scholarly journals Development and validation of a deep learning algorithm based on fundus photographs for estimating the CAIDE dementia risk score

2021 ◽  
Author(s):  
Rong Hua ◽  
Jianhao Xiong ◽  
Gail Li ◽  
Yidan Zhu ◽  
Zongyuan Ge ◽  
...  
Keyword(s):  
Deep Learning ◽  
Risk Score ◽  
Learning Algorithm ◽  
External Validation ◽  
Population Based ◽  
Validation Dataset ◽  
Internal Validation ◽  
Deep Learning Algorithm ◽  
Dementia Risk ◽  
Fundus Photographs

AbstractImportanceThe Cardiovascular Risk Factors, Aging, and Incidence of Dementia (CAIDE) dementia risk score is a recognized tool for dementia risk stratification. However, its application is limited due to the requirements for multidimensional information and fasting blood draw. Consequently, effective, convenient and noninvasive tool for screening individuals with high dementia risk in large population-based settings is urgently needed.ObjectiveTo develop and validate a deep learning algorithm using retinal fundus photographs for estimating the CAIDE dementia risk score and identifying individuals with high dementia risk.DesignA deep learning algorithm trained via fundus photographs was developed, validated internally and externally with cross-sectional design.SettingPopulation-based.ParticipantsA health check-up population with 271,864 adults were randomized into a development dataset (95%) and an internal validation dataset (5%). The external validation used data from the Beijing Research on Ageing and Vessel (BRAVE) with 1,512 individuals.ExposuresThe estimated CAIDE dementia risk score generated from the algorithm.Main Outcome and MeasureThe algorithm’s performance for identifying individuals with high dementia risk was evaluated by area under the receiver operating curve (AUC) with 95% confidence interval (CI).ResultsThe study involved 258,305 participants (mean aged 42.1 ± 13.4 years, men: 52.7%) in development, 13,559 (mean aged 41.2 ± 13.3 years, men: 52.5%) in internal validation, and 1,512 (mean aged 59.8 ± 7.3 years, men: 37.1%) in external validation. The adjusted coefficient of determination (R2) between the estimated and actual CAIDE dementia risk score was 0.822 in the internal and 0.300 in the external validations, respectively. The algorithm achieved an AUC of 0.931 (95%CI, 0.922–0.939) in the internal validation group and 0.782 (95%CI, 0.749–0.815) in the external group. Besides, the estimated CAIDE dementia risk score was significantly associated with both comprehensive cognitive function and specific cognitive domains.Conclusions and RelevanceThe present study demonstrated that the deep learning algorithm trained via fundus photographs could well identify individuals with high dementia risk in a population-based setting. Our findings suggest that fundus photography may be utilized as a noninvasive and more expedient method for dementia risk stratification.Key PointsQuestionCan a deep learning algorithm based on fundus images estimate the CAIDE dementia risk score and identify individuals with high dementia risk?FindingsThe algorithm developed by fundus photographs from 258,305 check-up participants could well identify individuals with high dementia risk, with area under the receiver operating characteristic curve of 0.931 in internal validation and 0.782 in external validation dataset, respectively. Besides, the estimated CAIDE dementia risk score generated from the algorithm exhibited significant association with cognitive function.MeaningThe deep learning algorithm based on fundus photographs has potential to screen individuals with high dementia risk in population-based settings.

scholarly journals Predicting Sex from Retinal Fundus Photographs Using Automated Deep Learning

2021 ◽  
Author(s):  
Edward Korot ◽  
Nikolas Pontikos ◽  
Xiaoxuan Liu ◽  
Siegfried K Wagner ◽  
Livia Faes ◽  
...  
Keyword(s):  
Deep Learning ◽  
Characteristic Curve ◽  
External Validation ◽  
Model Development ◽  
Model Performance ◽  
Validation Dataset ◽  
Internal Validation ◽  
Fundus Photographs ◽  
The Uk ◽  
Retinal Fundus

Abstract Deep learning may transform health care, but model development has largely been dependent on availability of advanced technical expertise. Herein we present the development of a deep learning model by clinicians without coding, which predicts reported sex from retinal fundus photographs. A model was trained on 84,743 retinal fundus photos from the UK Biobank dataset. External validation was performed on 252 fundus photos from a tertiary ophthalmic referral center. For internal validation, the area under the receiver operating characteristic curve (AUROC) of the code free deep learning (CFDL) model was 0.93. Sensitivity, specificity, positive predictive value (PPV) and accuracy (ACC) were 88.8%, 83.6%, 87.3% and 86.5%, and for external validation were 83.9%, 72.2%, 78.2% and 78.6% respectively. Clinicians are currently unaware of distinct retinal feature variations between males and females, highlighting the importance of model explainability for this task. The model performed significantly worse when foveal pathology was present in the external validation dataset, ACC: 69.4%, compared to 85.4% in healthy eyes, suggesting the fovea is a salient region for model performance OR (95% CI): 0.36 (0.19, 0.70) p = 0.0022. Automated machine learning (AutoML) may enable clinician-driven automated discovery of novel insights and disease biomarkers.

scholarly journals Development and validation of a deep learning algorithm using fundus photographs to predict 10-year risk of ischemic cardiovascular diseases among Chinese population

2021 ◽  
Author(s):  
Yanjun Ma ◽  
Jianhao Xiong ◽  
Yidan Zhu ◽  
Zongyuan Ge ◽  
Rong Hua ◽  
...  
Keyword(s):  
Deep Learning ◽  
Cardiovascular Diseases ◽  
Risk Prediction ◽  
Chinese Population ◽  
Goodness Of Fit ◽  
Medical Information ◽  
Learning Algorithm ◽  
External Validation ◽  
Deep Learning Algorithm ◽  
Fundus Photographs

Background Ischemic cardiovascular diseases (ICVD) risk predict models are valuable but limited by its requirement for multidimensional medical information including that from blood drawing. A convenient and affordable alternative is in demand. Objectives To develop and validate a deep learning algorithm to predict 10-year ICVD risk using retinal fundus photographs in Chinese population. Methods We firstly labeled fundus photographs with natural logarithms of ICVD risk estimated by a previously validated 10-year Chinese ICVD risk prediction model for 390,947 adults randomly selected (95%) from a health checkup dataset. An algorithm using convolutional neural network was then developed to predict the estimated 10-year ICVD risk by fundus images. The algorithm was validated using both internal dataset (the other 5%) and external dataset from an independent source (sample size = 1,309). Adjusted R2 and area under the receiver operating characteristic curve (AUC) were used to evaluate the goodness of fit. Results The adjusted R2 between natural logarithms of the predicted and calculated ICVD risks was 0.876 and 0.638 in the internal and external validations, respectively. For detecting ICVD risk ≥ 5% and ≥ 7.5%, the algorithm achieved an AUC of 0.971 (95% CI: 0.967 to 0.975) and 0.976 (95% CI: 0.973 to 0.980) in internal validation, and 0.859 (95% CI: 0.822 to 0.895) and 0.876 (95% CI: 0.816 to 0.837) in external validation. Conclusions The deep learning algorithm developed in the study using fundus photographs to predict 10-year ICVD risk in Chinese population had fairly good capability in predicting the risk and may have values to be widely promoted considering its advances in easy use and lower cost. Further studies with long term follow up are warranted. Keywords Deep learning, Ischemic cardiovascular diseases, risk prediction.

scholarly journals Predicting sex from retinal fundus photographs using automated deep learning

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Edward Korot ◽  
Nikolas Pontikos ◽  
Xiaoxuan Liu ◽  
Siegfried K. Wagner ◽  
Livia Faes ◽  
...  
Keyword(s):  
Deep Learning ◽  
Characteristic Curve ◽  
External Validation ◽  
Model Development ◽  
Model Performance ◽  
Validation Dataset ◽  
Internal Validation ◽  
Fundus Photographs ◽  
The Uk ◽  
Retinal Fundus

AbstractDeep learning may transform health care, but model development has largely been dependent on availability of advanced technical expertise. Herein we present the development of a deep learning model by clinicians without coding, which predicts reported sex from retinal fundus photographs. A model was trained on 84,743 retinal fundus photos from the UK Biobank dataset. External validation was performed on 252 fundus photos from a tertiary ophthalmic referral center. For internal validation, the area under the receiver operating characteristic curve (AUROC) of the code free deep learning (CFDL) model was 0.93. Sensitivity, specificity, positive predictive value (PPV) and accuracy (ACC) were 88.8%, 83.6%, 87.3% and 86.5%, and for external validation were 83.9%, 72.2%, 78.2% and 78.6% respectively. Clinicians are currently unaware of distinct retinal feature variations between males and females, highlighting the importance of model explainability for this task. The model performed significantly worse when foveal pathology was present in the external validation dataset, ACC: 69.4%, compared to 85.4% in healthy eyes, suggesting the fovea is a salient region for model performance OR (95% CI): 0.36 (0.19, 0.70) p = 0.0022. Automated machine learning (AutoML) may enable clinician-driven automated discovery of novel insights and disease biomarkers.

scholarly journals Development and Verification of a Deep Learning Algorithm to Evaluate Small-Bowel Preparation Quality

Diagnostics ◽  
2021 ◽  
Vol 11 (6) ◽  
pp. 1127
Author(s):  
Ji Hyung Nam ◽  
Dong Jun Oh ◽  
Sumin Lee ◽  
Hyun Joo Song ◽  
Yun Jeong Lim
Keyword(s):  
Deep Learning ◽  
Small Bowel ◽  
Scoring System ◽  
Operating Characteristic ◽  
Clinical Evidence ◽  
Learning Algorithm ◽  
Characteristic Curve ◽  
External Validation ◽  
Test Results ◽  
Deep Learning Algorithm

Capsule endoscopy (CE) quality control requires an objective scoring system to evaluate the preparation of the small bowel (SB). We propose a deep learning algorithm to calculate SB cleansing scores and verify the algorithm’s performance. A 5-point scoring system based on clarity of mucosal visualization was used to develop the deep learning algorithm (400,000 frames; 280,000 for training and 120,000 for testing). External validation was performed using additional CE cases (n = 50), and average cleansing scores (1.0 to 5.0) calculated using the algorithm were compared to clinical grades (A to C) assigned by clinicians. Test results obtained using 120,000 frames exhibited 93% accuracy. The separate CE case exhibited substantial agreement between the deep learning algorithm scores and clinicians’ assessments (Cohen’s kappa: 0.672). In the external validation, the cleansing score decreased with worsening clinical grade (scores of 3.9, 3.2, and 2.5 for grades A, B, and C, respectively, p < 0.001). Receiver operating characteristic curve analysis revealed that a cleansing score cut-off of 2.95 indicated clinically adequate preparation. This algorithm provides an objective and automated cleansing score for evaluating SB preparation for CE. The results of this study will serve as clinical evidence supporting the practical use of deep learning algorithms for evaluating SB preparation quality.

scholarly journals Essentials of a Robust Deep Learning System for Diabetic Retinopathy Screening: A Systematic Literature Review

2020 ◽  
Vol 2020 ◽  
pp. 1-11
Author(s):  
Aan Chu ◽  
David Squirrell ◽  
Andelka M. Phillips ◽  
Ehsan Vaghefi
Keyword(s):  
Diabetic Retinopathy ◽  
Deep Learning ◽  
Learning Algorithm ◽  
Learning Algorithms ◽  
Validation Dataset ◽  
Cochrane Library ◽  
Clinical Implementation ◽  
Diabetic Retinopathy Screening ◽  
Deep Learning Algorithm ◽  
Retinopathy Screening

This systematic review was performed to identify the specifics of an optimal diabetic retinopathy deep learning algorithm, by identifying the best exemplar research studies of the field, whilst highlighting potential barriers to clinical implementation of such an algorithm. Searching five electronic databases (Embase, MEDLINE, Scopus, PubMed, and the Cochrane Library) returned 747 unique records on 20 December 2019. Predetermined inclusion and exclusion criteria were applied to the search results, resulting in 15 highest-quality publications. A manual search through the reference lists of relevant review articles found from the database search was conducted, yielding no additional records. A validation dataset of the trained deep learning algorithms was used for creating a set of optimal properties for an ideal diabetic retinopathy classification algorithm. Potential limitations to the clinical implementation of such systems were identified as lack of generalizability, limited screening scope, and data sovereignty issues. It is concluded that deep learning algorithms in the context of diabetic retinopathy screening have reported impressive results. Despite this, the potential sources of limitations in such systems must be evaluated carefully. An ideal deep learning algorithm should be clinic-, clinician-, and camera-agnostic; complying with the local regulation for data sovereignty, storage, privacy, and reporting; whilst requiring minimum human input.

scholarly journals Deep Learning Model for Screening Sepsis Using Electrocardiography

2021 ◽  
Author(s):  
Joon-myoung Kwon ◽  
Ye Rang Lee ◽  
Min-Seung Jung ◽  
Yoon-Ji Lee ◽  
Yong-Yeon Jo ◽  
...  
Keyword(s):  
Septic Shock ◽  
Deep Learning ◽  
Characteristic Curve ◽  
External Validation ◽  
Medical Emergency ◽  
Validation Dataset ◽  
Internal Validation ◽  
Significant Difference ◽  
Life Threatening ◽  
Sepsis And Septic Shock

Abstract Background: Sepsis is a life-threatening organ dysfunction and is a major healthcare burden worldwide. Although sepsis is a medical emergency that requires immediate management, it is difficult to screen the occurrence of sepsis. In this study, we propose an artificial intelligence based on deep learning-based model (DLM) for screening sepsis using electrocardiography (ECG).Methods: This retrospective cohort study included 46,017 patients who admitted to two hospitals. 1,548 and 639 patients underwent sepsis and septic shock. The DLM was developed using 73,727 ECGs of 18,142 patients and internal validation was conducted using 7,774 ECGs of 7,774 patients. Furthermore, we conducted an external validation with 20,101 ECGs of 20,101 patients from another hospital to verify the applicability of the DLM across centers.Results: During the internal and external validation, the area under the receiver operating characteristic curve (AUC) of an DLM using 12-lead ECG for screening sepsis were 0.901 (95% confidence interval 0.882–0.920) and 0.863 (0.846–0.879), respectively. During internal and external validation, AUC of an DLM for detecting septic shock were 0.906 (95% CI = 0.877–0.936) and 0.899 (95% CI = 0.872–0.925), respectively. The AUC of the DLM for detecting sepsis using 6-lead and single-lead ECGs were 0.845–0.882. A sensitivity map showed that the QRS complex and T wave was associated with sepsis. Subgroup analysis was conducted using ECGs from 4,609 patients who admitted with infectious disease, The AUC of the DLM for predicting in-hospital mortality was 0.817 (0.793–0.840). There was a significant difference in the prediction score of DLM using ECG according to the presence of infection in the validation dataset (0.277 vs 0.574, p<0.001), including severe acute respiratory syndrome coronavirus 2 (0.260 vs 0.725, p=0.018).Conclusions: The DLM demonstrated reasonable performance for screening sepsis using 12-, 6-, and single-lead ECG. The results suggest that sepsis can be screened using not only conventional ECG devices, but also diverse life-type ECG machine employing the DLM, thereby preventing irreversible disease progression and mortality.

scholarly journals Deep Learning for Identification of Acute Illness and Facial Cues of Illness

2021 ◽  
Vol 8 ◽  
Author(s):  
Castela Forte ◽  
Andrei Voinea ◽  
Malina Chichirau ◽  
Galiya Yeshmagambetova ◽  
Lea M. Albrecht ◽  
...  
Keyword(s):  
Deep Learning ◽  
Data Augmentation ◽  
Learning Algorithm ◽  
External Validation ◽  
Facial Feature ◽  
Acute Illness ◽  
Facial Features ◽  
Genetic Syndromes ◽  
Coronary Syndrome ◽  
Deep Learning Algorithm

Background: The inclusion of facial and bodily cues (clinical gestalt) in machine learning (ML) models improves the assessment of patients' health status, as shown in genetic syndromes and acute coronary syndrome. It is unknown if the inclusion of clinical gestalt improves ML-based classification of acutely ill patients. As in previous research in ML analysis of medical images, simulated or augmented data may be used to assess the usability of clinical gestalt.Objective: To assess whether a deep learning algorithm trained on a dataset of simulated and augmented facial photographs reflecting acutely ill patients can distinguish between healthy and LPS-infused, acutely ill individuals.Methods: Photographs from twenty-six volunteers whose facial features were manipulated to resemble a state of acute illness were used to extract features of illness and generate a synthetic dataset of acutely ill photographs, using a neural transfer convolutional neural network (NT-CNN) for data augmentation. Then, four distinct CNNs were trained on different parts of the facial photographs and concatenated into one final, stacked CNN which classified individuals as healthy or acutely ill. Finally, the stacked CNN was validated in an external dataset of volunteers injected with lipopolysaccharide (LPS).Results: In the external validation set, the four individual feature models distinguished acutely ill patients with sensitivities ranging from 10.5% (95% CI, 1.3–33.1% for the skin model) to 89.4% (66.9–98.7%, for the nose model). Specificity ranged from 42.1% (20.3–66.5%) for the nose model and 94.7% (73.9–99.9%) for skin. The stacked model combining all four facial features achieved an area under the receiver characteristic operating curve (AUROC) of 0.67 (0.62–0.71) and distinguished acutely ill patients with a sensitivity of 100% (82.35–100.00%) and specificity of 42.11% (20.25–66.50%).Conclusion: A deep learning algorithm trained on a synthetic, augmented dataset of facial photographs distinguished between healthy and simulated acutely ill individuals, demonstrating that synthetically generated data can be used to develop algorithms for health conditions in which large datasets are difficult to obtain. These results support the potential of facial feature analysis algorithms to support the diagnosis of acute illness.

Deep learning-assisted (automatic) diagnosis of glaucoma using a smartphone

2021 ◽  
pp. bjophthalmol-2020-318107
Author(s):  
Kenichi Nakahara ◽  
Ryo Asaoka ◽  
Masaki Tanito ◽  
Naoto Shibata ◽  
Keita Mitsuhashi ◽  
...  
Keyword(s):  
Deep Learning ◽  
Learning Algorithm ◽  
Fundus Photography ◽  
Training Dataset ◽  
Mean Deviation ◽  
Fundus Camera ◽  
Deep Learning Algorithm ◽  
Testing Dataset ◽  
Advanced Glaucoma ◽  
Fundus Photographs

Background/aimsTo validate a deep learning algorithm to diagnose glaucoma from fundus photography obtained with a smartphone.MethodsA training dataset consisting of 1364 colour fundus photographs with glaucomatous indications and 1768 colour fundus photographs without glaucomatous features was obtained using an ordinary fundus camera. The testing dataset consisted of 73 eyes of 73 patients with glaucoma and 89 eyes of 89 normative subjects. In the testing dataset, fundus photographs were acquired using an ordinary fundus camera and a smartphone. A deep learning algorithm was developed to diagnose glaucoma using a training dataset. The trained neural network was evaluated by prediction result of the diagnostic of glaucoma or normal over the test datasets, using images from both an ordinary fundus camera and a smartphone. Diagnostic accuracy was assessed using the area under the receiver operating characteristic curve (AROC).ResultsThe AROC with a fundus camera was 98.9% and 84.2% with a smartphone. When validated only in eyes with advanced glaucoma (mean deviation value < −12 dB, N=26), the AROC with a fundus camera was 99.3% and 90.0% with a smartphone. There were significant differences between these AROC values using different cameras.ConclusionThe usefulness of a deep learning algorithm to automatically screen for glaucoma from smartphone-based fundus photographs was validated. The algorithm had a considerable high diagnostic ability, particularly in eyes with advanced glaucoma.

Sign in / Sign up

Export Citation Format

Share Document