Expert-Level Distinction of Systemic Sclerosis from Hand Photographs Using Deep Convolutional Neural Networks

Norimatsu, Yuta; Yoshizaki, Ayumi; Kabeya, Yoshinori; Fukasawa, Takemichi; Omatsu, Jun; Fukayama, Masahisa; Kuzumi, Ai; Ebata, Satoshi; Yoshizaki‐Ogawa, Asako; Asano, Yoshihide; Ichimura, Haruka; Yonezawa, S.; Nakano, H.; Sato, Shinichi

doi:10.1016/j.jid.2021.03.020

Cited by 8 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning has been widely used in recent medical research, such as automatic diagnosis from clinical images 1 – 4 , recognition of human genes 5 , and cognitive neuroscience 6 , 7 . This technique also aids in electrocardiogram (ECG) pattern recognition, such as predicting demographic features 8 and automatically identifying cardiovascular comorbidity 9 – 11 .…”

Section: Introductionmentioning

confidence: 99%

Predicting extremely low body weight from 12-lead electrocardiograms using a deep neural network

Kurisu,

Yamazaki,

Yoshiuchi

2024

Sci Rep

View full text Add to dashboard Cite

Previous studies have successfully predicted overweight status by applying deep learning to 12-lead electrocardiogram (ECG); however, models for predicting underweight status remain unexplored. Here, we assessed the feasibility of deep learning in predicting extremely low body weight using 12-lead ECGs, thereby investigating the prediction rationale for highlighting the parts of ECGs that are associated with extremely low body weight. Using records of inpatients predominantly with anorexia nervosa, we trained a convolutional neural network (CNN) that inputs a 12-lead ECG and outputs a binary prediction of whether body mass index is ≤ 12.6 kg/m2. This threshold was identified in a previous study as the optimal cutoff point for predicting the onset of refeeding syndrome. The CNN model achieved an area under the receiver operating characteristic curve of 0.807 (95% confidence interval, 0.745–0.869) on the test dataset. The gradient-weighted class activation map showed that the model focused on QRS waves. A negative correlation with the prediction scores was observed for QRS voltage. These results suggest that deep learning is feasible for predicting extremely low body weight using 12-lead ECGs, and several ECG features, such as lower QRS voltage, may be associated with extremely low body weight in patients with anorexia nervosa.

show abstract

Section: Introductionmentioning

confidence: 99%

Predicting extremely low body weight from 12-lead electrocardiograms using a deep neural network

Kurisu,

Yamazaki,

Yoshiuchi

2024

Sci Rep

View full text Add to dashboard Cite

show abstract

“…The secondary form of RP is associated with an underlying disease, usually autoimmune diseases and connective tissue disorders. Within these disorders, PR is a characteristic early-onset cutaneous manifestation that occurs in patients with systemic scleroderma [ 7 ] and appears in up to 90 % of these patients, between 10 and 45 % with systemic lupus erythematosus, in 33 % with Sjögren’s syndrome, and in 20 % with dermatomyositis/polymyositis [ 8 ].…”

Section: Introductionmentioning

confidence: 99%

Analysis of Hand Function, Upper Limb Disability, and Its Relationship with Peripheral Vascular Alterations in Raynaud’s Phenomenon

Tapia-Haro,

García-Ríos,

Castro-Sánchez

et al. 2023

Diagnostics

View full text Add to dashboard Cite

This study aimed to compare vascular involvement, hand functionality, and upper limb disability between Raynaud’s phenomenon participants and controls. Also, we analyzed the relationships between vascular impairment, mobility, and strength with disability in this Raynaud population. We conducted a case–control study with fifty-seven participants. We registered sociodemographic and clinical data; vascular variables (temperature, cold test, blood flow, and oxygen saturation); functional variables (pinch strength, range of motion), and disability (Shortened Disabilities of the Arm, Shoulder and Hand Questionnaire) (Q-DASH). Raynaud participants present more disability in all Q-DASH subscales, lower hands’ temperature pre and post cold test, decreased blood flow on radial artery, decreased ranges of motions at passive extension of index finger, and active flexion and extension of thumb than the healthy controls. The multivariate regression analysis showed that extension of the index finger, lateral pinch strength, and oxygen saturation were significantly associated with disability in RP, almost the 55% of the total variance on the upper limb, 27% at sports/arts, and 42% at work. Our findings suggest that RP has a disabling effect on the upper extremities and a practice of activities in people who suffer it. Also, disability in Raynaud seems to be more related with hand mobility and strength impairment than vascular injury.

show abstract

“…1 Although SSc has a variety of specific skin symptoms, including skin sclerosis and Raynaud's symptoms, it is sometimes difficult to reach a correct diagnosis because other diseases can also cause similar symptoms. 2 The VEDOSS (very early diagnosis of SSc) criteria were recently proposed to detect SSc at the early stage. Capillaroscopy to observe the capillary abnormalities characteristic of SSc is available only in a limited number of facilities, so SSc's capillaroscopic pattern is considered one of the most difficult items to evaluate in the VEDOSS criteria.…”

mentioning

confidence: 99%

Case report: Very early systemic sclerosis with anti‐Sjögren's syndrome/scleroderma autoantigen 1 antibody accompanied by gastric antral vascular ectasia

Norimatsu,

Akatsuka,

Ito

et al. 2024

Int J of Rheum Dis

Self Cite

View full text Add to dashboard Cite

Expert-Level Distinction of Systemic Sclerosis from Hand Photographs Using Deep Convolutional Neural Networks

Cited by 8 publications

References 12 publications

Predicting extremely low body weight from 12-lead electrocardiograms using a deep neural network

Predicting extremely low body weight from 12-lead electrocardiograms using a deep neural network

Analysis of Hand Function, Upper Limb Disability, and Its Relationship with Peripheral Vascular Alterations in Raynaud’s Phenomenon

Case report: Very early systemic sclerosis with anti‐Sjögren's syndrome/scleroderma autoantigen 1 antibody accompanied by gastric antral vascular ectasia

Contact Info

Product

Resources

About