Could not download file: This paper is available to authorised users only.

AICAM: INTERACTIVE LEARNING TOOL FOR BREAST CANCER USING NON-PREDICTIVE INTERACTIVE VIDEOS

Objective:
Creating a software platform for education with generic use, following the various algorithms for decision-making, showing an interactive video about breast cancer cases, at random and accompanied by pictures, bibliography, diagrams, and so on. This approach applied in health can be used not only in this condition but also in any clinical situation where decision making algorithms are necessary, not only in healthcare but also in other areas of knowledge.

Material and methods:
We have selected 10 clinical cases of real patients with breast cancer, collecting all the related iconography, resulting in a collection of images and videos of the different diagnostic tests (mammography, needle aspiration, surgical, histopathological techniques, etc.) and other therapeutic options (radiotherapy, chemotherapy, hormone therapy), all accompanied by the necessary references and explanatory texts and schemes. In all cases there are no information to prevent patient identification.

Once the material an “as hoc” software platform has been developed, which consists of various modules properly integrated with specific functions:

1. Building trees for decision-making support based on fuzzy logic.
2. The clinical case definition, which allows us to incorporate multimedia elements that are necessary to define a case and assign tags for each element.
3. The non-predictive feedback system that makes the automatic interchange of different multimedia elements possible, in order to eliminate the learning by repetition of the same case.
4. Storage of the activity undertaken by the student: clinical case used, number of errors and successes, etc.
5. Module that lets you select the style: from the most basic one to the most sophisticated like the non-predictive interactive video.
6. Execution module for display depending on the selection chosen, and all operating rules that allow the presentation according to the desired media (web, conventional software, etc.)


Results:
The use of this rule-based engine is what makes it special to AICAM, allowing various resources intermixed to create different practical cases whenever used. Each time the student makes a decision, the program will act according to the defined algorithm, and allowing to the user the access to the latest literature published on the subject matter, teaching schemes, etc.

After the use of the platform, students get:

• Integrate the knowledge obtained on breast cancer in this case, or any other use framework.
• Learning techniques that could be difficult to access in normal situations, making possible that the student might know.
• Facilitate the assessment of learning, both for the students themselves (reinforcement) and Professor / tutor.

Conclusions:
The application of immersive and realistic tools, introduce the student to the reality of daily clinical practice in a non-predictive environment. Easily introducing the use of algorithms for decision-making and the proper use of bibliographical sources.

The constructed system can be applied in cases where manipulating algorithms for decision-making, regardless of the area of knowledge and level of education that is applied.