Project Spotlight: Personalized Pain Treatment (update)

In 2019, we first learned about the Personalized Pain Treatment (PPT)TM project. Chronic pain impacts more than one third of the US population, generating total annual health care costs exceeding $600 billion. A key contributor to the growing financial burden of chronic pain is the fact that patient response to different pain treatments varies dramatically between individuals. PPTTM is a shared decision-making tool that utilizes machine learning to predict an individual patient’s response to various pain treatments. Today, the project is wrapping up and we had a chance to connect with investigator Dr. Ajay D. Wasan, Professor of Anesthesiology and Perioperative Medicine and Psychiatry and Vice Chair for Pain Medicine at the University of Pittsburgh, to learn about the key takeaways.

Can you please provide a brief refresher on your project and its goals?

PPT TM is a software prototype whose Phase 1 development was funded by UPMC Enterprises and the PHDA. It is a shared decision-making tool to help patients and providers decide which treatment(s) are most likely to work in treating chronic pain. The machine learning algorithms apply to the most frequent chronic painful conditions, such as low back pain, arthritis pain, fibromyalgia, and diabetic neuropathic pain. Based on the patient’s individual phenotype, PPT TM provides personalized pain treatment recommendations for which classes of treatments are most likely to be effective: medications (non-opioid and/or opioid), rehabilitation (physical or occupational therapy), injections, integrative medicine (such as acupuncture) or behavioral health (pain psychology or psychiatry). There are predictive analytical models for 20 different treatments (such as different medication classes or types of injections), and the models all have high accuracy.

What has been the most exciting or unexpected learning from your project so far?

We had to do a lot of pioneering data science in this project to generate the most robust, accurate, and clinically useful prediction models. We are at the bleeding edge of innovation in this field. On a personal level, I am learning so much about what it takes to create a startup company and I am in a much better place now to do so.

Have you encountered any roadblocks that you did not anticipate?

Yes, there were sizable roadblocks in almost every aspect of our project plan. Once we worked through these and produced an actual working prototype of PPT TM, I think the main roadblock has been communicating to all the different stakeholders the value of PPT TM and getting them to believe in it. For instance, the key message to a clinician is much different than the key message to a researcher, a healthcare administrator, an insurance company, or an investor. It has been very hard to anticipate what issues are most critical to them. On the flip side, we really believe in PPT TM and it has so much value in each of these areas, and it has been hard to communicate this magnitude without people getting lost in the details.

What are some of the biggest takeaways from your project so far?

Successful innovation is a key ingredient, but the invention is not a reality unless a dedicated team with expertise in commercialization is just as involved.

What are your project’s next steps? 

The PPT TM team intends to commercialize the software for use within and outside of UPMC. We are working with the PHDA to secure funding for a Phase 2 period of extensive testing in primary care.

Subscribe to our newsletter to get the latest Alliance news, event invitations and updates, and behind-the-scenes spotlights on our researchers, projects, and team members.
Subscribe

By clicking Submit, I agree to the Pittsburgh Health Data Alliance's Terms of Use and Privacy Policy.