The U.S. is being ravaged by an opioid epidemic that costs tens of thousands of lives and billions of dollars each year.
THE PROBLEM
Dr. Tina Hernandez-Boussard, associate prof astatine the Stanford University School of Medicine, and her chap researchers said they could not fto this continue.
"Our extremity was to usage large information and precocious technologies to place the causes of opioid addiction and urge strategies to stem this chronic use," she stated.
Medicaid is simply a susceptible colonisation with a peculiarly precocious hazard of opioid misuse. The Stanford team's occupation was determination presently are nary ample publically disposable Medicaid claims information sets that would enactment this research.
To execute this study, the squad needed a ample measurement of data. And that's wherever vendor Gainwell Technologies came in.
"Gainwell is the person successful Medicaid healthcare exertion services, and it manages claims information for millions of Medicaid beneficiaries done the company's authorities clients," Hernandez-Boussard said.
"Gainwell enabled this survey by providing Stanford with a unsocial probe database of millions of de-identified claims. Select Gainwell Medicaid clients approved utilizing this data, knowing it would beryllium utilized to assistance lick a devastating healthcare situation and prevention lives."
"We utilized a instrumentality learning exemplary to foretell the progression from acute to chronic opioid use."
Dr. Tina Hernandez-Boussard, Stanford University School of Medicine
Stanford reviewed the database utilizing technologies specified arsenic instrumentality learning and heavy learning to probe this question.
"We identified 180,000 Medicaid de-identified enrollees from six states showing grounds of postoperative opioid usage disorder," Hernandez-Boussard explained. "That cohort of enrollees formed the ground for this study."
PROPOSAL
Hernandez-Boussard said Gainwell shared Stanford's committedness to tackling the opioid situation – and it operated with urgency. The company's main relation was to present the de-identified claims information to Stanford successful a format the researchers could recognize and analyze.
"Gainwell created a longitudinal claims database containing six years of de-identified claims information for a geographically varied radical of Medicaid states," Hernandez-Boussard explained. "This database was housed successful a unafraid unreality situation and accessed done a caller idiosyncratic interface.
"Stanford researchers could taxable project-specific requests to entree the information aft completing ceremonial information usage agreements," she added.
MEETING THE CHALLENGE
Gainwell's exertion is simply a standalone probe level that is not integrated with different systems. Within this platform, Stanford researchers tin usage a assortment of analytical tools, including R and Python, to parse the data. This enactment was done nether Hernandez-Boussard's supervision by some postgraduate students and postdoctoral researchers astatine the Stanford School of Medicine.
"Using artificial quality and instrumentality learning tools, our researchers looked for cardinal indicators starring to chronic opioid usage (addiction)," Hernandez-Boussard said. "Some of the accusation they uncovered was some astonishing and instructive.
"For instance, Tramadol, an opioid that has been touted arsenic being safer and little addictive than others, was really highly predictive of semipermanent opioid use," she continued. "Hopefully, this probe and our conclusions volition supply a roadmap to halt opioid-naïve patients from turning into opioid-dependent ones."
RESULTS
The Stanford probe squad concluded that a patient's archetypal acquisition with an opioid medicine is the biggest origin fueling addiction.
"Of the patients who had ne'er taken an opioid oregon hadn't taken an opioid for 2 months oregon more, 29.9% developed an opioid dependency pursuing their archetypal prescription," Hernandez-Boussard revealed. "The survey concluded the larger the quantity and longer the duration of patients' prescriptions, the much prone they were to make an opioid dependency.
"This probe should springiness doctors pause," she warned. "We would impulse them to see prescribing non-opioid medications arsenic a superior attraction for symptom earlier prescribing opioids, arsenic recommended by nationalist guidelines."
The afloat study, "Prescription quantity and duration foretell progression from acute to chronic opioid usage successful opioid-naïve Medicaid patients and its findings," tin beryllium recovered connected PLOS Digital Health.
ADVICE FOR OTHERS
"I'd counsel others to ever get the astir implicit acceptable of information imaginable earlier opening this benignant of research," said Hernandez-Boussard. "And, arsenic you tin imagine, this information is hard to gather. You'll besides request a exertion spouse to hole that accusation for research. Importantly, you'll request to bring that grounds to the hands of the caretakers.
"We utilized a instrumentality learning exemplary to foretell the progression from acute to chronic opioid use," she said. "Aside from this, you request a large interior squad to execute the research. Fortunately, astatine Stanford we person nary shortage of apical researchers and postgraduate students with a large aptitude for this work."
Twitter: @SiwickiHealthIT
Email the writer: bsiwicki@himss.org
Healthcare IT News is simply a HIMSS Media publication.
English (US)