Neural Network Approach to Investigating the Importance of Test Items for Predicting Physical Activity in Chronic Obstructive Pulmonary Disease
Contracting COPD reduces a patient’s physical activity and restricts everyday activities (physical activity disorder). However, the fundamental cause of physical activity disorder has not been found. In addition, costly and specialized equipment is required to accurately examine the disorder; hence,...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-06-01
|
| Series: | Journal of Clinical Medicine |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0383/12/13/4297 |
| _version_ | 1797591408162373632 |
|---|---|
| author | Yoshiki Nakahara Shingo Mabu Tsunahiko Hirano Yoriyuki Murata Keiko Doi Ayumi Fukatsu-Chikumoto Kazuto Matsunaga |
| author_facet | Yoshiki Nakahara Shingo Mabu Tsunahiko Hirano Yoriyuki Murata Keiko Doi Ayumi Fukatsu-Chikumoto Kazuto Matsunaga |
| author_sort | Yoshiki Nakahara |
| collection | DOAJ |
| description | Contracting COPD reduces a patient’s physical activity and restricts everyday activities (physical activity disorder). However, the fundamental cause of physical activity disorder has not been found. In addition, costly and specialized equipment is required to accurately examine the disorder; hence, it is not regularly assessed in normal clinical practice. In this study, we constructed a machine learning model to predict physical activity using test items collected during the normal care of COPD patients. In detail, we first applied three types of data preprocessing methods (zero-padding, multiple imputation by chained equations (MICE), and k-nearest neighbor (kNN)) to complement missing values in the dataset. Then, we constructed several types of neural networks to predict physical activity. Finally, permutation importance was calculated to identify the importance of the test items for prediction. Multifactorial analysis using machine learning, including blood, lung function, walking, and chest imaging tests, was the unique point of this research. From the experimental results, it was found that the missing value processing using MICE contributed to the best prediction accuracy (73.00%) compared to that using zero-padding (68.44%) or kNN (71.52%), and showed better accuracy than XGBoost (66.12%) with a significant difference (<i>p</i> < 0.05). For patients with severe physical activity reduction (total exercise < 1.5), a high sensitivity (89.36%) was obtained. The permutation importance showed that “sex, the number of cigarettes, age, and the whole body phase angle (nutritional status)” were the most important items for this prediction. Furthermore, we found that a smaller number of test items could be used in ordinary clinical practice for the screening of physical activity disorder. |
| first_indexed | 2024-03-11T01:36:59Z |
| format | Article |
| id | doaj.art-470d689ad2e74f43ae36b3797e358d21 |
| institution | Directory Open Access Journal |
| issn | 2077-0383 |
| language | English |
| last_indexed | 2024-03-11T01:36:59Z |
| publishDate | 2023-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Clinical Medicine |
| spelling | doaj.art-470d689ad2e74f43ae36b3797e358d212023-11-18T16:51:51ZengMDPI AGJournal of Clinical Medicine2077-03832023-06-011213429710.3390/jcm12134297Neural Network Approach to Investigating the Importance of Test Items for Predicting Physical Activity in Chronic Obstructive Pulmonary DiseaseYoshiki Nakahara0Shingo Mabu1Tsunahiko Hirano2Yoriyuki Murata3Keiko Doi4Ayumi Fukatsu-Chikumoto5Kazuto Matsunaga6Graduate School of Sciences and Technology for Innovation, Yamaguchi University, Yamaguchi 7558611, JapanGraduate School of Sciences and Technology for Innovation, Yamaguchi University, Yamaguchi 7558611, JapanDepartment of Respiratory Medicine and Infectious Disease, Yamaguchi University Hospital, Yamaguchi 7558505, JapanDepartment of Respiratory Medicine and Infectious Disease, Yamaguchi University Hospital, Yamaguchi 7558505, JapanDepartment of Respiratory Medicine and Infectious Disease, Yamaguchi University Hospital, Yamaguchi 7558505, JapanDepartment of Respiratory Medicine and Infectious Disease, Yamaguchi University Hospital, Yamaguchi 7558505, JapanDepartment of Respiratory Medicine and Infectious Disease, Yamaguchi University Hospital, Yamaguchi 7558505, JapanContracting COPD reduces a patient’s physical activity and restricts everyday activities (physical activity disorder). However, the fundamental cause of physical activity disorder has not been found. In addition, costly and specialized equipment is required to accurately examine the disorder; hence, it is not regularly assessed in normal clinical practice. In this study, we constructed a machine learning model to predict physical activity using test items collected during the normal care of COPD patients. In detail, we first applied three types of data preprocessing methods (zero-padding, multiple imputation by chained equations (MICE), and k-nearest neighbor (kNN)) to complement missing values in the dataset. Then, we constructed several types of neural networks to predict physical activity. Finally, permutation importance was calculated to identify the importance of the test items for prediction. Multifactorial analysis using machine learning, including blood, lung function, walking, and chest imaging tests, was the unique point of this research. From the experimental results, it was found that the missing value processing using MICE contributed to the best prediction accuracy (73.00%) compared to that using zero-padding (68.44%) or kNN (71.52%), and showed better accuracy than XGBoost (66.12%) with a significant difference (<i>p</i> < 0.05). For patients with severe physical activity reduction (total exercise < 1.5), a high sensitivity (89.36%) was obtained. The permutation importance showed that “sex, the number of cigarettes, age, and the whole body phase angle (nutritional status)” were the most important items for this prediction. Furthermore, we found that a smaller number of test items could be used in ordinary clinical practice for the screening of physical activity disorder.https://www.mdpi.com/2077-0383/12/13/4297COPDphysical activitypredictionneural networkautoencoder |
| spellingShingle | Yoshiki Nakahara Shingo Mabu Tsunahiko Hirano Yoriyuki Murata Keiko Doi Ayumi Fukatsu-Chikumoto Kazuto Matsunaga Neural Network Approach to Investigating the Importance of Test Items for Predicting Physical Activity in Chronic Obstructive Pulmonary Disease Journal of Clinical Medicine COPD physical activity prediction neural network autoencoder |
| title | Neural Network Approach to Investigating the Importance of Test Items for Predicting Physical Activity in Chronic Obstructive Pulmonary Disease |
| title_full | Neural Network Approach to Investigating the Importance of Test Items for Predicting Physical Activity in Chronic Obstructive Pulmonary Disease |
| title_fullStr | Neural Network Approach to Investigating the Importance of Test Items for Predicting Physical Activity in Chronic Obstructive Pulmonary Disease |
| title_full_unstemmed | Neural Network Approach to Investigating the Importance of Test Items for Predicting Physical Activity in Chronic Obstructive Pulmonary Disease |
| title_short | Neural Network Approach to Investigating the Importance of Test Items for Predicting Physical Activity in Chronic Obstructive Pulmonary Disease |
| title_sort | neural network approach to investigating the importance of test items for predicting physical activity in chronic obstructive pulmonary disease |
| topic | COPD physical activity prediction neural network autoencoder |
| url | https://www.mdpi.com/2077-0383/12/13/4297 |
| work_keys_str_mv | AT yoshikinakahara neuralnetworkapproachtoinvestigatingtheimportanceoftestitemsforpredictingphysicalactivityinchronicobstructivepulmonarydisease AT shingomabu neuralnetworkapproachtoinvestigatingtheimportanceoftestitemsforpredictingphysicalactivityinchronicobstructivepulmonarydisease AT tsunahikohirano neuralnetworkapproachtoinvestigatingtheimportanceoftestitemsforpredictingphysicalactivityinchronicobstructivepulmonarydisease AT yoriyukimurata neuralnetworkapproachtoinvestigatingtheimportanceoftestitemsforpredictingphysicalactivityinchronicobstructivepulmonarydisease AT keikodoi neuralnetworkapproachtoinvestigatingtheimportanceoftestitemsforpredictingphysicalactivityinchronicobstructivepulmonarydisease AT ayumifukatsuchikumoto neuralnetworkapproachtoinvestigatingtheimportanceoftestitemsforpredictingphysicalactivityinchronicobstructivepulmonarydisease AT kazutomatsunaga neuralnetworkapproachtoinvestigatingtheimportanceoftestitemsforpredictingphysicalactivityinchronicobstructivepulmonarydisease |