Latest News

9-1-1 Opioid Addiction: A Long-Term Problem For A Short-Term Solution

Contributed Commentary By Elizabeth Marshall

November 3, 2017 | “I just need something for the pain.”

These are words almost everyone in healthcare has heard before. And, of course the patient does need something. Pain is probably the most relatable condition in healthcare. At some point everyone has experienced it – except for those having rare genetic diseases such as Congenital Insensitivity to Pain. For the 25.3 million Americans that suffer from daily pain, this condition may sound like bliss, but, pain does have a purpose.

Pain warns us when damage is done and keeps us from severely injuring ourselves even more. However, living with chronic pain is nothing short of torture. Without some relief, pain can lead to hopelessness, depression and sleepless nights - a combination that can make one desperate for relief and willing to do just about anything to make the pain stop. Unfortunately, when the price of this relief comes in the form of opioids, too many people get more than just a prescription.

A long term problem

Many of us with medical backgrounds were taught that opioids were safe for short-term relief, making 5-to-10-day prescriptions relatively common. Unfortunately, the CDC now says that dependency starts within just a handful of days. As a physician, I find this alarming. As a former research scientist who has viewed thousands of patient mental health records, I wonder how many individuals became addicts as a result of a seemingly innocent interaction between an individual seeking guidance for pain relief and a clinician wanting to relieve an individual’s pain.

Clearly this is a problem...now what do we do?

You can’t solve a problem if you can’t identify it. Hence, you need to identify addicts in order to treat them. At first, addicts are very hard to identify. They rarely seek help for their problem. Instead, they stay busy trying to find more relief – that is, they find creative ways to seek more opioids.

Their behavior makes sense because withdrawal peaks about 72 hours after the last dose and can last a week. Most symptoms resemble a bad stomach flu: fever, sweating, heart palpitations, nausea, vomiting, diarrhea, cramping, and muscle aches. Add in the pain they were originally trying to alleviate and the cravings for the opioids that they knew fixed the pain and is there any wonder why addicts don’t want to stop?

To fix the problem, we must identify patterns as early as possible. Yes, I know - easier said than done. However, with vigilance and informatic solutions we can identify patterns that provide a clearer picture. For example, patterns can be revealed using analytical reporting techniques supported with robust data extracted by using Natural Language Processing (NLP) over a multitude of data sources. For a clear depiction of patients, structured data is not enough; we also need insights from unstructured free-text, which can be revealed using NLP text-mining.

A few examples of ways that NLP-supported analytical reporting can help include:

  • To closely monitor the clinician notes of patients with chronic pain to look for symptoms that may identify addiction or withdrawal from opioids.
  • To supplement/help create pain registries within hospital systems that identify timelines for prescribed medications used to combat pain. Metrics should include dosage, reason prescribed, and factors that put patients at risk for abuse, such as feelings of hopelessness.
  • To identify people that seem to be ‘accident’ prone that have a history of injuries requiring pain medications. For example: Does the patient have medical issues that are causing so many accidents? Should the patient have a referral to an otolaryngologist for balance? Or, are there signs of addiction present in the clinician's notes that might indicate self-harm in order to receive medications? 
  • To identify individuals that often visit urgent care type settings for various reasons and ask for pain relief medications. Clinician observations within notes should be checked for behaviors that suggest a patient may be drug-seeking.

Adding known risk factors to reporting enhances clinical decision making, especially if a patient has multiple risk-factors for opioid abuse, such as a personal or family history of alcohol abuse, illicit drug use, or sexual abuse, or has a common psychiatric disorder (bipolar, or a mood, anxiety, personality or stress disorder.) Once a reporting process is in production, however, it’s essential for institutions to utilize the reports within workflows that help providers identify and treat at-risk patients.

Addicts are creative, so we must be too. Despite all our perceived efforts to help people in pain, healthcare professionals have unknowingly contributed to this epidemic. It is our responsibility to do what we can to stop what is now labeled a national public health emergency.

Elizabeth (Liz) Marshall, MD, MBA is the Director of Clinical Analytics at Linguamatics. Early in her career she was on active duty for United States Air Force, serving in computer operations as a logistics team member for Operation Enduring Freedom, the military’s response to the 9-11 Attacks. After her military career, she became a research physician and dedicated her time to the development of informatics solutions to improve the effectiveness of mental health treatments for military veterans. She can be reached at elizabeth.marshall@linguamatics.com.