We present efforts in the fields of machine learning and time series forecasting to accurately predict counts of future opioid overdose incidents recorded by Emergency Medical Services (EMS) in the state of Kentucky. Forecasts are useful to state government agencies to properly prepare and distribute resources related to opioid overdoses effectively. Our approach uses county and district level aggregations of EMS opioid overdose encounters and forecasts future counts for each month. A variety of additional covariates were tested to determine their impact on the model's performance. Models with different levels of complexity were evaluated to optimize training time and accuracy. Our results show that when special precautions are taken to address data sparsity, useful predictions can be generated with limited error by utilizing yearly trends and covariance with additional data sources.

Since 1999, the opioid epidemic has killed around 645,000 people in America--a number that would no doubt be even higher were it not for naloxone, an opioid antagonist that can effectively reverse the effects of an overdose. However, time is critical: if naloxone is not administered promptly, the victim's chances of survival diminish rapidly. In a paper published August 14 in Device, a team of researchers describe a device designed to detect the signs of an overdose and automatically deliver a dose of naloxone in as little as 10 seconds. The device–which researchers describe as a "robotic first responder"–is named the "implantable system for opioid safety" (iSOS). It's implanted under the user's skin, in the same way as a heart loop recorder.

In this paper, we propose a system to estimate heterogeneous concurrent drug usage effects on overdose estimation, that consists of efficient co-variate selection, sub-group selection, generation of and heterogeneous causal effect estimation. Although, there has been several association studies have been proposed in the state-of-art methods, heterogeneous causal effects have never been studied in concurrent drug usage and drug overdose problem. We apply our framework to answer a critical question, "can concurrent usage of benzodiazepines and opioids has heterogeneous causal effects on opioid overdose epidemic?" Using Truven MarketScan claim data collected from 2001 to 2013 have shown significant promise of our proposed framework's efficacy. Our efficient causal inference model estimated that the causal effect is higher (19%) than the regression studies (15%) to estimate the risks associated with the concurrent usage of opioid and benzodiazepines on opioid overdose.

Far more people in the US may have died from opioids in the past two decades than previously reported, according to a new analysis of unclassified drug deaths carried out using machine-learning algorithms. Elaine Hill and her colleagues at the University of Rochester, New York, were examining data on drug overdose deaths when they realised that 22 per cent of such cases reported between 1999 and 2016 were listed on death certificates as overdoses without specifying the substance involved. "We found that remarkable, given the scale of the issue," says team member Andrew Boslett. The team tried to estimate what percentage of these unclassified deaths were due to opioids by analysing the coroners' and medical reports from opioid overdoses and unclassified overdoses. First, the researchers used machine-learning algorithms to analyse deaths that had been recorded as being due to opioid overdose.

Health IT company Cerner is leveraging its partnership with Amazon Web Services to launch a new cloud-based health platform to incorporate artificial intelligence to improve usability and provide predictive insights for patient care. The new platform, called Project Apollo, brings a more cognitive approach to practicing medicine, Cerner Chairman and CEO Brent Shafer said during his keynote address at Cerner Health Conference, according to a company press release. Shafer said the new platform will leverage Cerner's health care technology and the AWS infrastructure to accelerate the speed that innovations are integrated by removing manual steps for clients that slow the pace of adoption. Cerner also is creating an "intelligence ecosystem" to innovate next-generation user experiences and care delivery algorithms, the company said. We're looking to return the joy of delivering medicine, and we're focused on innovating for the future and delivering better usability today," Shafer said. The Kanas City-based company also announced new predictive modeling tools to help reduce opioid abuse, improved dashboards and analytics, and a new capability aimed at enhancing interoperability in the healthcare industry. In July, Cerner announced a collaboration with cloud giant AWS, which is part of Amazon, with the aim of accelerating healthcare innovation. As part of the agreement, Cerner named AWS its preferred cloud provider. During his keynote speech, Shafer said Cerner will focus on several key areas in its broader strategy to innovate with Amazon, including turning data into insights, increasing interoperability and usability, and rapid development and deployment, according to the Kansas City Business Journal. Matt Wood, vice president of artificial intelligence for AWS, also spoke at the conference on the partnership with Cerner and the possibilities that arise when companies can access "infrastructure as if it was a utility, according to the Kansas City Business Journal.

Opioid overdose is a growing public health crisis in the United States. This crisis, recognized as "opioid epidemic," has widespread societal consequences including the degradation of health, and the increase in crime rates and family problems. To improve the overdose surveillance and to identify the areas in need of prevention effort, in this work, we focus on forecasting opioid overdose using real-time crime dynamics. Previous work identified various types of links between opioid use and criminal activities, such as financial motives and common causes. Motivated by these observations, we propose a novel spatio-temporal predictive model for opioid overdose forecasting by leveraging the spatio-temporal patterns of crime incidents. Our proposed model incorporates multi-head attentional networks to learn different representation subspaces of features. Such deep learning architecture, called "community-attentive" networks, allows the prediction of a given location to be optimized by a mixture of groups (i.e., communities) of regions. In addition, 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. Our results on two real-world overdose datasets indicate that our model achieves superior forecasting performance and provides meaningful interpretations in terms of spatio-temporal relationships between the dynamics of crime and that of opioid overdose.

The crisis of opioid use, abuse, addiction, and subsequent overdose deaths has reached epidemic proportions in America with no clear end in sight. As of March 2018, the National Institutes of Health reported that more than 115 Americans per day are dying as a direct result of opioid overdoses. In late 2017, it was reported that the US life expectancy had dropped for a second consecutive year, due in part to a surge in fatal opioid overdoses. For perspective, US life expectancy had not dropped for a single year since 1993, which at the time was a direct result of the AIDS epidemic, and had not dropped for consecutive years since the 1960s. Further, the CDC has estimated that as a result of only prescription opioid abuse, the total yearly economic burden to the United States totaled upwards of $78.5 billion--including the costs of health care, lost productivity, addiction treatment, and involvement of the criminal justice system--and clearly this shocking figure excludes the abuse of illicit opioids, such as heroin.

We find ourselves on the cusp of some very interesting dynamics in 2019 from a healthcare technology and innovation perspective. Advances in artificial intelligence (AI) including machine learning, natural language processing (NLP) and robotics have shown incredible promise in terms of automating repetitive manual tasks as well as improving decision making. Leaders in the healthcare industry--as well as technology vendors--are witnessing this first hand and are planning to integrate AI with next generation analytics platforms to empower executives, clinicians and analysts with unprecedented actionable insights from the board room to the point of care. Here are some key trends enabled by AI that are empowering stakeholders across the healthcare continuum, from policy makers and executives, to physicians and patients. AI and analytics integrated with electronic health records (EHRs) will enable superior care delivery and personalized care at a lower cost.