Rocío Castrañeda
Computational techniques applied in the field of health, in addition to aiding in the processing of vast amounts of data, aim to provide technological tools to professionals in the medical sciences and contribute to the well-being of society. This is evident in the project "Detection of indicators of mental health in schizophrenia through passive sensing of data on mobile phones."
Schizophrenia is a mental illness diagnosed through clinical criteria and the combination of history and symptoms, making computer science a potential aid in quicker and more effective detection of the condition.
This viewpoint was put forth by Brandon Alejandro Mosqueda González, who recently completed his master's degree at the Centro de Investigación en Computación (CIC) of the Instituto Politécnico Nacional (IPN). He revisited a study conducted in 2015 by universities in the United States, involving 45 clinically diagnosed individuals with schizophrenia.
Each participant was provided with a mobile phone equipped with an application designed to passively collect information from various phone sensors related to their behavior, such as walking time, bicycle usage, resting periods, and the number of conversations, calls, and messages received.
In the study, participants were also asked to answer a questionnaire every third day to monitor their behavior and assess their mental well-being.
Using this information, the recent graduate from CIC evaluated four different machine learning algorithms to model schizophrenia: artificial neural networks, random forest, gradient boosting machine, and multiple linear regression.
In the Data Science and Software Technology Laboratory at CIC, under the guidance of Drs. Adolfo Guzmán Arenas and Gilberto Lorenzo Martínez Luna, his work also included the analysis and evaluation of different techniques to generate a model capable of predicting mental well-being based on data obtained passively from mobile phones.
"Currently, evaluations for monitoring individuals with mental health conditions, such as depression or schizophrenia, involve responding to questionnaires. Now, from data generated by the use of mobile phones, distinctive patterns of our well-being state can be automatically inferred," noted Brandon Mosqueda.
Mosqueda González explained that such research will enable health specialists in the future to have a complete and automatic follow-up of patients. With the information recorded on users' phones, possible relapses can be identified.
"The main results of my work indicate that simple and explainable machine learning algorithms are capable of capturing the essence of this problem compared to more complex programs. However, with a greater amount of data, the results of these algorithms would be more accurate," he stated.
New Opportunities in France
Brandon Alejandro Mosqueda studied Software Engineering at the University of Colima. After participating in a Scientific and Technological Research Summer Program (Delfín Program) at CIC, he decided to pursue his master's in Computer Science at this research center of the IPN.
At CIC, he also had the opportunity to spend a semester abroad at the National Institute of Applied Sciences (INSA) in Lyon, France, where he was invited by a professor to continue with his Ph.D., albeit in a different area than his master's.
The knowledge acquired at CIC, proficiency in the English language, as well as scholarships from the Consejo Nacional de Humanidades, Ciencias y Tecnologías (Conahcyt) and the Ministry of Foreign Affairs of IPN at the postgraduate level, were decisive for his stay in France. This time, he is sponsored by the French National Research Center.
In light of these opportunities, Brandon Alejandro Mosqueda encouraged Polytechnic students to leverage the intelligence, talent, and cutting-edge knowledge of CIC researchers. Thanks to its academic connections with various foreign institutions, CIC contributes to the excellent training of future generations that the country requires.
Selección Gaceta Politécnica #167. (October 31st, 2023). IPN Imagen Institucional: Read the full magazine in Spanish here
INSTITUTO POLITÉCNICO NACIONAL
D.R. Instituto Politécnico Nacional (IPN). Av. Luis Enrique Erro S/N, Unidad Profesional Adolfo López Mateos, Zacatenco, Alcaldía Gustavo A. Madero, C.P. 07738, Ciudad de México. Conmutador: 55 57 29 60 00 / 55 57 29 63 00.
Esta página es una obra intelectual protegida por la Ley Federal del Derecho de Autor, puede ser reproducida con fines no lucrativos, siempre y cuando no se mutile, se cite la fuente completa y su dirección electrónica; su uso para otros fines, requiere autorización previa y por escrito de la Dirección General del Instituto.
