Using Machine Learning Algorithms to Pool Data from Meta-Analysis for the Prediction of Countermovement Jump Improvement
Abstract
:1. Introduction
2. Methods
2.1. Source of Data
2.2. Identification of Predictors
2.3. Developing Machine Learning Models
2.4. Metrics and Model Tuning
3. Results
3.1. Prediction Accuracy
3.2. Feature Importance
4. Discussion
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
Appendix A
Variable | Range | Frequency (By Groups If Applicable) * |
---|---|---|
CMJ change | −4.57 to 9.7 | N/A |
Age | 10.1 to 81.1 | N/A |
Gender | N/A | Male: 247 |
Female: 75 | ||
Ethnicity | N/A | African: 35 |
American: 60 | ||
Asian: 12 | ||
Australian: 22 | ||
European: 193 | ||
Type of sport | N/A | American football: 4 |
Baseball: 3 | ||
Basketball: 23 | ||
Dancing: 2 | ||
Distance running: 12 | ||
General conditioning: 5 | ||
Golf: 4 | ||
Gymnastics: 2 | ||
Handball: 12 | ||
Mixed or not well defined: 101 | ||
Rugby: 3 | ||
Skiing: 2 | ||
Soccer: 109 | ||
Sprinting: 5 | ||
Swimming: 3 | ||
Tennis: 7 | ||
Track and field: 3 | ||
Volleyball: 15 | ||
Water polo: 7 | ||
Level of sport participation | Junior team: 121 | |
League game: 84 | ||
Recreational/amateur/collegiate: 117 | ||
Total training sessions | 0 to 144 sessions | 0 session: 91 |
1 to 10 sessions: 18 | ||
11 to 20 sessions: 117 | ||
21 to 30 sessions: 57 | ||
31 to 40 sessions: 26 | ||
41 to 50 sessions: 4 | ||
51 to 60 sessions: 1 | ||
61 to 70 sessions: 0 | ||
71 to 80 sessions: 1 | ||
81 to 90 sessions: 1 | ||
91 to 100 sessions: 3 | ||
Above 100: 3 | ||
Methods | No training: 99 | |
Normal sports training: 215 | ||
Balance: 3 | ||
Cardio or related: 11 | ||
Core stability or related: 25 | ||
Flexibility: 5 | ||
Lower limb strength/resistance: 153 | ||
Olympic weightlifting: 8 | ||
Plyometric: 123 | ||
Sprint/agility/quickness: 28 | ||
Upper limb strength/resistance: 44 | ||
Other general resistance: 1 | ||
Whole body vibration: 8 | ||
Special training drills involved (squat, lunge, deadlift, or hip thrust) | Yes: 178 | |
No: 144 | ||
Periodization | No periodization: 183 | |
Linear: 102 | ||
Non-linear: 37 | ||
Volume per week | 180 repetitions or above: 97 | |
Below 180 repetitions: 225 | ||
Intraset rest used | Yes: 34 | |
No: 288 | ||
Baseline CMJ | 5.6 to 67.8 cm | N/A |
References
- Sandbakk, Ø. Let’s Close the Gap Between Research and Practice to Discover New Land Together! Int. J. Sports Physiol. Perform. 2018, 13, 961. [Google Scholar] [CrossRef] [PubMed]
- Keegan, R.J.; Cotteril, S.; Woolway, T.; Appaneal, R.; Hutter, V. Strategies for bridging the research-practice ‘gap’ in sport and exercise psychology. Rev. Psicol. Del Deporte 2017, 26, 75–80. [Google Scholar]
- Mallonee, S.; Fowler, C.; Istre, G.R. Bridging the gap between research and practice: A continuing challenge. Inj. Prev. 2006, 12, 357–359. [Google Scholar] [CrossRef]
- Reade, I.; Rodgers, W.; Hall, N. Knowledge transfer: How do high performance coaches access the knowledge of sport sci-entists? Int. J. Sport Sci. Coach. 2008, 3, 319–334. [Google Scholar] [CrossRef]
- Blonde, L.; Khunti, K.; Harris, S.B.; Meizinger, C.; Skolnik, N.S. Interpretation and Impact of Real-World Clinical Data for the Practicing Clinician. Adv. Ther. 2018, 35, 1763–1774. [Google Scholar] [CrossRef] [PubMed]
- Kim, S.; Kim, H. A new metric of absolute percentage error for intermittent demand forecasts. Int. J. Forecast. 2016, 32, 669–679. [Google Scholar] [CrossRef]
- Mallappallil, M.; Sabu, J.; Gruessner, A.; Salifu, M. A review of big data and medical research. SAGE Open Med. 2020, 8. [Google Scholar] [CrossRef]
- Haidich, A.B. Meta-analysis in medical research. Hippokratia 2010, 14 (Suppl. S1), 29–37. [Google Scholar]
- Hagger, M. Meta-analysis in sport and exercise research: Review, recent developments, and recommendations. Eur. J. Sport Sci. 2006, 6, 103–115. [Google Scholar] [CrossRef]
- Faltinsen, E.G.; Storebø, O.J.; Jakobsen, J.C.; Boesen, K.; Lange, T.; Gluud, C. Network meta-analysis: The highest level of medical evidence? BMJ Evid. Based Med. 2018, 23, 56–59. [Google Scholar] [CrossRef]
- Walker, E.; Hernandez, A.V.; Kattan, M. Meta-analysis: Its strengths and limitations. Clevel. Clin. J. Med. 2008, 75, 431–439. [Google Scholar] [CrossRef] [PubMed]
- Zhang, J.; Mucs, D.; Norinder, U.; Svensson, F. LightGBM: An Effective and Scalable Algorithm for Prediction of Chemical Toxicity–Application to the Tox21 and Mutagenicity Data Sets. J. Chem. Inf. Model. 2019, 59, 4150–4158. [Google Scholar] [CrossRef] [PubMed]
- Choubin, B.; Khalighi-Sigaroodi, S.; Malekian, A.; Kişi, Ö. Multiple linear regression, multi-layer perceptron network and adaptive neuro-fuzzy inference system for forecasting precipitation based on large-scale climate signals. Hydrol. Sci. J. 2016, 61, 1001–1009. [Google Scholar] [CrossRef]
- Jeong, J.H.; Resop, J.P.; Mueller, N.D.; Fleisher, D.H.; Yun, K.; Butler, E.E.; Timlin, D.J.; Shim, K.-M.; Gerber, J.S.; Reddy, V.R.; et al. Random Forests for Global and Regional Crop Yield Predictions. PLoS ONE 2016, 11, e0156571. [Google Scholar] [CrossRef] [PubMed]
- Balfer, J.; Bajorath, J. Systematic Artifacts in Support Vector Regression-Based Compound Potency Prediction Revealed by Statistical and Activity Landscape Analysis. PLoS ONE 2015, 10, e0119301. [Google Scholar] [CrossRef] [PubMed]
- Shipe, M.E.; Deppen, S.A.; Farjah, F.; Grogan, E.L. Developing prediction models for clinical use using logistic regression: An overview. J. Thorac. Dis. 2019, 11, S574–S584. [Google Scholar] [CrossRef]
- Pagaduan, J.; Pojskic, H. A Meta-Analysis on the Effect of Complex Training on Vertical Jump Performance. J. Hum. Kinet. 2020, 71, 255–265. [Google Scholar] [CrossRef]
- Bauer, P.; Uebellacker, F.; Mitter, B.; Aigner, A.J.; Hasenoehrl, T.; Ristl, R.; Tschan, H.; Seitz, L.B. Combining higher-load and lower-load resistance training exercises: A systematic review and meta-analysis of findings from complex training studies. J. Sci. Med. Sport 2019, 22, 838–851. [Google Scholar] [CrossRef]
- Petrigna, L.; Karsten, B.; Marcolin, G.; Paoli, A.; D’antona, G.; Palma, A.; Bianco, A. A Review of Countermovement and Squat Jump Testing Methods in the Context of Public Health Examination in Adolescence: Reliability and Feasibility of Current Testing Procedures. Front. Physiol. 2019, 10, 1384. [Google Scholar] [CrossRef]
- Claudino, J.G.; Cronin, J.; Mezêncio, B.; McMaster, D.T.; McGuigan, M.; Tricoli, V.; Amadio, A.C.; Serrão, J.C. The countermovement jump to monitor neuromuscular status: A meta-analysis. J. Sci. Med. Sport 2017, 20, 397–402. [Google Scholar] [CrossRef]
- Pagaduan, J.; Schoenfeld, B.J.; Pojskić, H. Systematic Review and Meta-Analysis on the Effect of Contrast Training on Vertical Jump Performance. Strength Cond. J. 2019, 41, 63–78. [Google Scholar] [CrossRef]
- Milanović, Z.; Pantelić, S.; Čović, N.; Sporiš, G.; Mohr, M.; Krustrup, P. Broad-spectrum physical fitness benefits of recreational football: A systematic review and meta-analysis. Br. J. Sports Med. 2018, 53, 926–939. [Google Scholar] [CrossRef] [PubMed]
- Berton, R.; Lixandrão, M.E.; Pinto E Silva, C.M.; Tricoli, V. Effects of weightlifting exercise, traditional resistance and plyometric training on countermovement jump performance: A meta-analysis. J. Sports Sci. 2018, 36, 2038–2044. [Google Scholar] [CrossRef] [PubMed]
- Slimani, M.; Paravlic, A.; Granacher, U. A Meta-Analysis to Determine Strength Training Related Dose-Response Relationships for Lower-Limb Muscle Power Development in Young Athletes. Front. Physiol. 2018, 9, 1155. [Google Scholar] [CrossRef]
- Moran, J.J.; Sandercock, G.R.; Ramírez-Campillo, R.; Meylan, C.M.; Collison, J.A.; Parry, D.A. Age-related variation in male youth athletes’ countermovement jump following plyometric training. J. Strength Cond. Res. 2017, 31, 552–565. [Google Scholar] [CrossRef] [PubMed]
- Slimani, M.; Paravlić, A.; Bragazzi, N.L. Data concerning the effect of plyometric training on jump performance in soccer players: A meta-analysis. Data Brief. 2017, 15, 324–334. [Google Scholar] [CrossRef]
- Stojanovic, E.; Ristić, V.; McMaster, D.; Milanović, Z. Effect of Plyometric Training on Vertical Jump Performance in Female Athletes: A Systematic Review and Meta-Analysis. Sports Med. 2016, 47, 975–986. [Google Scholar] [CrossRef]
- Taylor, J.; Macpherson, T.; Spears, I.; Weston, M. The Effects of Repeated-Sprint Training on Field-Based Fitness Measures: A Meta-Analysis of Controlled and Non-Controlled Trials. Sports Med. 2015, 45, 881–891. [Google Scholar] [CrossRef]
- Manimmanakorn, N.; Hamlin, M.; Ross, J.J.; Manimmanakorn, A. Long-Term Effect of Whole Body Vibration Training on Jump Height. J. Strength Cond. Res. 2014, 28, 1739–1750. [Google Scholar] [CrossRef]
- Osawa, Y.; Oguma, Y.; Ishii, N. The effects of whole-body vibration on muscle strength and power: A meta-analysis. J. Musculoskelet. Neuronal Interact. 2013, 13, 380–390. [Google Scholar]
- de Villarreal, E.S.-S.; Kellis, E.; Kraemer, W.J.; Izquierdo, M. Determining Variables of Plyometric Training for Improving Vertical Jump Height Performance: A Meta-Analysis. J. Strength Cond. Res. 2009, 23, 495–506. [Google Scholar] [CrossRef] [PubMed]
- Markovic, G.; Newton, R.U. Does plyometric training improve vertical jump height? A meta-analytical review. Br. J. Sports Med. 2007, 41, 349–355. [Google Scholar] [CrossRef] [PubMed]
- Chicco, D.; Warrens, M.J.; Jurman, G. The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation. PeerJ Comput. Sci. 2021, 7, e623. [Google Scholar] [CrossRef] [PubMed]
- Roe, K.D.; Jawa, V.; Zhang, X.; Chute, C.G.; Epstein, J.A.; Matelsky, J.; Shpitser, I.; Taylor, C.O. Feature engineering with clinical expert knowledge: A case study assessment of machine learning model complexity and performance. PLoS ONE 2020, 15, e0231300. [Google Scholar] [CrossRef]
- Zhang, B.; Cao, P. Classification of high dimensional biomedical data based on feature selection using redundant removal. PLoS ONE 2019, 14, e0214406. [Google Scholar] [CrossRef]
- Nigro, F.; Bartolomei, S. A comparison between the squat and the deadlift for lower body strength and power training. J. Hum. Kinet. 2020, 73, 145–152. [Google Scholar] [CrossRef]
- González-García, J.; Morencos, E.; Balsalobre-Fernández, C.; Cuéllar-Rayo, Á.; Romero-Moraleda, B. Effects of 7-Week Hip Thrust Versus Back Squat Resistance Training on Performance in Adolescent Female Soccer Players. Sports 2019, 7, 80. [Google Scholar] [CrossRef]
- Mujika, I.; Halson, S.; Burke, L.M.; Balagué, G.; Farrow, D. An Integrated, Multifactorial Approach to Periodization for Optimal Performance in Individual and Team Sports. Int. J. Sports Physiol. Perform. 2018, 13, 538–561. [Google Scholar] [CrossRef]
- Rouis, M.; Attiogbé, E.; Vandewalle, H.; Jaafar, H.; Noakes, T.D.; Driss, T. Relationship between vertical jump and maximal power output of legs and arms: Effects of ethnicity and sport. Scand. J. Med. Sci. Sports 2014, 25, e197–e207. [Google Scholar] [CrossRef]
- Focke, A.; Strutzenberger, G.; Jekauc, D.; Worth, A.; Woll, A.; Schwameder, H. Effects of age, sex and activity level on counter-movement jump performance in children and adolescents. Eur. J. Sport Sci. 2013, 13, 518–526. [Google Scholar] [CrossRef]
- Oliver, J.M.; Jagim, A.R.; Sanchez, A.C.; Mardock, M.A.; Kelly, K.A.; Meredith, H.J.; Smith, G.L.; Greenwood, M.; Parker, J.L.; Riechman, S.E.; et al. Greater Gains in Strength and Power with Intraset Rest Intervals in Hypertrophic Training. J. Strength Cond. Res. 2013, 27, 3116–3131. [Google Scholar] [CrossRef] [PubMed]
- Perez-Gomez, J.; Calbet, J.A.L. Training methods to improve vertical jump performance. J. Sports Med. Phys. Fit. 2013, 53, 339–357. [Google Scholar]
- McCurdy, K.W.; Langford, G.A.; Doscher, M.W.; Wiley, L.P.; Mallard, K.G. The Effects of Short-Term Unilateral and Bilateral Lower-Body Resistance Training on Measures of Strength and Power. J. Strength Cond. Res. 2005, 19, 9–15. [Google Scholar] [CrossRef] [PubMed]
- Sharifai, G.A.; Zainol, Z. Feature Selection for High-Dimensional and Imbalanced Biomedical Data Based on Robust Correlation Based Redundancy and Binary Grasshopper Optimization Algorithm. Genes 2020, 11, 717. [Google Scholar] [CrossRef]
- Lin, Y.-W.; Zhou, Y.; Faghri, F.; Shaw, M.J.; Campbell, R.H. Analysis and prediction of unplanned intensive care unit readmission using recurrent neural networks with long short-term memory. PLoS ONE 2019, 14, e0218942. [Google Scholar] [CrossRef]
- De Rooij, M.; Weeda, W. Cross-Validation: A method every psychologist should know. Adv. Methods Pract. Psychol. Sci. 2020, 3, 248–263. [Google Scholar] [CrossRef]
- Rotich, N.K.; Backman, J.; Linnanen, L.; Daniil, P. Wind Resource Assessment and Forecast Planning with Neural Networks. J. Sustain. Dev. Energy Water Environ. Syst. 2014, 2, 174–190. [Google Scholar] [CrossRef]
- Ho, I.M.K.; Cheong, K.Y.; Weldon, A. Predicting student satisfaction of emergency remote learning in higher education during COVID-19 using machine learning techniques. PLoS ONE 2021, 16, e0249423. [Google Scholar] [CrossRef]
- Bergstra, J.; Bengio, Y. Random search for hyper-parameter optimization. J. Mach. Learn. 2012, 13, 281–305. Available online: http://dl.acm.org/citation.cfm?id=2503308.2188395 (accessed on 28 January 2020).
- McGovern, A.; Lagerquist, R.; Gagne, D.J.; Jergensen, G.E.; Elmore, K.L.; Homeyer, C.R.; Smith, T. Making the Black Box More Transparent: Understanding the Physical Implications of Machine Learning. Bull. Am. Meteorol. Soc. 2019, 100, 2175–2199. [Google Scholar] [CrossRef]
- Li, Y.; Chen, W. A Comparative Performance Assessment of Ensemble Learning for Credit Scoring. Mathematics 2020, 8, 1756. [Google Scholar] [CrossRef]
- Winters-Stone, K.M.; E Neil-Sztramko, S.; Campbell, K.L. Attention to principles of exercise training: A review of exercise studies for survivors of cancers other than breast. Br. J. Sports Med. 2013, 48, 987–995. [Google Scholar] [CrossRef] [PubMed]
- Vikmoen, O.; Raastad, T.; Ellefsen, S.; Rønnestad, B.R. Adaptations to strength training differ between endurance-trained and untrained women. Eur. J. Appl. Physiol. 2020, 120, 1541–1549. [Google Scholar] [CrossRef] [PubMed]
- Wetmore, A.B.; Moquin, P.A.; Carroll, K.M.; Fry, A.C.; Hornsby, W.G.; Stone, M.H. The Effect of Training Status on Adaptations to 11 Weeks of Block Periodization Training. Sports 2020, 8, 145. [Google Scholar] [CrossRef] [PubMed]
- Hortobágyi, T.; Lesinski, M.; del Olmo, M.F.; Granacher, U. Small and inconsistent effects of whole body vibration on athletic performance: A systematic review and meta-analysis. Eur. J. Appl. Physiol. 2015, 115, 1605–1625. [Google Scholar] [CrossRef]
- McMahon, J.J.; Rej, S.J.E.; Comfort, P. Sex Differences in Countermovement Jump Phase Characteristics. Sports 2017, 5, 8. [Google Scholar] [CrossRef]
- Hunter, G.R.; Singh, H.; Carter, S.J.; Bryan, D.R.; Fisher, G. Sarcopenia and Its Implications for Metabolic Health. J. Obes. 2019, 2019, 8031705. [Google Scholar] [CrossRef]
- Asadi, A.; Ramirez-Campillo, R.; Arazi, H.; de Villarreal, E.S. The effects of maturation on jumping ability and sprint adaptations to plyometric training in youth soccer players. J. Sports Sci. 2018, 36, 2405–2411. [Google Scholar] [CrossRef]
Variable | Description | Format |
---|---|---|
CMJ change | Raw difference of CMJ before and after intervention or control in cm by post-training CMJ–pre-training CMJ | Numerical |
Age | Age of subjects | Numerical |
Gender | Sex of subjects | Categorical |
Ethnicity | Subjects’ ethnicity including American, Asian, Australian, African, and European | Categorical |
Type of sport | Major movement directions or involvements in sports including horizontal based, vertical based, and other sports that are mixed or not well defined | Categorical |
Level of sport participation | Level of subjects including league team, junior team, or recreational/amateur/collegiate | Categorical |
Total training sessions | Total sessions completed by frequency × number of weeks. For the control group that received no intervention, 0 was inputted | Numerical |
Method | Training methods or interventions involved in the study including control (no training), normal sports training, core stability or training-related, lower limb resistance, lower limb strength, plyometric (mixed fast/slow SSC), weightlifting, upper limb resistance, upper limb strength, flexibility training, balance training, sprint-related, agility/quickness training, cardio or aerobic-related, and whole-body vibration | Categorical |
Special training drills | To indicate if training programs included squat, lunge, deadlift, or hip thrust movements or variants by marking true or false | Categorical |
Periodization | To indicate if any periodization strategies were adopted within programs including no periodization, linear periodization, or undulating periodization | Categorical |
Volume per week | To indicate the overall weekly training volume. Number of repetitions ≥ 180 per week indicated as high, while those <180 indicated as low | Categorical |
Intraset rest | To indicate if intraset rest or cluster sets were adopted in the program by marking true or false | Categorical |
Baseline CMJ | Indicated as the pre-CMJ value (cm) before intervention as the baseline | Numerical |
RF | SVM | MLPR | LightGBM | |||||
---|---|---|---|---|---|---|---|---|
Metrics | Training | Testing | Training | Testing | Training | Testing | Training | Testing |
MAE | 0.069 | 0.071 | 1.18 | 1.20 | 0.134 | 0.141 | 0.072 | 0.074 |
RMSE | 0.296 | 0.300 | 1.66 | 1.69 | 0.354 | 0.365 | 0.296 | 0.300 |
R2 | 0.985 | 0.985 | 0.523 | 0.510 | 0.978 | 0.977 | 0.985 | 0.985 |
Pre-CMJ Value (cm) | Age | Predicted CMJ Change (cm) |
---|---|---|
10 * | 18 * | −0.19 |
20 | 18 | −0.24 |
30 | 18 | −0.39 |
40 | 18 | −0.02 |
50 | 18 | −0.15 |
60 | 18 | 0.31 |
70 or above | 18 | 0.30 |
10 | 10 | 0.36 |
10 | 15 | 0.10 |
10 | 20 | 0.20 |
10 | 30 | 0.28 |
10 | 50 or above | 0.27 |
Variable | The Change Made | Predicted CMJ Change (cm) |
---|---|---|
Squat_Lunge_Deadlift_Hipthrust_True | 1 | 1.61 |
Squat_Lunge_Deadlift_Hipthrust_False | 0 | 2.08 |
Plyometric (mixed fast/slow SSC) | 1 | 2.49 |
Race_Asian or Australian (meanwhile turn off “Race_American”) | 1 | 4.04 |
Level_Junior team (meanwhile turn off “Level_Recreational/amateur/collegiate”) | 1 | 4.36 |
Periodization_No periodized program used (meanwhile turn on “Periodization_Linear periodization used”) | 0 | 4.69 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Ho, I.M.K.; Weldon, A.; Yong, J.T.H.; Lam, C.T.T.; Sampaio, J. Using Machine Learning Algorithms to Pool Data from Meta-Analysis for the Prediction of Countermovement Jump Improvement. Int. J. Environ. Res. Public Health 2023, 20, 5881. https://doi.org/10.3390/ijerph20105881
Ho IMK, Weldon A, Yong JTH, Lam CTT, Sampaio J. Using Machine Learning Algorithms to Pool Data from Meta-Analysis for the Prediction of Countermovement Jump Improvement. International Journal of Environmental Research and Public Health. 2023; 20(10):5881. https://doi.org/10.3390/ijerph20105881
Chicago/Turabian StyleHo, Indy Man Kit, Anthony Weldon, Jason Tze Ho Yong, Candy Tze Tim Lam, and Jaime Sampaio. 2023. "Using Machine Learning Algorithms to Pool Data from Meta-Analysis for the Prediction of Countermovement Jump Improvement" International Journal of Environmental Research and Public Health 20, no. 10: 5881. https://doi.org/10.3390/ijerph20105881