Investigation of a chest radiograph-based deep learning model to identify an imaging biomarker for malnutrition in older adults

Summary: Background & Aims: In recent years, artificial intelligence (AI) models based on chest radiography have gained attention in various fields, including cardiac function, age estimation, and clinical assessment during hospitalization. The Global Leadership Initiative on Malnutrition (...

Full description

Saved in:
Bibliographic Details
Main Authors: Ryo Sasaki, Yasuhiko Nakao, Fumihiro Mawatari, Takahito Nishihara, Masafumi Haraguchi, Masanori Fukushima, Ryu Sasaki, Satoshi Miuma, Hisamitsu Miyaaki, Kazuhiko Nakao
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:Clinical Nutrition Open Science
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2667268524001050
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850061594473529344
author Ryo Sasaki
Yasuhiko Nakao
Fumihiro Mawatari
Takahito Nishihara
Masafumi Haraguchi
Masanori Fukushima
Ryu Sasaki
Satoshi Miuma
Hisamitsu Miyaaki
Kazuhiko Nakao
author_facet Ryo Sasaki
Yasuhiko Nakao
Fumihiro Mawatari
Takahito Nishihara
Masafumi Haraguchi
Masanori Fukushima
Ryu Sasaki
Satoshi Miuma
Hisamitsu Miyaaki
Kazuhiko Nakao
author_sort Ryo Sasaki
collection DOAJ
description Summary: Background & Aims: In recent years, artificial intelligence (AI) models based on chest radiography have gained attention in various fields, including cardiac function, age estimation, and clinical assessment during hospitalization. The Global Leadership Initiative on Malnutrition (GLIM) criteria are widely used in malnutrition diagnosis. The objective of this study is to examine the predictive ability of chest radiographs using deep learning techniques in relation to hematological parameters that are already known to be associated with malnutrition, as well as malnutrition scores, including GLIM criteria. Methods: A total of 3701 older patients (age ≥65 years) were admitted to our hospital from January 2021 to January 2022, and after excluding those with missing data, participants (N=2862) were enrolled. Chest Radiographs, Basic information (height, weight, age, and sex), hematological parameters (albumin, hemoglobin, lymphocyte count, and C-reactive protein), malnutritional assessments: GLIM severity, Geriatric Nutritional Risk Index (GNRI), modified Controlling Nutritional status (mCONUT), and Subjective Global Assessment (SGA), and Nutritional Support Team (NST) intervention were extracted and utilized as training and validation data. We used chest radiographic image's matrix as explanatory variables for numerical (hematological parameters) or categorical (scoring) nutritional data as objective variables. A previously reported deep learning model helped construct a chest radiography-based prediction model from the training data. The predicted data were evaluated by computing the correlation coefficients and area under the curve (AUC). Results: As a numerical variables analysis, albumin and hemoglobin predictions were relatively accurate (R=0.71, 0.74). As a categorical malnutritional prediction, chest radiograph-based AI effectively aided nutritional decisions based on GNRI (AUC: 0.88, 0.83, 0.88, and 0.90), SGA (0.75, 0.71, and 0.88), mCONUT (0.84, 0.88, 0.90, and 0.88), and GLIM severity (0.88, 0.82, and 0.85) class indices. The Class activation maps (CAM) analysis identified variation in the X-ray sites for each malnutritional AI prediction, with some sites in agreement and others in disagreement. Conclusion: Deep learning-based chest radiographic AI has the potential to more accurately reflect malnutrition scoring than hematologic parameters. Furthermore, it can predict outcomes and assess malnutrition, including GLIM criteria. It is anticipated that AI will be integrated into the NST workflow in the future.
format Article
id doaj-art-3262eeb8b439420fbc65b95232d62455
institution DOAJ
issn 2667-2685
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series Clinical Nutrition Open Science
spelling doaj-art-3262eeb8b439420fbc65b95232d624552025-08-20T02:50:09ZengElsevierClinical Nutrition Open Science2667-26852024-12-015824025110.1016/j.nutos.2024.10.010Investigation of a chest radiograph-based deep learning model to identify an imaging biomarker for malnutrition in older adultsRyo Sasaki0Yasuhiko Nakao1Fumihiro Mawatari2Takahito Nishihara3Masafumi Haraguchi4Masanori Fukushima5Ryu Sasaki6Satoshi Miuma7Hisamitsu Miyaaki8Kazuhiko Nakao9Department of Rehabilitation, Juzenkai Hospital, JapanDepartment of Gastroenterology and Hepatology, Graduate School of Biomedical Sciences Nagasaki University, Japan; Corresponding author. Department of Gastroenterology and Hepatology, Nagasaki University, 1-7-1 Sakamoto, Nagasaki 852-8501, Japan.Department of Gastroenterology and Hepatology, Juzenkai Hospital, JapanDepartment of Gastroenterology and Hepatology, Isahaya General Hospital, 24-1 Eishohigashimachi, Isahaya, Nagasaki, JapanDepartment of Gastroenterology and Hepatology, Graduate School of Biomedical Sciences Nagasaki University, JapanDepartment of Gastroenterology and Hepatology, Graduate School of Biomedical Sciences Nagasaki University, JapanDepartment of Gastroenterology and Hepatology, Graduate School of Biomedical Sciences Nagasaki University, JapanDepartment of Gastroenterology and Hepatology, Graduate School of Biomedical Sciences Nagasaki University, JapanDepartment of Gastroenterology and Hepatology, Graduate School of Biomedical Sciences Nagasaki University, JapanDepartment of Gastroenterology and Hepatology, Graduate School of Biomedical Sciences Nagasaki University, JapanSummary: Background & Aims: In recent years, artificial intelligence (AI) models based on chest radiography have gained attention in various fields, including cardiac function, age estimation, and clinical assessment during hospitalization. The Global Leadership Initiative on Malnutrition (GLIM) criteria are widely used in malnutrition diagnosis. The objective of this study is to examine the predictive ability of chest radiographs using deep learning techniques in relation to hematological parameters that are already known to be associated with malnutrition, as well as malnutrition scores, including GLIM criteria. Methods: A total of 3701 older patients (age ≥65 years) were admitted to our hospital from January 2021 to January 2022, and after excluding those with missing data, participants (N=2862) were enrolled. Chest Radiographs, Basic information (height, weight, age, and sex), hematological parameters (albumin, hemoglobin, lymphocyte count, and C-reactive protein), malnutritional assessments: GLIM severity, Geriatric Nutritional Risk Index (GNRI), modified Controlling Nutritional status (mCONUT), and Subjective Global Assessment (SGA), and Nutritional Support Team (NST) intervention were extracted and utilized as training and validation data. We used chest radiographic image's matrix as explanatory variables for numerical (hematological parameters) or categorical (scoring) nutritional data as objective variables. A previously reported deep learning model helped construct a chest radiography-based prediction model from the training data. The predicted data were evaluated by computing the correlation coefficients and area under the curve (AUC). Results: As a numerical variables analysis, albumin and hemoglobin predictions were relatively accurate (R=0.71, 0.74). As a categorical malnutritional prediction, chest radiograph-based AI effectively aided nutritional decisions based on GNRI (AUC: 0.88, 0.83, 0.88, and 0.90), SGA (0.75, 0.71, and 0.88), mCONUT (0.84, 0.88, 0.90, and 0.88), and GLIM severity (0.88, 0.82, and 0.85) class indices. The Class activation maps (CAM) analysis identified variation in the X-ray sites for each malnutritional AI prediction, with some sites in agreement and others in disagreement. Conclusion: Deep learning-based chest radiographic AI has the potential to more accurately reflect malnutrition scoring than hematologic parameters. Furthermore, it can predict outcomes and assess malnutrition, including GLIM criteria. It is anticipated that AI will be integrated into the NST workflow in the future.http://www.sciencedirect.com/science/article/pii/S2667268524001050Nutritional support teamAIOlder patientsDeep learningChest radiograph
spellingShingle Ryo Sasaki
Yasuhiko Nakao
Fumihiro Mawatari
Takahito Nishihara
Masafumi Haraguchi
Masanori Fukushima
Ryu Sasaki
Satoshi Miuma
Hisamitsu Miyaaki
Kazuhiko Nakao
Investigation of a chest radiograph-based deep learning model to identify an imaging biomarker for malnutrition in older adults
Clinical Nutrition Open Science
Nutritional support team
AI
Older patients
Deep learning
Chest radiograph
title Investigation of a chest radiograph-based deep learning model to identify an imaging biomarker for malnutrition in older adults
title_full Investigation of a chest radiograph-based deep learning model to identify an imaging biomarker for malnutrition in older adults
title_fullStr Investigation of a chest radiograph-based deep learning model to identify an imaging biomarker for malnutrition in older adults
title_full_unstemmed Investigation of a chest radiograph-based deep learning model to identify an imaging biomarker for malnutrition in older adults
title_short Investigation of a chest radiograph-based deep learning model to identify an imaging biomarker for malnutrition in older adults
title_sort investigation of a chest radiograph based deep learning model to identify an imaging biomarker for malnutrition in older adults
topic Nutritional support team
AI
Older patients
Deep learning
Chest radiograph
url http://www.sciencedirect.com/science/article/pii/S2667268524001050
work_keys_str_mv AT ryosasaki investigationofachestradiographbaseddeeplearningmodeltoidentifyanimagingbiomarkerformalnutritioninolderadults
AT yasuhikonakao investigationofachestradiographbaseddeeplearningmodeltoidentifyanimagingbiomarkerformalnutritioninolderadults
AT fumihiromawatari investigationofachestradiographbaseddeeplearningmodeltoidentifyanimagingbiomarkerformalnutritioninolderadults
AT takahitonishihara investigationofachestradiographbaseddeeplearningmodeltoidentifyanimagingbiomarkerformalnutritioninolderadults
AT masafumiharaguchi investigationofachestradiographbaseddeeplearningmodeltoidentifyanimagingbiomarkerformalnutritioninolderadults
AT masanorifukushima investigationofachestradiographbaseddeeplearningmodeltoidentifyanimagingbiomarkerformalnutritioninolderadults
AT ryusasaki investigationofachestradiographbaseddeeplearningmodeltoidentifyanimagingbiomarkerformalnutritioninolderadults
AT satoshimiuma investigationofachestradiographbaseddeeplearningmodeltoidentifyanimagingbiomarkerformalnutritioninolderadults
AT hisamitsumiyaaki investigationofachestradiographbaseddeeplearningmodeltoidentifyanimagingbiomarkerformalnutritioninolderadults
AT kazuhikonakao investigationofachestradiographbaseddeeplearningmodeltoidentifyanimagingbiomarkerformalnutritioninolderadults