CardioLearn: A Cloud Deep Learning Service for Cardiac Disease Detection from Electrocardiogram

Hong, Shenda; Fu, Zhaoji; Zhou, Rongbo; Yu, Jie; Li, Yongkui; Wang, Kai; Cheng, Guanlin

doi:10.1145/3366424.3383529

Cited by 14 publications

(9 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…AI techniques have recently shown significant potential in cardiology [ 22 , 23 , 24 , 25 , 26 , 27 ] owing to their ability to automatically learn effective features from data without the help of domain experts. When focusing on deep learning methods applying ECG data, various architectures have been proposed for disease detection [ 15 , 17 , 28 , 29 , 30 , 31 , 32 , 33 , 34 , 35 , 36 , 37 , 38 ], sleep staging [ 39 , 40 ], and biometric identification [ 41 , 42 , 43 , 44 ], among others (see a recent survey in [ 22 ]).…”

Section: Methodsmentioning

confidence: 99%

“… ECG diagnostic results are difficult to understand by ordinary users. Although there are a few cloud services that can provide analysis capabilities [ 15 ], the results include professional terminology, requiring a professional to interpret. Such terms are quite difficult to understand by typical users, thus, it is difficult to encourage ordinary people to use such tools for cardiovascular health management.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Artificial-Intelligence-Enhanced Mobile System for Cardiovascular Health Management

Hong

Zhang

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

The number of patients with cardiovascular diseases is rapidly increasing in the world. The workload of existing clinicians is consequently increasing. However, the number of cardiovascular clinicians is declining. In this paper, we aim to design a mobile and automatic system to improve the abilities of patients’ cardiovascular health management while also reducing clinicians’ workload. Our system includes both hardware and cloud software devices based on recent advances in Internet of Things (IoT) and Artificial Intelligence (AI) technologies. A small hardware device was designed to collect high-quality Electrocardiogram (ECG) data from the human body. A novel deep-learning-based cloud service was developed and deployed to achieve automatic and accurate cardiovascular disease detection. Twenty types of diagnostic items including sinus rhythm, tachyarrhythmia, and bradyarrhythmia are supported. Experimental results show the effectiveness of our system. Our hardware device can guarantee high-quality ECG data by removing high-/low-frequency distortion and reverse lead detection with 0.9011 Area Under the Receiver Operating Characteristic Curve (ROC–AUC) score. Our deep-learning-based cloud service supports 20 types of diagnostic items, 17 of them have more than 0.98 ROC–AUC score. For a real world application, the system has been used by around 20,000 users in twenty provinces throughout China. As a consequence, using this service, we could achieve both active and passive health management through a lightweight mobile application on the WeChat Mini Program platform. We believe that it can have a broader impact on cardiovascular health management in the world.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Artificial-Intelligence-Enhanced Mobile System for Cardiovascular Health Management

Hong

Zhang

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…In addition, ECG will be measured using a mobile ECG recorder (CardioLearn; HeartVoice Medical Technology Co., Ltd., Anhui, China) at each timepoint following the manufacturer’s instructions. The mobile device has been widely used in China to simply measure the ECGs and automatically analyze their results based on a novel deep learning-based cloud service as earlier reported [ 27 , 28 ]. Furthermore, the anesthesiologists will be invited to record their ECG whenever they feel discomfort during the night shift.…”

Section: Methodsmentioning

confidence: 99%

The use of virtual reality to reduce stress among night-shift anesthesiologists: study protocol for a crossover trial

Chen

Shen

et al. 2021

Trials

View full text Add to dashboard Cite

Background Because of the lack of anesthesia workforce, anesthesiologists are forced to work overtime and more night shifts, which can disturb their biological rhythm and cause severe stress and depression, potentially leading to negative and even devastating outcomes for both themselves and patients. Virtual reality (VR), a new method to reduce stress and pain for patients, has been widely used in biomedical fields. The purpose of this study is to evaluate the potential effectiveness of VR technology in reducing stress among night-shift anesthesiologists. Methods In this randomized controlled, crossover, single-center clinical trial, a total of 30 anesthesiologists will be enrolled and randomized in a 1:1 allocation to either the VR immersion group (intervention group) or the routine night-shift group (control group) with a washout of 1 week. Anesthesiologists in the intervention group will undergo VR immersion twice, while anesthesiologists in the control group will not watch VR videos during the night shift. The primary outcome will be the difference in the NASA Task Load Index (NASA-TLX) score between the two groups. Secondary outcomes will include the Chinese Perceived Stress Scale (CPSS), perceived stress scores (visual analogue scale (VAS)), and Multidimensional Fatigue Inventory (MFI-20) scores; levels of satisfaction among the participants; incidence of arrhythmia; and incidence of chest tightness, headache, and palpitations. Discussion It is unknown whether the use of VR technology during the night shift can reduce stress among anesthesiologists. With the widespread use of VR technology, a positive result in this trial could spur hospitals to apply VR technology to reduce stress among night-shift doctors in every department and provide a relatively relaxed working environment. Trial registration Chinese Clinical Trial Registry ChiCTR2000031025. Registered on 21 March 2020

show abstract

“…They also designed a portable smart hardware device, along with an interactive mobile program, to demonstrate its practical use. Zhang et al [52] established the Cardiovascular Disease Whole Process Management Platform for automated detection and classification of ECG signals. They obtained 98.27% accuracy for recognition of 18 classes of heart rhythms based on a CNNs model.…”

Section: Benchmarking Over Other DL Algorithms With the Cloud Systemmentioning

confidence: 99%

AFibNet: an implementation of atrial fibrillation detection with convolutional neural network

Tutuko

Nurmaini

Tondas³

et al. 2021

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

Background Generalization model capacity of deep learning (DL) approach for atrial fibrillation (AF) detection remains lacking. It can be seen from previous researches, the DL model formation used only a single frequency sampling of the specific device. Besides, each electrocardiogram (ECG) acquisition dataset produces a different length and sampling frequency to ensure sufficient precision of the R–R intervals to determine the heart rate variability (HRV). An accurate HRV is the gold standard for predicting the AF condition; therefore, a current challenge is to determine whether a DL approach can be used to analyze raw ECG data in a broad range of devices. This paper demonstrates powerful results for end-to-end implementation of AF detection based on a convolutional neural network (AFibNet). The method used a single learning system without considering the variety of signal lengths and frequency samplings. For implementation, the AFibNet is processed with a computational cloud-based DL approach. This study utilized a one-dimension convolutional neural networks (1D-CNNs) model for 11,842 subjects. It was trained and validated with 8232 records based on three datasets and tested with 3610 records based on eight datasets. The predicted results, when compared with the diagnosis results indicated by human practitioners, showed a 99.80% accuracy, sensitivity, and specificity. Result Meanwhile, when tested using unseen data, the AF detection reaches 98.94% accuracy, 98.97% sensitivity, and 98.97% specificity at a sample period of 0.02 seconds using the DL Cloud System. To improve the confidence of the AFibNet model, it also validated with 18 arrhythmias condition defined as Non-AF-class. Thus, the data is increased from 11,842 to 26,349 instances for three-class, i.e., Normal sinus (N), AF and Non-AF. The result found 96.36% accuracy, 93.65% sensitivity, and 96.92% specificity. Conclusion These findings demonstrate that the proposed approach can use unknown data to derive feature maps and reliably detect the AF periods. We have found that our cloud-DL system is suitable for practical deployment

show abstract

CardioLearn: A Cloud Deep Learning Service for Cardiac Disease Detection from Electrocardiogram

Cited by 14 publications

References 18 publications

Artificial-Intelligence-Enhanced Mobile System for Cardiovascular Health Management

Artificial-Intelligence-Enhanced Mobile System for Cardiovascular Health Management

The use of virtual reality to reduce stress among night-shift anesthesiologists: study protocol for a crossover trial

AFibNet: an implementation of atrial fibrillation detection with convolutional neural network

Contact Info

Product

Resources

About