Applied AI in Healthcare – Fundamentals and Applications
Training details
Location
Faculty of Medical Engineering, National University of Science and Technology POLITEHNICA Bucharest
Start Date
22/04/2026
Time
08 : 00
End Date
13/05/2026
Target Audiance
Non-Technical
Teaching language(s)
Romanian
Organizing institution
ICI Bucharest
Delivery mode
On-site
Level
Introductory
Format
Case Study Session, Lecture, Workshop
Capacity or seats limit
38
Industrial domains
Health
Topics / Keywords
Artificial Intelligence, Machine Learning, Deep Learning, Clinical AI, Medical Data, Digital Health, Telemedicine, Administrative AI, AI Ethics, Explainable AI, Responsible AI, GDPR, Biomedical Engineering
What You Will Learn
After attending this session, participants will be able to:
- Understand fundamental concepts of Artificial Intelligence, Machine Learning, Deep Learning, and Generative AI in healthcare contexts.
- Distinguish between supervised, unsupervised, and reinforcement learning, as well as modern deep learning architectures, and understand how AI models are trained, validated and evaluated.
- Understand how AI systems learn from healthcare data and identify the main types of medical data used by AI models.
- Understand key concepts such as data preprocessing, model validation, explainability, and interpret evaluation metrics such as accuracy, sensitivity, specificity, precision, recall, and F1-score.
- Explore practical AI applications in healthcare such as clinical decision support, predictive analytics, remote patient monitoring, hospital administration, and digital health systems.
- Recognize the importance of explainable AI and the human-in-the-loop approach in ensuring safe and responsible medical AI deployment.
- Analyse real-world AI tools used by healthcare organizations, evaluate their limitations, implementation requirements and challenges, and distinguish between administrative and clinical AI applications.
- Understand ethical challenges related to responsibility, fairness, accountability, transparency, automation bias, and over-reliance in AI-assisted healthcare.
- Understand the main legal and regulatory frameworks governing healthcare AI, including GDPR, the EU AI Act, MDR/IVDR, and Software as a Medical Device (SaMD) requirements.
- Apply EU risk classification criteria to healthcare software, identify the steps of the CE certification process, and understand the importance of interoperability standards such as HL7 FHIR, DICOM, and IEC 62304.
- Develop critical thinking skills and practical evaluation skills when assessing AI vendor proposals, identifying red flags, and making responsible adoption decisions.
Agenda
Agenda
Module 1 – Foundations of AI in Healthcare
| 08:00 – 08:10 | Opening & Introduction to BSC AI Factory
Introduction to the BSC AI Factory initiative, available support mechanisms, and opportunities for healthcare innovation. |
| 08:10 – 08:50 | Why AI in Healthcare Matters
Overview of current developments in medical AI, AI-assisted diagnosis, healthcare market evolution, and European regulatory developments. |
| 08:50 – 09:30 | Interactive Activity: Play the Role of an AI Model
Hands-on exercises focused on understanding AI limitations, incomplete datasets, and decision-making uncertainty using a fictional clinical scenario. |
| 09:30 – 09:45 | Ethics Discussion: Moral Machine Experiment
Interactive discussion on cultural bias, ethical dilemmas, and automated decision-making. |
| 09:45 – 10:00 | Q&A and Conclusions
Discussion regarding responsible AI development, human oversight, and future opportunities in healthcare AI. |
Module 2 – Introduction to Artificial Intelligence in Healthcare
| 08:00 – 08:10 | Introduction to Artificial Intelligence and Machine Learning
Overview of AI, Machine Learning, Deep Learning, and healthcare applications. |
| 08:10 – 08:20 | Core Concepts in Machine Learning
Training, prediction, optimization, datasets, overfitting, and generalization. |
| 08:20 – 08:50 | Supervised and Unsupervised Learning
lassification, regression, clustering, dimensionality reduction, and healthcare examples. |
| 08:50 – 09:05 | Reinforcement Learning Fundamentals
Introduction to reinforcement learning concepts and healthcare-related applications. |
| 09:05 – 09:25 | Neural Networks and Deep Learning Architectures
Overview of CNNs, RNNs, Transformers, GANs, and Diffusion Models. |
| 09:25 – 09:40 | Healthcare Data Types and Data Preprocessing
Medical imaging, clinical records, wearable data, genomics, preprocessing, and validation. |
| 09:40 – 10:00 | AI Applications, Evaluation, Challenges, and Q&A
Evaluation metrics, explainability, privacy, limitations, and ethical considerations. |
Module 3 – Artificial Intelligence in Digital Health and Telemedicine
| 08:00 – 08:15 | Opening, Course Introduction & Interactive Warm-up
Discussion regarding perceptions of AI in medical practice and digital healthcare. |
| 08:15 – 09:15 | AI and Telemedicine in Digital Healthcare
Introduction to telemedicine, remote patient monitoring, wearable devices, digital health platforms, and AI-assisted clinical support systems. |
| 09:15 – 09:45 | Interactive Quiz and Applied Discussion
Applied scenarios exploring benefits, limitations, ethical concerns, and responsible implementation of AI in telemedicine. |
| 09:45 – 10:00 | Q&A and Conclusions
Human-in-the-loop decision-making, patient safety, digital communication, and future directions in telemedicine. |
Module 4 – Administrative AI, Ethics, and Regulation in Healthcare
| 08:00 – 08:15 | Administrative AI Applications in Hospital Operations
AI systems for workflow optimization, scheduling, documentation, billing, and patient communication. |
| 08:15 – 08:30 | Complexity, Prediction, and Operational Dependencies
Hospital logistics, patient flow forecasting, predictive models, and operational dependencies. |
| 08:30 – 08:55 | Discussion on Real-World AI Systems
Presenting two case studies of AI tools, including their technical architecture, deployment challenges, infrastructure requirements, and implementation limitations. |
| 08:55 – 09:15 | Interactive Activities: AI Classification and System Design
Classification of AI systems as administrative or clinical and group proposal activity for hospital AI deployment. |
| 09:15 – 09:35 | Ethics, Bias, and Responsibility
Automation bias, fairness, accountability, transparency, and practical ethical evaluation frameworks. |
| 09:35 – 09:50 | Legal and Regulatory Frameworks
GDPR, EU AI Act, MDR/IVDR, Software as a Medical Device certification, CE marking, interoperability, and healthcare standards. |
| 09:50 – 10:00 | Interactive Case Studies, Q&A, and Conclusions
Role-play activities, vendor evaluation exercises, red flag identification, and responsible acquisition decisions. |
Instructor name(s)
- Corina Petean – Junior Researcher
- Ana Vasilevsch – Junior Researcher
- Alina Mihaescu – Junior Researcher
- Andreea Gusatu – Junior Researcher
- Dr. Elena Paraschiv – Scientific Researcher
Course Description
Artificial Intelligence is transforming healthcare by supporting diagnosis, medical imaging analysis, predictive analytics, hospital operations, and digital health services. Despite its promising results, the successful integration of AI into clinical practice also requires an understanding of clinical workflows, data quality, ethical responsibility, regulatory compliance, and patient safety. This course programme offers a structured and applied introduction to AI in healthcare, combining foundational technical concepts with practical applications. Participants explore how AI systems learn from medical data, how machine learning and deep learning models are trained and evaluated, and how these systems are applied across clinical, operational, and digital health contexts.This programme introduces core concepts in Artificial Intelligence such as Machine Learning, Deep Learning, supervised and unsupervised learning, reinforcement learning, neural networks, and modern AI architectures including CNNs, RNNs, Transformers, GANs, and Diffusion Models. Participants also explore healthcare-specific applications, such as medical imaging, clinical records, genomics, wearable sensor data, and remote monitoring systems.
The course also presents AI applications in digital health and telemedicine, where participants learn how AI systems support teleconsultations, remote patient monitoring, wearable devices, symptom triage, and AI-assisted decision support systems. The course examines both the benefits and limitations of AI-enabled healthcare delivery, including issues related to explainability, patient communication, validation, and digital trust.Additionally, this programme addresses the growing use of administrative AI systems in healthcare organizations. Participants analyse how AI is used to optimize scheduling, documentation, patient flow management, discharge planning, and operational efficiency. Through real-world case studies, they evaluate implementation challenges, infrastructure requirements, transferability limitations, and the boundary between administrative and clinical AI systems.
Ethics and responsible AI deployment are integrated throughout the course. Participants examine bias in healthcare datasets, learn about automation bias, accountability, transparency, fairness, informed consent, and the role of healthcare professionals in AI-assisted decision-making. Interactive activities and case studies encourage participants to critically evaluate AI systems from both technical and ethical perspectives.The course also introduces the European legal and regulatory landscape governing healthcare AI systems, including GDPR, the EU AI Act, MDR 2017/745, IVDR requirements, and Software as a Medical Device (SaMD) certification pathways. Participants also become familiar with interoperability principles and international standards such as HL7 FHIR, DICOM, SNOMED CT, ISO 14971, IEC 62304, and ISO 27001.Throughout the programme, learning is reinforced through interactive discussions, quizzes, role-play activities, applied scenarios, vendor evaluation exercises, and collaborative problem-solving sessions, designed to develop practical reasoning and responsible decision-making skills. By the end of the course, participants gain foundational knowledge and applied critical thinking abilities necessary to understand, evaluate, and responsibly contribute to the development and implementation of AI systems for healthcare.
Required readings or materials