Yamamoto Norio
,
Sukegawa Shintaro
,
Kitamura Akira
,
Goto Ryosuke
,
Noda Tomoyuki
,
Nakano Keisuke
,
Takabatake Kiyofumi
,
Kawai Hotaka
,
Nagatsuka Hitoshi
,
Kawasaki Keisuke
,
Furuki Yoshihiko
,
Ozaki Toshifumi
… This study considers the use of deep learning to diagnose osteoporosis from hip radiographs, and whether adding clinical data improves diagnostic performance over the image mode alone. … We also investigated ensemble models with clinical covariates added to each CNN. … Among the five ensemble models, EfficientNet b3 exhibited the best accuracy, recall, npv, F1 score, and AUC score when patient variables were included. …
IR