AI clinical

Comment: Individuals have unique muscle activation signatures.

We used a machine learning approach to test the uniqueness and robustness of muscle activation patterns. Our results show that activation patterns not only vary between individuals, but are unique to each individual. Individual differences should, therefore, be considered relevant information for addressing fundamental questions about the control of movement.

Hug, F. et al. (2019). Individuals have unique muscle activation signatures as revealed during gait and pedaling. Journal of Applied Physiology.

Machine learning algorithms have been able to identify unique individuals based on their gait pattern for a while. Now we have this study showing that ML can identify individuals from their unique muscle activation patterns. For me the main takeaway is that technology has a level of insight into our bodies that is just going to keep getting better.

As much as we may think that our observations, palpation, and special tests give us useful information to integrate into patient management it’s not even close to the level of detail we can get from machines. I’m fairly convinced that pretty soon we’ll start seeing studies exploring what aspects of physiotherapy assessment are more accurate when conducted by algorithms.

See also, What AI means for the physical exam.

assessment education

Assessing teams instead of individuals

Patient outcomes are almost always influenced by how well the team works together, yet all of the disciplines conduct assessments of individual students. Yes, we might ask students who they would refer to, or who else is important in the management of the patient, but do we ever actually watch a student talk to a nurse, for example? We assess communication skills based on how they interact with the patient, but why don’t we make observations of how students communicate with other members of the team when it comes to preparing a management plan for the patient?

What would an assessment task look like if we assessed teams, rather than individuals. What if we we asked an OT, physio and SALT student to sit down and discuss the management of a patient? Imagine how much insight this would give us in terms of students’ 1) interdisciplinary knowledge, 2) teamwork, 3) communication skills, 4) complex clinical reasoning, and 5) patient-centred practice? What else could we learn in such an assessment? I propose that we would learn a lot more about power relations between the students in different disciplines. We might even get some idea of students’ levels of empathy for peers and colleagues, and not just patients.

What are the challenges to such an assessment task? There would be logistical issues around when the students would be available together, setting concurrent clinical practice exams, getting 2-3 examiners together (if the students are going to be working together, so should the examiners). What else? Maybe the examiners would realise that we have different expectations of what constitutes “good” student performance. Maybe we would realise that our curricula are not aligned i.e. that we think about communication differently? Maybe even – horror – that we’re teaching the “wrong” stuff. How would we respond to these challenges?

What would the benefits be to our curricula? How much would we learn about how we teach? We say that our students graduate with skills in communication, teamwork, conflict resolution, etc? But how do we know? With the increasing trend of institutions talking about interprofessional education, I would love to hear what they have to say about interprofessional assessment in the hospital with real patients (And no, having students from the different disciplines do a slideshow presentation on their research project doesn’t count). Or, assessment of the students working together with community members in rural areas, where we actually watch them sit down with real people and observe their interactions.

If you have any thoughts on how to go about doing something like this, please get in touch. I’d love to talk about some kind of collaborative research project.