scholarly journals A Random Forest Machine Learning Framework to Reduce Running Injuries in Young Triathletes

Sensors ◽  
2020 ◽  
Vol 20 (21) ◽  
pp. 6388
Author(s):  
Javier Martínez-Gramage ◽  
Juan Pardo Albiach ◽  
Iván Nacher Moltó ◽  
Juan José Amer-Cuenca ◽  
Vanessa Huesa Moreno ◽  
...  
Keyword(s):  
Random Forest ◽  
Classification Tree ◽  
Gluteus Medius ◽  
Important Variable ◽  
Initial Contact ◽  
Learning Framework ◽  
Linear Relationships ◽  
Limb Injuries ◽  
Running Injuries ◽  
Trunk Extension

Background: The running segment of a triathlon produces 70% of the lower limb injuries. Previous research has shown a clear association between kinematic patterns and specific injuries during running. Methods: After completing a seven-month gait retraining program, a questionnaire was used to assess 19 triathletes for the incidence of injuries. They were also biomechanically analyzed at the beginning and end of the program while running at a speed of 90% of their maximum aerobic speed (MAS) using surface sensor dynamic electromyography and kinematic analysis. We used classification tree (random forest) techniques from the field of artificial intelligence to identify linear and non-linear relationships between different biomechanical patterns and injuries to identify which styles best prevent injuries. Results: Fewer injuries occurred after completing the program, with athletes showing less pelvic fall and greater activation in gluteus medius during the first phase of the float phase, with increased trunk extension, knee flexion, and decreased ankle dorsiflexion during the initial contact with the ground. Conclusions: The triathletes who had suffered the most injuries ran with increased pelvic drop and less activation in gluteus medius during the first phase of the float phase. Contralateral pelvic drop seems to be an important variable in the incidence of injuries in young triathletes.

scholarly journals Is There a Pathological Gait Associated With Common Soft Tissue Running Injuries?

2018 ◽  
Vol 46 (12) ◽  
pp. 3023-3031 ◽  
Author(s):  
Christopher Bramah ◽  
Stephen J. Preece ◽  
Niamh Gill ◽  
Lee Herrington
Keyword(s):  
Soft Tissue ◽  
Three Dimensional ◽  
Achilles Tendinopathy ◽  
Important Variable ◽  
Iliotibial Band ◽  
Initial Contact ◽  
Iliotibial Band Syndrome ◽  
Running Injuries ◽  
Limb Kinematics

Background: Previous research has demonstrated clear associations between specific running injuries and patterns of lower limb kinematics. However, there has been minimal research investigating whether the same kinematic patterns could underlie multiple different soft tissue running injuries. If they do, such kinematic patterns could be considered global contributors to running injuries. Hypothesis: Injured runners will demonstrate differences in running kinematics when compared with injury-free controls. These kinematic patterns will be consistent among injured subgroups. Study Design: Controlled laboratory study. Methods: The authors studied 72 injured runners and 36 healthy controls. The injured group contained 4 subgroups of runners with either patellofemoral pain, iliotibial band syndrome, medial tibial stress syndrome, or Achilles tendinopathy (n = 18 each). Three-dimensional running kinematics were compared between injured and healthy runners and then between the 4 injured subgroups. A logistic regression model was used to determine which parameters could be used to identify injured runners. Results: The injured runners demonstrated greater contralateral pelvic drop (CPD) and forward trunk lean at midstance and a more extended knee and dorsiflexed ankle at initial contact. The subgroup analysis of variance found that these kinematic patterns were consistent across each of the 4 injured subgroups. CPD was found to be the most important variable predicting the classification of participants as healthy or injured. Importantly, for every 1° increase in pelvic drop, there was an 80% increase in the odds of being classified as injured. Conclusion: This study identified a number of global kinematic contributors to common running injuries. In particular, we found injured runners to run with greater peak CPD and trunk forward lean as well as an extended knee and dorsiflexed ankle at initial contact. CPD appears to be the variable most strongly associated with common running-related injuries. Clinical Relevance: The identified kinematic patterns may prove beneficial for clinicians when assessing for biomechanical contributors to running injuries.

Using Machine Learning to Predict Patterns of Employment and Day Program Participation

2021 ◽  
Vol 126 (6) ◽  
pp. 477-491
Author(s):  
Michael D. Broda ◽  
Matthew Bogenschutz ◽  
Parthenia Dinora ◽  
Seb M. Prohn ◽  
Sarah Lineberry ◽  
...  
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Policy Making ◽  
Classification Tree ◽  
Evidence Base ◽  
Important Variable ◽  
Current Evidence ◽  
Learning Approaches ◽  
Annual Survey ◽  
Current Evidence Base

Abstract In this article, we demonstrate the potential of machine learning approaches as inductive analytic tools for expanding our current evidence base for policy making and practice that affects people with intellectual and developmental disabilities (IDD). Using data from the National Core Indicators In-Person Survey (NCI-IPS), a nationally validated annual survey of more than 20,000 nationally representative people with IDD, we fit a series of classification tree and random forest models to predict individuals' employment status and day activity participation as a function of their responses to all other items on the 2017–2018 NCI-IPS. The most accurate model, a random forest classifier, predicted employment outcomes of adults with IDD with an accuracy of 89 percent on the testing sample, and 80 percent on the holdout sample. The most important variable in this prediction was whether or not community employment was a goal in this person's service plan. These results suggest the potential machine learning tools to examine other valued outcomes used in evidence-based policy making to support people with IDD.

scholarly journals Effectiveness of Abdominal and Gluteus Medius Training in Lumbo-Pelvic Stability and Adductor Strength in Female Soccer Players. A Randomized Controlled Study

2021 ◽  
Vol 18 (4) ◽  
pp. 1528
Author(s):  
Héctor Guerrero-Tapia ◽  
Rodrigo Martín-Baeza ◽  
Rubén Cuesta-Barriuso
Keyword(s):  
Repeated Measures ◽  
Gluteus Medius ◽  
Soccer Players ◽  
Controlled Study ◽  
Control Group ◽  
Extrinsic Factors ◽  
Randomized Controlled ◽  
Limb Injuries ◽  
Experimental Group

Background. Abdominal and lumbo-pelvic stability alterations may be the origin of lower limb injuries, such as adductor pathology in soccer players. Imbalance can be caused by both intrinsic and extrinsic factors. Methods: In this randomized controlled trial over 8 weeks, 25 female footballers were randomly allocated to an experimental group (isometric abdominal training and gluteus medius-specific training) or a control group (isometric abdominal training). Evaluations were performed at baseline, at the end of the intervention and after a 4-week follow-up period. The exercise protocol in common for both groups included three exercises: Plank, Lateral plank and Bird dog. Specific exercises for the gluteus medius were: Pelvic drop and Stabilization of the gluteus medius in knee valgus. Outcome measures were lumbar-pelvic stability and adductor strength. Results: After the intervention, there was an increase in lumbo-pelvic stability in both groups, being greater in the control group than in the experimental group (mean differences [MD]: 4.84 vs. MD: 9.58; p < 0.01) with differences in the analysis of repeated measures (p < 0.001), but not in group interaction (p = 0.26). Changes were found in adductor strength in the experimental group (MD: −2.48; p < 0.001 in the left adductor; MD: −1.48; p < 0.01 in right adductor) and control group (MD: −1.68; p < 0.001 in the left adductor; MD: −2.05; p < 0.001 in the right adductor) after the intervention, with differences in the analysis of repeated measures in left (p < 0.001) and right (p < 0.001) adductor strength. Conclusions: An abdominal and gluteal training protocol shows no advantage over a protocol of abdominal training alone for lumbo-pelvic stability and adductor strength, while improvements in both variables are maintained at four weeks follow-up.

scholarly journals The Assessment of the Innovativeness of a New Medicine in Italy

2021 ◽  
Vol 8 ◽  
Author(s):  
Filomena Fortinguerra ◽  
Serena Perna ◽  
Roberto Marini ◽  
Alessandra Dell'Utri ◽  
Maurizio Trapanese ◽  
...  
Keyword(s):  
Decision Process ◽  
Classification Tree ◽  
Orphan Drugs ◽  
Important Variable ◽  
Medical Product ◽  
Chi Square ◽  
New Approach ◽  
Exact Test ◽  
Therapeutic Value

Objectives: Starting from April 2017, the Italian Medicine Agency (AIFA) has approved new criteria for defining any new medicinal product with an innovative indication. The purpose of the study is to analyze the activity of innovativeness evaluation according to the new approach, to estimate the weight of each criterion considered for innovativeness definition, and to evaluate how the new approach works in terms of consistency and reproducibility.Methods: A retrospective analysis was performed on the final reports evaluating the drug innovativeness assessment published on the AIFA's website between April 2017 and January 2021. Descriptive statistics, chi-square test, whether the conditions were respected, or Fisher's exact test was used to explore the association between characteristics of drugs and the innovativeness status and the association between the three criteria. Profiles of the decision process and their relationship with innovativeness response were described. In order to evaluate the weight of each criterion in predicting the innovativeness status, a Classification Tree (CT) algorithm was applied.Results: Overall, of the 109 published drugs reports, 37 (33.9%) were recognized as fully innovative, 29 (26.6%) were considered conditionally innovative, while for 43 (39.4%) reports innovativeness was not recognized. Considering the three criteria of the decision process, the added therapeutic value was the only criterion statistically associated with a drug's degree of innovation (p &lt; 0.001). The therapeutic need and the quality of clinical evidence were statistically associated (p = 0.008) even if only a mild association was observed. The added therapeutic value was the most important variable in predicting the innovativeness status according to the classification tree (CT) model applied, achieving an accuracy of 89.4%. No difference was found between orphans and non-orphan drugs or oncological and non-oncological drugs.Discussion: The added therapeutic value is the most important criterion of the multidimensional approach for the innovativeness status definition of a new medical product. A mild association was found between the therapeutic need and the quality of evidence. Overall, similar decision profiles bring the same evaluation of innovativeness status, indicating a good consistency and reproducibility between decisions.

scholarly journals Effects of 12-week cadence retraining on impact peak, load rates and lower extremity biomechanics in running

PeerJ ◽  
2020 ◽  
Vol 8 ◽  
pp. e9813
Author(s):  
Junqing Wang ◽  
Zhen Luo ◽  
Boyi Dai ◽  
Weijie Fu
Keyword(s):  
Lower Extremity ◽  
Impact Force ◽  
Peak Load ◽  
Control Group ◽  
Initial Contact ◽  
Vertical Load ◽  
Impact Peak ◽  
Peak Knee ◽  
Running Injuries ◽  
Lower Extremity Biomechanics

Background Excessive impact peak forces and vertical load rates are associated with running injuries and have been targeted in gait retraining studies. This study aimed to determine the effects of 12-week cadence retraining on impact peak, vertical load rates and lower extremity biomechanics during running. Methods Twenty-four healthy male recreational runners were randomised into either a 12-week cadence retraining group (n = 12), which included those who ran with a 7.5% increase in preferred cadence, or a control group (n = 12), which included those who ran without any changes in cadence. Kinematics and ground reaction forces were recorded simultaneously to quantify impact force variables and lower extremity kinematics and kinetics. Results Significantly decreased impact peak (1.86 ± 0.30 BW vs. 1.67 ± 0.27 BW, P = 0.003), vertical average load rates (91.59 ± 18.91 BW/s vs. 77.31 ± 15.12 BW/s, P = 0.001) and vertical instantaneous load rates (108.8 ± 24.5 BW/s vs. 92.8 ± 18.5 BW/s, P = 0.001) were observed in the cadence retraining group, while no significant differences were observed in the control group. Foot angles (18.27° ± 5.59° vs. 13.74° ± 2.82°, P = 0.003) and vertical velocities of the centre of gravity (CoG) (0.706 ± 0.115 m/s vs. 0.652 ± 0.091 m/s, P = 0.002) significantly decreased in the cadence retraining group at initial contact, but not in the control group. In addition, vertical excursions of the CoG (0.077 ± 0.01 m vs. 0.069 ± 0.008 m, P = 0.002) and peak knee flexion angles (38.6° ± 5.0° vs. 36.5° ± 5.5°, P < 0.001) significantly decreased whilst lower extremity stiffness significantly increased (34.34 ± 7.08 kN/m vs. 38.61 ± 6.51 kN/m, P = 0.048) in the cadence retraining group. However, no significant differences were observed for those variables in the control group. Conclusion Twelve-week cadence retraining significantly increased the cadence of the cadence retraining group by 5.7%. This increased cadence effectively reduced impact peak and vertical average/instantaneous load rates. Given the close relationship between impact force variables and running injuries, increasing the cadence as a retraining method may potentially reduce the risk of impact-related running injuries.

scholarly journals Effectiveness of Abdominal and Gluteus Medius Training in Lumbo-pelvic Stability and Adductor Strength in Women Soccer Players. A Randomized Controlled Study.

2020 ◽  
Author(s):  
Héctor Guerrero-Tapia ◽  
Rodrigo Martín-Baeza ◽  
Rubén Cuesta-Barriuso
Keyword(s):  
Repeated Measures ◽  
Controlled Trial ◽  
Gluteus Medius ◽  
Soccer Players ◽  
Controlled Study ◽  
Control Group ◽  
Extrinsic Factors ◽  
Randomized Controlled ◽  
Limb Injuries ◽  
Experimental Group

Abstract Background: Abdominal and lumbo-pelvic stability alterations may origin lower limb injuries, such as for example adductor pathology in soccer players. Imbalance can be caused by both intrinsic and extrinsic factors. Methods: This randomized controlled trial conducted over an 8-week period included 25 female footballers randomly allocated to an experimental group (isometric abdominal training and gluteus medius-specific training) or a control group (isometric abdominal training). The exercise protocol in common for both groups included three exercises: Plank, Lateral plank and Bird dog. Specific exercises for the gluteus medius were: Pelvic drop and Stabilization of the gluteus medius in knee valgus. Outcome measures were lumbo-pelvic stability and adductor strength.Results. Lumbo-pelvic stability after surgery was higher in the control group (MD: 4.84 vs MD: 9.58; p < .01) with differences in the analysis of repeated measures (p<.001), but not in group interaction (p =.26). Changes were found in adductor strength in the experimental group (MD: -2.48; p<.001 in the left adductor; MD: -1.48; p<.01 in right adductor) and control group (MD: -1.68; p<.001 in the left adductor; MD: -2.05; p<.001 in the right adductor) after the intervention, with differences in the analysis of repeated measures in left (p<.001) and right (p<.001) adductor strength.Conclusions. An abdominal and gluteal training protocol shows no advantage over a protocol of abdominal training alone for lumbo-pelvic stability and adductor strength and flexibility, while improvements are maintained at four weeks follow-up. Trial Registration Number: NCT03617887.

scholarly journals Multiple linear regression and random forest to predict and map soil properties using data from portable X-ray fluorescence spectrometer (pXRF)

2017 ◽  
Vol 41 (6) ◽  
pp. 648-664 ◽  
Author(s):  
Sérgio Henrique Godinho Silva ◽  
Anita Fernanda dos Santos Teixeira ◽  
Michele Duarte de Menezes ◽  
Luiz Roberto Guimarães Guilherme ◽  
Fatima Maria de Souza Moreira ◽  
...  
Keyword(s):  
Random Forest ◽  
Linear Regression ◽  
Soil Properties ◽  
Multiple Linear Regression ◽  
Low Cost ◽  
High Accuracy ◽  
Important Variable ◽  
X Ray ◽  
Element Contents ◽  
Fluorescence Spectrometer

ABSTRACT Determination of soil properties helps in the correct management of soil fertility. The portable X-ray fluorescence spectrometer (pXRF) has been recently adopted to determine total chemical element contents in soils, allowing soil property inferences. However, these studies are still scarce in Brazil and other countries. The objectives of this work were to predict soil properties using pXRF data, comparing stepwise multiple linear regression (SMLR) and random forest (RF) methods, as well as mapping and validating soil properties. 120 soil samples were collected at three depths and submitted to laboratory analyses. pXRF was used in the samples and total element contents were determined. From pXRF data, SMLR and RF were used to predict soil laboratory results, reflecting soil properties, and the models were validated. The best method was used to spatialize soil properties. Using SMLR, models had high values of R² (≥0.8), however the highest accuracy was obtained in RF modeling. Exchangeable Ca, Al, Mg, potential and effective cation exchange capacity, soil organic matter, pH, and base saturation had adequate adjustment and accurate predictions with RF. Eight out of the 10 soil properties predicted by RF using pXRF data had CaO as the most important variable helping predictions, followed by P2O5, Zn and Cr. Maps generated using RF from pXRF data had high accuracy for six soil properties, reaching R2 up to 0.83. pXRF in association with RF can be used to predict soil properties with high accuracy at low cost and time, besides providing variables aiding digital soil mapping.

scholarly journals A nearest-neighbour model for forecasting skier-triggered dry-slab avalanches on persistent weak layers in the Columbia Mountains, Canada

2004 ◽  
Vol 38 ◽  
pp. 166-172 ◽  
Author(s):  
Antonia Zeidler ◽  
Bruce Jamieson
Keyword(s):  
Classification Tree ◽  
Regional Scale ◽  
Rank Correlation ◽  
Stability Index ◽  
Important Variable ◽  
Slab Thickness ◽  
Nearest Neighbour ◽  
Avalanche Forecasting ◽  
Columbia Mountains ◽  
Snowpack Properties

AbstractNearest-neighbour models for avalanche forecasting have made little use of snowpack properties; however, slab thickness (H), slab load (Load) and a skier stability index (Sk38) have proven useful for regional avalanche forecasting in the Columbia Mountains, western Canada. This study explores 21 meteorological, snowpack and elaborated variables including Sk38, H and Load. A daily skier instability index (DSI) is developed as a response variable using skier-triggered avalanche activity on persistent weak layers and stability ratings at the end of the day. In rank correlation analysis, Sk38, Load, previous avalanche activity, H and some meteorological variables were highly ranked. The physical explanations are discussed. In classification-tree analysis, Sk38 was ranked as the most important variable and used in the development of the tree structure along with Load. Besides Sk38 and Load, snowpack thickness, the number of previously triggered avalanches and H have potential to predict DSI. Further we included once all 21 variables, and once all variables except Sk38, H and Load in nearest-neighbour models. Comparing the performance of these models shows that Sk38 along with Load and H have high potential to forecast the DSI on a regional scale.

Sign in / Sign up

Export Citation Format

Share Document