A Blog by Jonathan Low


May 22, 2019

How AI Can Predict Opioid Overdoes From Crime and Socio-Economic Data

It's basically economic profiling, with the ostensibly added benefit of being able to predict future behavior...as if having knowledgeable social scientists naming them, to say nothing of the fact that driving through such neighborhoods would make it obvious to even the casual observer.

Which is why there is such concern about sources and uses of AI. JL

Kyle Wiggers reports in Venture Beat:

The algorithm  learns numerical representation of the “dynamics” in communities that share similar behaviors. Features) from communities inform predictions for given locations within the AI model, and identify which local and global features are most predictive. Static included census data about economic status, education level, vacant housing, median household income, high school graduation rates, and the dynamic features captured per-neighborhood crime stats

Opioid abuse is on the rise nationwide. An estimated 1.7 million people in the United States suffered from substance use disorders related to prescription opioid pain relievers in 2017, and from July 2016 through September 2017 in 45 states, the U.S. Centers for Disease Control and Prevention recorded a 30% uptick in overdoses. Additionally, according to a recent study published in the journal Pain, roughly 21% to 29% of patients prescribed opioids for chronic pain misuse them.
It is, needless to say, imperative that the trend is reversed, and toward that end, researchers at the East Technical University in Turkey and the University of Pittsburgh say they’ve made encouraging progress. In a new paper (“CASTNet: Community-Attentive Spatio-Temporal Networks for Opioid Overdose Forecasting“) published on the preprint server Arxiv.org, they describe an AI system capable of forecasting overdoses from socioeconomics and patterns of crime incidents.
“[Our] proposed model allows for interpreting what features, from what communities, have more contributions to predicting local incidents as well as how these communities are captured through forecasting,” explained the paper’s coauthors. “[S]tudies have identified relationships between opioid use and crime incidences, including cause (that opioid use leads to criminal activities), effect (that involvement in criminal behavior leads to drug use), and common causes (that crime and drug tend to co-occur).”
The researchers’ algorithm — CASTNet — learns numerical representation of the “dynamics” in communities that share similar behaviors in a “community-attentive” fashion. Overdose contributors (features) from several communities inform predictions for given locations within the AI model’s purview, and moreover enable the model to identify which local and global features are most predictive and isolate high-risk communities.
The team employed two types of features to inform their AI’s projections: static and dynamic. The former included 2010 census data about economic statuses, education level, vacant housing, median household income, high school graduation rates, and more, while the dynamic features captured per-neighborhood crime stats culled from public safety data portals, such as the number of total crimes and the number of total opioid overdose incidents.
To keep the scope manageable, the team focused on two regions — the City of Chicago (47 neighborhoods) and City of Cincinnati (50 neighborhoods) — for which they collected the geolocation, time, and category for each crime feature. For Chicago specifically, they collected opioid overdose death records from the open source Opioid Mapping Initiative Open Datasets, and for Cincinnati, they used the EMS response data.
The coauthors report that CASTNet achieved better performance than the baseline architecture against which it was tested, and that it selected crimes like “narcotics,” “assault,” “theft,” and “burglary” as the most important features for future opioid overdose deaths in the same locations (along with diversity and population density).
“Based on these results, the neighborhoods with higher population and lower or moderate gender diversity may require additional resources to prevent opioid overdose in both cities,” wrote the researchers. “Also, economic status is important for neighborhoods of both cities, which is consistent with the previous work that suggested communities with a higher concentration of economic stressors (e.g. low income, poverty) may be vulnerable to abuse of opioids as a way to manage chronic stress and mood disorders.”
They leave to future work investigating the link between opioid use and other social phenomena.

Siemens and Chronicle will monitor cyber threats for energy industry

Above: Solar Panels
Image Credit: Google
Siemens and Alphabet company Chronicle have announced a partnership to protect the energy industry’s critical infrastructure from increasingly sophisticated and malicious industrial cyber threats.
The companies unveiled the alliance at Spotlight on Innovation, Siemens’ U.S. technology and innovation conference. Through a unified approach that will leverage Chronicle’s Backstory platform and Siemens’ strength in industrial cybersecurity, the combined offering gives energy customers visibility across information technology (IT) and operational technology (OT) to enable them to act on threats.
The energy industry has historically been unable to centrally apply analytics to process data streams, cost-effectively store and secure data, or identify malicious threats within OT systems.
Research conducted by Siemens and the Ponemon Institute found that while 60% of energy companies want to leverage analytics, only 20% are currently using any analytics for security monitoring. Small and mid-sized enterprises are particularly vulnerable to security breaches as they frequently lack the internal expertise to manage and address increasingly sophisticated attacks.
“The innovative partnership between Siemens and Chronicle demonstrates a new frontier in applying the power of security analytics to critical infrastructure that is increasingly dependent on digital technology,” said Leo Simonovich, vice president of industrial cyber and digital security at Siemens Gas and Power.
He added, “Cyber attacks targeting energy companies have reached unprecedented speeds, and our cutting-edge managed service unlocks the analytics ecosystem and offers a new level of protection from potential operational, business, and safety losses.”
“Energy infrastructure is an obvious example of cyber attacks affecting the physical world and directly impacting people’s lives,” said Ansh Patnaik, chief product officer at Chronicle, in a statement. “Backstory’s security telemetry processing capabilities, combined with Siemens’ deep expertise, gives customers new options for protecting their operations.”
The partnership between Siemens and Chronicle promises to help energy companies securely and cost-effectively leverage the cloud to store and categorize data while applying analytics, artificial intelligence, and machine learning to OT systems that can identify patterns, anomalies, and cyber threats.
Chronicle’s Backstory, a global security telemetry platform for investigation and threat hunting, will be the backbone of Siemens’ managed service for industrial cyber monitoring — in both hybrid and cloud environments.


Post a Comment