Tags Posts tagged with "Opioid Crisis"

Opioid Crisis

H. Andrew Schwartz Photo from SBU

By Daniel Dunaief

Ideally, doctors would like to know about health threats or dangers such as diseases or chronic conditions before they threaten a person’s quality of life or expected lifespan.

On a larger scale, politicians and planners would also like to gauge how people are doing, looking for markers or signs that something may be threatening the health or safety of a community.  

Researchers in computer science at Stony Brook University have been designing artificial intelligence programs that explore the language used in social media posts as gauges of mental health.

Recently, lead author Matthew Matero, a PhD student in Computer Science at Stony Brook; senior author H. Andrew Schwartz, Associate Professor in Computer Science at Stony Brook; National Institute on Drug Abuse data scientist Salvatore Giorgi; Lyle H. Ungar, Professor of Computer and Information Science at the University of Pennsylvania; and Brenda Curtis, Assistant Professor of Psychology at the University of Pennsylvania published a study in the journal Nature Digital Medicine in which they used the language in social media posts to predict community rates of opioid-related deaths in the next year.

By looking at changes in language from 2011 to 2017 in 357 counties, Schwartz and his colleagues built a model named TrOP (Transformer for Opioid Prediction) with a high degree of accuracy in predicting the community rates of opioid deaths in the following year.

“This is the first time we’ve forecast what’s going to happen next year,” Schwartz said. The model is “much stronger than other information that’s available” such as income, unemployment, education rates, housing, and demographics.

To be sure, Schwartz cautioned that this artificial intelligence model, which uses some of the same underlying techniques as the oft-discussed chatGPT in coming up with a model of ordered data, would still need further testing before planners or politicians could use it to mitigate the opioid crisis.

“We hope to see [this model] replicated in newer years of data before we would want to go to policy makers with it,” he said.

Schwartz also suggested that this research, which looked at the overall language use in a community, wasn’t focused on finding characteristics of individuals at risk, but, rather at the overall opioid death risks to a community.

Schwartz used the self-reported location in Twitter profiles to look at representation of a community.

The data from the model, which required at least 100 active accounts each with at least 30 posts, have proven remarkably effective in their predictions and hold out the potential not only of encouraging enforcement or remediation to help communities, but also of indicating what programs are reducing mortality. Their model forecast the death rates of those communities with about a 3 percent error.

Both directions

Schwartz explained that the program effectively predicted positive and negative changes in opioid deaths.

On the positive side, Schwartz said language that reflected a reduction in opioid mortality included references to future social events, vacation, travel and discussions about the future.

Looking forward to travel can be a “signal of prosperity and having adventures in life,” Schwartz said. Talking about tomorrow was also predictive. Such positive signals could also reflect on community programs designed to counteract the effect of the opioid epidemic, offering a way of predicting how effective different efforts might be in helping various communities.

On the negative side, language patterns that preceded increases in opioid deaths included mentions of despair and boredom.

Within community changes

Other drug and opioid-related studies have involved characterizing what distinguishes people from different backgrounds, such as educational and income levels.

Language use varies in different communities, as words like “great” and phrases like “isn’t that special” can be regional and context specific.

To control for these differences, Schwartz, Matero and Giorgi created an artificial intelligence program that made no assumptions about what language was associated with increases or decreases. It tested whether the AI model could find language that predicted the future reliably, by testing against data the model had never seen before.

By monitoring social media in these specific locales over time, the researchers can search for language changes within the community. 

Scientists can explore the word and phrases communities used relative to the ones used by those same communities in the past.

“We don’t make any assumptions about what words mean” in a local context, Schwartz said. He can control for language differences among communities by focusing on language differences within a community.

Schwartz recognized that fine refinements to the model in various communities could enhance the predictive ability of the program.

“If we could fully account for differences in cultural, ethnic and other variables about a community, we should be able to increase the ability to predict what’s going to happen next year,” he said.

With its dependence on online language data, the model was less effective in communities where the number of social media posts is lower. “We had the largest error in communities with the lowest rates of posting,” Schwartz explained. On the opposite side, “we were the most accurate in communities with the highest amounts” of postings or data.

Broader considerations

While parents, teachers and others sometimes urge friends and their children to limit their time on social media because of concerns about its effects on people, a potential positive is that these postings might offer general data about a community’s mental health. The study didn’t delve into individual level solutions, but these scientists and others have work that suggests this is possible.

As for his future work, Schwartz said he planned to use this technique and paradigm in other contexts. He is focusing on using artificial intelligence for a better understanding of mental health.

“We hope to take this method and apply it to other outcomes, such as depression rates, alcohol use disorder rates,” post traumatic stress disorder and other conditions, Schwartz said. “A big part of the direction in my lab is trying to focus on creating AI methods that focus on time based predictions.”

Public officials gathered at the H. Lee Dennison Building in Hauppauge Monday, July 25, to announce the opening of grant applications for programs targeting the opioid crisis.

The first round of program funding, which will total up to $25 million, is made available through an approximately $180 million settlement Suffolk is expected to receive “in litigation recovery dollars” over the next 18 years between the county and various manufacturers and distributors.

Last year, Suffolk County Executive Steve Bellone (D) convened a joint legislative and executive task force to assess proper responses and coordinate efforts to counteract the opioid epidemic throughout the county.

A report prepared by the opioid task force suggests that the available funds target “prevention, harm reduction, treatment and recovery,” according to Bellone.

“These are the categories in which we will see the most significant gaps in programs and services and the greatest potential return on investment with respect to combating the opioid epidemic,” the county executive said. 

‘The decisions that were made really created the dramatic rise in opioid overdoses.’ —Sarah Anker

The task force’s report also recommends a process through which organizations and institutions can apply for the available funding. Starting this week and running through Aug. 22, an opioid grant application is available on the county’s website.

The program is open to public, private, for-profit and nonprofit organizations. “If you’re an agency or organization in this opioid fight and you have a proposal that will help, especially in the areas outlined in the report, then we want to hear from you,” Bellone said.

Also in attendance were several members of the Suffolk County Legislature. Presiding Officer Kevin McCaffrey (R-Lindenhurst), a member of the opioid task force, stated that he and his colleagues in the Legislature are committed to making the best use of these resources as possible.

“This money came with a cost and that cost was lives,” McCaffrey said. “Although we can never get those lives back again, we can … use this money to make sure that others don’t have to suffer and that we [don’t] lose more lives.”

The presiding officer spoke of the ways in which opioids affect communities and the toll they take on families. “Every one of us here knows somebody that has been affected, whether that person has passed away or went to treatment and is still in recovery,” he said, adding, “The scourge that this has caused for the families … you would not want to wish this on any family that’s out there.”

This is a disease, and I still see a system that doesn’t recognize it as such.’ — Kara Hahn

Legislator Sarah Anker (D-Mount Sinai), chair of the opioid committee, advanced several reasons to combat the opioid epidemic aggressively. She recalled the decades of drug profiteering, failed policies and the absence of federal oversight, which all contributed to a steady rise in opioid-related deaths nationwide.

“The decisions that were made really created the dramatic rise in opioid overdoses,” she said. “There are so many companies and people that created this tsunami of death and now we are here to pick up the pieces.”

Anker referred to the $180 million made available to the county as “a drop in the bucket” compared to the billions in profits generated by those who have exploited opioid users in recent decades. While this money will catalyze the county’s efforts to rectify these past failures, she acknowledged that there remains much more work to be done.

“We’re going to use these funds for opioid addiction, prevention and helping those who are in treatment, but I implore the folks here listening to this press event to take an active role in helping those who have succumbed to addiction,” Anker said.

Legislator Leslie Kennedy (R-Nesconset), chair of the health committee, offered her own unique perspective on addiction, having witnessed its effects firsthand before joining the county Legislature.

“As a nurse for 30 years, as someone who has worked in an addiction facility on top of that for 10 years, I have lived the pain and have lived the death,” she said.

Kennedy acknowledged the contributions of those who initiated the lawsuit that made these funds available. While this money cannot compensate for the destruction of life and the carnage inflicted upon the community, she offered that this is a positive step in honoring those who are now lost to this disease.

“It’s not perfect, it’s not a lot, but if we didn’t sue, we would have nothing,” she said, adding that counteracting “addiction is a bipartisan effort.”

Another powerful voice for this cause is Legislator Kara Hahn (D-Setauket). She said she is familiar with the plight of opioid addiction, having witnessed the degradation of families and communities personally.

“This is a disease, and I still see a system that doesn’t recognize it as such,” Hahn said. “The disease model of addiction, trauma-informed practices, and recognizing what individuals go through when they face addiction is incredibly important.” She added, “We all have to work together, work strong, work hard and double down on our efforts.”

Applications for opioid grant funding will be open until Aug. 22 and can be accessed at: ce.suffolkcountyny.gov/opioidgrantsapplication

Suffolk County Legislator Sarah Anker speaks during a press conference in 2017 about the creation of a permanent panel to address the ever-growing opioid crisis. File photo by Kyle Barr

Suffolk County’s 2020 annual report on the lingering opioid crisis showed an increase in the number of overdoses from the previous year, with experts expressing concern for the impact the pandemic has had on addiction rates.

The Suffolk County Heroin and Opiate Epidemic Advisory Panel released its findings Dec. 29 showing there were 345 fatal overdoses in 2020, which includes pending analysis of some drug overdose cases, according to the county medical examiner’s office. While, on its face, that number did not increase over the past year, nonfatal overdoses climbed by 90 to 1,208, com-pared to 2019, according to Suffolk County police. This increase defies a general trending de-crease in nonfatal overdoses since 2017. Police also reported 910 opioid overdose-antidote na-loxone saves for individuals compared to 863 in 2019.

In some ways more worrying than overall overdose numbers has been the treatment situation on the ground, with professionals in the field reporting an increase in relapses during the pan-demic, according to the report.

Numbers released by police after a May inquiry from TBR News Media showed overdoses were up dramatically when comparing months before the start of the shutdown orders in March to the weeks directly afterward. Medical experts and elected officials all agreed that pandemic-related anxiety, plus the economic downturn and mandated isolation led to increased drug use overall. People in the treatment industry have also said the pandemic has pushed them toward utilizing telehealth.

Legislator Sarah Anker (D-Mount Sinai), the panel chair, said COVID-19 has led to challenges among all county governmental and community agencies, with “overwhelmed hospitals fighting on the frontline, addiction rates skyrocketing with limited resources and economic un-certainty due to business disruption.”

There have been 184 deaths related to opioids in 2020, according to the report, with 161 poten-tial drug overdoses still pending review. Among the North Shore towns, not accounting for those still in review, there were 18 deaths reported in Huntington, 13 in Smithtown and 69 in Brookhaven, the latter of which had the most opioid-related deaths of any Suffolk township. Police data also shows the 6th Precinct bore the brunt of the most overdoses and the most Narcan saves.

National data also bears a grim toll. According to the U.S. Centers for Disease Control and Pre-vention’s National Center for Health Statistics there has been a 10% increase in drug overdose deaths from March 2019 to March 2020. Approximately 19,416 died from overdoses in the U.S. in the first three months of 2020, compared to 16,682 in 2019. 

In addition to Suffolk’s report, the advisory panel has sent letters to state and federal reps ask-ing them not to cut any state funding for treatment and prevention and for the state to  sup-port provider reimbursement rates for telehealth and virtual care that are on par with face-to-face rates. They also requested that New York State waives the in-person meeting requirement for people to receive buprenorphine treatment, which can help aid in addiction to painkillers.

County legislators are also touting a new youth addiction panel, which is set to begin meeting in the new year. The county is also continuing its lawsuits against several pharmaceutical com-panies for their hand in starting the opioid epidemic. 

That’s not to say there haven’t been other setbacks in Suffolk’s efforts against opioids. Last Oc-tober, county Legislator William “Doc” Spencer (D-Centerport) was arrested for an alleged at-tempt to trade oxycodone for sex. Spencer was the one to initiate the creation of the youth panel. He has pleaded not guilty, though he has stepped down from his position on the panel, among other responsibilities.

There are currently 29 members on the opioid advisory panel, including representatives from the county Legislature, law enforcement, first responders, treatment centers and shelters.

While Anker thanked current members of the panel for their continued efforts, she said more work is needed.

“The opioid epidemic is an ongoing issue that needs to be addressed continuously from all fronts,” she said.