Health Analytics

Date of proposal: May 17, 2024

Type of activity: PhD course

Title: Health Analytics

Organizer(s):
Jonas Valbjørn Andersen, Associate Professor, Department of Business IT
Daniel Fürstenau, Associate Professor, Department of Business IT

Course advertisement:
This PhD course is focused on advanced health analytics as a research topic. It will feature lecture slots by Jonas Valbjørn Andersen, Daniel Fürstenau and selected guests (senior scholars from the health analytics field) and is geared towards questions of advanced questions of health analytics. For instance, it will benefit PhD students working on patient-generated, EHR, or billing data, which are increasingly important for IT researchers in applied computer science, machine learning, information systems, health informatics, and adjacent fields. It will consider processes of data collection, sharing, and analyzing healthcare data as well as analyzing the economic and sustainability impacts. The course will take an international perspective with examples from Denmark, other European countries and the United States. Students will work on their own projects within health analytics and discuss in class to receive feedback and further develop it based thereupon.

Lecturer(s):
Jonas Valbjørn Andersen, Associate Professor, Department of Business IT
Daniel Fürstenau, Associate Professor, Department of Business IT

 

Date(s) of the course: August 2, 2024

 

Time: Friday: 9:00-17:30

 

Room: ITU, room tbd.

 

Course description:
Beyond the traditional econometric and statistical methodologies, researchers increasingly begin to use machine learning, deep learning, and generative AI methods to tackle healthcare challenges. These challenges arise in all areas of healthcare, including diagnosis, treatment and management of patients, administration, and billing. In this course, we put a focus on quantitative methods and their use in a healthcare context. Main topics addressed are preparing data for analysis in healthcare, formulation of research questions, model selection and analytical toolkits, data visualization and interpretation of results. While the focus will be on retrospective routine data analysis, the course will occasionally also talk about prospectively collected data (e.g., from surveys, experiments or within clinical trials).

 

ILOs:

1. Be able to formulate a health-analytical research question
2. Reflect on the implication of different research designs in health analytics
3. Be able to correctly interpret the findings of a health analytics study

 

Reading list:

Baird, A., Xia, Y. Precision Digital Health. Bus Inf Syst Eng (2024). https://doi.org/10.1007/s12599-024-00867-6

Ben-Assuli O, Padman R (2020) Trajectories of Repeated Readmissions of Chronic Disease Patients: Risk Stratification, Profiling, and Prediction. MIS Q 44:201–226.  https://doi.org/10.25300/MISQ/2020/15101

Brodersen KH, Gallusser F, Koehler J, Remy N, Scott SL (2015) Inferring causal impact using Bayesian structural time-series models. Ann. Appl. Stat. 9. https://doi.org/10.1214/14-AOAS788

Chen W, Lu Y, Qiu L, Kumar S (2021) Designing Personalized Treatment Plans for Breast Cancer. Inf Syst Res 32:932–949. https://doi.org/10.1287/isre.2021.1002   

Feuerriegel S, Frauen D, Melnychuk V, Schweisthal J, Hess K, Curth A, Bauer S, Kilbertus N, Kohane IS, van der Schaar M (2024) Causal machine learning for predicting treatment outcomes. Nat Med. 2024 Apr;30(4):958-968. https://doi.org/10.1038/s41591-024-02902-1  

Ghose A, Guo X, Li B, Dang Y (2022) Empowering Patients Using Smart Mobile Health Platforms: Evidence of a Randomized Field Experiment. MIS Q 46:151–192. https://doi.org/10.25300/MISQ/2022/16201 

Soroush A, Glicksberg BS, Zimlichman E, Barash Y, Freeman R, Charney AW, Nadkarni GN, Klang E (2024) Large Language Models Are Poor Medical Coders — Benchmarking of Medical Code Querying. NEJM AI 1. https://doi.org/10.1056/AIdbp2300040

                                                                                                                                                    

Programme:

9:00 – 10:00 Welcome and lecture by Daniel and Jonas

10:00 – 12:00 PhD’s present their work and receive feedback on their projects

13:00 – 13:45 Keynote by Karl Werder (BIT department)

13:45 – 15:15 PhD’s present their work and receive feedback on their projects

15:15 – 15:45 Coffee break

15:45 – 17:00 PhD’s present their work and receive feedback on their projects

17:00 – 17:30 Wrap-Up and Conclusion

19:00 – 21:00 Dinner at Restaurant Lola (or similar)

 

Prerequisites:
None

 

Assessment:
Written research-in-progress report (4 pages)

 

Credits:
1 ECTS point

 

Number of hours the student is expected to use on the course:
Participation: 7 hours
Preparation: 28 hours

 

Participants: 10-12

 

How to sign up: via e-mail to the course coordinators (Jonas and Daniel) with a 2 page motivation letter by June 30, 2024