The United States is being ravaged by a opioid epidemic that claims tens of thousands of lives and billions of dollars every year.
THE PROBLEM
Dr. Tina Hernandez-Boussard, associate professor at Stanford University School of Medicine, and fellow researchers said they can’t let this continue.
“Our goal was to use big data and cutting-edge technologies to identify the causes of opioid addiction and recommend strategies to stem this chronic use,” she said.
Medicaid is a vulnerable population with a particularly high risk of opioid abuse. The problem for the Stanford team was that there is currently no large, publicly available Medicaid claims dataset that would support this research.
To carry out this study, the team needed a large volume of data. And that’s where the seller Gainwell Technology has arrived.
“Gainwell is the leader in Medicaid health technology services, and it manages claims data for millions of Medicaid beneficiaries through the company’s public clients,” Hernandez-Boussard said.
“Gainwell enabled this study by providing Stanford with a unique research database of millions of anonymized claims. Some Gainwell Medicaid customers approved the use of this data, knowing it would be used to help solve a devastating health crisis and save lives.”
“We used a machine learning model to predict progression from acute to chronic opioid use.”
Dr. Tina Hernandez-Boussard, Stanford University School of Medicine
Stanford examined the database using technologies such as machine learning and deep learning to research this question.
“We identified 180,000 anonymized Medicaid enrollees in six states with evidence of postoperative opioid use disorder,” Hernandez-Boussard explained. “This cohort of enrollees formed the basis of this study.”
PROPOSAL
Hernandez-Boussard said Gainwell shared Stanford’s commitment to tackling the opioid crisis — and he operated urgently. The company’s primary role was to provide the anonymized claim data to Stanford in a format that researchers could understand and analyze.
“Gainwell created a longitudinal claims database containing six years of anonymized claims data for a geographically diverse group of Medicaid states,” Hernandez-Boussard explained. “This database was hosted in a secure cloud environment and accessed through a new user interface.
“Stanford researchers could submit project-specific requests for access to data after entering into formal data use agreements,” she added.
TRY THE CHALLENGE
Gainwell’s technology is a standalone research platform that is not integrated with other systems. Within this platform, Stanford researchers can use a variety of analytical tools, including R and Python, to analyze the data. This work was carried out under the supervision of Hernandez-Boussard by graduate students and postdoctoral researchers from the Stanford School of Medicine.
“Using artificial intelligence and machine learning tools, our researchers looked for key indicators leading to chronic opioid use (addiction),” Hernandez-Boussard said. “Some of the information they uncovered was both surprising and instructive.
“For example, tramadol, an opioid that has been touted as safer and less addictive than others, was actually very predictive of long-term opioid use,” she continued. “Hopefully, this research and our findings will provide a roadmap to prevent opioid-naïve patients from turning into opioid-dependent patients.”
RESULTS
The Stanford research team concluded that a patient’s first experience with an opioid prescription is the biggest factor fueling addiction.
“Among patients who had never taken opioids or had not taken them for two months or more, 29.9% developed opioid dependence after their first prescription,” Hernandez-Boussard revealed. “The study concluded that the greater the quantity and duration of patients’ prescriptions, the more likely they were to develop opioid addiction.
“This research should give doctors pause,” she warned. “We urge them to consider prescribing non-opioid medications as primary pain treatment before prescribing opioids, as recommended by national guidelines.”
The full study, “Prescription Quantity and Duration Predict Progression from Acute to Chronic Opioid Use in Opioid-Naïve Medicaid Patients and Its Outcomes,” can be viewed at PLOS digital health.
TIPS FOR OTHERS
“I would advise others to always get the most comprehensive dataset possible before starting this type of research,” said Hernandez-Boussard. “And, as you can imagine, this data is difficult to collect. You will also need a technology partner to prepare this information for research. Above all, you will need to bring this evidence to the guardians.
“We used a machine learning model to predict progression from acute to chronic opioid use,” she said. “Other than that, you need a great in-house team to do the research. Luckily, at Stanford, we have no shortage of top researchers and graduate students with great aptitude for this work.”
Twitter: @SiwickiHealthIT
Email the author: bsiwicki@himss.org
Healthcare IT News is a HIMSS Media publication.
#helps #Stanford #researchers #show #link #opioid #treatment #addiction