PainRelief.com: What should readers take away from your report?
Response: Our goal is to improve people’s health by helping them gain access to treatments that can effectively reduce pain. We know that many people have become users and over users of pain medications after surgery, and we want to help reduce that burden for patients, their families, and society at large. As physicians, we want to be able to get the right treatments for the right patients and help our colleagues to make the right decisions. We believe that with the advent of electronic data capture for medical records, many opportunities exist to utilize these data to generate novel tools to help improve the treatments we provide patients. For this study, we, as anesthesiologists, wanted to accurately predict which patients were at the highest risk to experience severe pain and who would need the highest doses of opioid pain medication after surgery. Creating a tool that can take multifaceted data and identify the at-risk patients prior to surgery means that our surgical and anesthesia teams can create tailored personalized approaches for patients. This will mean that the patients can experience less pain, and also means that patients will get optimal opioid pain medication after surgery.
Our current model can accurately predict which patients will require high doses of opioids to control their pain 80% of the time. This prediction value is only the beginning and we believe that we can improve the performance of the model as we add more components and patient data to it. We also are excited to be able to share this approach with our colleagues.
PainRelief.com: What recommendations do you have for future research as a result of this work?
Response: The first step is external validation at another Boston hospital. At the same time, we plan to integrate the models with our electronic medical record (EMR) and are looking to partner with EMR vendors to integrate our model into their systems. This will allow for a message to pop up when the surgeon and/or anesthesiologists open the patient’s chart, alerting them that the patient is at high risk for high opioid requirements after surgery. The team taking care of the patient can then adjust their plan to maximize non-opioid analgesic strategies (e.g. nerve blocks, other non-opioid pain medication) with the goal to reduce the opioid needs after surgery and ultimately the risk for chronic opioid use.
We are excited to share our models with other institutions and groups as well. They could use the provided code to implement and integrate the models into their systems. The first step would be validating and calibrating the models within their environment/patient populations. For this study, we have developed 3 different models with similar performance: logistic regression, random forest and artificial neural networks (ANN). Currently, the logistic regression and random forest models perform slightly better than the artificial neural network model. However, with the input of additional data and deep learning techniques, we anticipate the ANN to improve over time and it may become the preferred model in the future.
PainRelief.com: Is there anything else you would like to add?
Response: I have no conflict of interest or disclosures. We are thrilled to share this approach with our colleagues, and we think that it can be readily built up on and improved and we look forward to future collaborations.
We hope that this tool will help reduce unnecessary prescriptions of opioids for those who don’t need them and help gain access to non-opioid treatments after surgery that may be more beneficial.
Citation: Anesthesiology 2020 abstract
Predictors Of Severe Acute Post-surgical Pain And Opioid Use After Cesarean Delivery
Jingui He, B.S., Claudia Cao, M.D., Kara Fields, M.S., Pankaj Sarin, M.D., Kristin Schreiber, M.D.,Ph.D., Mieke A. Soens, M.
The information on PainRelief.com is provided for educational purposes only, and is in no way intended to diagnose, cure, or treat any medical or other condition. Always seek the advice of your physician or other qualified health and ask your doctor any questions you may have regarding a medical condition. In addition to all other limitations and disclaimers in this agreement, service provider and its third party providers disclaim any liability or loss in connection with the content provided on this website.