Pitch-classifier model for professional pitchers utilizing 3D motion capture and machine learning algorithms.

Introduction: 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. Objective: 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. Methods: 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. Results: 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. Conclusions: 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.

Relationships between throwing mechanics and shoulder anterior force in high school and professional baseball pitchers.

Background: Excessive shoulder anterior force has been implicated in pathology of the rotator cuff in little league and professional baseball pitchers; in particular, anterior laxity, posterior stiffness, and glenohumeral joint impingement. Distinctly characterized motions associated with excessive shoulder anterior force remain poorly understood. Methods: High school and professional pitchers were instructed to throw fastballs while being evaluated with 3D motion capture (480 Hz). A supplementary random forest model was designed and implemented to identify the most important features for regressing to shoulder anterior force, with subsequent standardized regression coefficients to quantify directionality. Results: 130 high school pitchers (16.3 ± 1.2 yrs; 179.9 ± 7.7 cm; 74.5 ± 12.0 kg) and 322 professionals (21.9 ± 2.1 yrs; 189.7 ± 5.7 cm; 94.8 ± 9.5 kg) were included. Random forest models determined nearly all the variance for professional pitchers (R2 = 0.96), and less than half for high school pitchers (R2 = 0.41). Important predictors of shoulder anterior force in high school pitchers included: trunk flexion at maximum shoulder external rotation (MER) (X.IncMSE = 2.4, ß = -0.23, p < 0.001), shoulder external rotation at ball release (BR)(X.IncMSE = 1.7, ß = -0.34, p < 0.001), and shoulder abduction at BR (X.IncMSE = 3.1, ß = 0.17, p < 0.001). In professional pitchers, shoulder horizontal adduction at foot contact (FC) was the highest predictor (X.IncMSE = 13.9, ß = 0.50, p < 0.001), followed by shoulder external rotation at FC (X.IncMSE = 3.6, ß = 0.26, p < 0.001), and maximum elbow extension velocity (X.IncMSE = 8.5, ß = 0.19, p < 0.001). Conclusion: A random forest model successfully selected a subset of features that accounted for the majority of variance in shoulder anterior force for professional pitchers; however, less than half of the variance was accounted for in high school pitchers. Temporal and kinematic movements at the shoulder were prominent predictors of shoulder anterior force for both groups. Clinical relevance: : Our statistical model successfully identified a combination of features with the ability to adequately explain the majority of variance in anterior shoulder force among high school and professional pitchers. To minimize shoulder anterior force, high school pitchers should emphasize decreased shoulder abduction at BR, while professionals can decrease shoulder horizontal adduction at FC.

Kinematic and Kinetic Comparisons of Arm Slot Position Between High School and Professional Pitchers.

Background: Throwing arm kinetics differ in pitchers at varying arm slot (AS) positions (frontal-plane arm position at ball release relative to the vertical axis). Purpose: To determine how kinematic and kinetic values differ between professional and high school pitchers with varying AS positions, and whether these differences are similarly observed in both populations. Methods: High school (n = 130) and professional (n = 288) pitchers threw 8 to 12 fastballs under 3-dimensional motion capture technology. Pitchers in each cohort were subdivided based on mean AS position at ball release: AS1 (least degree of AS: most overhand throwing styles), AS2 (intermediate degree of AS: three-quarter throwing styles), or AS3 (greatest degree of AS: most sidearm throwing styles). Kinetic and kinematic parameters were compared between groups. Study Design: Controlled laboratory study. Results: High school pitchers had a more overhand AS at ball release (50° ± 11°) compared with professional pitchers (58° ± 14°) (P < .001). In both cohorts, AS1 pitchers had significantly greater shoulder abduction (high school, P <0.001; professional, P <0.0001) and lateral trunk flexion (high school, P < 0.001; professional, P <0.0001) at ball release compared with AS3 pitchers. Professional pitchers with an AS3 position had significantly delayed timing of maximum upper trunk angular velocity compared with AS1 pitchers (64% ± 7% vs 57% ± 7% of pitch time, respectively; P < .0001). A significant positive correlation between AS and elbow flexion torque was found in high school pitchers (P = .002; ß = 0.28), and a significant negative correlation between AS and elbow varus torque (P < .001; ß = -0.22) and shoulder internal rotation torque (P < .001; ß = -0.20) was noted in professional pitchers. Conclusion: AS position was related to shoulder abduction and trunk lateral tilt. Professional and high school pitchers with varying AS positions did not experience similar changes in throwing arm kinetics. Clinical Relevance: In professional pitchers, the earlier onset of maximum upper trunk angular velocity with overhand throwing style may reflect inappropriate pelvis-trunk timing separation, a parameter implicated in upper extremity injury, and the negative correlation between AS and elbow varus and shoulder internal rotation torque suggests that both excessive and minimal AS positions have negative implications.

Geographic and Temporal Trends in COVID-Associated Acute Kidney Injury in the National COVID Cohort Collaborative.

BACKGROUND: AKI is associated with mortality in patients hospitalized with coronavirus disease 2019 (COVID-19); however, its incidence, geographic distribution, and temporal trends since the start of the pandemic are understudied. METHODS: Electronic health record data were obtained from 53 health systems in the United States in the National COVID Cohort Collaborative. We selected hospitalized adults diagnosed with COVID-19 between March 6, 2020, and January 6, 2022. AKI was determined with serum creatinine and diagnosis codes. Time was divided into 16-week periods (P1-6) and geographical regions into Northeast, Midwest, South, and West. Multivariable models were used to analyze the risk factors for AKI or mortality. RESULTS: Of a total cohort of 336,473, 129,176 (38%) patients had AKI. Fifty-six thousand three hundred and twenty-two (17%) lacked a diagnosis code but had AKI based on the change in serum creatinine. Similar to patients coded for AKI, these patients had higher mortality compared with those without AKI. The incidence of AKI was highest in P1 (47%; 23,097/48,947), lower in P2 (37%; 12,102/32,513), and relatively stable thereafter. Compared with the Midwest, the Northeast, South, and West had higher adjusted odds of AKI in P1. Subsequently, the South and West regions continued to have the highest relative AKI odds. In multivariable models, AKI defined by either serum creatinine or diagnostic code and the severity of AKI was associated with mortality. CONCLUSIONS: The incidence and distribution of COVID-19-associated AKI changed since the first wave of the pandemic in the United States. PODCAST: This article contains a podcast at https://dts.podtrac.com/redirect.mp3/www.asn-online.org/media/podcast/CJASN/2023_08_08_CJN0000000000000192.mp3.

Comparative Merits of Available Mortality Data Sources for Clinical Research.

Obtaining reliable data on patient mortality is a critical challenge facing observational researchers seeking to conduct studies using real-world data. As these analyses are conducted more broadly using newly-available sources of real-world evidence, missing data can serve as a rate-limiting factor. We conducted a comparison of mortality data sources from different stakeholder perspectives - academic medical center (AMC) informatics service providers, AMC research coordinators, industry analytics professionals, and academics - to understand the strengths and limitations of differing mortality data sources: locally generated data from sites conducting research, data provided by governmental sources, and commercially available data sets. Researchers seeking to conduct observational studies using extant data should consider these factors in sourcing outcomes data for their populations of interest.

COVID-19-associated AKI in hospitalized US patients: incidence, temporal trends, geographical distribution, risk factors and mortality.

Background: Acute kidney injury (AKI) is associated with mortality in patients hospitalized with COVID-19, however, its incidence, geographic distribution, and temporal trends since the start of the pandemic are understudied. Methods: Electronic health record data were obtained from 53 health systems in the United States (US) in the National COVID Cohort Collaborative (N3C). We selected hospitalized adults diagnosed with COVID-19 between March 6th, 2020, and January 6th, 2022. AKI was determined with serum creatinine (SCr) and diagnosis codes. Time were divided into 16-weeks (P1-6) periods and geographical regions into Northeast, Midwest, South, and West. Multivariable models were used to analyze the risk factors for AKI or mortality. Results: Out of a total cohort of 306,061, 126,478 (41.0 %) patients had AKI. Among these, 17.9% lacked a diagnosis code but had AKI based on the change in SCr. Similar to patients coded for AKI, these patients had higher mortality compared to those without AKI. The incidence of AKI was highest in P1 (49.3%), reduced in P2 (40.6%), and relatively stable thereafter. Compared to the Midwest, the Northeast, South, and West had higher adjusted AKI incidence in P1, subsequently, the South and West regions continued to have the highest relative incidence. In multivariable models, AKI defined by either SCr or diagnostic code, and the severity of AKI was associated with mortality. Conclusions: Uncoded cases of COVID-19-associated AKI are common and associated with mortality. The incidence and distribution of COVID-19-associated AKI have changed since the first wave of the pandemic in the US.

The influence of stride width on kinematic and kinetics in high school and professional baseball pitchers: A propensity-matched biomechanical evaluation.

OBJECTIVES: To evaluate kinematic and kinetic parameters for high school (HS) and professional (PRO) pitchers differentiated by stride width. DESIGN: Descriptive laboratory study. METHODS: HS (n = 36) and PRO (n = 172) baseball pitchers pitched 8-12 fastballs using 3D-motion capture (480-Hz). Pitchers were 1:1 propensity-scored matched by age, height, weight, and ball velocity based on 'narrow' versus 'wide' stride widths and kinematics and kinetics were compared using independent t-tests. Independent associations between variables and stride width were determined utilizing linear regressions. RESULTS: At foot contact, HS wide (n = 18) had significantly less lead knee flexion (41 ±â€¯9° vs. 49 ±â€¯6°, p = 0.007, d = -1.0) and less pelvis rotation (66 ±â€¯9° vs. 57 ±â€¯14°, p = 0.003 d = 0.8) compared to HS narrow (n = 18). PRO wide (n = 86) at ball release had significantly less pelvis rotation (-10 ±â€¯10° vs. -15 ±â€¯14°, p = 0.008, d = 0.4) and increased shoulder horizontal adduction (4±8° vs. -1±9°, p=0.003, d=0.5) compared to PRO narrow (n = 86). For every 10 cm increase in stride width, pelvis rotation at ball release decreased by 2° (B:0.10, ß:0.20, p < 0.001) in HS and 1.3° (B:0.08, ß:0.13, p = 0.002) in PRO. CONCLUSIONS: HS and PRO pitchers differentiated by stride width demonstrated no significant difference in throwing arm kinetics. For both groups, wider stride width was associated with decreased pelvis rotation, which may contribute to inefficient utilization of kinetic energy. Ultimately, coaches and players may better focus their efforts on refining other kinematics for enhanced performance outcomes and safe pitching mechanics.

Interferon-alpha for treating polycythemia vera yields improved myelofibrosis-free and overall survival.

Interferon-alpha (rIFNα) is the only disease-modifying treatment for polycythemia vera (PV), but whether or not it prolongs survival is unknown. This large single center retrospective study of 470 PV patients compares the myelofibrosis-free survival (MFS) and overall survival (OS) with rIFNα to two other primary treatments, hydroxyurea (HU) and phlebotomy-only (PHL-O). The median age at diagnosis was 54 years (range 20-94) and the median follow-up was 10 years (range 0-45). Two hundred and twenty-nine patients were women (49%) and 208 were high-risk (44%). The primary treatment was rIFNα in 93 (20%), HU in 189 (40%), PHL-O in 133 (28%) and other cytoreductive drugs in 55 (12%). The treatment groups differed by ELN risk score (p < 0.001). In low-risk patients, 20-year MFS for rIFNα, HU, and PHL-O was 84%, 65% and 55% respectively (p < 0.001) and 20-year OS was 100%, 85% and 80% respectively (p = 0.44). In high-risk patients, 20-year MFS for rIFNα, HU, and PHL-O was 89%, 41% and 36% respectively (p = 0.19) and 20-year OS was 66%, 40%, 14% respectively (p = 0.016). In multivariable analysis, longer time on rIFNα was associated with a lower risk of myelofibrosis (HR: 0.91, p < 0.001) and lower mortality (HR: 0.94, p = 0.012). In conclusion, this study supports treatment of PV with rIFNα to prevent myelofibrosis and potentially prolong survival.

Prevalence and risk factors for Pulmonary Hypertension associated with chronic Myeloproliferative Neoplasms.

OBJECTIVES: Pulmonary hypertension (PH) is commonly reported in Philadelphia-chromosome negative myeloproliferative neoplasms (MPNs) including polycythemia vera (PV), essential thrombocythemia (ET), and myelofibrosis (MF). PH may be diagnosed directly by right heart catheterization (RHC) or estimated by transthoracic echocardiography (TTE). Survival is shortened by PH but despite the potential significance of PH to management and prognosis of MPN, estimates of its prevalence in MPNs vary and risk factors for the condition are poorly established. We performed a systematic review and meta-analysis of available studies to fill this void. METHODS: We searched EMBASE, MEDLINE, and Clinicaltrials.gov for the terms "pulmonary hypertension," "myeloproliferative disorders," "polycythemia vera," "essential thrombocythemia," and "myelofibrosis." We restricted analysis to the 1999-2019 window to improve uniformity of MPN diagnostic criteria. We retrieved 221 records and, after abstract and full-text screening, identified 17 papers meeting criteria for inclusion in our meta-analysis. A modified Newcastle-Ottawa scale was used to assess quality. RESULTS: Results for 935 patients were available, 309 of these having PH (33%). Using logistic mixed-effect regression, we found that diagnosis mode (RHC vs TTE) and MPN duration influenced PH prevalence. Studies employing predominantly TTE yielded prevalence estimates ~5-fold higher than those using RHC (35% vs 7.2%). We identified MF and duration of MPN as significant risk factors for development of PH. CONCLUSIONS: Prevalence of PH in MPNs is poorly understood with estimates ranging from 3.8% to 58%. Patients with MF and longer duration of disease seem at particularly high risk and should be carefully monitored for PH.

Use of pegylated interferon in young patients with polycythemia vera and essential thrombocythemia.

Myeloproliferative neoplasms (MPN) are rare disorders in young patients, and because of this, standardized treatment recommendations are not available. Pediatric patients are more frequently treated with hydroxyurea than interferon, yet there are no data suggesting this is the best practice. Current treatment guidelines for adults suggest using interferon as upfront therapy in young patients. We reviewed the cases of 13 young patients with polycythemia vera or essential thrombocythemia, who were treated with interferon. Extreme thrombocytosis was well controlled and the medication was tolerated by many. Our work shows the need for prospective studies evaluating interferon in our youngest patients with MPN.

Extracting and classifying diagnosis dates from clinical notes: A case study.

Myeloproliferative neoplasms (MPNs) are chronic hematologic malignancies that may progress over long disease courses. The original date of diagnosis is an important piece of information for patient care and research, but is not consistently documented. We describe an attempt to build a pipeline for extracting dates with natural language processing (NLP) tools and techniques and classifying them as relevant diagnoses or not. Inaccurate and incomplete date extraction and interpretation impacted the performance of the overall pipeline. Existing lightweight Python packages tended to have low specificity for identifying and interpreting partial and relative dates in clinical text. A rules-based regular expression (regex) approach achieved recall of 83.0% on dates manually annotated as diagnosis dates, and 77.4% on all annotated dates. With only 3.8% of annotated dates representing initial MPN diagnoses, additional methods of targeting candidate date instances may alleviate noise and class imbalance.

Incremental Utility of Right Ventricular Dysfunction in Patients With Myeloproliferative Neoplasm-Associated Pulmonary Hypertension.

BACKGROUND: Myeloproliferative neoplasm (MPN) has been associated with pulmonary hypertension (PH) on the basis of small observational studies, but the mechanism and clinical significance of PH in MPN are not well established. The aims of this study were to expand understanding of PH in a well-characterized MPN cohort via study of PH-related symptoms, mortality risk, and cardiac remodeling sequalae of PH using quantitative echocardiographic methods. METHODS: The population comprised a retrospective cohort of patients with MPN who underwent transthoracic echocardiography: Doppler-derived pulmonary arterial systolic pressure applied established cutoffs for PH (≥35 mm Hg) and advanced PH (≥50 mm Hg); right ventricular (RV) performance was assessed via conventional indices (tricuspid annular plane systolic excursion [TAPSE], S') and global longitudinal strain. Symptoms and mortality were discerned via standardized review. RESULTS: Three hundred one patients were studied; 56% had echocardiography-demonstrated PH (20% advanced) paralleling a high prevalence (67%) among patients with invasively quantified PASP. PH was associated with adverse left ventricular (LV) remodeling indices, including increased myocardial mass and diastolic dysfunction (P ≤ .001 for all): LV mass and filling pressure (P < .01) were associated with PH independent of LV ejection fraction. RV dysfunction by strain and TAPSE and S' increased in relation to PH (P ≤ .001) and was about threefold greater among patients with advanced PH compared with those without PH. Patients with RV dysfunction were more likely to report dyspnea, as were those with advanced PH (P < .05). During median follow-up of 2.2 years, all-cause mortality was 27%. PH grade (hazard ratio, 1.9; 95% CI, 1.1-3.0; P = .012) and TAPSE- and S'-demonstrated RV dysfunction (hazard ratio, 3.3; 95% CI, 1.3-8.2; P = .01) were independently associated with mortality; substitution of global longitudinal strain for TAPSE and S' yielded similar associations of RV dysfunction with death (hazard ratio, 3.2; 95% CI, 1.5-6.7; P = .003) independent of PH. CONCLUSIONS: PH is highly prevalent in patients with MPN and is linked to LV diastolic dysfunction; echocardiography-quantified RV dysfunction augments risk for mortality independent of PH.

Distinguishing essential thrombocythemia JAK2V617F from polycythemia vera: limitations of erythrocyte values.

Distinguishing essential thrombocythemia JAK2V617F from polycythemia vera is difficult because of shared mutation and phenotypic characteristics. The World Health Organization suggested hemoglobin and hematocrit values to diagnose polycythemia vera (PV), but their sensitivity and specificity were not tested. Moreover, red cell values do not accurately predict red cell mass, which we use to discriminate essential thrombocythemia JAK2V617F from PV. Eighty-three PV and 39 essential thrombocythemia JAK2V617F patients were diagnosed based on JAK2V617F positivity, chromium-51 red cell mass, and marrow biopsy findings. Red cell values used to construct a receiver operating characteristic analysis determined optimal thresholds for distinguishing essential thrombocythemia JAK2V617F from PV. Red cell value frequencies were plotted determining if overlap existed. Chromium-51 red cell mass separated PV from essential thrombocythemia JAK2V617F, but red cell values overlapped in 25.0-54.7%. Our data indicate that a significant proportion of PV patients may be underdiagnosed by using only red cell values. A bone marrow biopsy was performed in 199 of 410 (48.5%) and a serum erythropoietin value was measured in 225 of 410 (54.9%) of potential PV patients at our institution. Without isotope studies, marrow biopsies and serum erythropoietin values should improve diagnostic accuracy and become mandatory, but clinical data suggest these tests have not been routinely performed. Therefore, the clinical hematologist must be aware of imperfect accuracy when using only red cell values for distinguishing essential thrombocythemia JAK2V617F from PV.

Lessons Learned in the Development of a Computable Phenotype for Response in Myeloproliferative Neoplasms.

Determining response status in patients with myeloproliferative neoplasms is a complex problem requiring the integration of both structured and unstructured data elements from disparate information systems. By applying multiple techniques, a collaborative team of informatics professionals and research personnel were able to determine which elements were amenable to automated extraction and which required expert adjudication. With this knowledge in mind, we were able to build a system that joins together programmatically-derived and manually-abstracted data elements to facilitate response assessment - an important end point in clinical and translational research in this disease area.