• Team Composition: Teams should consist of 2 members.
• Project Selection:
  • Option 1: Choose from a list of pre-defined project ideas provided below.
  • Option 2: Propose your own project idea, which requires approval from the course team.

Each team will:

• Implement their chosen project idea, building a model or system that addresses a specific medical data science problem.
• Evaluate their approach using appropriate metrics (accuracy, precision, recall, etc.), and compare results to existing state-of-the-art methods.
• Document their progress and findings in both a formal report and presentation.

• Objective: Define the research context by reviewing and summarising related work in the area you are addressing.
  • Action Items:
    • Conduct a thorough literature review of papers, articles, and studies relevant to your project. - 0.6
    • Summarise the current state-of-the-art methods in the field. - 0.2
    • Identify gaps in the research or areas for potential improvement. - 0.2
  • Documentation: Create a report section (minimum of 2 pages) detailing your findings, including citations of key papers and a summary of how your project will build upon or differ from existing work.

• Objective: Obtain the datasets required for your project and implement a baseline model for comparison.
  • Action Items:
    • Dataset Collection (0.6):
      • Obtain a relevant dataset, either from the provided resources or other public sources (e.g., Kaggle, UCI, Papers with Code).
      • Preprocess the data (e.g., cleaning, normalization, dealing with missing values, etc.).
    • Baseline Model (0.4):
      • Implement at least one baseline method (e.g., logistic regression, support vector machines, or a simple neural network).
      • Obtain preliminary results to compare against future improvements.
    • Evaluation Metrics: Choose appropriate metrics (e.g., accuracy, F1-score, ROC-AUC) and document initial performance.
  • Documentation: Submit a report section (minimum of 2 pages) describing the dataset, preprocessing steps, baseline model, and results.

• Objective: Implement your novel contribution to the field, either by solving a new problem or improving an existing method.
  • Types of Contributions:
    • Address a New Problem: Tackle a medical data science issue that hasn’t been addressed by related work.
    • Improve Existing Methods:
      • Improve Results: Enhance the performance of an existing solution by optimising models or experimenting with different techniques.
      • Extensive Experiments: Conduct extensive experiments to assess your model’s robustness, including testing with different datasets or under varying conditions.
      • New Approach: Introduce a new method or architecture (e.g., switching from traditional CNNs to transformers), even if it doesn’t outperform state-of-the-art methods, as long as it provides a novel perspective.
        • Examples:
          • Use a different deep learning architecture (e.g., ResNet vs. EfficientNet).
          • Apply a novel training strategy, such as self-supervised learning or data augmentation techniques.
          • Propose a hybrid model that combines multiple approaches (e.g., combining CNNs with decision trees).
  • Documentation: Write a report section (minimum of 2 pages) detailing your contribution, how it differs from existing work, and your experimental results.

• Objective: Compile your project into a well-organised academic report.
  • Action Items:
    • Write a research-style report following the IEEE conference paper format.
    • Structure:
      • Abstract: Briefly summarize your project, contributions, and key findings.
      • Introduction: Explain the problem you are addressing, motivation, and background.
      • Related Work: Include the summary from Milestone 1.
      • Methodology: Detail your approach, including algorithms, models, and techniques used.
      • Experiments: Describe the datasets, baseline methods, and results from Milestone 2.
      • Own Contribution: Document your original contribution, as outlined in Milestone 3.
      • Results and Discussion: Present detailed results with visualizations (graphs, tables) and discuss their implications.
      • Conclusion: Summarize the outcomes, limitations, and future work.
  • Documentation: Submit a polished, formal academic report in IEEE format (6-8 pages).

• Objective: Present your project and findings to the class.
  • Action Items:
    • Prepare a 10-15 minute presentation covering:
      • The problem you addressed and its relevance.
      • Key steps of your methodology.
      • Experimental results and key contributions.
      • Conclusions and potential areas for future research.
    • Create slides with clear visuals, including figures, graphs, and performance metrics.
  • Evaluation: Your presentation will be graded based on clarity, depth of explanation, and the quality of results. The final project grade will be weighted by your presentation quality.

• Total Points = (M1 + M2 + M3 + M4) x M5
  • Each milestone (M1 to M4) will be awarded a maximum of 1 point.
  • M5 (presentation) will serve as a multiplier (e.g., if your presentation quality is evaluated at 90%, the total score from M1 to M4 will be multiplied by 0.9).

• Objective: Detect posture abnormalities from videos or images and suggest exercises to correct them.
• Potential Contribution: Develop a system using deep learning (e.g., CNNs or pose estimation algorithms like OpenPose) to detect poor posture.
• Relevant work: Posture Detection.

• Objective: Identify whether a person is a smoker based on lung capacity, voice analysis, or X-ray images.
• Potential Contribution: Use CNNs for X-ray image analysis or apply audio signal processing methods to detect smoking patterns from voice recordings.
• Dataset: Gather data from publicly available voice or medical image datasets.
• Note: Each of the modalities (audio, video, image) chosen, or their combination may result in a different project, without much overlap.

• Objective: Detect retinal lesions from medical images, aiding early diagnosis of conditions like diabetic retinopathy.
• Potential Contribution: Develop a novel segmentation or classification approach using CNNs or U-Net models.
• Proposed Dataset: Retinal Lesions Dataset.

• Objective: Develop a model that identifies fractures in X-ray images, which could help radiologists in making faster diagnoses.
• Potential Contribution: Train a CNN or use a pre-trained model (e.g., ResNet) to classify fracture types.
• Proposed Datasets: MURA, RSNA etc.

• Objective: Predict whether a patient has diabetes based on features like blood glucose levels and other health indicators.
• Potential Contribution: Compare various machine learning techniques (e.g., logistic regression, decision trees, or neural networks).
• Proposed Dataset: Diabetes Dataset.

• Objective: Predict the likelihood of heart disease based on patient medical data.
• Potential Contribution: Apply feature engineering and machine learning models (random forests, logistic regression) to improve prediction accuracy.
• Proposed Dataset: UCI Heart Disease dataset.

• Objective: Predict the severity of COVID-19 cases using patient data such as demographics, clinical tests, and symptoms.
• Potential Contribution: Use gradient boosting, random forests, or deep learning to predict hospitalization risk.
• Proposed Dataset: Gather publicly available COVID-19 datasets (e.g., from Kaggle).

• Objective: Predict the progression of Alzheimer’s disease using imaging (e.g., MRI) or genetic data.
• Potential Contribution: Train deep learning models (e.g., 3D CNNs) to predict cognitive decline.
• Proposed dataset: OASIS Alzheimer's Detection.

• Objective: Detect epileptic seizures using EEG data to support automated diagnosis.
• Potential Contribution: Train machine learning models to analyze EEG signals for seizure detection.
• Proposed datasets: Here.

• Objective: -
• Potential Contribution: -
• Proposed datasets: -