Title:	Digital Health and Artificial Intelligence
Keywords:	Research Qualitative methods Informatics Digital-Health
Country:	Germany
Institution:	Germany - Institute of International Health, Berlin
Course coordinator:	Moumita Mukherjee
Date start:	2025-04-07
Date end:	2025-04-16
About duration and dates:	Duration: 8 days (plus 2 days for post-course assignment) Application deadline: 4 weeks prior to first presence course day. No preparation/prereading required. Final due date for post-course assignment: 10 days after the last scheduled course day (if not otherwise agreed on).
Classification:	advanced optional
Mode of delivery:	Face to face
Course location: Institute of International Health Charité - Universitätsmedizin Berlin Campus Virchow-Klinikum Augustenburger Platz 1, 13353 Berlin, Germany
ECTS credit points:	3 ECTS credits
SIT: SIT: 90 hours Contact: 53 hours (24 hours lectures + 6 hours guided group work + 2 hours written test and evaluation+ 19 hours practical lab work + 2 hours case studies) Self-study: 37 hours (12 hours of reading during the face-to-face week, 25 hours of practicing data analysis)
Language:	English
Description: This module will focus on capacity building on contemporary theories in the field of digital health and health care informatics with special focus on creating AI based solutions for health systems strengthening in LMIC settings. At the end of the module the student should be able to: ● Propose AI algorithms in health systems research to improve health outcomes in form of the research proposal ● Design AI guided decision support system (using Python) for innovations in the decision-making process ● Test digital health theoretical frameworks using publicly available demographic and health data from LMICs using various data analytic techniques ● Employ and Distinguish the applicability of Machine Learning and Deep Learning algorithms to develop insights and improve problem solving skills ● Explain different types of data analytic techniques
Assessment Procedures: (1) Written exam A ca. 1.5 hour closed book written exam (multiple choice and open-ended questions), accounting 50% to the overall mark). The exam covers the topics taught during the course. The pass mark is 60% or more of the achievable points gained. If the student does not achieve the pass mark he/she can re-sit on a date agreed on with the module coordinator (preferably within 4 weeks after the module). (2) Assignment An assignment of 2000 words (+/- 10%), accounting for 80% of the overall mark. In the assignment students are asked to apply Ai algorithms in health systems research in the form of a research proposal. It will be marked for content (80%) and layout (20%) by the coordinator using an evaluation matrix. The assignment is passed if 60% or more of the achievable points are gained. If the pass mark is not achieved students can re-submit the assignment taking the feedback of the module coordinator (as outlined in the evaluation matrix) into account. A date for the resubmission will be agreed on with the module coordinator (preferably within 4 weeks after the student has received the feedback). A second re-examination for both types of assessment is permitted but may be linked to conditions set by the Committee of Admissions and Degrees, such as attending the course again in the following year (no additional fees). The results of the assessments will be communicated to the students during the week after the course and within two weeks after the due date of the assignment, respectively. To pass the course, students have to achieve pass marks (60% or more) in both assessments. Students receive two grades based on their overall mark, one according to the German (absolute) 6-point decimal grading system: 1.0 [excellent/sehr gut] – 6.0 [not sufficient/ ungenügend], pass mark: ≥ 4.0 [sufficient/ ausreichend]) and one according to the (relative) ECTS grading system (A top 10%, B next 25%, C next 30%, D next 25%, E lowest 10%)
Content: Day 1: ● Introduction to digital transformation of healthcare systems with digital health interventions (2 hours). ● Different digitalisation methods and instruments including mHealth Applications, IoMT (Smart medical devices), RWE (Real World Evidence) (2 hours). ● Digitalisation in primary care with special emphasis on Electronic Health Records and Telemedicine (2 hours). Day 2: ● Digital health interventions in LMICs with specific focus areas of interventions o Population health, Patient’s and caregiver’s experience, Provider’s experience, Cost minimization. It will be based on Consolidated Framework for Implementation Research (CFIR) as the conceptual framework (3 hours). ● The Theories, Models and Frameworks used to assess the effectiveness of digital health interventions (3 hours). o Examples – Unified Theory on Acceptance and Use of Technology, Diffusion of Innovation Theory, Normalisation Process Theory. Day 3: ● Basic applications of analytics in healthcare. o The process of health system digitalisation o Analytical architecture in health informatics. (3 hours). ● Big data analytics in healthcare (3 hours). ● Case studies followed by exploring possible research problems (2 hours). Day 4: ● Introduction to the artificial intelligence frameworks and applications – o machine learning and o deep learning models (3 hours) ● Interactive discussion on research problems, the application of the theoretical models, possible AI-driven solutions (3 hours). Day 5: ● Group Work on case studies: (e.g., Integrated digital surveillance system, Digitalisation of health records, Use and acceptability of mHealth application, Application of artificial intelligence to improve clinical diagnosis) (4 hours). ● Group Work on case studies: o Identifying research gaps and research problems o Developing research questions for each group specific research problem (2 hours). Day 6: ● Selection of a dataset (e.g., DHS). ● Hands on practical sessions with Stata and Python. ● Cover data preparation, data cleaning, pre-processing, standardisation, normalisation etc., related to the research questions (2 hours). ● Session on data analytics o Descriptive analytics, o Exploratory analytics o Predictive analytics (4 hours). Day 7: ● Development of visual dashboard with PowerBI (4 hours). ● Learn the application of classification and prediction techniques using machine learning models. (3 hours). Day 8: ● MCQ Test (Revision: Day 1 to Day 8) (1 hour). ● Learn the application of classification and prediction techniques using neural networks to solve more complex problems. (4 hours). ● Prepare all the final analyses in the lab and write the lab report (2 hours). ● Evaluation and Feedback (1 hour)
Methods: The learning method is a combination of teacher centered (lecture, discussion, lab work) as well as learner centered (group work, practical, self-study, and assignment) methods.
Prerequisites: ● English TOEFL test 550 or 213 computer-based or 79/80 internet-based or IELTS band 6.0 ● Successful completion of the core course ● Quantitative aptitude ● Basic knowledge of Statistics ● Notebook (MS Office) and pen (Note taking) ● Software Stata (to be purchased by the student him-/ herself) ● Python (Google Colab) (free)
Attendance: Maximum number of students: 30 students (unlimited tropEd students). Minimum number of students for the course to take place: 5 students In order to be permitted to write the exam and receive a grade report or an attendance certificate, students have to attend 85% of the contact time.
Selection: Participants are selected on a first come first served basis. Deadline for application: 4 weeks before module start Deadline for payment: 4 weeks after having received the invoice (if not otherwise agreed on) We shall confirm the module 4 weeks before the module starts which is subject to a sufficient number of applications Late applications will be considered as long as places are available. Application forms can be found here
Fees: 1050.00 EUR TropEd MScIH students and alumni 1312.50 EUR for others
Scholarships: Not available
tropEd accreditation: Accredited in Edinburgh, Sept. 2024; The accreditation is valid until Sept. 2029
Remarks: Recommended reading (books) 1. Hovenga, E. and Grain, H. eds. 2022. Roadmap to successful digital health ecosystems: A global perspective, Academic Press. 2. Gundlapalli, A.V., Jaulent, M.C. and Zhao, D. eds., 2018. MEDINFO 2017: Precision Healthcare Through Informatics: Proceedings of the 16th World Congress on Medical and Health Informatics (Vol. 245). IOS Press. 3. Monlezun, D.J., 2023. The thinking healthcare system: Artificial intelligence and human equity. Elsevier. 4. Mohanty, S.N., Nalinipriya, G., Jena, O.P. and Sarkar, A. eds., 2021. Machine learning for healthcare applications. John Wiley & Sons 5. Singh, B.K. and Sinha, G.R., 2022. Machine learning in healthcare: fundamentals and recent applications. CRC Press.
Email Address:	mscih-student@charite.de
Date Of Record Creation:	2024-10-11 05:39:32 (W3C-DTF)
Date Of Record Release:	2024-10-11 11:50:48 (W3C-DTF)
Date Record Checked:	2024-10-11 (W3C-DTF)
Date Last Modified:	2024-10-11 11:50:48 (W3C-DTF)