Machine Learning Approach for Pitch Type Classification Based on Pelvis and Trunk Kinematics Captured with Wearable Sensors.

The large stream of data from wearable devices integrated with sports routines has changed the traditional approach to athletes' training and performance monitoring. However, one of the challenges of data-driven training is to provide actionable insights tailored to individual training optimization. In baseball, the pitching mechanics and pitch type play an essential role in pitchers' performance and injury risk management. The optimal manipulation of kinematic and temporal parameters within the kinetic chain can improve the pitcher's chances of success and discourage the batter's anticipation of a particular pitch type. Therefore, the aim of this study was to provide a machine learning approach to pitch type classification based on pelvis and trunk peak angular velocity and their separation time recorded using wearable sensors (PITCHPERFECT). The Naive Bayes algorithm showed the best performance in the binary classification task and so did Random Forest in the multiclass classification task. The accuracy of Fastball classification was 71%, whilst the accuracy of the classification of three different pitch types was 61.3%. The outcomes of this study demonstrated the potential for the utilization of wearables in baseball pitching. The automatic detection of pitch types based on pelvis and trunk kinematics may provide actionable insight into pitching performance during training for pitchers of various levels of play.

Individualised Ball Speed Prediction in Baseball Pitching Based on IMU Data.

Ball velocity is considered an important performance measure in baseball pitching. Proper pitching mechanics play an important role in both maximising ball velocity and injury-free participation of baseball pitchers. However, an individual pitcher's characteristics display individuality and may contribute to velocity imparted to the ball. The aim of this study is to predict ball velocity in baseball pitching, such that prediction is tailored to the individual pitcher, and to investigate the added value of the individuality to predictive performance. Twenty-five youth baseball pitchers, members of a national youth baseball team and six baseball academies in The Netherlands, performed ten baseball pitches with maximal effort. The angular velocity of pelvis and trunk were measured with IMU sensors placed on pelvis and sternum, while the ball velocity was measured with a radar gun. We develop three Bayesian regression models with different predictors which were subsequently evaluated based on predictive performance. We found that pitcher's height adds value to ball velocity prediction based on body segment rotation. The developed method provides a feasible and affordable method for ball velocity prediction in baseball pitching.

Predicting elbow load based on individual pelvis and trunk (inter)segmental rotations in fastball pitching.

The baseball pitch is a repetitive, full-body throwing motion that exposes the elbow to significant loads, leading to a high incidence of elbow injuries. Elbow injuries in pitching are often attributed to high external valgus torques as these are generally considered to be a good proxy for the load on the Ulnar Collateral Ligament. The aim of the study is to contribute to elbow load monitoring by developing a prediction model based on the pelvis and trunk peak angular velocities and their separation time. Eleven male youth elite baseball pitchers (age 17 ± 2.2 years) threw 25 fastballs at full effort off a mound. Two-level varying-intercept, varying-slope Bayesian models were used to predict external valgus torque based on (inter)segmental rotation in fastball pitching with pitcher's weight and height added to strengthen the individualisation of the prediction. The results revealed the high predictive performance of the models including a set of kinematic parameters trunk peak angular velocity and the separation time between the pelvis and trunk peak angular velocities. Such an approach allows individualised prediction of the external valgus torque for each pitcher, which has a great practical advantage compared to group-based predictions in terms of injury assessment and injury prevention.

The ulnar collateral ligament response to valgus stress, repetitive pitching, and elbow muscle contraction in asymptomatic baseball pitchers.

Background: In baseball, repetitive pitching leads to medial elbow injuries, particularly to the ulnar collateral ligament (UCL). To prevent pitchers from UCL injuries, it is important to quantify the response to elbow stress. Repetitive elbow external valgus torque and muscular fatigue induced by repetitive pitching could affect markers of the response, that is, humeroulnar joint gap and UCL morphology. The aims of the study were three-folded: to investigate the effect of (1) exerted handgrip force on the humeroulnar joint gap, (2) repetitive pitching on the humeroulnar joint gap and the UCL morphology, and (3) exerted handgrip force on the humeroulnar joint gap for different levels of elbow valgus stress is different after compared to before repetitive pitching in asymptomatic baseball pitchers. Methods: Medial elbow ultrasound images were collected in 15 asymptomatic male baseball pitchers. Three levels of static elbow valgus stress (0N, 50N, 100N) were applied with a TELOS device before and after repetitive pitching and with or without handgrip force. These images were used to assess the humeroulnar joint gap size and UCL length and thickness. After 110 fastball pitches or when 80% self-perceived fatigue on a VAS scale was reached, participants were instructed to stop throwing. Repeated measures ANOVAs were used to statistically test significant differences. Results: Handgrip force did not significantly affect the humeroulnar joint gap. The UCL thickness and length and the humeroulnar joint gap were also not different after compared to before repetitive pitching. While higher levels of applied valgus stress significantly increased the humeroulnar joint gap (P < .001), this effect was not significantly different in the interaction with handgrip force and repetitive pitching. Conclusion: The humeroulnar joint gap changes for different levels of elbow valgus stress. However, adult baseball pitchers did not respond to elbow stress after a single pitching session with or without submaximal handgrip force in the humeroulnar joint gap and UCL morphology.

Magnitude and variability of individual elbow load in repetitive baseball pitching.

In baseball pitchers the elbow is exposed to high and repetitive loads (i.e. external valgus torque), caused by pitching a high number of balls in a practice session or game. This can result in overuse injuries like the ulnar collateral ligament (UCL) injury. To understand injury mechanisms, the effect of repetitive pitching on the elbow load magnitude and variability was investigated. In addition, we explored whether repetitive pitching affects elbow muscle activation during pitching. Fifteen pitchers threw each 60 to 110 balls. The external valgus torque and electromyography of three elbow muscles were quantified during each pitch. Linear mixed model analyses were performed to investigate the effect of repetitive pitching. On a group level, the linear mixed models showed no significant associations of repetitive pitching with valgus torque magnitude and variability and elbow muscle activity. Significant differences exist between pitchers in their individual trajectories in elbow valgus torque and muscle activity with repetitive pitching. This shows the importance of individuality in relation to repetitive pitching. In order to achieve effective elbow injury prevention in baseball pitching, individual characteristics of changes in elbow load and muscle activity in relation to the development of UCL injuries should be investigated.

Fastball pitching performance only slightly decreases after mobility impediment of the pelvis and trunk-Do (catch-up) compensation strategies come into play?

Background: Baseball pitching performance can be mechanically explained by the summation of speed principle and the principle of optimal coordination of partial momenta. Impeding optimal energy generation or transfer by or between the pelvis and trunk segments could provide valuable insight into possible compensation or catch-up mechanisms that may manifest themselves based on these principles. Aim: The aim of the present study was to explore the effects of experimentally impeding the mobility of and between the pelvis and trunk segments (1) on ball speed and mechanical peak joint power, and (2) on mechanical peak load of the elbow and shoulder joints at maximal external rotation (MER) during fastball pitching. Methods: Eleven elite baseball pitchers (mean age 17.4, SD 2.2 years; mean pitching experience 8.9, SD 3.0 years) were instructed to throw at least 15 fastballs as fast and accurately as possible under two conditions. One condition involved impeding the mobility of the pelvis and trunk segments to hamper their ability to rotate independently, which consequently should affect the separation time, defined as the time interval between the pelvis and trunk peak angular velocities. In the other condition, pitchers threw unimpeded. Ball speed, mechanical peak joint power and peak net moment of the elbow and shoulder at MER were compared between conditions using Generalized Estimating Equations (GEE). Results: In the impeded pitching condition, the mean difference of the separation time was 12.4 milliseconds [95% CI (4.0, 20.7)] and for ball speed 0.6 mph [95% CI (0.2, 0.9)] lower compared to the unimpeded condition. Only the peak pelvic angular velocity, in addition to the trunk, upper arm and forearm, was 45 deg/s [95% CI (24, 66)] higher impeded condition. The mean differences of the joint power and net moments at the shoulder and elbow did not reach statistical significance. Conclusion: In elite adolescent baseball, the observed pitching performance after experimentally impeding pelvic and trunk mobility undermines a potential distal catch-up strategy based on the summation of speed principle. The increased peak pelvic angular velocity may indicate a compensation strategy following the optimal coordination of partial momenta principle to practically maintain pitching performance.

Energy flow through the lower extremities in high school baseball pitching.

It is generally accepted that most of the energy transferred to the ball during a baseball pitch is generated in the trunk and lower extremities. Therefore, purpose of this study was to assess the energy flow through the lower extremities during a baseball pitch. It was hypothesised that the (stabilising) leading leg mainly transfers energy in a distal-to-proximal order as a kinetic chain while the (driving) trailing leg generates most energy, primarily at the hip. A joint power analysis was used to determine the rates of energy (power) transfer and generation in the ankles, knees, hips and lumbosacral joint (L5-S1) for 22 youth pitchers. Analyses showed that the leading leg mainly transfers energy upwards in a distal-to-proximal order just before stride foot contact. Furthermore, energy generation was higher in the trailing leg and primarily arose from the trailing hip. In conclusion, the legs contribute differently to the energy flow where the leading leg acts as an initial kinetic chain component and the trailing leg drives the pitch by generating energy. The actions of both legs are combined in the pelvis and passed on to the subsequent, more commonly discussed, open kinetic chain starting at L5-S1.

The ulnar collateral ligament loading paradox between in-vitro and in-vivo studies on baseball pitching (narrative review).

Ulnar collateral ligament (UCL) weakening or tears occur in 16% of professional baseball pitchers. To prevent players from sustaining a UCL injury, it is important to understand the relationship between the UCL properties and elbow stabilizers with the load on the UCL during pitching. In-vitro studies showed that the ultimate external valgus torque of 34 Nm would rupture the UCL, which is in apparent conflict with the reported peak valgus torques in pitching (40-120 Nm). Assuming both observations are correct, the question rises why 'only' 16 out of 100 professional pitchers sustain a UCL rupture. Underestimation of the effect of other structures in in-vivo studies is most likely the explanation of this mismatch because the calculated in-vivo torque also includes possible contributions of functional and structural stabilizers. In-vitro studies show that the flexor-pronator mass has the potential to counteract valgus torque directly, whereas the elbow flexor-extensor muscles combined with the humeroradial joint might have an indirect effect on valgus torque by increasing the joint compression force. Accurate experimental electromyography data and a more detailed (musculoskeletal)mechanical model of the elbow are needed to investigate if and to what extent the structural and functional stabilizers can shield the UCL during pitching.

Establishing the Role of Elbow Muscles by Evaluating Muscle Activation and Co-contraction Levels at Maximal External Rotation in Fastball Pitching.

Background: Baseball pitching is associated with a high prevalence of ulnar collateral ligament injuries, potentially due to the high external valgus load on the medial side of the elbow at the instant of maximal shoulder external rotation (MER). In-vitro studies show that external valgus torque is resisted by the ulnar collateral ligament but could also be compensated by elbow muscles. As the potential active contribution of these muscles in counteracting external valgus load during baseball pitching is unknown, the aim of this study is to determine whether and to what extent the elbow muscles are active at and around MER during a fastball pitch in baseball. Methods: Eleven uninjured pitchers threw 15 fastball pitches. Surface electromyography of six muscles crossing the elbow were measured at 2000 Hz. Electromyography signals were normalized to maximal activity values. Co-contraction index (CCI) was calculated between two pairs of the flexor and extensor elbow muscles. Confidence intervals were calculated at the instant of MER. Four ranges of muscle activity were considered; 0-20% was considered low; 21-40% moderate; 41-60% high and over 60% as very high. To determine MER, the pitching motion was captured with a highspeed camera at 240 Hz. Results: The flexor pronator mass, pronator teres, triceps brachii, biceps brachii, extensor supinator mass and anconeus show moderate activity at MER. Considerable variation between participants was found in all muscles. The CCI revealed co-contraction of the two flexor-extensor muscle pairs at MER. Interpretation: The muscle activation of the flexor and pronator muscles at MER indicates a direct contribution of forearm muscles crossing the medial side of the elbow in counteracting the external valgus load during fastball pitching. The activation of both flexor and extensor muscles indicates an in-direct contributory effect as the combined activity of these muscles counteract opening of the humeroulnar joint space. We believe that active muscular contributions counteracting the elbow valgus torque can be presumed to relieve the ulnar collateral ligament from maximal stress and are thus of importance in injury risk assessment in fastball pitching in baseball.

Fixation effects of different types of cannulated screws on vertical femoral neck fracture: A finite element analysis and experimental study.

Femoral neck fractures (FNFs) in young patients usually result from high-energy violence, and the vertical transcervical type is typically challenging for its instability. FNFs are commonly treated with three cannulated screws (CS), but the role of screws type on fixation effects (FE) is unclear. The purpose of this study was to evaluate the FE of ten types of CS with different diameters, lengths, depths, and pitches of thread via finite element analysis which was validated by a biomechanical test. Ten vertical FNF models were grouped, fixed by ten types of CS, respectively, all in a parallel, inverted triangular configuration. Their FE were scored comprehensively from six aspects via an entropy evaluation method, as higher scores showed better results. For partial-thread screws, thread length and thread shape factor (TSF) are determinative factors on stability of FNF only if thread depth is not too thick, and they have less cut-out risk, better compression effects and better detached resistance of fracture than full-thread screws, whereas full-thread screws appear to have better shear and shortening resistance. A combination of two superior partial-thread screws and one inferior full-thread screw for vertical FNF may get optimal biomechanical outcomes. The type of cannulated screw is important to consider when treating vertical FNF.

Fear of movement is not associated with trunk movement variability during gait in patients with low back pain.

BACKGROUND: Literature describing differences in motor control between low back pain (LBP) patients and healthy controls is very inconsistent, which may be an indication for the existence of subgroups. Pain-related psychological factors might play a role causing these differences. PURPOSE: To examine the relation between fear of movement and variability of kinematics and muscle activation during gait in LBP patients. STUDY DESIGN: Cross-sectional experimental design. PATIENT SAMPLE: Thirty-one Chinese LBP patients. OUTCOME MEASURES: Self-report measures: Visual Analog Score for pain; TAMPA-score; Physiologic measures: electromyography, range of motion. FUNCTIONAL MEASURES: LBP history; the physical load of profession, physical activity. METHODS: Patients were divided in high and low fear of movement groups. Participants walked on a treadmill at four speeds: very slow, slow, preferred and fast. Kinematics of the thorax and the pelvis were recorded, together with the electromyography of five bilateral trunk muscle pairs. Kinematic and electromyography data were analysed in terms of stride-to-stride pattern variability. Factor analysis was applied to assess interdependence of 11 variability measures. To test for differences between groups, a mixed-design multivariate analysis of variance was conducted. RESULTS: Kinematic variability and variability of muscle activation consistently loaded on different factors and thus represented different underlying variables. No significant Group effects on variability of kinematics and muscle activation were found (Hotelling's Trace F=0.237; 0.396, p=.959; .846, respectively). Speed significantly decreased kinematic variability and increased variability in muscle activation (Hotelling's Trace F=8.363; 4.595, p<.0001; <.0001, respectively). No significant interactions between Group and Speed were found (Hotelling's Trace F=0.204; 0.100, p=.762; .963, respectively). CONCLUSIONS: The results of this study do not support the hypothesis that variability in trunk kinematics and trunk muscle activation during gait in LBP patients are associated with fear of movement.

Knee Angle and Stride Length in Association with Ball Speed in Youth Baseball Pitchers.

The purpose of this study was to determine whether stride length and knee angle of the leading leg at foot contact, at the instant of maximal external rotation of the shoulder, and at ball release are associated with ball speed in elite youth baseball pitchers. In this study, fifty-two elite youth baseball pitchers (mean age 15.2 SD (standard deviation) 1.7 years) pitched ten fastballs. Data were collected with three high-speed video cameras at a frequency of 240 Hz. Stride length and knee angle of the leading leg were calculated at foot contact, maximal external rotation, and ball release. The associations between these kinematic variables and ball speed were separately determined using generalized estimating equations. Stride length as percentage of body height and knee angle at foot contact were not significantly associated with ball speed. However, knee angles at maximal external rotation and ball release were significantly associated with ball speed. Ball speed increased by 0.45 m/s (1 mph) with an increase in knee extension of 18 degrees at maximal external rotation and 19.5 degrees at ball release. In conclusion, more knee extension of the leading leg at maximal external rotation and ball release is associated with higher ball speeds in elite youth baseball pitchers.