One of the problems facing medical students is gaining access to a wide variety of patients within a patient population. Conditions such as diabetes mellitus have a wide spectrum of symptoms, and in order to develop their diagnostic skills the student needs experience of dealing with as many varied examples as possible. Dr Jeroen Donkers, Assistant Professor in e-learning at Maastricht University is currently applying artificial intelligence principles to virtual patients in order to help students develop their diagnostic reasoning skills.

As Jeroen explains: “The problem with doctors is that when they do diagnostic reasoning they have to deal with a lot of uncertainties. They see the symptom, but what is the probability that the diagnosis belongs to that symptom? It’s an important ability that students have to develop.”

However, as probabilities depend largely on the patient population, limited exposure to a wide range of patient cases within that population can hamper diagnostic skills.

“For instance” says Jeroen, “If you see a lot of patients who have a headache caused by drinking too much, the next time you see a patient with a headache you’ll think that he drinks too much. On the other hand, if you only see patients with headaches because of brain tumours, the next time you see one [patient with headache] you immediately think of brain tumour.”

To address this issue, Jeroen and colleagues developed a system where information about a given disease state – in this case, diabetes mellitus – is encoded into a probabilistic network. This includes adding demographic and epidemiological data that produces a large number of brief virtual patients, giving an accurate picture of that patient population.

Students were exposed to a set of approximately 100 virtual patients that represented the diabetic population. They chose diabetes because medical students at Maastricht University are unlikely to treat these patients on their internships as the patients are looked after by specialist nurses.

“We hope to find differences between the students who had treatment with the specialized model with those students who hadn’t,” he says. “If this works, it will be a great advantage,” he adds. “Because we will be able to present students with a population that will enhance their abilities to reason with probabilities.”

Jeroen and colleagues will present their findings at the International Conference on Virtual Patients 2010 and the MedBiquitous Annual Meeting.

Listen to Jeroen talk about his research here:

[Please note - this video is in German. Scroll down for an overview in English]

Click here to view the embedded video.

Daniel: I’m here to talk about advantages and disadvantages of e-assessment in medical education.

Sebastian: What is e-assessment and what characterizes electronic exams apart from the fact that they are done by computer?

Daniel: I don’t know, what are your ideas?

Sebastian: Well some e-learning tools are just as good as paper-based exams. Here there is an advantage for assessors, but nothing for students. The added value is if extra media for students is incorporated into the e-exams.

Daniel: You can also get more realistic patient cases on computers, and there’s the possibility of designing the programme so mistakes done once are not carried on throughout the entire exam.

Sebastian: I agree, but muliti-media exams take more time to design than plain paper cases.

Daniel: Yes, but there is also the possibility to make the tasks more realistic. For example, the identification of pathological finding on chest x-ray is more realistic on screen with interactive elements than it is on paper.

Sebastian: Sure. Some subjects might be more suitable for multi-media exams than others, radiology being a good example. They can only work if cases are developed in interdisciplinary teams.

Daniel. There is the possibility of applying all assessment in e-assessment format, for example free text – free text being much easier for markers than hand writing. With the development of better text recognition programs, electronic pre-marking by computer might be possible.

Sebastian: Summative assessment has many advantages, especially on the organisational and judicial side. But it is expensive. So we need to consider the financial resources before these ideas can be put into practice.

Here, Daniel Tolks who is co-ordinating the German side of the ICON project talks to medical student Ole Jung about his experiences with e-learning.

[Please note - the video is in German. Please scroll down for the English translation]

Click here to view the embedded video.

Daniel: Hi, my name is Daniel Tolks

Ole: My name is Ole Jung

Daniel: I am working at the institute for teaching in health sciences at the university Witten/Herdecke(Martin Fischer) and we did an exchange project this summer with the Harvard University which was about Virtual patients  (ICON).  I’m here with Ole Jung who took this course over the summer.

Ole: Yes, my name is Ole Jung and I am a medical student.

Daniel: Please tell me about how you came to the project?

Ole: E-mail. Harvard was the call sign. Working together with students from Harvard was very interesting and it was new.

Daniel: Have you had any experiences with e-learning?

Ole: No, not at all. I heard that for example, a lecturer in Munich is talking via internet to students in Witten. But nothing else.

Daniel: Okay, tell me about your experiences concerning the work amount and if there was any additional benefit. Is it useful to implement e-learning on a long term?

Ole: I think it is useful and reasonable. In the beginning it was very difficult and exhausting, nobody knew exactly how all this will work. We had some coordination problems. But then it got better. You have to adjust to the new way of learning.

But we felt that the face-to-face meeting once a week are very important and most useful. Only e-learning is not recommended. Meetings are also very important.

Daniel: Do you think that the e-learning is not that important compared to face-to-face meetings?

Ole: No, not necessarily. But it is good to talk about personal problems and questions. Discussing topics is a totally different experience to writing. E-learning with video conference would be better and more useful in my opinion.

Daniel: Would you say that the learning process changed due to the use of e-learning? Maybe in comparison to PBL?

Ole: First of all we worked on different topics than we normally would. Mostly a cure was not possible. It was a more scientific approach. But in sum the effect of PBL is to go to the university and then work at home. If you go to a lecture or watch a lecture filmed and broadcasted via the Internet, there is no difference. You normally work on your own.

Daniel: We had two phases of the project. In the first phase the Witten and Harvard students  worked on a case on their own, and in the second case you worked together with the students from Harvard. Have you noticed a big change in the learning process?

Ole:  The mentality is different. The American students were more determined and single-minded and took it in their stride. This could be because they all wanted to go to Harvard. The mentality to achieve something is very different. Although it was requested that they were not willing to work in a group, we instead wanted to work in a group and meet each other.

Daniel: Okay, last question: Do you think that it is useful to extend the e-learning?

Ole: Of course! But with some improvements. For example, the use of video conferences would be good, e.g. e-Learning with lectures (podcasts).

Daniel: Thank you very much for this interview.