Hamstrings, running cadence, ping-pong

and other things I read about recently

Machine learning for hamstring injury prediction

John Kiely, a previous guest on the podcast, reports that the Orecco Motion Data Collective (of which he a team member) has recently claimed a high level of success in predicting hamstring injury in athletes by using machine learning algorithms. This was done by using high fidelity cameras to determine a player’s “movement signature”, and then identify significant changes in the signature, which indicate risk.

Here are some quotes from their website explaining the research:

Each player, over time, develops a personalised motion signal – a set of habitually recurring movement characteristics and sequences including patterns of runs, turns, accelerations and decelerations executed at varying intensities. These signatures which, although persistently adapted and modified to respond to specific game events, remain remarkably consistent during games and across seasons, typically only deviating outside preferred movement bandwidths following some perturbing event or sequence of events – for example, the accumulation of fatigue, painful sensitisation, psycho-emotional distress and/or concussive events.

…

This transition, from habituated to unhabituated solutions, imposes unaccustomed mechanical stress, increases movement error, diminishes movement smoothness and drives a creeping cascade of negative events serving to escalate injury likelihood.  

In short, deviations outside of habituated movement bandwidths reflect risk.  

…

We have built a predictive model, with interpretable features, using a combination of computationally intensive statistical models and machine learning algorithms. The model correctly identified 85% of hamstring injuries (i.e. sensitivity), when applied to data independent of the model building process, with 86% specificity.  

A lot of this material is over my head, and these results should certainly be interpreted with caution. But this looks like an interesting development to follow. Maybe I will ask John Kiely to come on the podcast again and explain these results in more detail.

You can find my earlier conversation with John, where we talked about the issue of hamstring injuries, here.

Federer retires

As a tennis player I’m biased. But for me, Roger Federer was the most graceful athlete of all time. (With the possible exception of Michael Jordan.) Even the way he walked around the court between points was impressive.

David Foster Wallace was also impressed. He wrote a famous article called Roger Federer as Religious Experience. Here’s ten minutes of Federer backhands.

Quiet eye for ping pong

There is a robust line of research on the benefits of a "quiet eye" in sports with a target. It finds that (1) experts fix their gaze on the target earlier and longer than novices (2) gaze fixation is longer on hits than misses; and (3) practicing a quiet eye is a reliable way to improve performance.

A new study (h/t Rob Gray) measured quiet eye duration in ping pong players while they hit shots that were either simple (where the target was the whole table) or more complex (where the target was a narrow part of the table.)

It found that gaze fixation was: (1) longer when the task was more complex; (2) shorter on missed attempts; and (3) longer immediately following a miss.

The authors concluded that

quiet eye sustains performance in an interceptive timing sport, by helping athletes to process and respond to complex information, and by helping them to recover after missed shots.

More on quiet eye research here.

Predictions can fool you

I’ve seen several versions of this cool illusion but this one was too good not to share. I had to read it three times:

Here’s a post on predictive processing to help explain why this happens and why it matters for understanding pain and movement.

For more on predictive processing, check out this podcast with Mark Miller.

Music and running cadence

Many running experts recommend increasing running cadence as a way to reduce injury risk. There doesn't seem to be much direct evidence supporting this claim, but there is a lot of indirect evidence showing that increased cadence can reduce over-striding, reduce breaking forces, and reduce peak vertical forces, all of which sound like good things. So if want to improve your form, playing with cadence might be a productive experiment.

What is the right cadence? 180 strides per minute is often recommended as a goal, but the optimum will of course depend on the individual.

I gravitate toward a pace of around 165, and have played around with speeding up. This feels OK, but it takes a lot of concentration to maintain, and as soon as my mind wanders, it gravitates back to 165.

Tom Goom recently pointed to a new study describing what might be an easy way to change your cadence - just listen to music with the right rhythm and run to the beat.

The study asked runners with low baseline cadence to run in sync with music that would speed their stride rate by 7-10%. They ran for four weeks with the music and then another four weeks without music while attempting to maintain the same rhythm.

Each runner was able to increase their cadence about 8% while listening to music and maintain most of this change when the music was removed. The increased cadence did not cause any increases in speed or heart rate.

Here’s a spotify playlist to help you run at 180 strides per minute. I can’t vouch for its musical quality.

I can say from my own experience that my fastest 5K run of the past year came while listening to Master of Puppets (220 BPM) on what was intended to be an easy run.

Podcast on posture

I recently appeared as a guest on a podcast by Jenni Rawlins and Travis Pollen. We talked about how posture is overrated. It was a very nice conversation.

Brain specific genes and chronic and acute back pain

Another piece of evidence that chronic pain is a different beast from acute pain, and that the main differences lies in the brain: A genome-wide association study of 375,000 individuals in the UK biobank was able to identify genes that predispose people to chronic pain, but they could not find any such genes increasing the risk for acute back pain.

Some relevant quotes from the paper:

The background:

Heritability estimates for back pain from twin studies range from 30% to 68%. Twin studies also show shared heritability between chronic back pain and lumbar disc degeneration, depression, anxiety, education, obesity, and chronic widespread musculoskeletal pain.

One important question is whether acute pain and chronic pain have similar underlying genetic pathways. Here, we performed GWAS for both acute and chronic back pain groups in 2 large human cohorts to characterize the corresponding molecular and cellular pathways contributing to these pain states.

The conclusion:

Chronic back pain is substantially more heritable than acute back pain. This heritability is mostly attributed to genes expressed in the brain.

Previous genetic and imaging studies have reported a CNS component contributing to multisite chronic pain. Our results together with others imply that a central component may be important for localized chronic back pain as well, but not for acute back pain.

…

we found genetic overlap of chronic back pain with sleep disorders, neuroticism, and BMI … the overlap is localized in genes predominantly expressed in the CNS: limbic system, parietal lobe, brain stem, cerebral cortex, entorhinal cortex, cerebellum, hippocampus, and metencephalon.

For more on connections between chronic pain and the brain, see this post.

2-hour workshop on rolling movements

In case you missed it my post last week, I am offering a 2-hour workshop on rolling movements on October 2. Learn more by clicking here.