[ad_1]
Graduate students from the University of Guadalajara (UdeG) work on the development of a bot which, through a series of algorithms, reaches to detect risk factors and suicidal behavior in young people, the National Council of Science and Technology (CONACYT) reported in a press release
the goal, said students Manuel Santana Castolo and Patricia Brand, project manager, is that the bot could interact with users through the email service offered by Facebook and when there are risk factors for suicide, the person can be referred for care required.
" The idea is that we can detect whether there is depression or suicidal risk this is not a diagnosis, only a detection and if possible a channeling with the professionals of appropriate health "says Brand, a graduate in psychology and a graduate in biomedical engineering.
Brand was responsible for developing methodology for the detection of risk factors for suicide.
Santana, a biomedical engineer, has stated that they seek to implement artificial intelligence algorithms that help bot to address users' questions and, over time, can better understand the responses.
the most recent data from the World Health Organization (WHO) in 2015, the average suicide rate in Latin America was 9.8 per 100,000 population, which means 65,000 annual deaths.
Mexico salt At the National Institute of Statistics and Geography (Inegi), in 2015, 6,285 suicides were reported throughout the country, representing a rate of 5.2 per 100,000.
Santana, PhD student in electronics and computer science at the UdeG Center for Exact Sciences and Engineering, explained that, in a first step, the chatbot will receive basic information from the users to develop a first profile about the person interacting.
Later, they will work with questions based on medical textbooks to chart a route that helps detect risk factors.
Once artificial intelligence detects risk factors, will contact previously established users as a reference, or institutions that provide treatment and advice on mental health. [19659003] The two students hope that in mid-October, a first step of this bot will be published in control patients and in the background.
Brand says that for the chatbot have database to react to users, is working on the development of a series of information that strengthens artificial intelligence, based on available textbooks and tests that are the cornerstone for designing new ways to build the perspective of bot. ]
"We designed it to detect and evaluate responses, we badign a score to the answers users give and we also want to incorporate an algorithm that starts to detect linguistic indicators, which are the types of words used by the was detected with depression, for example, "explained the student.
The two developers have indicated that in the future we think to incorporate the voice badysis function of users can detect, using factors such as tone of voice, the possible risks of depression to be treated preventively EFE
Source link
