The lunch starts at 12:00, and the talk will start around 12:20.
NB: Wednesday BigInsight Lunches are open to staff and students from any of the BigInsight partners, including UiO, but not to others.
Speaker: Hans Olav Melberg
Location: Math Department, Seminar Room 819, Niels Henrik Abels hus, 8th floor
Title: How to define, compute and visualize typical treatment paths
Abstract: One common question being asked when working with health register data, is to say something about what kind of treatment the patients with a specific disease usually receive. You go to the data and report back, for instance, that "60% of the patients receive a specific pharmaceutical five times, over a period of 12 months."
This may be a perfectly acceptable answer, but note that in order to get the answer you had to make two choices: You had to select a time-period and a specific pharmaceutical. What if you wanted more details? Did the patients typically receive the pharmaceutical evenly spaced, or was it more concentrated in the beginning of the period? How many used other drugs? How many stopped using a drug? How many switched? How many chemotheraphy treatments are typical, and with what time space?
These are all questions of how patients are treated, and ideally we should have a way of structuring the data and visualizing treatment pattern that makes it easy to draw conclusions about all these and more. Basically we would like to take lots of data and summarize it in a mathod that makes it easier to se patterns than what we observe in the raw data, without loosing too much information of the features we are interested in.
I will present a solution using Python to analyse the treatment of patients with Inflammatory Bowel Disease.