The United States is being ravaged by a The opioid epidemic claims tens of thousands of lives and billions of dollars each year.
PROBLEM
Dr. Tina Hernandez-Boussard, associate professor at Stanford University School of Medicine, and her fellow researchers say they can’t let this continue.
“Our goal is to use big data and cutting-edge technology to identify the causes of opioid addiction and recommend strategies to prevent this chronic use,” she said.
Medicaid covers vulnerable populations at particularly high risk of opioid abuse. The problem for the Stanford team is that there are currently no large publicly available Medicaid claims datasets to support this study.
To carry out this study, the team needed a large amount of data. And that’s where the supplier Gainwell Technology has arrived.
“Gainwell is a leader in Medicaid healthcare technology services and claims management company for millions of Medicaid beneficiaries through state clients,” said Hernandez-Boussard. of the company”.
“WOODainwell enabled this research by providing Stanford with a single research database of millions of de-identified claims. Select Gainwell Medicaid customers approved to use this data, knowing that the data will be used to help solve the devastating health care crisis and save lives.”
“We used a machine learning model to predict progression from acute to chronic opioid use.”
Tina Hernandez-Boussard, Stanford University School of Medicine
Stanford looked at databases using technologies like machine learning and deep learning to research this question.
“We identified 180,000 unidentified Medicaid enrollees from six states with evidence of postoperative opioid use disorder,” Hernandez-Boussard explains. “That group of subscribers formed the basis for this study.”
SUGGESTIONS
Hernandez-Boussard said that Gainwell shared Stanford’s commitment to addressing the opioid crisis — and that commitment works urgently. The company’s primary role is to provide unidentified claims data to Stanford in a format that researchers can understand and analyze.
“Gainwell created a longitudinal claims database containing six years of unspecified claims data for a geographically different group of Medicaid states,” Hernandez-Boussard explains. “This database is located in a secure cloud environment and is accessed through the new user interface.
“Stanford researchers can submit project-specific requests for data access after completing formal data use agreements,” she added.
MEET CHALLENGES ONLY
Gainwell technology is an independent 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, for data analysis. This work was carried out under Hernandez-Boussard’s supervision by both graduate students and postdoctoral researchers at the Stanford School of Medicine.
“Using artificial intelligence and machine learning tools, our researchers looked for key indicators that lead to chronic (addiction) opioid use,” said Hernandez-Boussard. “Some of the information they discovered was both surprising and instructive.
“For example, Tramadol, an opiate advertised as safer and less addictive than others, is actually highly predictive of long-term opiate use,” she continued. “It is hoped that this study and our conclusions will provide a pathway to prevent opioid-nave patients from becoming opioid dependent.”
RESULT
The Stanford team concluded that a patient’s first experience with an opioid prescription is the single biggest driver of addiction.
“Among patients who have never taken an opioid or have been opioid-free for two months or more, 29.9 percent developed opioid dependence after their first prescription,” Hernandez-Boussard revealed. “The study concluded that the larger the number of medications prescribed to patients and the longer the duration of the prescription, the more likely they were to become dependent on opioids.
“This study will give doctors pause,” she warned. “We encourage them to consider prescribing non-opioid medications as a primary method of pain management before prescribing opioids, as recommended by national guidelines.”
The full study, “Prescribing quantity and duration predicts progression from acute to chronic opioid use in opioid-nave Medicaid patients and its findings,” can be found. above PLOS Digital Wellbeing.
TIPS FOR OTHER PEOPLE
“I advise others to always get the most complete data set possible before starting this type of research,” said. Hernandez-Boussard. “And, as you can imagine, this data is difficult to collect. You’ll also need a technology partner to prepare that information for the study. It’s important that you get that evidence in your hands. caregivers.
“We used a machine learning model to predict progression from acute to chronic opioid use,” she said. “Besides, you need a great in-house team to do the research. Fortunately, at Stanford, we have no shortage of top researchers and fellows with a great aptitude for the job. this.”
Twitter: @SiwickiHealthIT
Email the writer: [email protected]
Healthcare IT News is a publication of HIMSS Media.
