Neuroscience Can Project On-Base Percentages Now by Eno Sarris January 11, 2018 I have an early, hazy memory of Benito Santiago explaining to a reporter the approach that had led to his game-winning hit moments earlier. “I see the ball, I hit it hard,” said Santiago in his deep accent. From which game, in what year, I can’t remember. Also, it isn’t really important: it’s a line we’ve heard before. Nevertheless, it contains multitudes. We know, for example, that major-league hitters have to see well to hit well. Recent research at Duke University has once again made explicit the link between eye sight, motor control, and baseball outcomes. This time, though, they’ve split out some of the skills involved, and it turns out that Santiago’s deceptively simple description involves nuanced levels of neuromotor activity, each predictive of different aspects of a hitter’s abilities. Will our developing knowledge about those different skills help us better sort young athletes, or better develop them? That part’s to be determined. A team of researchers spread across Duke ran baseball players from two full professional organizations through a battery of nine tests on Nike Sensory Stations to measure different aspects of a player’s sensory motor abilities. After creating something similar to Major League Equivalency lines for each player, the researchers were able to test the effect of each of the scores against real-life baseball outcomes. “If you have a 23-year-old, completely average outfielder, the model predicts that his on-base percentage in the major leagues would be .292,” explains Kyle Burris, one of the researchers on the project. “The model would expect a similar player who scores one standard deviation higher on the perception span task to have an OBP of .300.” The high-level, easy takeaway from their study is that these skills, taken as a whole, are predictive of good plate discipline. There was no link to slugging percentage, though, so we’re not quite yet predicting full batting lines from your neuromotor scores. But if you drill down a bit into these new findings, you’ll see that there is a great deal here to get excited about. Here’s a profound image that shows how each subsection of the larger skill set was linked to baseball outcomes. Darker colors denote a stronger relationship between the skill and the baseball statistic. A table of findings reprinted with permission from Kyle Burris, Kelly Vittetoe, Benjamin Ramger, Sunith Suresh, Surya T. Tokdar, Jerome P. Reiter & L. Gregory Appelbaum “Sensorimotor abilities predict on-field performance in professional baseball” in Scientific Reports Take a look at the row labeled “perception span,” in particular, and you find an interesting story. That task was linked to good on-base percentages and strikeout rates, but not necessarily good walk rates. “It’s kind of like a game of Simon,” says Burris as he tries to explain the perception-span task, “but for a split second, it gives you shapes that appear in various aspects of your peripheral vision, and you have to determine was there a square there, or a pentagon there, and it flashed at you in a split second and you have to try and remember what the shape was.” When we asked players what they see when the ball is released, a good portion of the responses detailed how little is ultimately visible to the eye. And there’s that study of cricket which suggests that cricket players get more from information they gather before the release of the ball than after. This finding fits right in: players who are good at noticing things on the periphery — like the way a forearm might look different on a breaking ball, or the way the body might drag on a changeup — are better at making contact. Hidden within the other differences between the tasks and their links to outcomes is a similar story: both the ability to suss out quickly the difference between shapes seen both near and far, and also to capture a target quickly were both good for making contact. That makes sense. But why would hand-eye coordination be better for player’s walk rate than his strikeout rate? Partly, this could be because players have to start their swing before they know if they want to swing — a requirement velocity puts upon them — and hand-eye coordination helps them to better stop that swing if the pitch is a ball. Partly, this could be a result of the limited capacity for actually testing hand-eye coordination. The particular task linked to that number requires respondents to tap baseballs as they appear on a screen, testing how fast they can do so. “I’m not sure that it actually goes and tests hand-eye coordination,” admitted Burris, who is headed to Cleveland for a summer internship with the Indians. “There is a little bit of hand-eye coordination in that you have to see it and then immediately translate that to a motor response, but I’d say that that was almost response-time-esque.” If you look at the separate reaction-time outcomes, you’ll see a similar link to walk rate, so maybe that’s the key skill in taking walk. Reacting quicker. Or there’s another way to separate the skills. You could consider the first three tasks — visual clarity, contrast sensitivity, and depth perception — as “hardware.” They’re linked to outcomes, of course, because there’s a decent part of the game that requires good eye sight. But they’re the sort of thing with which you’re born. “There will never be a blind ballplayer,” said co-author Gregory Appelbaum. Those other six tasks, though? They represent the software of our neuromotor system. They represent our ability to take the visual information given to us and process it. Software is more malleable, subject to updates. Software can be changed for the better. “There is evidence that these processes can be improved,” agreed Appelbaum. “There have been demonstrations of neuroplasticity in these processes.” Appelbaum pointed to two interesting studies that pointed to the fact that our neuromotor system’s software could be trained. A study from 2015 of which he was part showed that “significant learning was observed in tasks with high visuomotor control demands but not in tasks of visual sensitivity,” for one. A 2014 study at the University of California-Riverside found that actual baseball outcomes could be improved by using a “perceptual learning program.” In that study, players reported improvements such as being able to see further, and having eyes that felt stronger and didn’t tire as quickly. Appelbaum is ready to find out what these visual training technologies will look like as we go forward. He’s helping launch the Duke Vision Sports Center, a clinic and lab where researchers will use sensory stations, immersive reality, and more, in order to pursue this line of thinking. When it comes to new stats coming out of Statcast, I’ve personally seen a change in how players assess the numbers. Early distaste has given away to curiosity, as more players — Yonder Alonso and Andrew Heaney, for example, in my own experience — now speak up at the end of interviews to ask me about launch angle, exit velocity, and how they can use that data to train and improve. So, while the Boston Red Sox have long been using the link between neuromotor skills and baseball outcomes in their minor leagues in an effort to bring “neuroscouting” to their own organization, these new findings offer a different use for neuromotor study. Instead of sorting players, there’s major potential to use these activities to develop players and get the most out of them. There may never be a blind baseball player, sure. But that’s just hardware. Let’s see how we can make the most out of our favorite player’s software.