Training: AI in Medicine – from Predictive Model to Clinical Deployment
Level
IntermediateDuration
16h / 2 daysDate
Individually arrangedPrice
Individually arrangedTraining: AI in Medicine – from Predictive Model to Clinical Deployment
This intermediate-level training is designed for participants who already understand the basics of artificial intelligence and want to develop their skills in the context of healthcare applications. Participants will learn how to prepare medical data for analysis, build and train ML/DL models, interpret results, and understand how to deploy AI solutions in clinical environments—in compliance with legal and ethical regulations. The course combines theory with practice: coding in Python, working with real datasets, modeling, validation, and case studies of real-world deployments.
What will you learn?
- Medical data processing – Load, transform, and prepare data to meet AI model requirements
- Building and training AI models – Create your own predictive models in Python and evaluate their performance
- Model validation and interpretation – Learn validation methods and techniques for interpreting models in a clinical context
- AI deployment in practice – Understand how to implement AI models in healthcare facilities while ensuring compliance with regulations and ethics
Requirements
- Knowledge of Python (NumPy, Pandas, scikit-learn)
- Basic understanding of ML and neural networks
- Basic familiarity with medical data analysis (preferred: EHR, DICOM)
Who is this training for?
Developers and data analysts in the medical sector-
Data engineers and ML Ops professionals in healthcare
-
Physicians and researchers running AI projects
-
R&D employees in medtech and biotech companies
-
Participants who have completed an introductory AI training or have basic AI knowledge
Training Program
-
1. Introduction and overview of the AI pipeline in medicine
- End-to-end AI project: from data to deployment
- The role of data, model, interpretation, and integration
-
Advanced work with medical data
- Data preprocessing: EHR, CSV, DICOM
- Detecting and handling errors, gaps, and anomalies
- Data standardization according to HL7/FHIR
-
2. Building predictive models in Python (hands-on)
- Logistic regression, decision trees, random forest
- Deep learning in medical imaging
-
Working with DICOM images – segmentation, classification
- CNN basics and applications in diagnostics
-
3. Explainable AI (XAI)
- SHAP, LIME, Grad-CAM – understanding model decisions
- Examples of model interpretation on clinical datasets
-
4. Ethics and responsibility in AI
- Explainability, bias, fairness
- Case studies of model errors and their clinical consequences
-
5. Law and regulations for AI in medicine
- AI Act (EU), MDR, FDA
- Technical documentation, validation, and system registration
-
6. MLOps and model lifecycle
- Validation, retraining, model monitoring
-
7. Case studies and deployment workshop
- Case study: deploying an AI model for patient triage
- Mini-project: implementing AI in a hospital setting
