Manzi Joseph E, Dowling Brittany, Krichevsky Spencer, Roberts Nicholas L S, Sudah Suleiman Y, Moran Jay, Chen Frank R, Quan Theodore, Morse Kyle W, Dines Joshua S
Department of Orthopaedic Surgery, Northwell Health, New York, NY, USA.
Sports Performance Center, Midwest Orthopaedics at Rush, Chicago, IL, USA.
J Orthop. 2023 Dec 20;49:140-147. doi: 10.1016/j.jor.2023.12.007. eCollection 2024 Mar.
A pitcher's ability to achieve pitch location precision after a complex series of motions is of paramount importance. Kinematics have been used in analyzing performance benefits like ball velocity, as well as injury risk profile; however, prior utilization of such data for pitch location metrics is limited.
To develop a pitch classifier model utilizing machine learning algorithms to explore the potential relationships between kinematic variables and a pitcher's ability to throw a strike or ball.
This was a descriptive laboratory study involving professional baseball pitchers (n = 318) performing pitching tests under the setting of 3D motion-capture (480 Hz). Main outcome measures included accuracy, sensitivity, specificity, F1 score, positive predictive value (PPV), and negative predictive value (NPV) of the random forest model.
The optimized random forest model resulted in an accuracy of 70.0 %, sensitivity of 70.3 %, specificity of 48.5 %, F1 equal to 80.6 %, PPV of 94.3 %, and a NPV of 11.6 %. Classification accuracy for predicting strikes and balls achieved an area under the curve of 0.67. Kinematics that derived the highest % increase in mean square error included: trunk flexion excursion(4.06 %), pelvis obliquity at foot contact(4.03 %), and trunk rotation at hand separation(3.94 %). Pitchers who threw strikes had significantly less trunk rotation at hand separation(p = 0.004) and less trunk flexion at ball release(p = 0.003) compared to balls. The positive predictive value for determining a strike was within an acceptable range, while the negative predictive value suggests if a pitch was determined as a ball, the model was not adequate in its prediction.
Kinematic measures of pelvis and trunk were crucial determinants for the pitch classifier sequence, suggesting pitcher kinematics at the proximal body segments may be useful in determining final pitch location.
投手在一系列复杂动作后实现投球位置精准度的能力至关重要。运动学已被用于分析诸如球速等表现优势以及受伤风险状况；然而，此前此类数据在投球位置指标方面的应用有限。
利用机器学习算法开发一个投球分类模型，以探索运动学变量与投手投出好球或坏球能力之间的潜在关系。
这是一项描述性实验室研究，涉及318名职业棒球投手在3D动作捕捉（480赫兹）环境下进行投球测试。主要结果指标包括随机森林模型的准确率、灵敏度、特异度、F1分数、阳性预测值（PPV）和阴性预测值（NPV）。
优化后的随机森林模型准确率为70.0%，灵敏度为70.3%，特异度为48.5%，F1分数为80.6%，PPV为94.3%，NPV为11.6%。预测好球和坏球的分类准确率在曲线下面积为0.67。导致均方误差增加百分比最高的运动学指标包括：躯干前屈偏移（4.06%）、脚触地时骨盆倾斜（4.03%）以及手分开时躯干旋转（3.94%）。与投出坏球相比，投出好球的投手在手分开时躯干旋转明显更少（p = 0.004），在球出手时躯干前屈也更少（p = 0.003）。确定好球的阳性预测值在可接受范围内，而阴性预测值表明，如果一个投球被判定为坏球，该模型的预测并不充分。
骨盆和躯干的运动学测量是投球分类序列的关键决定因素，表明近端身体节段的投手运动学可能有助于确定最终投球位置。
