Cargando…

Effect of Patient Clinical Variables in Osteoporosis Classification Using Hip X-rays in Deep Learning Analysis

Background and Objectives: A few deep learning studies have reported that combining image features with patient variables enhanced identification accuracy compared with image-only models. However, previous studies have not statistically reported the additional effect of patient variables on the imag...

Descripción completa

Detalles Bibliográficos
Autores principales: Yamamoto, Norio, Sukegawa, Shintaro, Yamashita, Kazutaka, Manabe, Masaki, Nakano, Keisuke, Takabatake, Kiyofumi, Kawai, Hotaka, Ozaki, Toshifumi, Kawasaki, Keisuke, Nagatsuka, Hitoshi, Furuki, Yoshihiko, Yorifuji, Takashi
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8398956/
https://www.ncbi.nlm.nih.gov/pubmed/34441052
http://dx.doi.org/10.3390/medicina57080846
_version_ 1783744961981710336
author Yamamoto, Norio
Sukegawa, Shintaro
Yamashita, Kazutaka
Manabe, Masaki
Nakano, Keisuke
Takabatake, Kiyofumi
Kawai, Hotaka
Ozaki, Toshifumi
Kawasaki, Keisuke
Nagatsuka, Hitoshi
Furuki, Yoshihiko
Yorifuji, Takashi
author_facet Yamamoto, Norio
Sukegawa, Shintaro
Yamashita, Kazutaka
Manabe, Masaki
Nakano, Keisuke
Takabatake, Kiyofumi
Kawai, Hotaka
Ozaki, Toshifumi
Kawasaki, Keisuke
Nagatsuka, Hitoshi
Furuki, Yoshihiko
Yorifuji, Takashi
author_sort Yamamoto, Norio
collection PubMed
description Background and Objectives: A few deep learning studies have reported that combining image features with patient variables enhanced identification accuracy compared with image-only models. However, previous studies have not statistically reported the additional effect of patient variables on the image-only models. This study aimed to statistically evaluate the osteoporosis identification ability of deep learning by combining hip radiographs with patient variables. Materials andMethods: We collected a dataset containing 1699 images from patients who underwent skeletal-bone-mineral density measurements and hip radiography at a general hospital from 2014 to 2021. Osteoporosis was assessed from hip radiographs using convolutional neural network (CNN) models (ResNet18, 34, 50, 101, and 152). We also investigated ensemble models with patient clinical variables added to each CNN. Accuracy, precision, recall, specificity, F1 score, and area under the curve (AUC) were calculated as performance metrics. Furthermore, we statistically compared the accuracy of the image-only model with that of an ensemble model that included images plus patient factors, including effect size for each performance metric. Results: All metrics were improved in the ResNet34 ensemble model compared with the image-only model. The AUC score in the ensemble model was significantly improved compared with the image-only model (difference 0.004; 95% CI 0.002–0.0007; p = 0.0004, effect size: 0.871). Conclusions: This study revealed the additional effect of patient variables in identification of osteoporosis using deep CNNs with hip radiographs. Our results provided evidence that the patient variables had additive synergistic effects on the image in osteoporosis identification.
format Online
Article
Text
id pubmed-8398956
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-83989562021-08-29 Effect of Patient Clinical Variables in Osteoporosis Classification Using Hip X-rays in Deep Learning Analysis Yamamoto, Norio Sukegawa, Shintaro Yamashita, Kazutaka Manabe, Masaki Nakano, Keisuke Takabatake, Kiyofumi Kawai, Hotaka Ozaki, Toshifumi Kawasaki, Keisuke Nagatsuka, Hitoshi Furuki, Yoshihiko Yorifuji, Takashi Medicina (Kaunas) Article Background and Objectives: A few deep learning studies have reported that combining image features with patient variables enhanced identification accuracy compared with image-only models. However, previous studies have not statistically reported the additional effect of patient variables on the image-only models. This study aimed to statistically evaluate the osteoporosis identification ability of deep learning by combining hip radiographs with patient variables. Materials andMethods: We collected a dataset containing 1699 images from patients who underwent skeletal-bone-mineral density measurements and hip radiography at a general hospital from 2014 to 2021. Osteoporosis was assessed from hip radiographs using convolutional neural network (CNN) models (ResNet18, 34, 50, 101, and 152). We also investigated ensemble models with patient clinical variables added to each CNN. Accuracy, precision, recall, specificity, F1 score, and area under the curve (AUC) were calculated as performance metrics. Furthermore, we statistically compared the accuracy of the image-only model with that of an ensemble model that included images plus patient factors, including effect size for each performance metric. Results: All metrics were improved in the ResNet34 ensemble model compared with the image-only model. The AUC score in the ensemble model was significantly improved compared with the image-only model (difference 0.004; 95% CI 0.002–0.0007; p = 0.0004, effect size: 0.871). Conclusions: This study revealed the additional effect of patient variables in identification of osteoporosis using deep CNNs with hip radiographs. Our results provided evidence that the patient variables had additive synergistic effects on the image in osteoporosis identification. MDPI 2021-08-20 /pmc/articles/PMC8398956/ /pubmed/34441052 http://dx.doi.org/10.3390/medicina57080846 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/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/).
spellingShingle Article
Yamamoto, Norio
Sukegawa, Shintaro
Yamashita, Kazutaka
Manabe, Masaki
Nakano, Keisuke
Takabatake, Kiyofumi
Kawai, Hotaka
Ozaki, Toshifumi
Kawasaki, Keisuke
Nagatsuka, Hitoshi
Furuki, Yoshihiko
Yorifuji, Takashi
Effect of Patient Clinical Variables in Osteoporosis Classification Using Hip X-rays in Deep Learning Analysis
title Effect of Patient Clinical Variables in Osteoporosis Classification Using Hip X-rays in Deep Learning Analysis
title_full Effect of Patient Clinical Variables in Osteoporosis Classification Using Hip X-rays in Deep Learning Analysis
title_fullStr Effect of Patient Clinical Variables in Osteoporosis Classification Using Hip X-rays in Deep Learning Analysis
title_full_unstemmed Effect of Patient Clinical Variables in Osteoporosis Classification Using Hip X-rays in Deep Learning Analysis
title_short Effect of Patient Clinical Variables in Osteoporosis Classification Using Hip X-rays in Deep Learning Analysis
title_sort effect of patient clinical variables in osteoporosis classification using hip x-rays in deep learning analysis
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8398956/
https://www.ncbi.nlm.nih.gov/pubmed/34441052
http://dx.doi.org/10.3390/medicina57080846
work_keys_str_mv AT yamamotonorio effectofpatientclinicalvariablesinosteoporosisclassificationusinghipxraysindeeplearninganalysis
AT sukegawashintaro effectofpatientclinicalvariablesinosteoporosisclassificationusinghipxraysindeeplearninganalysis
AT yamashitakazutaka effectofpatientclinicalvariablesinosteoporosisclassificationusinghipxraysindeeplearninganalysis
AT manabemasaki effectofpatientclinicalvariablesinosteoporosisclassificationusinghipxraysindeeplearninganalysis
AT nakanokeisuke effectofpatientclinicalvariablesinosteoporosisclassificationusinghipxraysindeeplearninganalysis
AT takabatakekiyofumi effectofpatientclinicalvariablesinosteoporosisclassificationusinghipxraysindeeplearninganalysis
AT kawaihotaka effectofpatientclinicalvariablesinosteoporosisclassificationusinghipxraysindeeplearninganalysis
AT ozakitoshifumi effectofpatientclinicalvariablesinosteoporosisclassificationusinghipxraysindeeplearninganalysis
AT kawasakikeisuke effectofpatientclinicalvariablesinosteoporosisclassificationusinghipxraysindeeplearninganalysis
AT nagatsukahitoshi effectofpatientclinicalvariablesinosteoporosisclassificationusinghipxraysindeeplearninganalysis
AT furukiyoshihiko effectofpatientclinicalvariablesinosteoporosisclassificationusinghipxraysindeeplearninganalysis
AT yorifujitakashi effectofpatientclinicalvariablesinosteoporosisclassificationusinghipxraysindeeplearninganalysis