Use of computational algorithms to optimize memorization in preparation for medical residency

• Grant number: 18/15444-5
• Support Opportunities: Research Grants - Innovative Research in Small Business - PIPE
• Start date: March 01, 2019
• End date: November 30, 2019
• Field of knowledge: Physical Sciences and Mathematics - Probability and Statistics - Applied Probability and Statistics
• Principal Investigator: Matheus Bomfim de Carvalho Rocha
• Grantee: Matheus Bomfim de Carvalho Rocha
• Company: Eduq Soluções Educacionais Ltda
• CNAE: Desenvolvimento e licenciamento de programas de computador customizáveis
• City: São Paulo
• Associated researchers: Rodrigo Cardoso Cavalcante
• Associated scholarship(s): 19/08145-4 - Use of computational algorithms to optimize retention of knowledge in preparation for medical contests, BP.TT

Abstract

According to the medical demographics deport from 2015 of the Federal Council of Medicine [1], there are more than 20 thousand doctors graduating each year, with an outlook of more than 30 thousand new doctors per year by 2020. After graduation, most doctors choose to continue their training through the medical residency program, which requires approval in a highly competitive exam and has extensive content in their public notices. One of the main difficulties encountered by students in their preparation is the large amount of content to be studied in a short period of time, which sometimes lead to a psychological exhaustion syndrome [2]. Today, the methodology used in the courses is barely focused on the review of the subjects, making already studied contents to be forgotten over time. In addition, all content is studied with the same intensity, regardless of its incidence on exams or the student's affinity with each of them. In general terms, therefore, students feel overwhelmed and disoriented about the content they should study. In this context, we have identified some opportunities to provide a platform that will increase student performance. MedQ intends to use a modern learning methodology. Studies show that, with a traditional methodology, even highly motivated students forget about 30% of basic science content after 1 year and over 50% by the next year [3]. We will use the so-called "spaced repetition" study method which has been proven to allow for a more intelligent organization of the study schedule, balancing study sessions with review sessions, increasing content retention, and reducing overall study time. In addition, using the data from previous medical residency tests, it is possible to know the contents that have higher incidence in these evaluations and that, therefore, can be prioritized for a better performance. You can combine this data with the student's preferences, prioritizing more relevant contents and of greater interest when possible, in order to achieve the necessary result for approval. By the end of the project, we expect to have an algorithm that directs the studies in a personalized manner and is able to increase the retention of knowledge. This algorithm would work together with the methodology of traditional preparatory courses, being able to indicate the subjects that the student should review and for how long one should do it. (AU)