling */
+.resources ul {
+    list-style-type: none;
+    padding: 0;
+    margin: 0;
+}
+
+.resources ul li {
+    margin: 5px 0;
+}
+
+.resources ul li a {
+    background-color: #f9a825; /* Bright yellow background */
+    color: white; /* White text */
+    padding: 10px;
+    border-radius: 5px;
+    text-decoration: none;
+    display: block;
+    transition: background-color 0.3s ease;
+}
+
+.resources ul li a:hover {
+    background-color: #f57f17; /* Darker yellow on hover */
+}
+
+/* Adding space between prediction result and research buttons */
+.prediction-result {
+    margin-bottom: 20px; /* Adding space below the prediction result */
+}
+
+
+/* LLM Prompt Bar */
+.llm-prompt-bar {
+    position: fixed;
+    bottom: 0;
+    width: 100%;
+    background-color: #333;
+    padding: 10px;
+    text-align: center;
+}
+
+.llm-prompt-bar input[type="text"] {
+    width: 70%;
+    padding: 10px;
+    font-size: 1.1em;
+    border: none;
+    border-radius: 5px;
+}
+
+.llm-prompt-bar button {
+    background-color: #5a9bd4;
+    color: white;
+    padding: 10px 20px;
+    border: none;
+    cursor: pointer;
+    font-size: 1.1em;
+}
+
+.llm-prompt-bar button:hover {
+    background-color: #03355e;
+}
+
+/* Background Change Animation */
+@keyframes backgroundChange {
+    0% {
+        background-image: url('/static/images/back5.jpg');
+    }
+    50% {
+        background-image: url('/static/images/back6.jpg');
+    }
+    100% {
+        background-image: url('/static/images/back7.jpg');
+    }
+}

templates/index.html

@@ -0,0 +1,301 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>AI Health Assistant</title>
+    <link rel="stylesheet" href="{{ url_for('static', filename='styles.css') }}">
+    <style>
+        /* Additional styles for dropdown functionality */
+        .dropdown {
+            position: relative;
+            display: inline-block;
+        }
+
+        .dropdown-content {
+            display: none;
+            position: absolute;
+            background-color: #10477d;
+            box-shadow: 0px 8px 16px 0px rgba(0,0,0,0.2);
+            z-index: 1;
+        }
+
+        .dropdown-content a {
+            color: black;
+            padding: 12px 16px;
+            text-decoration: none;
+            display: block;
+        }
+
+        .dropdown-content a:hover {
+            background-color: #f1f1f153;
+        }
+
+        .dropdown:hover .dropdown-content {
+            display: block;
+        }
+
+        .dropdown:hover .dropbtn {
+            background-color: #072d4d;
+        }
+    </style>
+</head>
+<body>
+    <div class="container">
+        <h1>AI Health Assistant</h1>
+
+        <!-- Tab Buttons -->
+        <div class="tabs">
+            <button class="tab-button active" data-target="gastrointestinal">Gastrointestinal Disease Prediction</button>
+            <button class="tab-button" data-target="chest_ct">Chest CT Disease Prediction</button>
+            <button class="tab-button" data-target="chest_xray">Chest X-ray Disease Prediction</button>
+            <button class="tab-button" data-target="llm">Chat</button>
+        </div>
+
+        <!-- Gastrointestinal Model Form -->
+        <div id="gastrointestinal" class="tab-content active">
+            <h2>Upload Image for Gastrointestinal Disease Prediction</h2>
+            <form id="gastrointestinal-form" enctype="multipart/form-data">
+                <label for="file">Select Image:</label>
+                <input type="file" name="file" id="gastrointestinal-file" required>
+                <button type="button" onclick="predictDisease('gastrointestinal')">Predict</button>
+            </form>
+            <div class="prediction-result" id="gastrointestinal-result"></div>
+
+            <!-- Dropdown for Research Links -->
+            <div class="dropdown">
+                <button class="dropbtn">Research Papers</button>
+                <div class="dropdown-content" id="gastrointestinal-research-links"></div>
+            </div>
+            <!-- Dropdown for Case Reports -->
+            <div class="dropdown">
+                <button class="dropbtn">Case Reports</button>
+                <div class="dropdown-content" id="gastrointestinal-case-report-links"></div>
+            </div>
+        </div>
+
+        <!-- Chest CT Model Form -->
+        <div id="chest_ct" class="tab-content">
+            <h2>Upload Image for Chest CT Disease Prediction</h2>
+            <form id="chest_ct-form" enctype="multipart/form-data">
+                <label for="file">Select Image:</label>
+                <input type="file" name="file" id="ct-file" required>
+                <button type="button" onclick="predictDisease('chest_ct')">Predict</button>
+            </form>
+            <div class="prediction-result" id="chest_ct-result"></div>
+
+            <!-- Dropdown for Research Links -->
+            <div class="dropdown">
+                <button class="dropbtn">Research Papers</button>
+                <div class="dropdown-content" id="chest_ct-research-links"></div>
+            </div>
+            <!-- Dropdown for Case Reports -->
+            <div class="dropdown">
+                <button class="dropbtn">Case Reports</button>
+                <div class="dropdown-content" id="chest_ct-case-report-links"></div>
+            </div>
+        </div>
+
+        <!-- Chest X-ray Model Form -->
+        <div id="chest_xray" class="tab-content">
+            <h2>Upload Image for Chest X-ray Disease Prediction</h2>
+            <form id="chest_xray-form" enctype="multipart/form-data">
+                <label for="file">Select Image:</label>
+                <input type="file" name="file" id="xray-file" required>
+                <button type="button" onclick="predictDisease('chest_xray')">Predict</button>
+            </form>
+            <div class="prediction-result" id="chest_xray-result"></div>
+
+            <!-- Dropdown for Research Links -->
+            <div class="dropdown">
+                <button class="dropbtn">Research Papers</button>
+                <div class="dropdown-content" id="chest_xray-research-links"></div>
+            </div>
+            <!-- Dropdown for Case Reports -->
+            <div class="dropdown">
+                <button class="dropbtn">Case Reports</button>
+                <div class="dropdown-content" id="chest_xray-case-report-links"></div>
+            </div>
+        </div>
+
+        <!-- Chat with LLM -->
+        <div id="llm" class="tab-content">
+            <h2>Ask the AI Health Assistant</h2>
+            <div id="llm-answer"></div>
+        </div>
+    </div>
+
+    <!-- LLM Prompt Bar at the Bottom -->
+    <div class="llm-prompt-bar">
+        <input type="text" id="llm-prompt" placeholder="Ask your question here...">
+        <button onclick="askLLM()">Ask</button>
+    </div>
+
+    <!-- Scripts -->
+    <script>
+        const researchLinks = {
+            'Diverticulosis': {
+                papers: [
+                    { title: 'Diverticulosis Research Paper 1', url: 'https://www.ncbi.nlm.nih.gov/books/NBK430771/' },
+                    { title: 'Diverticulosis Research Paper 2', url: 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10410187/' }
+                ],
+                reports: [
+                    { title: 'Diverticulosis Case Report 1', url: 'https://jmedicalcasereports.biomedcentral.com/articles/10.1186/1752-1947-4-172' },
+                    { title: 'Diverticulosis Case Report 2', url: 'https://wjes.biomedcentral.com/articles/10.1186/1749-7922-3-10' },
+                    { title: 'Diverticulosis Case Report 3', url: 'https://www.sciencedirect.com/science/article/pii/S2210261223000743' }
+                ]
+            },
+            'Neoplasm': {
+                papers: [
+                    { title: 'Neoplasm Research Paper 1', url: 'https://www.sciencedirect.com/topics/pharmacology-toxicology-and-pharmaceutical-science/neoplasm' },
+                    { title: 'Neoplasm Research Paper 2', url: 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9846320/' }
+                ],
+                reports: [
+                    { title: 'Neoplasm Case Report 1', url: 'https://bmcwomenshealth.biomedcentral.com/articles/10.1186/s12905-022-01766-2' },
+                    { title: 'Neoplasm Case Report 2', url: 'https://issoonline.biomedcentral.com/articles/10.1186/1477-7800-6-6' },
+                    { title: 'Neoplasm Case Report 3', url: 'https://wjso.biomedcentral.com/articles/10.1186/1477-7819-5-98' }
+                ]
+            },
+            'Peritonitis': {
+                papers: [
+                    { title: 'Peritonitis Research Paper 1', url: 'https://my.clevelandclinic.org/health/diseases/17831-peritonitis' },
+                    { title: 'Peritonitis Research Paper 2', url: 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7152366/' }
+                ],
+                reports: [
+                    { title: 'Peritonitis Case Report 1', url: 'https://pubmed.ncbi.nlm.nih.gov/11396540/' },
+                    { title: 'Peritonitis Case Report 2', url: 'https://bmcinfectdis.biomedcentral.com/articles/10.1186/1471-2334-13-S1-P34' },
+                    { title: 'Peritonitis Case Report 3', url: 'https://ccforum.biomedcentral.com/articles/10.1186/cc12906' }
+                ]
+            },
+            'Ureters': {
+                papers: [
+                    { title: 'Ureters Research Paper 1', url: 'https://www.sciencedirect.com/topics/medicine-and-dentistry/ureter-disease' },
+                    { title: 'Ureters Research Paper 2', url: 'https://www.ncbi.nlm.nih.gov/books/NBK507817/' }
+                ],
+                reports: [
+                    { title: 'Ureters Case Report 1', url: 'https://bmcurol.biomedcentral.com/articles/10.1186/1471-2490-12-35' },
+                    { title: 'Ureters Case Report 2', url: 'https://bmcurol.biomedcentral.com/articles/10.1186/s12894-018-0396-6' },
+                    { title: 'Ureters Case Report 3', url: 'https://bmcurol.biomedcentral.com/articles/10.1186/s12894-018-0396-6' }
+                ]
+            },
+            'Large Cell Carcinoma': {
+                papers: [
+                    { title: 'Large Cell Carcinoma Research Paper 1', url: 'https://www.sciencedirect.com/topics/pharmacology-toxicology-and-pharmaceutical-science/large-cell-carcinoma' },
+                    { title: 'Large Cell Carcinoma Research Paper 2', url: 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4531643/' }
+                ],
+                reports: [
+                    { title: 'Large Cell Carcinoma Case Report 1', url: 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7481563/' },
+                    { title: 'Large Cell Carcinoma Case Report 2', url: 'https://wjso.biomedcentral.com/articles/10.1186/1477-7819-11-205' },
+                    { title: 'Large Cell Carcinoma Case Report 3', url: 'https://cardiothoracicsurgery.biomedcentral.com/articles/10.1186/s13019-023-02349-4' }
+                ]
+            },
+            'Adenocarcinoma': {
+                papers: [
+                    { title: 'Adenocarcinoma Research Paper 1', url: 'https://www.ncbi.nlm.nih.gov/books/NBK562137/' },
+                    { title: 'Adenocarcinoma Research Paper 2', url: 'https://biolres.biomedcentral.com/articles/10.1186/s40659-020-00281-8' }
+                ],
+                reports: [
+                    { title: 'Adenocarcinoma Case Report 1', url: 'https://hccpjournal.biomedcentral.com/articles/10.1186/1897-4287-8-S1-P4' },
+                    { title: 'Adenocarcinoma Case Report 2', url: 'https://cancerandmetabolism.biomedcentral.com/articles/10.1186/2049-3002-2-S1-P76' },
+                    { title: 'Adenocarcinoma Case Report 3', url: 'https://biologydirect.biomedcentral.com/articles/10.1186/s13062-023-00419-0' }
+                ]
+            },
+            'Squamous Cell Carcinoma': {
+                papers: [
+                    { title: 'Squamous Cell Carcinoma Research Paper 1', url: 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7319751/' },
+                    { title: 'Squamous Cell Carcinoma Research Paper 2', url: 'https://www.ncbi.nlm.nih.gov/books/NBK441939/' }
+                ],
+                reports: [
+                    { title: 'Squamous Cell Carcinoma Case Report 1', url: 'https://headandneckoncology.biomedcentral.com/articles/10.1186/1758-3284-1-S1-P32' },
+                    { title: 'Squamous Cell Carcinoma Case Report 2', url: 'https://headandneckoncology.biomedcentral.com/articles/10.1186/1758-3284-1-S1-P17' },
+                    { title: 'Squamous Cell Carcinoma Case Report 3', url: 'https://bmcproc.biomedcentral.com/articles/10.1186/1753-6561-7-S2-P25' }
+                ]
+            },
+            'Pneumonia': {
+                papers: [
+                    { title: 'Pneumonia Research Paper 1', url: 'https://www.who.int/news-room/fact-sheets/detail/pneumonia' },
+                    { title: 'Pneumonia Research Paper 2', url: 'https://www.ncbi.nlm.nih.gov/books/NBK513321/' }
+                ],
+                reports: [
+                    { title: 'Pneumonia Case Report 1', url: 'https://waojournal.biomedcentral.com/articles/10.1186/1939-4551-6-S1-P56' },
+                    { title: 'Pneumonia Case Report 2', url: 'https://ccforum.biomedcentral.com/articles/10.1186/cc12928' },
+                    { title: 'Pneumonia Case Report 3', url: 'https://waojournal.biomedcentral.com/articles/10.1186/1939-4551-6-S1-P191' }
+                ]
+            }
+            // Other disease links remain the same
+        };
+
+        // JavaScript to handle tab switching
+        const tabButtons = document.querySelectorAll('.tab-button');
+        const tabContents = document.querySelectorAll('.tab-content');
+
+        tabButtons.forEach(button => {
+            button.addEventListener('click', () => {
+                tabButtons.forEach(btn => btn.classList.remove('active'));
+                tabContents.forEach(content => content.classList.remove('active'));
+
+                button.classList.add('active');
+                document.getElementById(button.dataset.target).classList.add('active');
+            });
+        });
+
+        // Function to make predictions
+        function predictDisease(diseaseType) {
+            console.log('Predicting for: ' + diseaseType); // Add this for debugging
+            let formData = new FormData(document.getElementById(diseaseType + '-form'));
+            fetch(`/predict_${diseaseType}`, {
+                method: 'POST',
+                body: formData
+            })
+            .then(response => response.json())
+            .then(data => {
+                document.getElementById(diseaseType + '-result').innerText = data.prediction;
+                populateLinks(data.prediction, diseaseType); // Pass diseaseType to populateLinks
+            })
+            .catch(error => {
+                console.error('Error:', error);
+            });
+        }
+
+
+        // Populate the research and case report links
+        function populateLinks(prediction, diseaseType) {
+            const links = researchLinks[prediction.trim()];
+            const researchLinksDiv = document.getElementById(diseaseType + '-research-links');
+            const caseReportLinksDiv = document.getElementById(diseaseType + '-case-report-links');
+
+            if (links) {
+                researchLinksDiv.innerHTML = links.papers.map(paper => `<a href="${paper.url}" target="_blank">${paper.title}</a>`).join('');
+                caseReportLinksDiv.innerHTML = links.reports.map(report => `<a href="${report.url}" target="_blank">${report.title}</a>`).join('');
+            } else {
+                researchLinksDiv.innerHTML = '<p>No research papers available for this prediction</p>';
+                caseReportLinksDiv.innerHTML = '<p>No case reports available for this prediction</p>';
+            }
+
+        }
+
+
+        // JavaScript function to ask the LLM
+        function askLLM() {
+            const question = document.getElementById('llm-prompt').value;
+            const answerContainer = document.getElementById('llm-answer');
+
+            fetch('/ask_llm', {
+                method: 'POST',
+                headers: {
+                    'Content-Type': 'application/json',
+                },
+                body: JSON.stringify({ question: question }),
+            })
+            .then(response => response.json())
+            .then(data => {
+                answerContainer.innerHTML = `<h3>Answer: ${data.answer}</h3>`;
+            })
+            .catch(error => {
+                console.error('Error:', error);
+                answerContainer.innerHTML = '<h3>Error: Unable to fetch answer</h3>';
+            });
+        }
+    </script>
+</body>
+</html>