Metaheuristic-Based Feature Selection Methods for Diagnosing Sarcopenia with Machine Learning Algorithms
Source abstract
Abstract
This study explores the efficacy of metaheuristic-based feature selection in improving machine learning performance for diagnosing sarcopenia. Extraction and utilization of features significantly impacting diagnosis efficacy emerge as a critical facet when applying machine learning for sarcopenia diagnosis. Using data from the 8th Korean Longitudinal Study on Aging (KLoSA), this study examines harmony search (HS) and the genetic algorithm (GA) for feature selection. Evaluation of the resulting feature set involves a decision tree, a random forest, a support vector machine, and naïve bayes algorithms. As a result, the HS-derived feature set trained with a support vector machine yielded an accuracy of 0.785 and a weighted F1 score of 0.782, which outperformed traditional methods. These findings underscore the competitive edge of metaheuristic-based selection, demonstrating its potential in advancing sarcopenia diagnosis. This study advocates for further exploration of metaheuristic-based feature selection’s pivotal role in future sarcopenia research.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Nutrition and Health in Aging · Body Composition Measurement Techniques · Frailty in Older Adults
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of IT Convergence, Gachon University, 1342 Seongnamdaero, Sujeong-gu, Seongnam-si 13120, Gyeonggi-do, Republic of Korea
Department of Computer Engineering, Gachon University, 1342 Seongnamdaero, Sujeong-gu, Seongnam-si 13120, Gyeonggi-do, Republic of Korea
Department of Exercise Rehabilitation, Gachon University, 191 Hambakmoe-ro, Yeonsu-gu, Incheon 21936, Republic of Korea
School of Software, Kwangwoon University, 20 Kwangwoon-ro, Nowon-gu, Seoul 01897, Republic of Korea
Funding
National Research Foundation of Korea · Gachon University
References (63)
Show source-provided references
1. Clinical definition of sarcopenia
2. Sarcopenia definition, diagnosis and treatment: Consensus is growing10.1093/ageing/afac220 ↗
3. Detection of sarcopenia using deep learning-based artificial intelligence body part measure system (AIBMS)10.3389/fphys.2023.1092352 ↗
4. Development and verification of a combined diagnostic model for sarcopenia with random forest and artificial neural network10.1155/2022/2957731 ↗
5. Sarcopenia feature selection and risk prediction using machine learning: A cross-sectional study10.1097/MD.0000000000017699 ↗
6. Turimov Mustapoevich, D., and Kim, W. (2023). Machine learning applications in sarcopenia detection and management: A comprehensive survey. Healthcare, 11.10.3390/healthcare11182483 ↗
7. Dietary inflammatory potential and risk of sarcopenia: Data from national health and nutrition examination surveys10.18632/aging.202141 ↗
8. Sarcopenia, healthy living, and mortality in patients with chronic liver diseases10.1002/hep4.2061 ↗
9. Liao, H., Yang, Y., Zeng, Y., Qiu, Y., Chen, Y., Zhu, L., Fu, P., Yan, F., Chen, Y., and Yuan, H. (2023). Use machine learning to help identify possible sarcopenia cases in maintenance hemodialysis patients. BMC Nephrol., 24.10.1186/s12882-023-03084-7 ↗
10. Learning human insight by cooperative AI: Shannon-Neumann measure10.1088/2633-1357/abec9e ↗
11. Using machine learning to detect sarcopenia from electronic health records10.1177/20552076231197098 ↗
12. Seok, M., and Kim, W. (2023). Sarcopenia prediction for elderly people using machine learning: A case study on physical activity. Healthcare, 11.10.3390/healthcare11091334 ↗
13. Zupo, R., Moroni, A., Castellana, F., Gasparri, C., Catino, F., Lampignano, L., Perna, S., Clodoveo, M.L., Sardone, R., and Rondanelli, M. (2023). A machine-learning approach to target clinical and biological features associated with sarcopenia: Findings from northern and Southern Italian aging populations. Metabolites, 13.10.3390/metabo13040565 ↗
14. Laousy, O., Chassagnon, G., Oyallon, E., Paragios, N., Revel, M.P., and Vakalopoulou, M. (2021, January 27). Deep reinforcement learning for l3 slice localization in sarcopenia assessment. Proceedings of the Machine Learning in Medical Imaging: 12th International Workshop, MLMI 2021, Held in Conjunction with MICCAI 2021, Strasbourg, France. Proceedings 12.10.1007/978-3-030-87589-3_33 ↗
15. Teixeira, E., Bohn, L., Guimarães, J.P., and Marques-Aleixo, I. (2022). Portable digital monitoring system for sarcopenia screening and diagnosis. Geriatrics, 7.10.3390/geriatrics7060121 ↗
16. Measurement and interpretation of handgrip strength for research on sarcopenia and osteoporosis10.11005/jbm.2020.27.2.85 ↗
17. Asian Working Group for Sarcopenia: 2019 consensus update on sarcopenia diagnosis and treatment10.1016/j.jamda.2019.12.012 ↗
18. Validation of the Korean version of the SARC-F questionnaire to assess sarcopenia: Korean frailty and aging cohort study10.1016/j.jamda.2017.07.006 ↗
19. Gait speed as a mediator of the effect of sarcopenia on dependency in activities of daily living10.1002/jcsm.12444 ↗
20. Kostka, J., Sosowska, N., Guligowska, A., and Kostka, T. (2022). A proposed method of converting gait speed and TUG test in older subjects. Int. J. Environ. Res. Public Health, 19.10.3390/ijerph191912145 ↗
21. Seok, M., Kim, W., and Kim, J. (2023). Machine learning for sarcopenia prediction in the elderly using socioeconomic, infrastructure, and quality-of-life data. Healthcare, 11.10.3390/healthcare11212881 ↗
22. Lee, J., Choi, Y., and Yoon, Y. (2023, January 15–19). Genetic algorithm-based feature selection for machine learning system diagnosing sarcopenia with survey data. Proceedings of the Companion Conference on Genetic and Evolutionary Computation, Lisbon, Portugal.10.1145/3583133.3596943 ↗
23. Grip strength: An indispensable biomarker for older adults10.2147/CIA.S194543 ↗
24. Sousa-Santos, A., and Amaral, T. (2017). Differences in handgrip strength protocols to identify sarcopenia and frailty—A systematic review. BMC Geriatr., 17.10.1186/s12877-017-0625-y ↗
25. Handgrip strength as a valid practical tool to screen early-onset sarcopenia in acute care wards: A first evaluation10.1038/s41430-021-00906-5 ↗
26. Handgrip strength rather than chair stand test should be used to diagnose sarcopenia in geriatric rehabilitation inpatients: REStORing health of acutely unwell adulTs (RESORT)10.1093/ageing/afac242 ↗
27. A comprehensive review of dimensionality reduction techniques for feature selection and feature extraction10.38094/jastt1224 ↗
28. An introduction to variable and feature selection
29. Feature selection: A data perspective
30. Different metaheuristic strategies to solve the feature selection problem10.1016/j.patrec.2008.11.012 ↗
31. Nature inspired feature selection meta-heuristics10.1007/s10462-015-9428-8 ↗
32. Feature selection with harmony search10.1109/TSMCB.2012.2193613 ↗
33. A comprehensive survey on metaheuristic algorithm for feature selection techniques10.1016/j.matpr.2022.04.803 ↗
34. Mitchell, M. (1998). An Introduction to Genetic Algorithms, MIT Press.10.7551/mitpress/3927.001.0001 ↗
35. Lambora, A., Gupta, K., and Chopra, K. (2019, January 14–16). Genetic algorithm—A literature review. Proceedings of the 2019 International Conference on Machine Learning, Big Data, Cloud and Parallel Computing (COMITCon), Faridabad, India.10.1109/COMITCon.2019.8862255 ↗
36. Solving NP hard problems using genetic algorithm
37. Montazeri, M., Montazeri, M., Naji, H.R., and Faraahi, A. (2013, January 28–30). A novel memetic feature selection algorithm. Proceedings of the 5th Conference on Information and Knowledge Technology, Shiraz, Iran.10.1109/IKT.2013.6620082 ↗
38. A genetic algorithm tutorial10.1007/BF00175354 ↗
39. Adaptive probabilities of crossover and mutation in genetic algorithms10.1109/21.286385 ↗
40. A new heuristic optimization algorithm: Harmony search10.1177/003754970107600201 ↗
41. Yang, X.S. (2009). Music-Inspired Harmony Search Algorithm: Theory and Applications, Springer.
42. Sports data mining: Predicting results for the college football games10.1016/j.procs.2014.08.153 ↗
43. The variants of the harmony search algorithm: An overview10.1007/s10462-010-9201-y ↗
44. Feature selection based on improved binary global harmony search for data classification10.1016/j.asoc.2020.106402 ↗
45. Mean hand grip strength and cut-off value for sarcopenia in Korean adults using KNHANES VI10.3346/jkms.2017.32.5.868 ↗
46. The WEKA data mining software: An update10.1145/1656274.1656278 ↗
47. Learning the naive Bayes classifier with optimization models10.2478/amcs-2013-0059 ↗
48. Koch, P., Golovidov, O., Gardner, S., Wujek, B., Griffin, J., and Xu, Y. (2018, January 19–23). Autotune: A derivative-free optimization framework for hyperparameter tuning. Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, London, UK.10.1145/3219819.3219837 ↗
49. A tutorial on automatic hyperparameter tuning of deep spectral modelling for regression and classification tasks10.1016/j.chemolab.2022.104520 ↗
50. An improvement of the standard genetic algorithm fighting premature convergence in continuous optimization10.1016/S0965-9978(00)00070-3 ↗
51. Hall, M.A. (1999). Correlation-Based Feature Selection for Machine Learning. [Ph.D. Thesis, The University of Waikato].
52. Feature selection based on information gain
53. Crossover operators in genetic algorithms: A review
54. Kira, K., and Rendell, L.A. (1992). Machine Learning Proceedings 1992, Elsevier.
55. Hassanat, A., Almohammadi, K., Alkafaween, E., Abunawas, E., Hammouri, A., and Prasath, V.S. (2019). Choosing mutation and crossover ratios for genetic algorithms—A review with a new dynamic approach. Information, 10.10.3390/info10120390 ↗
56. On the ethics of algorithmic decision-making in healthcare10.1136/medethics-2019-105586 ↗
57. Heyen, N.B., and Salloch, S. (2021). The ethics of machine learning-based clinical decision support: An analysis through the lens of professionalisation theory. BMC Med. Ethics, 22.10.1186/s12910-021-00679-3 ↗
58. Ahsan, M.M., Luna, S.A., and Siddique, Z. (2022). Machine-learning-based disease diagnosis: A comprehensive review. Healthcare, 10.10.3390/healthcare10030541 ↗
59. Alufaisan, Y., Marusich, L.R., Bakdash, J.Z., Zhou, Y., and Kantarcioglu, M. (2021, January 2–9). Does explainable artificial intelligence improve human decision-making?. Proceedings of the AAAI Conference on Artificial Intelligence, Virtually.10.31234/osf.io/d4r9t ↗
60. The false hope of current approaches to explainable artificial intelligence in health care10.1016/S2589-7500(21)00208-9 ↗
61. A comprehensive survey on recent metaheuristics for feature selection10.1016/j.neucom.2022.04.083 ↗
62. Lundberg, S.M., and Lee, S.I. (2017, January 4–9). A Unified Approach to Interpreting Model Predictions. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA.
63. Designing a feature selection method based on explainable artificial intelligence10.1007/s12525-022-00608-1 ↗