Monday, May 14, 2018

Real world research worth exploring: Machine learning algorithms in injury prevention

Today, I would like to comment on a recent paper reporting the use of machine learning algorithms to estimate injury risk in team sports athletes (López-Valenciano et al., 2018). Machine learning (ML) is a relatively new approach in sports medicine and science that applies certain algorithms, mostly without pre-defined assumptions, to solve complex problems like the sports injury prediction. As the name indicates, machine learning attempts to make computers "learn" and produce more and more accurate algorithms. As a discipline it integrates statistics with computer science.

In the study of López-Valenciano, a total of 132 male professional soccer and handball players underwent pre-season screening evaluation which included personal, psychological and neuromuscular measures. In addition, injury surveillance was employed to all musculoskeletal injuries during the season. The authors employed different learning techniques to check their accuracy in injury prediction.

Their results showed that the machine learning algorithms presented moderate accuracy for identifying players at risk of injury. From other studies, we know that ML accuracy can be improved with more data entered in the analysis. Nevertheless, the novelty of the study of López-Valenciano and colleagues is they showed that machine learning can assist in solving problems like the identification of players at risk. However, one should bear in mind that ML algorithms work well for the population they were created and we cannot predict what will happen with another set of data.

Tuesday, May 8, 2018

Real world research worth exploring: Accelerometer-based prediction of sports injury

The use of accelerometers in studying the non-contact injury risk is a hot topic both in team and individual sports. Recently a research team from the University of California tested the hypothesis that the running-related injuries were the result of a combination of high load magnitude and strides number that result in accumulated microtrauma (Kiernan et al., 2018). During the studying period of 60 days, elite runners wore a hip-mounted activity monitor to record accelerations while training. From these accelerations the researchers estimated the vertical ground reaction forces (vGRFs). Their results showed that  the injured athletes had significantly greater peak vGRFs and weighted cumulative loading per run. 

The beauty of this study is the use of a common accelerometer to derive data associated with injury risk. Of course, these findings should be verified in bigger samples but the main message of this study is that this type of microtechnology, much cheaper that the GPS-embedded accelerometry, may assist in injury risk management for athletes/teams with limited resources.

Wednesday, May 2, 2018

Player performance metrics: time to reconsider our approach!

There are different performance metrics but most of them are looking at football performance in a fragmented way. For instance, match running distance at different speeds is considered as an important index, sometimes without taking into consideration the match context (player's position, opposition performance etc). 

Also, it seems that some actions, very decisive for the team performance, are not properly evaluated. As an example, in one moment in last night's match Bayern Munich striker defended very effectively against Ronaldo (at 6th minute of the match, match highlights here ). 

How would you rate an attacker's performance doing fantastic work while team is defending? Is it time to reconsider our approach and integrate physical performance  with technical and tactical data? Your thoughts?

Monday, February 5, 2018

How to test your players? 如何测试你的运动员的健身?

Fitness testing in football (soccer) can be a useful tool to 1) identify individual's needs, 2) reduce the risk of injuries, and 3) optimize training plans and performance. There is a number of tests that a sport scientist and practitioner can use. Before you choose, it would help if you answer the following questions:

-Why am I testing the players?
-What is my plan for the next month and the whole season?
-Which of the tests in the literature are valid, reliable and sensitive to training?
-Which of those that fulfill criterion 3 above, does my coach like?

To make it simple for you, I have summarized in table 1 below the most common tests. Their validity and reliability varies a lot and should you want to know the in-depth details you can read table 2 as well as our review paper on that topic (Paul & Nassis, 2015a). In general, all the below tests have acceptable validity and reliability.

While this is a guide, I advise you, especially the junior practitioners, before you go ahead and speak to the coach, better to have plan B too. Sometimes coaches may prefer a different test to the ones on the list. 

Table 1. Common tests used for fitness assessment in football (soccer)
Football Fitness Element
How to test?
Where can I find more info to back up my proposal?
 Sprinting ability
10-m, 20-m, 30-m, 40-m sprint
Paul & Nassis (2015a)
 Change of direction ability
T test
Slalom sprint
Slalom dribble sprint
Paul et al (2016) 
Huijgen et al (2010)
Huijgen et al (2010)
 Muscle strength/Power
Different types of jumps
Isokinetic dynamometry
Paul & Nassis (2015b)
 Aerobic fitness
 Yo-Yo intermittent recovery test
30-15 intermittent test
Bangsbo et al (2008)

Buchheit (2008)
Repeated Sprint Ability
7 X 30m or 6 X 20m 

Dribbling ability
 30-m slalom dribbling 
Huijgen et al (2010)

Table 2. Summary of the tests advantages and disadvantages (modified Paul & Nassis, 2015a)

Sources & related links

Bangsbo et al (2008). Sports Medicine 38(1): 37-51, read here

Buchheit (2008). Journal of Strength & Conditioning Research 22(2): 365-374, read here

Huijgen et al. (2010). Journal of Sports Science 28(7): 689-698, read. here

Paul, Gabbett & Nassis (2016). Sports Medicine 46(3): 421-442, read   here

Paul & Nassis (2015a). Pediatric Exercise Science 27(3): 301-313, read here

Paul & Nassis (2105b).  Journal of Strength & Conditioning Research 29(6): 1748-58, read here

Thursday, January 11, 2018

Coach, better to do whole body cryotherapy or cold water immersion?

This is a frequently asked questions by players and competitive athletes after they have completed prolonged and exhaustive exercise. Should you have the resources available in your club, this is a true dilemma. Both forms of cryotherapy, either whole body cryotherapy (BC) or cold water immersion (CWI) are used to speed up recovery. The suggested mechanism of potential beneficial effect of cryotherapy is associated with reduced inflammation, muscle damage and muscle soreness perception. Whether or not cryotherapy assists in a faster recovery of the functional capacity and sports performance is still debatable.

Whole body cryotherapy is gaining more popularity and this is due to the fact with this form of cryotherapy athletes can be exposed to far higher temperatures compared to CWI (around -85  °C vs. -10  °C). This level of air temperature during the whole BC is assumed to limit inflammation by reducing peripheral blood flow and, hence, speed up recovery after exhaustive exercise. However, there is very little evidence to support this assumption. Therefore, the effect of whole BC vs CWI is still under investigation.

In a recent study, published in the European Journal of Applied Physiology, 31 trained but recreational runners completed a test marathon and following the run they were allocated in 3 groups in terms of the recovery means they used: the CWI group, that immersed lower limbs and iliac crest at water of 8 °C for 10 min; the whole BC group, that was exposed to two cold treatments in a cryotherapy chamber (3 min at − 85 °C  followed by a 15-min warming period in ambient temperature + 4-min bout at − 85  °C); and the placebo group. Participants in the placebo group consumed 2 × 30 ml per day of a fruit flavored drink which did not contain any antioxidants or phytonutrients 5 days before the run, in the day of the run and for 2 days after. In this group, participants were simply asked to rest in ambient temperature for 10 min following completion of the marathon.

The results of this study showed that the implementation of a cryotherapy intervention resulted in at least unclear effects for every outcome measure when compared to the placebo intervention. As the authors state in their manuscript it seems that any beneficial effect of cryotheraphy after exercise is simply a product of the placebo effect.

These findings support the idea of planning the recovery strategy that best fits the beliefs and the needs of the individual athlete.


Wilson et al (2018). Recovery following a marathon: a comparison of cold water immersion, whole body cryotherapy and a placebo control. European Journal of Applied Physiology 118:153-163.

Tuesday, January 2, 2018

The best scientists get out and talk to the coaches

Are you a sport scientist and medical team member wondering why the coaches can't understand you? To make you feel better let me say you are not the only one. In a survey with high level football club staff it was reported that their injury prevention programs' effectiveness was lower than initially expected. The reason being the low coaches' engagement (1).

As many would agree there is a gap between the staff in the lab and the treatment room and the coaches. Sometimes or most of the times they don't speak the same language. What can we do? Let's start with small changes. The first step is to get out of the lab and talk to the coaches. Talk to them using a language they can understand. Talk when it's needed and communicate what's important. Day by day communication will build trust. Trust will build confidence in your relationship and, with time, trust and confidence will make things better.

The figure below is a short description of steps that could help in making the connection between team members stronger. Should you want to read more on tips of more effective communication you can read this article

Figure 1. Four tips to become a better professional.

For further reading
1.Akenhead and Nassis (2016). Training load and player monitoring in high-level football. Int J Sports Physiol Perform 11(5): 587-593  here