New AI model can predict patients at highest risk of severe pain post-surgery

Prashasti Awasthi Mumbai | Updated on October 07, 2020

New model can also help in personalised pain management

A new artificial intelligence (AI) model can predict which patients run the highest risk of having severe pain after surgery.

The new model can also help in personalised pain management plans that employ non-opioid alternatives, as per the study presented at the ANESTHESIOLOGY® 2020 annual meeting and published in the journal EurekAlert!.

The authors of the study maintained that some patients can have more severe pain after surgery. So, they have to rely on higher doses of opioids for longer periods of time, which increases their risk for opioid abuse disorder.

Opioids are substances that when reaching opioid receptors, have effects similar to those of morphine. Medically they are primarily used for pain relief, including anesthesia. However, opioid includes illegal substances like heroin.

Machine learning

So, the new AI model can help doctors navigate the risk of pain and opt for non-opioid alternatives — such as nerve blocks, epidurals, and other medications.

The researchers of the study sought a faster, more effective method using machine learning, where a system learns and evolves based on data it is provided.

They developed three machine learning models that analysed patients’ electronic medical records. This helped in identifying that younger age, higher body mass index, female gender, pre-existing pain and prior opioid use were the most predictive factors of post-surgical pain.

Mieke A Soens, M.D., lead author of the study and an anesthesiologist at Brigham and Women’s Hospital and anesthesiology instructor at Harvard Medical School, Boston said in a statement: “We plan to integrate the models with our electronic medical records to provide a prediction of post-surgical pain for each patient.”

He added: “If the patient is determined to be at high risk for severe post-surgical pain, the physician anesthesiologist can then adjust the patient’s anesthesia plan to maximise non-opioid pain management strategies that would reduce the need for opioids after surgery.”


The researchers divided the study into two parts and examined data gathered from 5,944 patients who had a wide variety of surgeries. This included gallbladder removal, hysterectomy, hip replacement and prostate surgery.

Of those, 1,287 (22 per cent) had consumed 90 morphine milligram equivalents (MME) in the first 24 hours after surgery, which is considered a high dose.

For the first study, researchers noted 163 potential factors that can cause severe pain. They then introduced a machine-learning algorithm to narrow down to only those factors that most accurately predicted the pain and potential opioid needs after surgery.

In the second part, they determined and compared all three models that could predict the actual opioid use in patients. All three models had similar predictive accuracy overall: 81 per cent for logistical regression and random forest methods and 80 per cent for artificial neural networks.

That means the models accurately identified which people were more likely to have severe pain and need higher doses of opioids about 80 per cent of the time.

Soens added: “Electronic medical records are a valuable and underused source of patient data and can be employed effectively to enhance patients’ lives.”

“Selectively identifying patients who typically need high doses of opioids after surgery is important to help reduce opioid misuse,” he concluded.

Published on October 07, 2020

Follow us on Telegram, Facebook, Twitter, Instagram, YouTube and Linkedin. You can also download our Android App or IOS App.

This article is closed for comments.
Please Email the Editor