The Neuroscience Of Pitch Recognition

When asked to describe Greg Maddux, the retired 4-time Cy Young award-winning pitcher, Wade Boggs, a Hall of Fame hitter with a .328 lifetime batting average, once said, “It seems like he's inside your mind with you. When he knows you're not going to swing, he throws a straight one. He sees into the future. It's like he has a crystal ball hidden inside his glove.” 

So, what did Maddux know that other pitchers don’t?  Neuro-engineers from Columbia University decided to actually look inside some hitters' brains to try to find out.

Maddux, who seems to be a lock for the 2014 Hall of Fame class, earned a reputation for knowing batters so well that he could think one step ahead of them.  "When you think it's a ball, it's a strike,” confessed former Yankees manager Joe Torre. “When you swing at what you think is a strike, it's in the dirt. He was a remarkable pitcher."  This lack of pitch recognition skill by hitters is what all good pitchers try to exploit.  While hours of batting practice try to teach this through repetition, there have been surprisingly few attempts at finding out what’s really happening under the batting helmet.

Jason Sherwin, Jordan Muraskin and Paul Sajda, biomedical engineers at Columbia’sLaboratory for Intelligent Imaging and Neural Computing, specialize in motion perception and high speed decision making but are also baseball fans.  Last year, they reported that they had been able to pinpoint the timing of pitch recognition within the brain.  Fitted with electroencephalography (EEG) skull caps, test volunteers watched 12 sets of 50 different video pitches that were either a fastball, a curve or a slider.  They were asked to immediately identify the pitch they just saw, before the pitch arrived over the plate, by pressing a certain computer key.

Comparing correct answers with the EEG data, the researchers were able to determine the exact millisecond when recognition happened in the brain, or when the hitter locks onto a pitch knowing what’s on the way.  Fastballs were the fastest to be recognized with curve balls taking the longest.  However, sliders had the highest average prediction accuracy at 91% while fastballs were only guessed correctly 72% of the time.

Mapping the response times with the trajectory of the ball, the recognition typically happened in the middle third, between 32 and 40 feet, of the ball’s path to the plate.

Their study appeared last year in Frontiers in Decision Neuroscience.

After discovering when pitch recognition happens in the brain, the team then wanted to see where it occurred.  By combining the timing clues from EEG with the location-specific data of functional magnetic resonance imaging (fMRI), they could see a more complete model of decision making.  This time they used college baseball players and showed them a combination of 468 fastballs, curves and sliders, while wearing EEG caps and lying inside an fMRI machine.

Figure 1

Cross-referencing the pitch’s trajectory, the “light bulb” recognition moment and the fMRI map of the player’s brain, they not only confirmed their earlier research of a pitch-guessing neural network but also a fascinating twist.  For correct guesses, the brain logically lit up in its visual and motor cortex areas.

However, for the incorrect guesses, activity moved to the prefrontal cortex of the brain, known to be used for conflict resolution and higher level decision making. As can be seen in Figure 1, red areas indicate regions that have higher activations during correct pitch guesses, while blue areas indicate regions with higher activations for incorrect choices.

So, when the visual information isn’t enough for an automatic recognition, it appears that the problem gets escalated to add in other known facts or previous experiences.

This new research was presented at last month’s Sloan Sports Analytics Conference.

So, what good would this baseball neuroscience be against today’s great pitchers?  The authors ask us to imagine a new era of baseball training, where step one is to capture a baseline of each player’s neural recognition ability.  Realizing when a hitter is able to make a correct prediction of a pitch and seeing first-hand their brain’s reaction time will identify specific training opportunities.  Step two is to use a pitch simulation tool to see hundreds of pitches, measuring performance improvement in accuracy and speed.

“Knowing the neural circuits involved in the rapid decision-making that occurs in baseball opens up the possibility for players to train themselves using their own neural signatures,” concluded Sajda.

Tony Gwynn, another Hall of Famer known for studying video of opposing pitchers, would have appreciated this technology twenty years ago when facing Maddux. “He’s like a meticulous surgeon out there...he puts the ball where he wants to," remembered Gwynn. "You see a pitch inside and wonder, 'Is it the fastball or the cutter?' That's where he's got you.”

Join Axon Sports on Twitter and Facebook.

Why The Best Soccer Players Are Real Head Turners

In soccer, like many sports, the goal scorers get the headlines. Yet, they will secretly admit that the final pass played to them is very often their key to unlock the defense. Without the vision of a teammate to pick them out of a crowd, their finishing skill is almost useless.

As players progress through the ranks of high school, college and beyond, not only do their opponents get quicker with their feet but also with their eyes and brains.  Their time with the ball gets shorter forcing them to either make the correct pass or avoid the oncoming defender.  The luxury of time to survey the field for targets after they receive the ball is now gone.  The available options need to be gathered and assessed constantly so that when the ball arrives at their feet, the homework is already done.

So, what do top players do differently that makes their decisions consistently fast and correct?  Geir Jordet, a professor at the Norwegian School of Sport Sciences, specializes in perceptual expertise in soccer.  At last month’s MIT Sloan Sports Analytics Conference, he presented new research on what he describes as “the hidden foundation of field vision.”
From previous studies, Jordet knew the importance of visual search strategies in soccer decision making.  However, the typical methods used to test a player’s perception seemed artificial.  Whether it be putting athletes in simulated field situations in a lab or merely relying on a computer joy stick movement, Jordet knew he needed to make the tests more realistic.

“These (lab-based) tasks do not simulate the functional links between perception and natural movements, which may be essential to capture, if the goal is to reveal knowledge about real-game visual perception,” he wrote.

So, he went back to just being a fan and admiring the sport’s best players.  Using SkySport’s Player Cam broadcasts (now discontinued) of English Premier League games, he and his research team could watch isolations of a single player in one screen, while seeing the entire game context on another screen (see image below).

“Such video footage makes it possible to examine how players engage in visual exploratory behaviors by moving their bodies and heads to better perceive events taking place behind their backs,” said Jordet.

From 64 different games, they watched the habits of 118 of the world’s best players to detect the clues they leave on the field during 1,279 actual game situations.  Jordet’s hypothesis was that those players who engaged in the most active search of their surroundings before they received the ball would produce the highest percentage of successful passes once they received possession. He defined an active search as the player turning their gaze and head away from the ball to prepare themselves by trying to pick-up as much information about the positions and movement of teammates and opponents.

Dividing the total exploratory events (turning the head) by the seconds of each scenario yields an average exploration frequency.  Not surprisingly, the two EPL players, Frank Lampard and Steven Gerrard, with the highest frequency rates of .62 searches per second are two of the most successful midfielders currently playing in the league.

In this video clip, watch (and try to count) the number of times Lampard moves his head while waiting for the ball:

When the player received an incoming pass, it was noted if he was able to complete the next pass successfully, especially if it was a forward pass in the direction of his opponent’s goal. A better search should yield better information which should improve the completion percentage of the next pass.

Sure enough, Jordet found a direct correlation between higher exploration frequency and pass completion rates.  Players with exploration frequency below .2 only completed 54% of their passes while those with more than .41 explorations per second had pass completion rates of 73% or higher.

As the research team notes, counting head turns still doesn’t tell us anything about what the player actually saw during those quick glimpses.  It seems they are able to put pieces of the puzzle together with each glance, allowing their brain to assemble the big picture.

“The findings can have major implications for both what scouts look for in players and for how coaches work to improve players’ receiving and passing skills,” concluded Jordet.

In Gerrard's case, this search habit pays off in creating scoring chances, especially in the final attacking third of the field.  The always useful website, EPL Index, just updated their analysis of the top EPL players this season, in these two categories.  As expected, Gerrard appeared in the top five of each ranking (see charts).

As Xavi, Barcelona’s midfield maestro, explains, “Think quickly, look for spaces. That's what I do: look for spaces. All day. I'm always looking. All day, all day. Here? No. There? No. People who haven't played don't always realise how hard that is. Space, space, space. I think, the defender's here, play it there. I see the space and pass. That's what I do.”

Join Axon Sports on Twitter and Facebook.

NBA Fans Hurt Their Home Team's Free Throws

Ask any NBA player or coach where they would prefer to play a high stakes game, home or away, and the vast majority will choose being in the friendly confines of their home arena.  Overall, the win-loss records of most teams would support that, but they would do even better if they taught their home fans a lesson in performance psychology.

When it comes to sports skills, research has shown that we’re better off to just do it rather than consciously thinking about the mechanics of each sub-component of the move.  Waiting for a pitch, standing over a putt or stepping up to the free throw line gives our brains too much opportunity to start breaking down the task.  Add competitive pressure brought on by a close game watched by a loyal home fans and we can easily slip out of the well-practiced mental map, known as automaticity, that usually gets the job done.

But what about elite athletes who are the best in the game?  Surely, they’ve found ways to handle pressure and keep their brains on auto-pilot without getting an online psychology degree?  Actually no, says researchers Matt Goldman and Justin Rao.  In a study presented at the recent Sloan Sports Analytics Conference, they revealed an interesting paradox; playing in front of a home crowd can be both a benefit and a curse for NBA players.

For most of a basketball game, players are in constant motion reacting to their teammates and opponents.  They have very little time for “self-focus” or thinking too much about the dozens of small movements that make up their motor skills, except for one event – the free throw.  After being fouled while taking a shot, the play comes to a halt.  The aggrieved player stands at the free throw line, fifteen feet from the basket, with the other nine players as well as thousands of fans staring at him.

The crowd, thinking they’re doing him a favor, gets eerily quiet.  The pressure builds as he’s allowed to remember the score of the game, how much time is left and the disappointment that he and almost everyone else there will feel if he misses this shot.  To counter this, he starts running through his mental checklist; find a focus point, keep your elbow in, bend your knees, follow-through.  Bringing all of these pieces into his conscious mind will most likely cause him to miss the shot, only adding more pressure if he’s fouled again.

Goldman and Rao compared the stage fright of shooting free throws with another very common basketball skill, offensive rebounding.  Recovering the ball after a missed shot is vital to a team’s chances of winning since it provides another possession opportunity to score.  It’s also a task that is done in the constant motion of the game with the crowd cheering.  There is no time to self-reflect on the skill components of rebounding, it just happens.  If a player does not get a rebound, there is no obvious public shame as the play immediately continues.

So, could playing in front of a home crowd affect one part a player’s game but not another?
Using detailed play by play data from every NBA game from 2005-2010 (six full seasons), including 1.3 million possessions and 300,000 free throw attempts, they first found an expected result that, in general, home team players have a higher overall free throw shooting percentage than the visitors.  However, Goldman and Rao then looked at what happens in clutch situations, which they define, in a detailed mathematical formula, as being late in the game when the score is close.  In those high pressure moments, the home team does significantly worse at the charity stripe than their opponents.  They blame this mostly on the actions of the fans.  To go from constant noise and fast action to perfect quiet and stillness is enough to take even the best basketball players in the world out of their rhythm and into a damaging self-talk state.

At the other end of the court, when visiting players are taking free throws, the crowd, again thinking they’re helping, goes crazy with waving arms, signs and noise.  However, the data showed that the free throw percentages of the visitors in clutch situations remains unchanged from their normal away percentage.  The researchers argue that the distractions actually help the opponents at the line by not allowing them to think about their complicated motor skills.

To show that the pressure doesn’t affect all skills, the stats also showed that the home team’s offensive rebounds got progressively better in clutch situations supporting the theory that positive support can increase effort.  As with free throws, the visiting team’s clutch performance in rebounding was unchanged from normal game situations.

Not all players are created equal.  The study called out a few NBA players as being either clutch at the free throw line or chokers under pressure, including two of the game’s top stars.  Manu Ginobili of the San Antonio Spurs, who has a career 83% free throw percentage, is the player you most want at the line when the game is close.  On the other hand, Paul Pierce of the Boston Celtcs, with an 80% career percentage, was the second worst free throw shooter in clutch situations.

Maybe a few brave Celtic fans at the Garden can begin to reverse the trend and go crazy when Pierce is at the line.  Just be sure to be near an exit.

Visit my new home at Axon Sports on Twitter and Facebook.