Reducing Intraoperative Opioid Use through AI

Annually, over 50 million surgical procedures take place in the United States. With the incidence of new persistent opioid use after surgical procedures estimated to exceed 6% (1), this results in over 2 million Americans becoming persistent opioid users following initial post-operative exposure. Currently, drug overdose is the leading cause of accidental death in the United States (2). Alongside recent evidence against the necessity of opioids in general anesthesia (3) and an opioid shortage, the opioid crisis is in dire need of being addressed. One approach to reducing opioid use is through AI.

The rise in artificial intelligence (AI)-based technologies has ushered in a new era of technological possibilities which can be leveraged to address public health challenges, including in the form of better health care and precision medicine (4,5). Meanwhile, despite $40 billion in federal spending on electronic health records (EHRs), physicians continue to struggle to use data meaningfully and effectively to improve patient outcomes (6). At the intersection of AI and EHRs lies a fertile ground to address the opioid crisis, and, in this vein, AI-facilitated “improvement science” has emerged as a promising way of refining patient care processes. 

A recent flagship project used AI to predict whether patients would need opioids for pain reduction. This project, spearheaded by the Brigham and Women’s Hospital, predicted post-operative opioid use by discerning trends foreshadowing the use thereof (7). To this end, Soens et al. gathered data from thousands of patients scheduled to receive general anesthesia and undergo surgical procedures without a peripheral nerve block. Three different machine learning algorithms allowed them to condense an exhaustive list of variables to a total of 21 predictive factors which could predict and thereby enable the early identification of patients at risk of opioid use, thereby facilitating better tailored interventions and proactive patient management protocols.

Since, AI has been successfully leveraged to the point of succeeding in eliminating intraoperative opioid administration entirely. In this initiative, anesthesiologists at Seattle Children's Hospital and its Bellevue Clinic and Surgery Center used a centralized platform to monitor and assess anesthesia protocols across key metrics, including pain scores, administration of pain-rescue medications, post-operative nausea and vomiting, post-anesthesia care unit (PACU) length of stay, and re-admissions (8). Using the AI-powered analytics platform MDmetrix, the team probed tens of thousands of surgical cases across different clinical approaches, re-assessing medications that had long been traditionally administered. Devising a series of alternative pain management protocols based on published research, they completed improvement cycles thereof in a record 12 weeks (9). As a result, multi-stakeholder staff was able to reduce intraoperative opioid administration from 84% to 8% and post-operative morphine administration from 11% to 6%. To date, over 6,000 patients have successfully undergone outpatient surgery with opioid-free anesthesia. In addition, clinicians found that these opioid-sparing protocols nearly eradicated postoperative nausea and vomiting – the most common side effect of anesthesia, caused by opioids – while patient satisfaction dramatically increased. Operational results included increasing capacity, optimizing resource utilization, and decreasing overall costs, including an 85% reduction in spending on analgesics.

Finally, alongside these pre-operative, operative and post-operative approaches, initiatives have also focused on leveraging AI post-operatively to help minimize the use of opioids after surgery through psychotherapeutic support. A recent study found that patients receiving messages from a chatbot experienced reduced overall pain levels and used a third fewer opioids after fracture surgery (10).

The healthcare industry has succeeded in leveraging digitized data using AI to improve patient safety and operational efficiency, and this transformative opioid reduction work represents a paradigm shift in the process of improving clinical outcomes harnessing the power of AI.

References

1.            Brummett CM, Waljee JF, Goesling J, Moser S, Lin P, Englesbe MJ, et al. New persistent opioid use after minor and major surgical procedures in us adults. JAMA Surg. 2017 Jun 1;152(6):170504. 

2.            Jones GH, Bruera E, Abdi S, Kantarjian HM. The opioid epidemic in the United States—Overview, origins, and potential solutions. Cancer. 2018. 

3.            Egan TD. Are opioids indispensable for general anaesthesia? Br J Anaesth. 2019;122:e127–35. 

4.            Ahmed Z, Mohamed K, Zeeshan S, Dong XQ. Artificial intelligence with multi-functional machine learning platform development for better healthcare and precision medicine. Database (Oxford). 2020 Jan 1;2020. 

5.            Patel VL, Shortliffe EH, Stefanelli M, Szolovits P, Berthold MR, Bellazzi R, et al. The coming of age of artificial intelligence in medicine. Artif Intell Med. 2009 May;46(1):5–17. 

6.            Global EHR market hits $31B but faces usability, interoperability challenges | FierceHealthcare [Internet]. Available from: https://www.fiercehealthcare.com/tech/global-ehr-market-hits-31-billion-but-faces-usability-interoperability-challenges

7.            Artificial intelligence can predict patients at highest risk for severe pain, increased opioid use after surgery [Internet]. Available from: https://www.asahq.org/about-asa/newsroom/news-releases/2020/10/artificial-intelligence-can-predict-patients-at-highest-risk-for-severe-pain-increased-opioid-use-after-surgery

8.            Hospital uses AI to move to opioid-free surgery, driving protocol improvements | Healthcare IT News [Internet]. Available from: https://www.healthcareitnews.com/news/hospital-uses-ai-move-opioid-free-surgery-driving-protocol-improvements

9.            Seattle Children’s Hospital Eliminates Opioids for Most Pediatric Outpatient Surgeries | Healthcare Innovation [Internet]. Available from: https://www.hcinnovationgroup.com/analytics-ai/article/21141080/seattle-childrens-hospital-eliminates-opioids-for-most-pediatric-outpatient-surgeries

10.          Anthony CA, Rojas EO, Keffala V, Glass NA, Shah AS, Miller BJ, et al. Acceptance and commitment therapy delivered via a mobile phone messaging robot to decrease postoperative opioid use in patients with orthopedic trauma: Randomized controlled trial. J Med Internet Res. 2020 Jul 1;22(7):e17750.