Predicting Epidemics and Other Complex, Dynamic and Dangerous Events.

And several decades ago, we also examined these data and methods, also aimed at epidemics, that aimed at doing this and bioterror as well.   We did not have all the methods or computing of today, but could have done lots with what we had.   Was always surprised that it was not taken further.  Please do that now.

AI could help with the next pandemic—but not with this one

Some things need to change if we want AI to be useful next time, and you might not like them.
by Will Douglas Heaven

It was an AI that first saw it coming, or so the story goes. On December 30, an artificial-intelligence company called BlueDot, which uses machine learning to monitor outbreaks of infectious diseases around the world, alerted clients—including various governments, hospitals, and businesses—to an unusual bump in pneumonia cases in Wuhan, China. It would be another nine days before the World Health Organization officially flagged what we’ve all come to know as Covid-19.

BlueDot wasn’t alone. An automated service called HealthMap at Boston Children’s Hospital also caught those first signs. As did a model run by Metabiota, based in San Francisco. That AI could spot an outbreak on the other side of the world is pretty amazing, and early warnings save lives.

This story is part of our coverage of the coronavirus/Covid-19 outbreak, all of which is available for free. You can also sign up for our coronavirus newsletter.   .... "

Wuhan Virus Detected by AI Epidemiologist

Quite interesting revelation.  The depth of this discovery still unclear.  Recall our work in detecting epidemics and bioterror by retail data.

AI Epidemiologist Sent First Warnings of Wuhan Virus in Wired via CACM   By Eric Niiler

Canadian health monitoring platform BlueDot was the first organization to alert its customers to the outbreak of coronavirus, on Dec. 31. BlueDot’s algorithm analyzes foreign-language news reports, animal and plant disease networks, and governmental information in order to warn its clients to avoid dangerous regions where disease outbreaks appear to be occurring. The algorithm also considers global airline ticketing data, to help predict where and when infected residents are traveling. BlueDot correctly predicted the coronavirus would jump from Wuhan, China, to Bangkok, Seoul, Taipei, and Tokyo in the days following its initial appearance. Said BlueDot CEO Kamran Khan, “What we have done is use natural language processing and machine learning to train this engine to recognize whether this is an outbreak of anthrax in Mongolia versus a reunion of the heavy metal band Anthrax.”

Epidemics and use of Personal GPS Data

Recall our work with bioterrorism modeling, link below.  Not just a matter of disease epidemics.

During Epidemics, Access to GPS Data from Smartphones Can Be Crucial
Ecole Polytechnique Fédérale de Lausanne (Switzerland)
By Sandrine Perroud

Researchers at Ecole Polytechnique Fédérale de Lausanne (EPFL) in Switzerland and the Massachusetts Institute of Technology have found that human mobility is a major factor in the spread of vector-borne diseases such as malaria and dengue. The researchers used mobile phone data and census models to effectively predict the spatial distribution of dengue cases in Singapore, based on data from actual reported cases in 2013 and 2014. The team also demonstrated that the types of data used in their study could be obtained without infringing on people's privacy. Said EPFL's Emanuele Massaro, "We need to think seriously about changing the law around accessing this kind of information – not just for scientific research, but for wider prevention and public health reasons." ... '

Flu Foreasting with Smart Thermometers

We also looked at epidemic forecasting.   Note the smart 'thermometers' mentioned here are taking human temperatures.  A slight confusion when I first read this.

Smart Thermometers Improve Flu Forecasting    By Joe Dysar

Researchers at the University of Iowa (UI) have found a way to get a jump on forecasting outbreaks of influenza-like illnesses by using real-time data from smart thermometers .

"Using simple forecasting models, we showed that thermometer data could be effectively used to predict influenza levels up to two to three weeks into the future," says Aaron Miller, an assistant professor or epidemiology at UI.

Miller's team secured its study data from Kinsa Inc., a maker of smart thermometer products.  The U.S. Food and Drug Administration-approved devices plug into Android or Apple smartphones and can send anonymized fever readings to Kinsa corporate headquarters in San Francisco.

Thanks to Kinsa, Miller's team was able to study more than 8 million temperature readings from all 50 U.S. states, which were provided over a period of nearly two years.

The team found that by using real-time data from the off-the-shelf thermometers, they were able to forecast outbreaks of flu-like illness in various parts of the country up to three weeks earlier than conventional forecasting methods. .... " 

How Viruses Spread

An impressive visual and description of of how viruses spread.  In Quartz   " ... A new genetic tool maps how deadly viruses spread around the world in real time ... ".   Recall a recent post on Kellogg work in using cell data for prediction.  Tag below on Epidemics.   And also links to our work on retail data for the same purpose.

Predicting Epidemics (Bioterror?) from Cell Data

If you have followed this blog for a long time, we looked at how to predict epidemics through OTC drug purchase data.  Here is a related idea that might be combined with earlier work.  Links to Bioterror detection?  See the tag links below.

Using Cell Phone Data to Predict the Next Epidemic    Insight Kellogg.
Who you call is linked to where you travel, which dictates how viruses spread.

Based on the research of Pierre Deville, Chaoming Song, Nathan Eagle, Albert-László Barabási and Dashun Wang  ... Can big data about whom we call be used to predict how a viral epidemic will spread?  .... " 

Flu Prediction Cognitive System

Using Watson, Twitter and CDC Data for predicting flu epidemics. Modeling under specific contexts. By Prof. Dr. Gordon Pipa, University of Osnabrueck  Embedded in the slide presentation.....    Audio recording.   Reminiscent of some of our own work in bioterror modeling , previously mentioned here.

Clorox Mapping Flu Real Time with Social

This relates to some work we did in the 90s on detecting epidemics and bioterror.  See the tag,

Clorox analyzes social media to predict flu outbreaks 
Clorox is promoting its sanitation products with an online push called Clorox Cold & Flu Pulse, which gives consumers a real-time flu report for their locality based on analysis of social media conversations. Clorox's tool is the first to use social chatter for flu predictions, rather than mapping outbreaks as they happen, said marketing professor Jonah Berger. Consumers can also add their own information using the hashtag #StoptheSpread. MediaPost Communications (10/28)

Forecasting the Flu

In the CACM:  We did sensor work some time ago that addressed bioterror forecasting.   This is related work that leverages social networks.   " ... A research team at the University of California, San Diego (UCSD) says it has refined and improved the predictions of Google Flu Trends (GFT).

The researchers report using social network analysis and combining the power of GFT's big data with traditional flu-monitoring data from the U.S. Centers for Disease Control and Prevention (CDC). ... " 

Google includes Flu Trend Data

Interesting.  Perhaps an admission that these kinds of patterns cannot be derived this way.  Recall we were also involved in a related project, which looked at retail pharma sales to predict bioterrorism.

" ... Finding that aggregate Web searches alone cannot provide an accurate assessment of where the flu has struck and its severity, Google will take into account data from the U.S. Centers for Disease Control and Prevention in its Google Flu Trends model. .... The Google tool is based on the premise that people turn to the Web when they are searching for information on the flu, making certain search terms good indicators of flu levels. The indicators of flu activity were also provided faster by Google than the weekly reports of the CDC. ... " 

National Retail Data Monitor

Colleague Mike Robinson of Laverdad Marketing  reminded me of an effort we were involved in: The National Retail Data Monitor.   Which is designed  to detect pharma sales patterns to provide early warning for epidemics and bio terrorism.  Mike did a great job supporting this early form of real time big data mining. Check out his inspired marketing work as well.