SATURDAY, JULY 26, 2025

(08:30-9:15) Teaching Unit 1: Patient Electronic Health Record Management


a. Electronic Health Records Management from https://ehealth.gov.gr/
Patient demographic data
i. Diagnoses
ii. Medical interventions
iii. Prescriptions
iv. Medications
v. Drug side effects
vi. Laboratory/Microbiology tests
vii. Patient health progress notes

b. Health data types (vital signs,
bio-indexes, ECGs, CT scans, MRIs, and other complex medical signals)

c. Case Study of a Boston Hospital's Data
(MIMIC III Medical Dataset)
i. Description
ii. Data Types (Clinical data (EHRs), ECGs, Chest X-Rays, Progress Notes, etc.)
iii. Database schema
iv. Application Demonstration for Real-time
Analysis and Visualization of Hospital Data

15 SAMPLE Slides

SUNDAY, JULY 27, 2025

(08:30-9:15) Teaching Unit 1: Ethical Issues of AI Application in Medicine and Protection of Sensitive Medical Data.

a. Artificial Intelligence and Ethical Issues in Its Application in Medicine
i. Fundamental principles of biomedical ethics
ii. Transparency, Justice, and Impartiality of AI
iii. Patient Consent in Clinical Decision Making
iv. European Union Artificial Intelligence ACT
b. Protection of Patients' Sensitive Personal Data.
i. Anonymization Techniques
ii. Date shifting
iii. Format Conversion
iv. Generalization of data interactions
v. K-Anonymity
vi. Adding Noise in Data
vii. Loss of Information
viii. Differential Privacy.

13 SAMPLE Slides

MONDAY, JULY 28, 2025

(08:30-9:15) Teaching Unit 1: AI Algorithms for Medical Data Assessment and Clinical Decision Support.

a. Innovative AI Algorithms in Biomedicine (e.g., Alphafold)
b. Linear Regression and Logistic Regression

c. Decision Tree Algorithm and Random Forest Algorithm

d. AI Algorithms for Drug Re-purposing (e.g., repurposing old drugs against COVID)

e. Deep Reinforcement Learning based on DeepMind algorithms by Google

f. Deep Neural Networks (MLPs, CNNs, RNNs, GCNs, etc.)

g. AI Algorithms and ChatGPT for Bioindex Generation (bioindexes generator)

i. AI Algorithms for Drug Re-purposing (using existing drugs for new diseases)

j. Application of AI Algorithms for the combinational assessment of clinical findings and genetic characteristics (DNA) of the patient.

20 SAMPLE Slides

(09:45-10:30) Teaching Unit 2: Using ChatGPT
for Image and Other Medical Signal Evaluation

How to use ChatGPT for interpreting and evaluating medical images and other complex medical signals, such as electrocardiograms (ECGs). Automated generation of reports based on combined imaging diagnostics and extraction of reasoned medical conclusions.

a. Computed Tomography (CT scans)

b. X-rays

c. Magnetic Resonance Imaging (MRI)

d. Electrocardiogram (ECGs)

e. Other complex medical signals

f. Demo of AI software to apply image processing over CT scans and classify patients into COVID and non-COVID disease.

14 SAMPLE Slides

(09:45-10:30) Teaching Unit 2: Advanced Clinical
Conclusion Extraction Using
Google's Med Gemini

Example of a Clinical Case study give to Med Gemini:
"A 45-year-old male presents with a three month history of progressive shortness of breath, fatigue, and occasional chest pain. His medical history includes hypertension and diabetes. Physical examination reveals a heart rate of 95 bpm, blood pressure of 140/90 mmHg, and bilateral basal lung crackles. Laboratory tests show elevated B-type natriuretic peptide (BNP) levels and mildly reduced kidney function. What is the most likely diagnosis, and what further tests would you recommend to confirm it?"

This task requires the model to integrate the patient's symptoms, medical history, physical examination findings, and laboratory results to suggest a likely diagnosis (such as heart failure) and recommend appropriate next steps for investigation (e.g., echocardiogram, chest X-ray).

a. Demonstration of several examples of
complex clinical reasoning decision tasks, made using the Med Gemini of Google.

e. ΑΙ software to predict drug
combinations to patients and explain the predictions using graph data (patient nodes, treatment node, drug node).

12 SAMPLE Slides

(09:45-10:30) Teaching Unit 2: Artificial Intelligence Applications for Medical Doctors

a. Precision Medicine and Personalized Medicine

b. Telemedicine and Telehealth Applications

c. Using "Speech to Text" applications to reduce the time spent on daily patient history documentation (e.g., OpenAI's whisper software)

d. AI applications for carbohydrate calculation and prediction of additional insulin doses (Diabetes, GlucoCalc, Abbott’s FreeStyle LibreLink, etc.)

e. Metrics for Evaluating Predictive Models

i. Confusion Matrix

ii. Precision, Recall, Roc curves and NDCG

iii. MAE, RMSE for Optimal Drug Dose Prediction

f. Explainability in Health

g. Demo of AI Software to recommend drug combinations to patients.

15 SAMPLE Slides

(09:45-10:30) Teaching Unit 2: Internet of Medical Things (IoMT)

a. Digitized recording of daily vital signs (measurement of blood oxygen saturation, blood pressure, systolic and diastolic pressure, body temperature, heart rate, respiratory rate, ECG, Glucose Continuous Monitoring, etc.) for real-time monitoring and timely notification of doctors, as well as for the analysis of polymorphic medical data enabling evidence-based medical conclusions/diagnoses.

b. Wearables (Smartwatches, Rings, etc.)

i. Samsung's Galaxy Ring (Samsung's ring for daily vital sign measurement)

ii. Medtronic glucose sensor for Continuous Glucose Monitoring (CGM).

c. Other Smart Medical Devices.

d. Application of AI algorithms over medical progress notes.

e ChatGPT and Retrieval Augmented Generation

f. Demo of AI software to send the electronic health record of a patient to ChatGPT API and get a possible therapeutic prediction based on the given vital signs.

15 SAMPLE Slides

(10:45-11:30) Teaching Unit 3. Machine learning algorithms for Image Processing and other complex medical signals

a. Convolution Neural Networks I. CNN architecture II. Pooling Layers III. ResNet

b. Applications over different medical signals i. Electrocardiogram ECG ii. Magnetic Resonance Imaging (MRI) iii. Computed Tomography Scan c. Support Vector machines

I. Finding Optimal Separators with Gradient Descent II. Hard and Soft SVMs

d. Programming Exercise with python to apply image processing over CT scans and classify patients into COVID and non-COVID disease.

9 SAMPLE Slides

Python code in Google Colab

(10:45-11:30) Teaching Unit 3. Medical Graph Data algorithms

a. Local based similarity algorithms (Shortest Path i. Common Neighbors, Jaccard similarity index, Salton similarity index, Adamic & Adar similarity index, Preferential Attachement.

b. Global-based algorithms i. Random Walk with Restart ii. SimRank iii. PathSim

c. Graph Convolution networks

d. Graph Embeddings

e. Programming Exercise with Python to predict drug combinations to patients and explain the predictions using graph data (patient nodes, treatment node, drug node).

10 SAMPLE Slides

Python code in Google Colab

(10:45-11:30) Teaching Unit 3. Transformers, Large Language Models, and ChatGPT

1.1 Transformers

1.2 Attention and Seif-Attention

1.3 Multi-head Attention

1.4 Positional Encoding

1.5 Large Language Models and ChatGPT

1.6 Encoder Transformers

1.7 Decoder Transformers

1.8 Encoder and Decoder Transformers

1.9 Multi-model Transformers and Google's Med Gemini

1.10 Explainability in Health

1.11 Programming Exercise with Python to recommend drug combinations to patients and measure quantitatively the predictions along with the unwanted side effects they have.

(10:45-11:30) Teaching Unit 3. New Trends and Apps in Health Care

i. Smart Medical Watches ii. Smart Medical Devices. b. Large Language Models, and Prompt Engineering

i. Application of AI algorithms over medical progress notes. ii. Vector space model and TF-IDF iii ChatGPT and RAG

iv. Bag of words and Tokenization

v. Word Embedding, Word2Vec and skip-grams approaches

vi. Decision Tree Classifier

vii. Feature Selection

viii. Naive Bayes Classifier

c. Programming Exercise with Python to send the electronic health record of a patient to ChatGPT API using a prompt request (prompt engineering) and get a possible therapeutic prediction based on the given vital signs.

10 SAMPLE Slides

(11:30 -   :  ) Working Groups of Medical Doctors from Related Specialties to Address a Patient Case Study.

Each working group will be provided with all medical data of a patient (lab tests, progress notes, medical interventions, prescriptions, CT scans, ECGs, EEGs, etc.), and using AI techniques, they will be required to provide a reasoned diagnosis and create an appropriate therapeutic plan.

(Optional participation)

(11:30 -   :  ) Working Groups of Medical Doctors from Related Specialties to Address a Patient Case Study.

Each working group will be provided with all medical data of a patient (lab tests, progress notes, medical interventions, prescriptions, CT scans, ECGs, EEGs, etc.), and using AI techniques, they will be required to provide a reasoned diagnosis and create an appropriate therapeutic plan.

(Optional participation)

(11:30 -   :  ) Working Groups of Medical Doctors from Related Specialties to Address a Patient Case Study.

Each working group will be provided with all medical data of a patient (lab tests, progress notes, medical interventions, prescriptions, CT scans, ECGs, EEGs, etc.), and using AI techniques, they will be required to provide a reasoned diagnosis and create an appropriate therapeutic plan.

(Optional participation)

(11:30 -   :  ) Working Groups of Medical Doctors from Related Specialties to Address a Patient Case Study.

Each working group will be provided with all medical data of a patient (lab tests, progress notes, medical interventions, prescriptions, CT scans, ECGs, EEGs, etc.), and using AI techniques, they will be required to provide a reasoned diagnosis and create an appropriate therapeutic plan.

(Optional participation)

(11:30 -   :  ) Working Groups of Medical Doctors from Related Specialties to Address a Patient Case Study.

Each working group will be provided with all medical data of a patient (lab tests, progress notes, medical interventions, prescriptions, CT scans, ECGs, EEGs, etc.), and using AI techniques, they will be required to provide a reasoned diagnosis and create an appropriate therapeutic plan.

(Optional participation)