Determining Relationships Between Kinematic Sequencing and Baseball Pitch Velocity Using pitchAITM
Bibliographic record
Abstract
Professional baseball pitchers have consistently been increasing pitch velocity since 2008 (the first year of automated pitch tracking and classification at all 30 MLB stadiums) and increasing the number of pitches thrown over 95mph (Sullivan, 2019). Fastball velocity is a primary risk factor for elbow injuries as there is a general linear relationship with increased elbow torques (Aguinaldo & Chambers, 2009; Chalmers et al., 2016; Slowik et al., 2019). The kinematic sequence has been referred to as the order and magnitude of joint angular velocities during the pitch delivery and has been associated with pitch velocity and elbow torque (Nicholson et al., 2022a, 2022b; Scarborough, Leonard, et al., 2021). The purpose of the research was to identify kinematic sequence metrics associated with pitch velocity and use them to predict pitch velocity using pitchAITM (Dobos et al., 2022). A total of 80 pitchers (187.2 ± 8.2 cm, age 20.1 ± 3.3 years) ranging in skill level from high school to professional baseball participated in this study. Video for pitchAITM, player height and weight were collected at 2 baseball training facilities. Extracted pitchAITM data included the peak magnitudes and relative timings of pelvis rotation velocity, trunk rotation velocity, elbow extension velocity, and shoulder internal rotation velocity. Average pitch velocity in the data set was 85.3 ± 5.7 mph or 38.1 ± 2.5 m/s. Pitch velocity was predicted using both a multilinear regression, as well as a custom neural network model. The multilinear regression generated a significant prediction for pitch velocity with an R2 = 0.368 and p < 0.01. Pitcher weight (β = 0.535, p < 0.001), peak pelvis rotational velocity timing (β = -0.157, p = 0.001), peak elbow extension timing (β = 0.122, p = 0.006), and peak shoulder internal rotation timing (β = -0.113, p = 0.018), were significant contributors to the multilinear model. The neural network model significantly predicted velocity with an R2 = 0.372, p < 0.01. Actual and predicted velocity were not significantly different (p = 0.353). In conclusion, pitchAITM kinematic sequencing can predict pitch velocity using both a multilinear regression and custom neural network.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".