scholarly journals A deep-learning-based prediction of refractive error using photorefraction images captured by smartphone: Model Development and Validation Study. (Preprint)

2019 ◽  
Author(s):  
Jaehyeong Chun ◽  
Youngjun Kim ◽  
Kyungyoon Shin ◽  
Sun Hyup Han ◽  
Sei Yeul Oh ◽  
...  
Keyword(s):  
Deep Learning ◽  
Refractive Error ◽  
Model Development ◽  
Screening Tools ◽  
Prediction Algorithm ◽  
Easy Access ◽  
Number Of Patients ◽  
Prediction Systems ◽  
Development And Validation ◽  
Efficient Screening

BACKGROUND Accurately predicting refractive error in children is crucial for detecting amblyopia, which can lead to permanent visual impairment, but is potentially curable if detected early. Various tools have been adopted to more easily screen a larger number of patients for amblyopia risk. OBJECTIVE For efficient screening, easy access to screening tools and an accurate prediction algorithm are the most important factors. In this study, we developed an automated deep-learning-based system to predict the range of refractive error in children (mean age: 4.32±1.87 years) using 305 eccentric photorefraction images captured with a smartphone. METHODS Photorefraction images were divided into seven classes according to their spherical values as measured by cycloplegic refraction. RESULTS The trained deep-learning models resulted in an overall accuracy of 81.6%, with the following accuracy for each refractive error class: 80.0% in ≤ -5.0 diopters (D), 77.8% in > -5.0 D and ≤ -3.0 D, 82.0% in > -3.0 D and ≤ -0.5 D, 83.3% in > -0.5 D and < +0.5 D, 82.8% in ≥ +0.5 D and < +3.0 D, 79.3% in ≥ +3.0 D and < +5.0 D, and 75.0% in ≥ +5.0 D. These results indicate that our deep-learning-based system performed sufficiently accurately. CONCLUSIONS This study demonstrated the potential for precise smartphone-based prediction systems for refractive error using deep learning and, further, yielded a robust collection of pediatric photorefraction images. CLINICALTRIAL

scholarly journals Deep Learning Approaches to Detect Atrial Fibrillation Using Photoplethysmographic Signals: Algorithms Development Study (Preprint)

2018 ◽  
Author(s):  
Soonil Kwon ◽  
Joonki Hong ◽  
Eue-Keun Choi ◽  
Euijae Lee ◽  
David Earl Hostallero ◽  
...  
Keyword(s):  
Neural Network ◽  
Atrial Fibrillation ◽  
Deep Learning ◽  
Diagnostic Accuracy ◽  
Diagnostic Performance ◽  
Wearable Devices ◽  
Screening Tools ◽  
Support Vector ◽  
Direct Current Cardioversion ◽  
Number Of Patients

BACKGROUND Wearable devices have evolved as screening tools for atrial fibrillation (AF). A photoplethysmographic (PPG) AF detection algorithm was developed and applied to a convenient smartphone-based device with good accuracy. However, patients with paroxysmal AF frequently exhibit premature atrial complexes (PACs), which result in poor unmanned AF detection, mainly because of rule-based or handcrafted machine learning techniques that are limited in terms of diagnostic accuracy and reliability. OBJECTIVE This study aimed to develop deep learning (DL) classifiers using PPG data to detect AF from the sinus rhythm (SR) in the presence of PACs after successful cardioversion. METHODS We examined 75 patients with AF who underwent successful elective direct-current cardioversion (DCC). Electrocardiogram and pulse oximetry data over a 15-min period were obtained before and after DCC and labeled as AF or SR. A 1-dimensional convolutional neural network (1D-CNN) and recurrent neural network (RNN) were chosen as the 2 DL architectures. The PAC indicator estimated the burden of PACs on the PPG dataset. We defined a metric called the confidence level (CL) of AF or SR diagnosis and compared the CLs of true and false diagnoses. We also compared the diagnostic performance of 1D-CNN and RNN with previously developed AF detectors (support vector machine with root-mean-square of successive difference of RR intervals and Shannon entropy, autocorrelation, and ensemble by combining 2 previous methods) using 10 5-fold cross-validation processes. RESULTS Among the 14,298 training samples containing PPG data, 7157 samples were obtained during the post-DCC period. The PAC indicator estimated 29.79% (2132/7157) of post-DCC samples had PACs. The diagnostic accuracy of AF versus SR was 99.32% (70,925/71,410) versus 95.85% (68,602/71,570) in 1D-CNN and 98.27% (70,176/71,410) versus 96.04% (68,736/71,570) in RNN methods. The area under receiver operating characteristic curves of the 2 DL classifiers was 0.998 (95% CI 0.995-1.000) for 1D-CNN and 0.996 (95% CI 0.993-0.998) for RNN, which were significantly higher than other AF detectors (P<.001). If we assumed that the dataset could emulate a sufficient number of patients in training, both DL classifiers improved their diagnostic performances even further especially for the samples with a high burden of PACs. The average CLs for true versus false classification were 98.56% versus 78.75% for 1D-CNN and 98.37% versus 82.57% for RNN (P<.001 for all cases). CONCLUSIONS New DL classifiers could detect AF using PPG monitoring signals with high diagnostic accuracy even with frequent PACs and could outperform previously developed AF detectors. Although diagnostic performance decreased as the burden of PACs increased, performance improved when samples from more patients were trained. Moreover, the reliability of the diagnosis could be indicated by the CL. Wearable devices sensing PPG signals with DL classifiers should be validated as tools to screen for AF.

Sign in / Sign up

Export Citation Format

Share Document