Early warning system by AI and SM

Response time from governments and their healthcare system could be improved during health security threads and emerging pandemics by using an array of technologies, including artificial intelligence, data analysis and social media feeds. The current trend analysis conducted by healthcare systems is reactive, in other words, new patients showing illness symptoms must first get into a hospital or healthcare facility in order for doctors and administrators to update relevant information about the emerging health thread. 

We propose the usage of the aforementioned technologies to aid in proactive data analysis about the emerging health security threads, in such a way that governments and their healthcare sectors would be better prepared by detecting hotspots of potential infections cases in an early manner.

If our solution would be scaled it could empower citizens, governments and healthcare systems to detect such threads, allocate resources, and quickly, effectively and efficiently respond to them.

During pandemics such as the one currently being experienced with COVID-19 and other health care emergencies, governments and their health care systems must be able to react quickly to protect the health of its citizens and the countries’ economies. However, current experience shows that most countries were not fully prepared to handle such pandemic. Hospitals quickly became overcrowded as new cases of infection increased; both human resources as well as personal protective equipment and hospital supplies were not enough to handle the increased patient volume or they were not properly distributed and managed according to needs from specific areas. 

Governments and hospital administrators must have up-to date real-time information about the pandemic evolution to better create policies and strategies to effectively manage the pandemic. The current approach to obtain information about the evolution of the pandemic is primarily reactive. This approach generates a response time that is not ideal in such scenarios. Health care system administrators, policymakers and government officials require support in obtaining relevant and timely information about the pandemic evolution to better identify potential geographical hotspots of new cases, and therefore respond appropriately by managing necessary resources to coordinate an optimal reaction to the trend changes.

Our solution is an early warning system platform that helps to increase the response capability from government and healthcare administrators by detecting potential new disease outbreaks and infection cases hotspots during pandemics and health care emergencies by using data analytics and artificial intelligence / machine learning algorithms and social media feeds. It uses currently deployed infrastructure to obtain real time data from social media; automatically obtains text data pertaining to the health care emergency terms used in social media platforms public feeds, and performs pre-processing and analyses on the obtained data to detect trend changes related to the healthcare emergency. 

In this way, the analyzed data will provide an indication of events and trends towards potential changes of infection cases per geographic area due to disease outbreaks. The information will be presented to healthcare administrators and/or government officials via an application interface either on a webpage or a PC application. This information will support the decision-making processes from healthcare administrators and governments officials to quickly, effectively and efficiently respond to the healthcare threads and/or emerging pandemics.

The intended audience of this solution are policymakers such as healthcare administrators and governments officials. We believe that by providing this technological solution to them we could also be potentially impacting, in a positive albeit indirect manner, the lives of most of the population that rely upon government and healthcare administrators to provide for care during challenging times such as emerging pandemics or health security threads.

The solution described will provide actionable intel about health care emergencies trends by regions and near real-time. Health care administrators and government officials could leverage this intel to better respond to the needs of the pandemic or health care emergency. 

Our idea is still in the concept phase, however our team members and work institution are in close communication with medical practitioners and related institutions. As such, we have conducted interviews and performed our own analysis to detect potential solutions that would increase the capabilities for data analysis from disease outbreaks in a manner that would improve the previously mentioned dimensions. 

We are planning for constant feedback from our intended audience during this project. The project development is proposed in a stage-gate approach where there are multiple stages of development and in specific stages there are planned feedback scenarios from health care administrators and policymakers about the analyses results, generated insights and user experience. The feedback obtained will help to improve our solution and better adapt to the specific needs of the end users.

In this challenge we are required to address how to prepare for, detect, and respond to emerging pandemics and health security threads. 

We believe that governments and healthcare administrators require better technological tools to help them in such tasks. In particular to detect disease outbreaks or other related health security threads before becoming unmanageable.

Our solution intends to function as an early warning predictive system that will strengthen their capability for disease surveillance. It uses no additional infrastructure, and could be scaled using cloud computing. If successful, our solution could help to modify pandemics evolution and related healthcare threads.

This project is at an initial development stage. The individual elements from this project related to social media feed interpretation by machine learning algorithms are documented separately in research articles by many authors, and there are also commercial products/services to obtain data from social media feeds that could be used as the data collection stage in this project for further processing. Additionally, there are online services for machine learning and computing as well. Overall, an integration of elements is possible to accomplish the objectives of this solution.

To the best of our knowledge, there is no currently deployed solution similar to ours regarding prediction of disease outbreaks using data from social media and artificial intelligence. Our solution is intended to use existing and well proved development technology as well as recent machine learning algorithms related to sentiment analysis, pattern identification, anomaly detection and event detection, and trend changes. Once deployed, our solution will provide new predicting capabilities that can effectively help healthcare administrators and government officials to monitor the evolution of pandemics and disease outbreaks to manage hospital and human resources in an optimal manner during healthcare emergencies.

We expect that due to spread of social media usage, and current deployment and maturity of the technologies proposed this proposal could have a positive impact for its intended purpose, in particular but not limited to, developed countries (i.e. Mexico and Latinamerica).

Our solution is currently in the concept phase, therefore it has not being deployed yet.

However, due to the possible deployment into cloud instances, our solution could reach a high percentage of the population that use social media in a regular basis. This is required to obtain information that will be processed and interpreted to provide the intended results that will be provided to hospital administrators, medical doctors, and government officials. We expect that in one year, if we deploy for Mexican users as intended and considering the novelty of the solution, we could be reaching between 2000-3000 hospitals. In five years time, we could expand operations to other Latin American countries aiming to obtain between 10000-15000 more hospitals. 

We will monitor and measure the performance from the solution to detect outbreaks, identification and response time from healthcare system and government officials. A mean time to anomaly detection (mtad) of 1 hour will be set as a key performance indicator (kpi), in comparison to current time to anomaly detection of days. Ratio of real anomaly detections vs false positives higher than 85%. Frequency of data collection of 5 minutes, and time for data readiness of less than 5 min are other of the indicators to be used during the development of the solution. 

Tecnologico de Monterrey University. Monterrey, Mexico.

Our team members are currently full-time employees from Tecnológico de Monterrey.

Christian Mendoza-Buenrostro, Ph.D in Technology and Communication, Data Scientist, Tecnologico de Monterrey University. Mexico.

Sergio Uribe-Gutierrez, Professor at Tecnologico de Monterrey University and Director of Center of Innovation in Design and Technology. Mexico.

Christian Mendoza-Buenrotro: M.Sc.IT., and Ph.D. in Information and Communication Technology. Experience in development of information systems, data analysis, and applied artificial intelligence. He also participates as consultant for industry at Monterrey, Mexico. He has been awarded Mexican government grants to establish bi-national collaboration between Tecnologico de Monterrey and University of Pisa, Italy.

Sergio Uribe-Gutierrez: He is the director of the Center for Innovation in Design and Technology at Tecnologico de Monterrey. He has 22 years of experience working in global companies in areas such Manufacturing Engineering, Product Development, Strategic Marketing, R&D and Innovation. During nine years he was Sr. Director for Innovation&Technology in Danfoss Denmark, designed and implemented an agile innovation framework to identify disruptive ideas and accomplish tested functional prototypes in 12 weeks, and responsible to develop and implement the strategy to adopt Additive Design and Manufacturing aiming product differentiation and faster Time-to-Market.

M.Sc. in Control Engineering and Ph.D. candidate in Artificial Intelligence for TEC de Monterrey; executive certificates in Innovation and Strategy from MIT Sloan School of Management and IMD business school for management.

Our combined expertise areas:

Innovation and Technology Management, Open Innovation, New Product Development Management, Business Strategy, Applied Artificial Intelligence, and Data Science.

Our solutions will be available to anyone working for government and hospital administration or medical teams. We do not discriminate race, color, sex, sexual orientation, gender identity, religion, disability, age, genetic information, veteran status, ancestry, or national or ethnic origin. 

Our only concern is to provide the best possible tool to help government officials and healthcare system to have a better insight into developing disease outbreaks and healthcare security risks.

Financial, technical, cultural, and market barrier could exist for this project.  

The project has to be sustainable in order to succeed, this is the reason why it is important to have an initial funding for the project. 

Additionally, we believe it is a challenging project with complexity from the AI/ML algorithms to implement and obtain precise and actionable information for the objective of this project. It would be helpful to join together with engineers from some of the Trinity Challenge partners, which could help accelerate the project development by providing insight and domain knowledge from both social media and AI related domains. 

Finally, we are no experts in terms of cultural and market barriers, therefore partnering with international companies with experience in a multi-cultural global setting would be a welcome accelerator in later developments of this project.

Our core expertise is in technology and strategy & development. 

This project requires the use of Twitter and Facebook API´s in order to obtain relevant public data from their social media feeds according to the objectives of this project. Therefore, we would like to partner with both organizations. One approach of collaboration could be a small joint team of developers working from our end and theirs to quickly develop a proof of concept prototype of this solution. In addition, Microsoft or Amazon could be a potential partner, we could use a hybrid approach using their online infrastructure and services for the development and deployment of this project.

On the other hand, another possible partnership during this project would be to collaborate with research groups from other Universities with research groups in engineering and technology such as Artificial Intelligence, Natural Language Processing, Data Analytics, and more. We are also open for collaboration with other Universities and research groups as well which might be interested in joining efforts for the development of this solution.