IGRNet: A Deep Learning Model for Non-Invasive, Real-Time Diagnosis of Prediabetes through Electrocardiograms

Wang, Liyang; Mu, Yao; Zhao, Jing; Wang, Xiaoya; Che, Huilian

doi:10.3390/s20092556

Cited by 31 publications

(26 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Through the larger database and augmentation from GLU, our DLM achieved an AUC of 0.8255. Moreover, both previous [ 45 ] and our own studies show that ECG based DM detection is more accurate for people with normal ranges of weight. The MAE of our noninvasive system (1.238) even approximately reached the 13 commercially available point-of-care HbA1c test devices ranging from −0.9 to 0.7 [ 46 ].…”

Section: Discussionsupporting

confidence: 61%

See 1 more Smart Citation

Deep Learning Algorithm for Management of Diabetes Mellitus via Electrocardiogram-Based Glycated Hemoglobin (ECG-HbA1c): A Retrospective Cohort Study

Lin

Lee

Fang

et al. 2021

JPM

View full text Add to dashboard Cite

Background: glycated hemoglobin (HbA1c) provides information on diabetes mellitus (DM) management. Electrocardiography (ECG) is a noninvasive test of cardiac activity that has been determined to be related to DM and its complications. This study developed a deep learning model (DLM) to estimate HbA1c via ECG. Methods: there were 104,823 ECGs with corresponding HbA1c or fasting glucose which were utilized to train a DLM for calculating ECG-HbA1c. Next, 1539 cases from outpatient departments and health examination centers provided 2190 ECGs for initial validation, and another 3293 cases with their first ECGs were employed to analyze its contributions to DM management. The primary analysis was used to distinguish patients with and without mild to severe DM, and the secondary analysis was to explore the predictive value of ECG-HbA1c for future complications, which included all-cause mortality, new-onset chronic kidney disease (CKD), and new-onset heart failure (HF). Results: we used a gender/age-matching strategy to train a DLM to achieve the best AUCs of 0.8255 with a sensitivity of 71.9% and specificity of 77.7% in a follow-up cohort with correlation of 0.496 and mean absolute errors of 1.230. The stratified analysis shows that DM presented in patients with fewer comorbidities was significantly more likely to be detected by ECG-HbA1c. Patients with higher ECG-HbA1c under the same Lab-HbA1c exhibited worse physical conditions. Of interest, ECG-HbA1c may contribute to the mortality (gender/age adjusted hazard ratio (HR): 1.53, 95% conference interval (CI): 1.08–2.17), new-onset CKD (HR: 1.56, 95% CI: 1.30–1.87), and new-onset HF (HR: 1.51, 95% CI: 1.13–2.01) independently of Lab-HbA1c. An additional impact of ECG-HbA1c on the risk of all-cause mortality (C-index: 0.831 to 0.835, p < 0.05), new-onset CKD (C-index: 0.735 to 0.745, p < 0.01), and new-onset HF (C-index: 0.793 to 0.796, p < 0.05) were observed in full adjustment models. Conclusion: the ECG-HbA1c could be considered as a novel biomarker for screening DM and predicting the progression of DM and its complications.

show abstract

Section: Discussionsupporting

confidence: 61%

“…The advantage of DLM compared to traditional methods is to extract useful features automatically [ 20 ]. Recently, a study developed a DLM for screening DM via ECG with AUCs of 0.777 in an OPD experiment [ 45 ]. Through the larger database and augmentation from GLU, our DLM achieved an AUC of 0.8255.…”

Section: Discussionmentioning

confidence: 99%

Deep Learning Algorithm for Management of Diabetes Mellitus via Electrocardiogram-Based Glycated Hemoglobin (ECG-HbA1c): A Retrospective Cohort Study

Lin

Lee

Fang

et al. 2021

JPM

View full text Add to dashboard Cite

show abstract

“…[35] To obtain the features from the raw signals, data processing techniques or pre-processing techniques are required. These [13], data normalization [19] [36], data sampling [20], signal segementation [37], wavelet decomposition [38], Fourier transform [39], filters such as Gaussian filters [40], Butterworth bandpass filter [41], other data processing methods also includes DBSCAN [21] for outlier detection, SMOTE [21] for unbalanced data set. All these techniques process the raw data to obtain the features, these features can be time or frequency domain features, time series values, numerical values, spatio-temporal features, images etc.…”

Section: B Feature Type Distributionsmentioning

confidence: 99%

Systematic Review on Machine-Learning Algorithms Used in Wearable-Based eHealth Data Analysis

2021

View full text Add to dashboard Cite

In this digitized world, data has become an integral part in any domain, including healthcare. The healthcare industry produces a huge amount of digital data, by utilizing information from all sources of healthcare, including the patients' demographics, medications, vital signs, physician's observations, laboratory data, billing data, data from various wearable sensors, etc. With the rapid growth of the wireless technology applications, there has also been a significant increase in the digital health data. New medical discoveries and new eHealth-related technologies, such as mobile apps, novel sensors, and wearable technology have contributed as important data sources for healthcare data. Nowadays, there is a huge potential to improve the healthcare quality and customer satisfaction with the help of machine learning (ML) algorithms applied on time-domain and frequency-domain healthcare data obtained from wearables and sensors. This systematic literature review examines in depth how health data from sensors can be processed and analyzed using ML techniques. The review focuses on the following diseases for obtaining the eHealth data: diabetes mellitus type 1 and type 2, hypertension and hypotension, atrial fibrillation, bradykinesia, dyskinesia, and fever related diseases. The data for the systematic literature review was collected from four databases, Medline, Proquest, Scopus, and Web of Science. We selected 67 studies for the final in-depth review out of the initial pre-selected papers. Our study identified that the major part of eHealth data is obtained from the sensors such as accelerometer, gyroscopes, ECG (Electrocardiogram), EEG (Electroencephalogram ) monitors, and blood glucose sensors. This study also examines the different feature types, feature extraction methods, and ML algorithms used for eHealth data analysis. Our review also shows that neural network (NN) algorithms and support vector machines (SVM) have shown so far the best performance for analyzing the healthcare data among other ML algorithms studied in the literature.

show abstract

“…The IGRNet model gained an accuracy of 85.6%, which was higher than any other model used for comparison. [ 53 ] DNN The data collection was retrieved from the UCI machine learning repository – PIMA Indian diabetes dataset. For the neural network, the hidden layer count is 4.…”

Section: Introductionmentioning

confidence: 99%

A comprehensive review of machine learning techniques on diabetes detection

Sharma

Shah

2021

Vis. Comput. Ind. Biomed. Art

View full text Add to dashboard Cite

Diabetes mellitus has been an increasing concern owing to its high morbidity, and the average age of individual affected by of individual affected by this disease has now decreased to mid-twenties. Given the high prevalence, it is necessary to address with this problem effectively. Many researchers and doctors have now developed detection techniques based on artificial intelligence to better approach problems that are missed due to human errors. Data mining techniques with algorithms such as - density-based spatial clustering of applications with noise and ordering points to identify the cluster structure, the use of machine vision systems to learn data on facial images, gain better features for model training, and diagnosis via presentation of iridocyclitis for detection of the disease through iris patterns have been deployed by various practitioners. Machine learning classifiers such as support vector machines, logistic regression, and decision trees, have been comparative discussed various authors. Deep learning models such as artificial neural networks and recurrent neural networks have been considered, with primary focus on long short-term memory and convolutional neural network architectures in comparison with other machine learning models. Various parameters such as the root-mean-square error, mean absolute errors, area under curves, and graphs with varying criteria are commonly used. In this study, challenges pertaining to data inadequacy and model deployment are discussed. The future scope of such methods has also been discussed, and new methods are expected to enhance the performance of existing models, allowing them to attain greater insight into the conditions on which the prevalence of the disease depends.

show abstract

IGRNet: A Deep Learning Model for Non-Invasive, Real-Time Diagnosis of Prediabetes through Electrocardiograms

Cited by 31 publications

References 36 publications

Deep Learning Algorithm for Management of Diabetes Mellitus via Electrocardiogram-Based Glycated Hemoglobin (ECG-HbA1c): A Retrospective Cohort Study

Deep Learning Algorithm for Management of Diabetes Mellitus via Electrocardiogram-Based Glycated Hemoglobin (ECG-HbA1c): A Retrospective Cohort Study

Systematic Review on Machine-Learning Algorithms Used in Wearable-Based eHealth Data Analysis

A comprehensive review of machine learning techniques on diabetes detection

Contact Info

Product

Resources

About