Applied Sports Science newsletter – May 20, 2016

… How did this Australian NBA revolution—referenced by both the Wall Street Journal and Newsweek over the last year—come about?

The answer lies in a training gym named after Longley at the Australian Institute of Sport (AIS) in Canberra—and a basketball programme that is fuelling an Aussie basketball revolution.

… Technically, McCaffrey is unlike anybody that any college football team has ever had: Never before in the sport’s history has a player amassed 3,864 all-purpose yards in a single season. And while record-breakers normally graduate or move on to the NFL draft, McCaffrey did that damage as a sophomore, so Stanford is enjoying the unique prospect of trying to improve upon last season’s production.

Even Stanford coach David Shaw didn’t anticipate McCaffrey’s progression as a sophomore. “The year he had last year,” Shaw said. “I anticipated that would be his junior year.”

Stanford coaches backed away from McCaffrey’s planned training regimen earlier this offseason to allow his body to recover from the 437-touch workload he endured last year.

Purpose The aim of this study was to quantify and predict relationships between RPE and GPS training load variables in professional Australian Football (AF) players using group and individualised modelling approaches. Methods Training load data (GPS and RPE) for 41 professional AF players was obtained over a period of 27 weeks. A total of 2711 training observations were analysed with a total of 66 ±13 sessions per player (range; 39 to 89). Separate generalised estimating equations (GEE) and artificial neural network analyses (ANN) were conducted to determine the ability to predict RPE from training load variables (i.e. session distance, high-speed running (HSR), high-speed running %, m·min-1) on a group and individual basis. Results Prediction error for the individualised ANN (root mean square error [RMSE]; 1.24 ±0.41) was lower than the group ANN (RMSE; 1.42 ±0.44), individualised GEE (RMSE; 1.58 ±0.41) and group GEE (RMSE; 1.85 ±0.49). Both the GEE and ANN models determined session distance as the most important predictor of RPE. Further, importance plots generated from the ANN revealed session distance was most predictive of RPE in 36 of the 41 players, whereas, HSR was predictive of RPE in just 3 players and m.min-1 as predictive as session distance in just 2 players. Conclusions This study demonstrates that machine learning approaches may outperform more traditional methodologies with respect to predicting athlete responses to training load. These approaches enable further individualisation of load monitoring, leading to more accurate training prescription and evaluation.

If at first you don’t succeed, try again — and then try something else.

Tim Rees, lead author of The Great British Medallists Project, wasn’t worried that his adage-debunking study would prove controversial. Rather, he was concerned that another academic would beat him to the punch.

Rees’s research was kept secret for two years so that its financial backer, UK Sport, could implement the findings and build a competitive advantage against the rest of the world.

In the end, Rees’s study took priority, and, in doing so, turned some conventional thoughts about sports development on its head.

The chances of success for this country’s teams on the world stage have received a further boost with the appointment of Dr Andrew Foskett as the Head of Sport Science for New Zealand Football.

The position is a consultancy role and Foskett will be given the directive to develop and oversee the implementation of sport science strategies across the high performance and development pathways.

… The Canucks’ interest in sleep began in 2008 when they partnered with Fatigue Science, a Vancouver-area company that helps a variety of clients through their Fatigue Avoidance Scheduling Tool (FAST), a proprietary wearable device that allows users to log their sleep patterns to optimize performance. The software algorithm used to map out a user’s sleep schedule was partially developed by the United States Air Force.

“A big part of our business is fatigue risk management,” said Jacob Fiedler, Fatigue Science’s sales director. “Which is using the technology to very precisely evaluate an individual’s fitness for duty. Whether they’re flying a plane or a guy working in a mine driving a truck in the middle of the night. Our technology can quantify both sleep and fatigue impairment. So it can be used to mitigate the risks associated with that.”

Google has announced a new version of its Android Wear software, called Android Wear 2.0, and with it announced two fitness-related updates: automatic activity tracking and a Google Fit data exchange API. The announcement was made at the Google IO event.

“We know that the most important role of your watch is helping you stay connected to what matters — to important timely information, to the people you love, and to your health, all from your wrist,” Google VP of Engineering David Singleton said at the Google IO event.

He added that the company is improving Android Wear’s fitness experience with automatic activity recognition. Earlier today, Fitbit announced that its app will include a similar feature for Google phones. The app update, which is for Google’s Nexus 5X and Nexus 6P devices, uses the Android Sensor Hub to automatically track movement without using a lot of power.

While urine dipstick tests are some of the easiest diagnostic tools physicians have, they can often be misleading if a poorly trained person does the test. Moreover, lighting and other factors can make colors seems not what they are and skew the results significantly.

At Stanford University researchers have been working on an easy-to-use device that can essentially automate the entire process and even read the results for you. It’s a black box with a mechanism that separates a urine sample into ten identical amounts and places those into ten holes at the bottom of the box. Each hole, just like on a traditional dipstick test, tests for a unique chemical biomarker. Once the sample is delivered, the user places the phone on top of the box and starts the matching app.

I recently read a review of research that has been conducted into devices for monitoring physical activity. One of the conclusions the authors came to was:

‘Co-operative work between engineers, computer scientists, and academics in relevant fields is needed to develop these technologies.’

Based on our latest research I would also add coach developers to this list.

At 6-foot-6, 314 pounds and in the best shape of his life, it takes a lot to intimidate Tariq Cole.

Allison Kreimeier needed just 10 words and a “silly look” to do the trick after the Rutgers football left tackle sat down next to her with a muffin from the new 24-hour snack stand in the Hale Center.

“She looked at it and said, ‘Oh wow, that’s a lot of sugar on a muffin,’” Cole said, laughing at the memory of feeling dejected. “I was like, Oh? OK.’ I put it back and got an apple. She monitors my plates and everything I need to eat. Having her around is great.”

The Ravens have changed their nutrition program and are putting in significant resources to make sure the players are as healthy as possible.

*In a previous article, which can be found here, I looked at why it’s the profile of the player that’s key when going on a recruitment drive and not their history or their current position. Scouting helps build up such a profile. In this article I look at how and why traditional scouting and stats based research are both necessary in the quest for the perfect signing.*

… Such a long layoff for one team and a tight turnaround for the other can spin either way — rest or rust — but there isn’t any statistical evidence that inequalities in rest between series help or harm teams in the playoffs.

Roy Hodgson’s team will go into Euro 2016 better prepared physically than any England tournament side before them thanks to a new collaborative partnership between Premier League clubs and the squad’s medical staff that has given them unprecedented access to performance data.

The two senior medical figures working with the squad, Dr Ian Beasley, the Football Association’s head of medical services, and Gary Lewin, the chief physiotherapist have reached agreement with the Premier League clubs to share their performance and fitness data for the first time.

… Each NFL Sunday, we see tactics and play calls that make the fans on the upper concourse howl and cause the message boards to hyperventilate. Coaches call plays that “everybody” knows have little chance of success.

But does “everybody” really know which plays work more often than others?

With the help of the Football Outsiders in-house database of tens of thousands of sortable NFL plays, I worked out the success rates for several of the most criticized and reviled NFL tactics.