Comparative study of imputation strategies to improve the sarcopenia prediction task
Objective Sarcopenia, a condition characterized by the progressive loss of skeletal muscle mass and strength, poses significant challenges in research due to missing data. Incomplete datasets undermine the accuracy and reliability of studies, necessitating effective imputation techniques. This study...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SAGE Publishing
2025-01-01
|
| Series: | Digital Health |
| Online Access: | https://doi.org/10.1177/20552076241301960 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841525281605550080 |
|---|---|
| author | Shakhzod Karimov Dilmurod Turimov Wooseong Kim Jiyoun Kim |
| author_facet | Shakhzod Karimov Dilmurod Turimov Wooseong Kim Jiyoun Kim |
| author_sort | Shakhzod Karimov |
| collection | DOAJ |
| description | Objective Sarcopenia, a condition characterized by the progressive loss of skeletal muscle mass and strength, poses significant challenges in research due to missing data. Incomplete datasets undermine the accuracy and reliability of studies, necessitating effective imputation techniques. This study conducts a comparative analysis of three advanced methods—multiple imputation by chained equations (MICE), support vector regression, and K-nearest neighbors (KNN)—to address data completeness issues in sarcopenia research. Methods Following imputation, we utilized machine learning models, including logistic regression, gradient boosting, support vector machine, and random forest, to classify sarcopenia. The methodology encompassed rigorous data preprocessing, normalization, and the synthetic minority oversampling technique to address class imbalance and ensure unbiased model performance. Results The results revealed substantial variations in model accuracy based on the imputation method employed. The gradient boosting model consistently exhibited superior performance across all imputation strategies, demonstrating its robustness with imputed datasets. Additionally, KNN and MICE emerged as effective imputation techniques, preserving the original data distribution and enabling more accurate classification outcomes. Conclusion This study underscores the pivotal role of imputation methods in maintaining data integrity and enhancing predictive accuracy in sarcopenia research. The gradient boosting model's reliability across all strategies highlights its potential as a robust classifier, while the suitability of KNN and MICE for preserving data distribution supports their application in similar research contexts. These findings contribute to more reliable and valid insights in sarcopenia studies, ultimately supporting improved clinical outcomes. |
| format | Article |
| id | doaj-art-27b2b8933a7b4755b7b529bdd14ff288 |
| institution | Kabale University |
| issn | 2055-2076 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | SAGE Publishing |
| record_format | Article |
| series | Digital Health |
| spelling | doaj-art-27b2b8933a7b4755b7b529bdd14ff2882025-01-17T17:03:54ZengSAGE PublishingDigital Health2055-20762025-01-011110.1177/20552076241301960Comparative study of imputation strategies to improve the sarcopenia prediction taskShakhzod Karimov0Dilmurod Turimov1Wooseong Kim2Jiyoun Kim3 Department of Computer Engineering, , Seongnam-si, Republic of Korea Department of Computer Engineering, , Seongnam-si, Republic of Korea Department of Computer Engineering, , Seongnam-si, Republic of Korea Department of Exercise Rehabilitation & Welfare, , Incheon, Republic of KoreaObjective Sarcopenia, a condition characterized by the progressive loss of skeletal muscle mass and strength, poses significant challenges in research due to missing data. Incomplete datasets undermine the accuracy and reliability of studies, necessitating effective imputation techniques. This study conducts a comparative analysis of three advanced methods—multiple imputation by chained equations (MICE), support vector regression, and K-nearest neighbors (KNN)—to address data completeness issues in sarcopenia research. Methods Following imputation, we utilized machine learning models, including logistic regression, gradient boosting, support vector machine, and random forest, to classify sarcopenia. The methodology encompassed rigorous data preprocessing, normalization, and the synthetic minority oversampling technique to address class imbalance and ensure unbiased model performance. Results The results revealed substantial variations in model accuracy based on the imputation method employed. The gradient boosting model consistently exhibited superior performance across all imputation strategies, demonstrating its robustness with imputed datasets. Additionally, KNN and MICE emerged as effective imputation techniques, preserving the original data distribution and enabling more accurate classification outcomes. Conclusion This study underscores the pivotal role of imputation methods in maintaining data integrity and enhancing predictive accuracy in sarcopenia research. The gradient boosting model's reliability across all strategies highlights its potential as a robust classifier, while the suitability of KNN and MICE for preserving data distribution supports their application in similar research contexts. These findings contribute to more reliable and valid insights in sarcopenia studies, ultimately supporting improved clinical outcomes.https://doi.org/10.1177/20552076241301960 |
| spellingShingle | Shakhzod Karimov Dilmurod Turimov Wooseong Kim Jiyoun Kim Comparative study of imputation strategies to improve the sarcopenia prediction task Digital Health |
| title | Comparative study of imputation strategies to improve the sarcopenia prediction task |
| title_full | Comparative study of imputation strategies to improve the sarcopenia prediction task |
| title_fullStr | Comparative study of imputation strategies to improve the sarcopenia prediction task |
| title_full_unstemmed | Comparative study of imputation strategies to improve the sarcopenia prediction task |
| title_short | Comparative study of imputation strategies to improve the sarcopenia prediction task |
| title_sort | comparative study of imputation strategies to improve the sarcopenia prediction task |
| url | https://doi.org/10.1177/20552076241301960 |
| work_keys_str_mv | AT shakhzodkarimov comparativestudyofimputationstrategiestoimprovethesarcopeniapredictiontask AT dilmurodturimov comparativestudyofimputationstrategiestoimprovethesarcopeniapredictiontask AT wooseongkim comparativestudyofimputationstrategiestoimprovethesarcopeniapredictiontask AT jiyounkim comparativestudyofimputationstrategiestoimprovethesarcopeniapredictiontask |