How Technologists and Clinicians Can Work Together on Identifying a Problem and Creating a Solution

Joe Marks bio photoJoe Marks, PhD, is the Executive Director of CMU’s Center for Machine Learning and Health (CMLH) and leads the strategic initiatives, business development, and negotiations for the Center. Joe brings a diverse background to CMLH that includes leadership roles at Disney Research and Mitsubishi Electric Research Labs (MERL), and involvement in multiple startups. We sat down with Joe to get his perspective on how technologists and clinicians can work together on identifying problems and creating solutions.

Why is it important that technologists and clinicians work together?

The main reason is that these people have different skillsets, objectives, and resources – the sum is better than the parts. It takes time to become an expert clinician and an expert technologist, so the best way to combine these areas is to get people to work together rather than trying to find the very rare person who would embody both sets of skills.

What are some of the challenges that face technologists and clinicians who are interested in coming together to develop solutions in healthcare?

The first step is finding a common language for collaboration so that these specialists can communicate and work toward a shared goal. Another thing is respecting the different incentives and motivations that each may have. For academics and universities, it’s publishable research. For clinicians, it’s serving their patients. For some technologists who aren’t academics, it can be commerce and entrepreneurship. So, when setting up a collaboration, you want to make sure that everyone’s incentives are understood and met – and that will go a long way in creating an effective team that marches in the same direction.

What are some strategies that can help?

Bringing different ‘worlds’ together can be challenging. Getting people together in the same physical space can play a part – although challenging right now given the current climate – but getting people to rub shoulders can be beneficial. Another thing that we can do to facilitate this collaboration is to create forums for these individuals to share their work, whether that be through tech talks or other presentations. These types of forums also have to be accessible to people in other areas. Then, you just need to get people to work together. Start out with a smaller problem as a ‘warmup’ exercise and allow these different teams to get to know one another and appreciate their different skillsets and motivations. Once they have a warmup problem under their belts, they can move on to tackle something really difficult.

Team sports are a great example of this. You don’t have teams made up of just one position. You have teams made up of various positions, each with a different skill set. They need to learn to appreciate each other’s strengths and skills in order for the entire team to be more effective.

And while we are focusing on teams of technologists and clinicians, even these teams are made up of more than just those two groups. Though they may be the principal investigators, it often takes many more people and positions to truly tackle these problems.

Can you provide 1 or 2 examples of technologists and clinicians working together to identify meaningful challenges and develop a solution?

Two projects come to mind from the current CMLH portfolio –

This project aims to measure intracranial pressure (ICP) non-invasively. Continuous measurements of ICP are currently only possible by means of invasive pressure probes, which require surgery. This team is developing non-invasive ways to measure ICP as well as to quantify such blood flow regulation. For this, they measure cerebral hemodynamic changes with optical techniques, such as near-infrared spectroscopy (NIRS) and diffuse correlation spectroscopy (DCS). Specifically, these techniques measure the light interaction with the brain, by placing optical probes on the surface of the head.

There’s fascinating technology taking place here focusing on the light absorption and detection, and the physics of that. There’s also fascination from the clinical issues such as why you are doing this in the first place, how it might work, and how it might benefit patients. You couldn’t possibly imagine doing this without deep expertise on both sides of the team.

Publication: Estimating Intracranial Pressure Using Pulsatile Cerebral Blood Flow Measured With Diffuse Correlation Spectroscopy

Researchers from CMU’s School of Computer Science and the University of Pittsburgh School of Medicine are combining areas of expertise and techniques that span machine learning, immunology, and genomics to develop new methods of diagnosing Alzheimer’s disease (AD) that are less expensive than current standards and that may help researchers discover possible treatments. This team is developing biomarkers that would enable AD to be diagnosed with a blood test, rather than by the use of expensive brain imaging techniques.

The team is bringing computational techniques to understand, analyze, and predict anything related to human genomics broadly defined. This work is at the cutting edge of computational biology, machine learning, and medicine.

Publication: Conserved Epigenomic Signals in Mice and Humans Reveal Immune Basis of Alzheimer’s Disease
Please share any other insights.

For great teams, it’s more than just technologists and clinicians – true impact requires even more people such as business folks, lawyers, project managers, designers, etc. Collaboration is the key to innovation in healthcare!

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.