This pilot study, conducted at the University of Atlántico Medio, seeks to transform the training of future nurses through a "Precision Education" model, moving away from generic simulations to focus on learning adapted to the student's individual profile. Through a clinical trial with 38 second-year students, the research evaluates whether using Artificial Intelligence to personalize educational narratives (gamification) according to the student's personality enhances academic performance in obstetrics (pregnancy and childbirth). The ultimate goal is to demonstrate that adapting teaching to each student's psychological characteristics is not only a sustainable strategy but also produces better-prepared professionals with higher knowledge retention, directly translating into safer and higher-quality care for patients and their families.
Imagine if education were like a suit: currently, most classes are "one-size-fits-all." All students receive the same lesson in the same way, regardless of whether they are shy, bold, analytical, or emotional. But what if the investigator could tailor a suit specifically for each student's mind? A new pilot study from the University of Atlántico Medio has set out to answer this question, exploring how Artificial Intelligence (AI) can revolutionize the way the investigators train our future healthcare professionals. The Problem: The investigators don't All Learn the Same Way Nursing training, especially in critical areas like obstetrics (pregnancy and childbirth care), requires not only technical skill but also rapid decision-making and empathy. Traditional simulation methods often overlook the student's "personal profile," offering a generic experience that doesn't motivate everyone equally. The Solution: Custom Stories Generated by AI have designed an innovative protocol combining psychology and technology. Instead of a standard class, the study uses educational games (gamification). The big breakthrough is the use of Artificial Intelligence. The AI analyzes each student's personality and adapts the game's narrative to their profile. Is the student competitive? The game might present high-stakes challenges. Are they more reflective? The story might offer deep data for analysis. To test if this works, a trial is being conducted with 38 second-year nursing students. They will be divided into two groups: Those learning with the traditional (generic) game method. Those learning with the "Precision Education" method, where AI adapts clinical pregnancy and childbirth cases to their personality. The goal is to measure not only how much they learn ("learning gain") but also how much they enjoy and engage in the process. Why Does This Matter for Everyone? This study isn't just about improving student grades. It is about safety and excellence in healthcare. If the investigators demonstrate that adapting education to a student's personality creates better-prepared and more committed nurses, the investigators will be opening the door to more humane and effective healthcare. Furthermore, the use of Generative AI makes this personalization-previously impossible due to cost-a sustainable and accessible tool for medical and nursing schools. The investigators are witnessing the shift from mass education to person-centered education, ensuring that those who care for us tomorrow have the best possible preparation today.
Study Type
INTERVENTIONAL
Allocation
RANDOMIZED
Purpose
OTHER
Masking
SINGLE
Enrollment
38
The Experimental Group receives a personalized experience generated by AI and adjusted to five personality profiles (PPDS scale). This adaptation transforms the learning "wrapper" by offering specific narrative tones (such as heroic, humorous, or empathetic), differentiated visual aesthetics, feedback styles adjusted to the student's motivation, and exclusive side missions (such as puzzles or speed challenges), which are accessed via specific codes according to their role.
The primary distinction between the two groups lies exclusively in the adaptation of the narrative and gamification elements, given that the clinical content, learning objectives, and difficulty remain invariant to ensure academic validity. The Control Group interacts with a linear and generic narrative characterized by a neutral academic tone, standard medical aesthetics, and conventional feedback without additional missions
Learning Gain
The main outcome variable will be academic performance, LG, understood to reflect new knowledge acquired on the subject under study. The degree of assimilation of the theoretical and practical concepts of pregnancy and childbirth in each of the four clinical cases will be evaluated. To this aim, an "ad hoc" questionnaire comprising 40 multi-ple-choice questions was designed by the PI, who is a certified Nurse Specialist in Obstetrics and Gynecology (Midwife) and the lecturer in charge of the class. The items were constructed to strictly align with the specific curricular contents and learning ob-jectives of the 'Reproductive Health' syllabus. To ensure external content validity prior to administration, this initial draft will be reviewed by an external panel of five experts (three academic midwives and two obstetricians). Regarding reliability, since this is a pilot study, internal consistency and item analysis will be calculated post hoc to validate the instrument for future trials.
Time frame: On day 1 of the intervention and in the end of treatment every session
Satisfaction with the gamification
The students' subjective perception of the usefulness, fun, and moti-vation generated by the activity will be evaluated using the Gameful Experience Scale (GAMEX). This validated 27-item instrument in Spanish is suitable for measuring game experience in nursing students' training. It uses Likert-type re-sponses to measure the multidimensional nature of the gamified experience in the educational context. The six dimensions include enjoyment, abstraction, creative thinking, activation, absence of negative effects, and mastery. This model demonstrated high overall reliability, with a Cronbach's alpha of 0.85. The scoring format uses a five-point Likert scale. In the proposed study, measurement will be con-ducted exclusively at the end of the intervention (Session 4) to capture the students' overall perception of the program. Prior to analysis, items with negative wording (reverse punctuation) will be recoded so that higher scores consistently reflect a more positive.
Time frame: At the end of treatment, at 4 weeks
Sociodemographic variables
Age is understood as the time that a person has lived, counting from birth to the time of the survey, measured in whole years; sex is understood as a variable that refers to the social and cultural construction that defines the roles, behaviors, activities, and attributes that a society considers appropriate, with the answer options male, female, and non-binary; and the average grade considered to mean the average grade achieved in the first year of the nursing program to monitor the differences between the groups.
Time frame: On day 1 of the intervention
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.