Training: AI in Medicine – Fundamentals
Level
BeginnerDuration
16h / 2 daysDate
Individually arrangedPrice
Individually arrangedTraining: AI in Medicine – Fundamentals
The AI in Medicine – Fundamentals course is an intensive two-day training that combines theory with practice, focusing on real applications of artificial intelligence in healthcare. Participants will learn the basics of AI, machine learning (ML), and deep learning (DL), understand how to use ready-made tools without the need for programming, and discover how to analyze medical data, diagnostic images, and predict clinical events. The training introduces participants to the world of AI in a medical context. It covers an overview of AI applications in diagnostics, medical image analysis, disease prediction, and clinical decision support.
What will you learn?
- AI fundamentals – Understand the differences between AI, ML, and DL, and how these technologies work in medicine
- AI applications in healthcare – Learn how AI supports diagnostics, medical image analysis, disease risk prediction, and clinical decision support
- Challenges with medical data – Learn how to prepare data for AI analysis, identify errors, and handle sensitive data properly
- Ethical and legal aspects – Understand the challenges AI faces in healthcare, including accountability, legal regulations, and privacy issues
Requirements
- Basic knowledge of Python programming
- Basic understanding of machine learning
Who is this training for?
Physicians and healthcare professionals-
Healthcare managers
-
IT specialists
-
R&D staff from medtech companies
Training Program
-
1. Key concepts: AI, ML, DL
- Definitions: artificial intelligence, machine learning, deep learning
- History of AI with a focus on medical applications
-
2. AI applications in healthcare
- Diagnostic imaging (radiology, ultrasound)
- Natural language processing (electronic health records)
- Clinical prediction (rehospitalization risk, identifying high-risk patients)
-
3. Medical data as the foundation of AI
- Types of data: imaging, text, numerical
- Data standards: HL7, FHIR, DICOM, ICD
- Challenges: data quality, missing data, sensitive data
- Anonymization, pseudonymization, and legal compliance
-
4. Overview of existing AI solutions in healthcare
- Commercial tools and platforms: Aidoc, PathAI, IBM Watson Health, BioMind
- Open-source and research projects: MONAI, Google Med-PaLM, BioGPT
- Performance and limitations of AI models on real data
-
5. Ethical aspects of AI in medicine
- Professional and legal responsibility
- Algorithmic transparency (explainability)
- Bias, fairness, and risk of discrimination
-
6. Regulations and legal standards
- AI Act (EU), MDR, FDA, HIPAA
- GDPR and patient data protection in AI models
-
7. No-code and low-code AI tools
- Platforms for building models without coding
- Creating predictive models with medical data
- Visualization and interpretation of results
-
8. Deployment and practical aspects of AI
- Architecture of clinical decision support systems
- Managing the AI model lifecycle
- Case studies of implementations in Poland and worldwide
