RESUMO
BACKGROUND AND OBJECTIVE: Deep learning usually achieves good performance in the supervised way, which requires a large amount of labeled data. However, manual labeling of electrocardiograms (ECGs) is laborious that requires much medical knowledge. Semi-supervised learning (SSL) provides an effective way of leveraging unlabeled data to improve model performance, providing insight for solving this problem. The objective of this study is to improve the performance of cardiovascular disease (CVD) detection by fully utilizing unlabeled ECG. METHODS: A novel SSL algorithm fusing consistency regularization and pseudo-labeling techniques (CPSS) is proposed. CPSS consists of supervised learning and unsupervised learning. For supervised learning, the labeled ECGs are mapped into prediction vectors by the classifier. The cross-entropy loss function is used to optimize the classifier. For unsupervised learning, the unlabeled ECGs are weakly and strongly augmented, and a consistency loss is used to minimize the difference between the classifier's predictions for the two augmentations. Pseudo-labeling techniques include positive pseudo-labeling (PL) and ranking-based negative pseudo-labeling (RNL). PL introduces pseudo-labels for data with high prediction confidence. RNL assigns negative pseudo-labels to the lower-ranked categories in the prediction vectors to leverage data with low prediction confidence. In this study, VGGNet and ResNet are used as classifiers, which are jointly optimized by labeled and unlabeled ECGs. RESULTS: CPSS has been validated on several databases. With the same number of labeled ECGs (10%), it improves the accuracies over pure supervised learning by 13.59%, 4.60%, and 5.38% in the CPSC2018, PTB-XL, and Chapman databases, respectively. CPSS achieves comparable results to the fully supervised method with only 10% of labeled ECGs, which reduces the labeling workload by 90%. In addition, to verify the practicality of CPSS, a cardiovascular disease monitoring system is designed by heterogeneously deploying the trained classifiers on an SoC (system-on-a-chip), which can detect CVD in real time. CONCLUSION: The results of this study indicate that the proposed CPSS can significantly improve the performance of CVD detection using unlabeled ECG, which reduces the burden of ECG labeling in deep learning. In addition, the designed monitoring system makes the proposed CPSS promising for real-world applications.
Assuntos
Algoritmos , Doenças Cardiovasculares , Aprendizado Profundo , Eletrocardiografia , Aprendizado de Máquina Supervisionado , Humanos , Eletrocardiografia/métodos , Doenças Cardiovasculares/diagnóstico , Aprendizado de Máquina não Supervisionado , Bases de Dados FactuaisRESUMO
CLINICAL RELEVANCE: microRNAs have been found to be involved in the progression of a variety of ocular diseases. BACKGROUND: Cataract and glaucoma often coexist, and combined surgery is a common treatment. The aim of this study is to analyse the correlation between miR-26a and visual quality in cataract patients with glaucoma. METHODS: Seventy patients with cataract and glaucoma and 70 healthy volunteers were enrolled and received phacoemulsification and trabeculectomy. The patients were divided into low and high miR-26a expression groups according to miR-26a mean expression. The objective scattering index, strehl ratio, and modulated transfer function cut-off were analysed by optical quality analysis system II. The changes of miR-26a, objective scattering index, strehl ratio, modulated transfer function cut-off, and the correlation between the indicators were analysed. The downstream genes of miR-26a were analysed by Gene Ontology and Kyoto Encyclopaedia of Genes and Genomes functional enrichment. RESULTS: There were significant differences between patients and controls in lipid biomarker levels and visual indicators. miR-26a was decreased in the patient group. Strehl ratio and modulated transfer function cut-off in the miR-26a low-expression group were lower than in high-expression group, while mean defect of the visual field and objective scattering index were higher than in high-expression group. The miR-26a expression was negatively correlated with the severity of disease and objective scattering index, and positively correlated with strehl ratio and modulated transfer function cut-off. After surgery, miR-26a, strehl ratio, and modulated transfer function cut-off were increased, and objective scattering index was decreased. The downstream genes of miR-26a were related to several biological processes and signalling pathways. CONCLUSION: In cataract patients with glaucoma, miR-26a expression was lower than matched controls and increased following combined cataract removal and trabeculectomy.
RESUMO
PRCIS: Goniotomy (GT) is an alternative surgery for patients with prior failed surgery for glaucoma. PURPOSE: To evaluate the efficacy and safety of GT in patients with prior failed surgery for glaucoma. MATERIALS AND METHODS: A prospective, observational multicentered study was performed for patients who underwent GT with prior single or multiple surgery for glaucoma. Outcome measures included intraocular pressure (IOP) change, best-corrected visual acuity change, ocular hypotensive medication use, and occurrence of adverse events through 12 months. Complete success was defined as a postoperative IOP within 6-18 mmHg and a 20% reduction from baseline without ocular hypotensive medications. Qualified success was the same as the definition of complete success, except for postoperative use of medication. Logistic regression models were used to investigate the potential factors for surgical success. RESULTS: A total of 38 eyes of 34 patients were included. Twenty-three eyes had only 1 prior surgery, 13 eyes had 2 prior surgeries, 1 eye had 3 prior surgeries, and 1 eye had 4 prior surgeries. At month 12, there was complete success in 42.1% of the eyes and qualified success in 78.9% of the eyes. Preoperatively, the mean IOP was 29.4±6.9 mmHg and the median number of glaucoma medications used was 3.0 (2.0, 4.0); this decreased to 16.7±3.6 mmHg (43.2% reduction; P <0.001) and 2.0 (0.0, 3.0) ( P <0.001) at month 12, respectively. The most common complications included hyphema (13.2%), IOP spike (7.9%), and corneal edema (5.2%). Older age significantly contributed to surgical success. CONCLUSIONS: GT seems to be a safe and effective procedure for patients with prior failed surgery for glaucoma.
Assuntos
Glaucoma , Trabeculectomia , Humanos , Glaucoma/cirurgia , Glaucoma/etiologia , Pressão Intraocular , Estudos Prospectivos , Estudos Retrospectivos , Malha Trabecular/cirurgia , Trabeculectomia/métodos , Resultado do TratamentoRESUMO
Can eyes tell the truth? Can the analysis of human eye-movement data reveal psychological activities and uncover hidden information? Lying is a prevalent phenomenon in human society, but research has shown that people's accuracy in identifying deceptive behavior is not significantly higher than chance-level probability. In this paper, simulated crime experiments were carried out to extract the eye-movement features of 83 participants while viewing crime-related pictures using an eye tracker, and the importance of eye-movement features through interpretable machine learning was analyzed. In the experiment, the participants were independently selected into three groups: innocent group, informed group, and crime group. In the test, the eye tracker was used to extract a total of five categories of eye-movement indexes within the area of interest (AOI), including the fixation time, fixation count, pupil diameter, saccade frequency, and blink frequency, and the differences in these indexes were analyzed. Building upon interpretable learning algorithms, further investigation was conducted to assess the contribution of these metrics. As a result, the RF-RFE suspect identification model was constructed, achieving a maximum accuracy rate of 91.7%. The experimental results further support the feasibility of utilizing eye-movement features to reveal inner psychological activities.
RESUMO
Most of the existing multi-lead electrocardiogram (ECG) detection methods are based on all 12 leads, which undoubtedly results in a large amount of calculation and is not suitable for the application in portable ECG detection systems. Moreover, the influence of different lead and heartbeat segment lengths on the detection is not clear. In this paper, a novel Genetic Algorithm-based ECG Leads and Segment Length Optimization (GA-LSLO) framework is proposed, aiming to automatically select the appropriate leads and input ECG length to achieve optimized cardiovascular disease detection. GA-LSLO extracts the features of each lead under different heartbeat segment lengths through the convolutional neural network and uses the genetic algorithm to automatically select the optimal combination of ECG leads and segment length. In addition, the lead attention module (LAM) is proposed to weight the features of the selected leads, which improves the accuracy of cardiac disease detection. The algorithm is validated on the ECG data from the Huangpu Branch of Shanghai Ninth People's Hospital (defined as the SH database) and the open-source Physikalisch-Technische Bundesanstalt diagnostic ECG database (PTB database). The accuracy for detection of arrhythmia and myocardial infarction under the inter-patient paradigm is 99.65% (95% confidence interval: 99.20-99.76%) and 97.62% (95% confidence interval: 96.80-98.16%), respectively. In addition, ECG detection devices are designed using Raspberry Pi, which verifies the convenience of hardware implementation of the algorithm. In conclusion, the proposed method achieves good cardiovascular disease detection performance. It selects the ECG leads and heartbeat segment length with the lowest algorithm complexity while ensuring classification accuracy, which is suitable for portable ECG detection devices.
RESUMO
PURPOSE: To evaluate the intraocular pressure (IOP)-lowering effect of the combination of phacoemulsification with intraocular lens implantation (PEI), goniosynechialysis (GSL), and goniotomy (GT) in eyes of advanced primary angle-closure glaucoma (PACG) with cataract. DESIGN: Multicenter observational study. METHODS: We enrolled 83 eyes of 83 patients with advanced PACG who received combined PEI+GSL+GT at 8 ophthalmic institutes. Each patient was assessed before treatment and at 1, 7 days, 1, 3, 6, and 12 months postsurgery. The criteria for complete success were IOP within 6 to 18 mm Hg and at least 20% of reduction in IOP from baseline without ocular hypotensive medications or reoperation. The definition of qualified success was similar to that of complete success, except for the need for ocular hypotensive medications. The potential prognostic factors for surgical success were investigated using a multivariate logistic model. RESULTS: All participants completed 1 year of follow-up. Complete and qualified success were achieved in 74 (89.1%) and 79 (95.2%) of 83 eyes, respectively. The mean preoperative and postsurgical IOPs were 27.4±7.3 and 14.2±2.6 mm Hg, respectively. Participants used an average of 2.0 and 0.3 types of ocular hypotensive medications before and after surgery, respectively. The chief complications included hyphema (n=9), IOP spike (n=9), and corneal edema (n=8). None of the eyes required reoperation or developed vision-threatening complications. Multivariate analysis showed that older age was associated with a higher probability of complete success (odds ratio=1.13; 95% CI: 1.02-1.25; P=0.020). CONCLUSIONS: The 1-year results of combination of PEI+GSL+GT in treating advanced PACG cases with cataract appear to be safe and effective. Further large-scale multination and multicenter studies are warranted.
Assuntos
Catarata , Glaucoma de Ângulo Fechado , Facoemulsificação , Trabeculectomia , Humanos , Facoemulsificação/métodos , Trabeculectomia/métodos , Pressão Intraocular , Glaucoma de Ângulo Fechado/cirurgia , Glaucoma de Ângulo Fechado/complicações , Catarata/complicações , Anti-Hipertensivos/uso terapêuticoRESUMO
In the past few years, deep learning-based electrocardiogram (ECG) compression methods have achieved high-ratio compression by reducing hidden nodes. However, this reduction can result in severe information loss, which will lead to poor quality of the reconstructed signal. To overcome this problem, a novel quality-guaranteed ECG compression method based on a binary convolutional auto-encoder (BCAE) equipped with residual error compensation (REC) was proposed. In traditional compression methods, ECG signals are compressed into floating-point numbers. BCAE directly compresses the ECG signal into binary codes rather than floating-point numbers, whereas binary codes take up fewer bits than floating-point numbers. Compared with the traditional floating-point number compression method, the hidden nodes of the BCAE network can be artificially increased without reducing the compression ratio, and as many hidden nodes as possible can ensure the quality of the reconstructed signal. Furthermore, a novel optimization method named REC was developed. It was used to compensate for the residual between the ECG signal output by BCAE and the original signal. Complemented with the residual error, the restoration of the compression signal was improved, so the reconstructed signal was closer to the original signal. Control experiments were conducted to verify the effectiveness of this novel method. Validated by the MIT-BIH database, the compression ratio was 117.33 and the root mean square difference (PRD) was 7.76%. Furthermore, a portable compression device was designed based on the proposed algorithm using Raspberry Pi. It indicated that this method has attractive prospects in telemedicine and portable ECG monitoring systems.
Assuntos
Compressão de Dados , Processamento de Sinais Assistido por Computador , Algoritmos , Arritmias Cardíacas , Compressão de Dados/métodos , Eletrocardiografia , HumanosRESUMO
Objective: To investigate the effects of recombinant human epidermal growth factor eye drops combined with phacoemulsification on short- and long-term visual acuity recovery and related dry eye complications in patients with senile cataract. Methods: Sixty patients with senile cataract cured from January 2019 to January 2021 were enrolled in our hospital. The patients in the control group were arbitrarily assigned into the control and the research group. The former group received phacoemulsification, and the latter group received recombinant human epidermal growth factor (RhEGF) eye drops combined with phacoemulsification. The curative effect, the incidence of xerophthalmia, short-term and long-term vision improvement, changes of corneal endothelial cells, serum factors, and life quality scores were compared. Results: The effective rate of the research group was 90.00%, and the effective rate of the control group was 66.67%; the curative effect of the research group was higher than that of the control group (P < 0.05). The incidence of dry eye in the research group was lower than that in the control group (P < 0.05). The short-term and long-term visual acuity improvement effect of the research group was better than that of the control group (P < 0.05). After treatment, the density of corneal endothelial cells in the research group was higher than that in the control group, while the proportion of hexagonal cells and the coefficient of variation of corneal endothelial cells in the research group were lower than those in the control group (P < 0.05). After treatment, IL-6 and TNF-α in the research group were lower than those in the control group (P < 0.05). Compared with the control group, the physical function, psychological function, social function, and healthy self-cognition scores of the research group were all lower (P < 0.05). Conclusion: Cataract is the leading cause of blindness in the world. With the continuous improvement of cataract phacoemulsification technology, the incidence of some serious complications has gradually lessened. Xerophthalmia is one of the most obvious and predictable complications after cataract surgery and may affect the recovery of postoperative visual acuity. Recombinant human epidermal growth factor eye drops can effectively enhance the visual acuity of patients, promote the curative effect, and strengthen the life quality.