Detection of cardiovascular diseases with HEALTHBOT.AI

Editorial note: this article documents an educational project and its results on the data used. It does not establish clinical validation or authorisation to diagnose or treat patients. Proposed healthcare applications are retained as the team’s goals, not demonstrated capabilities.

Due to the pandemic that we are currently experiencing worldwide, one of the most immediate problems that has been observed is the lack of medical personnel in hospitals in general and to care for people suffering from a disease other than COVID-19. According to this information, the objective of this work is to create a chatbot that allows easy early identification of diseases that have been the focus of deaths worldwide, as well as being able to help with patient follow-up, in a much more accessible way. For the first prototype and with the information we have, work will begin with the detection of cardiovascular diseases. As future work, it is intended to use the developed system, in some public health institution, to detect other diseases that have been the main causes of death in Mexico.

Context and problem

According to information provided by the WHO (World Health Organization), 7 of the 10 main causes of death have been due to non-communicable diseases. Of which greater attention needs to be paid to cardiovascular diseases, cancer, diabetes and chronic lung diseases, and to reduce trauma.
Cardiovascular diseases have been one of the main causes of death in the world. With the figures obtained in 2012, there were 17.5 million deaths registered worldwide. More than 80% of deaths mainly affect the low and middle countries, equally in men and women. In Mexico, 77% of deaths in adults are due to cardiovascular diseases, which is why risk factors are involved, such as 17% of the population being smokers, 22.8% suffering from hypertension and 1 in 3 adults being obese. Of which, obesity has been one of the main risk factors. This is due to the high consumption of sugar, and the lack of education on these issues in the country.

Solution Proposal

As a proposal for the early prevention of diseases, the HealthBot project arises, which consists of creating an interface (chatbot) with which the user initially interacts textually to find out their level of risk of suffering from cardiovascular diseases. Based on this risk, the chatbot will issue a series of recommendations for the user to take appropriate prevention or treatment measures. In addition, by collecting information on the risk factors provided by the user, the interface will generate clinical reports that the user can present to their doctor during the appointment or be sent directly from the interface to the health personnel if it is integrated into a system of a Health entity such as the IMSS.

Project development

In the development of the Chatbot, Natural Language Processing (NLP) models will be used to generate a dialogue focused on the target population. Through the dialogue, the chatbot will collect the relevant information to generate the diagnosis. One of the advantages of this project is that the identification of risk factors as well as the diagnostic model will be taken from the work of the orange team of the previous generation of Saturdays.AI., called CardioSight. This allows our team to focus on the development of the NLP-based interface and at the same time, promote and extend the functionality of a work previously generated through Saturdays.AI

Cardiovascular disease risk prediction model

For this project we will take as reference the model already generated by the orange team, from the previous generation of Saturdays.AI. This model takes into account 11 input variables: age, gender, systolic blood pressure, diastolic blood pressure, cholesterol, glucose, physical activity, height (cm), weight (kg) and body mass index. Below is the image according to the correlation between final variables, after the exploratory data analysis previously carried out by the orange team.

Figure 1. Result of the correlation of the aforementioned variables

Technical Description of the Project

Credits

The completion of this work was possible with the support at all times from our mentors: Grisell Reyes Rios and Mario Fonseca. Which were always guiding our process for the completion of the project.

More artificial intelligence!

The mission of Saturdays.ai is to make artificial intelligence more accessible (#ai4all) while carrying out social impact projects (#ai4good). If you want to learn more about this project (and others) join our community in or learn how to create yours in our AI Saturdays program.