RESUMO
Traditional biomedical data analysis technology faces enormous challenges in the context of the big data era. The application of deep learning technology in the field of biomedical analysis has ushered in tremendous development opportunities. In this paper, we reviewed the latest research progress of deep learning in the field of biomedical data analysis. Firstly, we introduced the deep learning method and its common framework. Then, focusing on the proposal of biomedical problems, data preprocessing method, model building method and training algorithm, we summarized the specific application of deep learning in biomedical data analysis in the past five years according to the chronological order, and emphasized the application of deep learning in medical assistant diagnosis. Finally, we gave the possible development direction of deep learning in the field of biomedical data analysis in the future.
Assuntos
Tecnologia Biomédica , Análise de Dados , Aprendizado Profundo , AlgoritmosRESUMO
S-palmitoylases and S-depalmitoylases are differentially expressed in various cancers and several malignant tumors and show a strong prognostic ability. Notwithstanding, the potential clinical impact of S-palmitoylases and S-depalmitoylases, particularly in the prognosis and progression of lung adenocarcinoma (LUAD), has not been clarified. Expression levels of S-palmitoylases and S-depalmitoylases in LUAD were investigated using TCGA. GEPIA was used to evaluate the mRNA levels of S-palmitoylases and S-depalmitoylases at different pathological stages. Metascape was used to investigate the biological significance of S-palmitoylases and S-depalmitoylases. The Kaplan-Meier plotter was used to analyze the prognostic value of S-palmitoylases and S-depalmitoylases. CBioportal was used to analyze gene alterations in S-palmitoylases and S-depalmitoylases. UALCAN was used to examine DNA promoter methylation levels of S-palmitoylases and S-depalmitoylases. Finally, we investigated the relationship between S-palmitoylases, S-depalmitoylases, and tumor-infiltrating immune cells using TIMER. Correlations with immune checkpoint-related genes were determined using the R packages reshape2, ggpubr, ggplot2, and corrplot. PCR was also performed to assess the degree of ZDHHC4/12/18/24 and APT2 transcript expression in lung adenocarcinoma and adjacent normal lung tissues. HPA was utilized to investigate protein levels of S-palmitoylases and S-depalmitoylases in LUAD and normal lung tissue. Our study found that ZDHHC2/3/4/5/6/7/9/12/13/16/18/20/21/23/24, APT1/2, PPT1, LYPLAL1, ABHD4/10/11/12/13 and ABHD17C mRNA expression was significantly upregulated in LUAD, whereas ZDHHC1/8/11/11B/14/15/17/19/22, ABHD6/16A and ABHD17A mRNA expression was significantly downregulated. The functions of the differentially expressed S-palmitoylases and S-depalmitoylases were mainly associated with protein-cysteine S-palmitoyltransferase and protein-cysteine S-acyltransferase activities. Patients with high expression of ZDHHC4/12/18/24, APT2, ABHD4, ABHD11 and ABHD12 had a shorter overall survival. Infiltration of six immune cells (B cells, CD8+ T cells, CD4+ T cells, macrophages, neutrophils, and dendritic cells) was closely associated with the expression of ZDHHC4/12/18/24 and APT2. ZDHHC4/12/18/24 and APT2 positively correlated with the immune checkpoint-related gene CD276. We assessed the mRNA levels of ZDHHC4/12/18/24 and APT2 using qRT-PCR and found increased expression of ZDHHC4/12/18/24 in LUAD compared with healty control lung tissues. ZDHHC4/12/18/24, and APT2 are potential prognostic biomarkers of LUAD. Their expression levels could be related to the tumor microenvironment in LUAD.
Assuntos
Adenocarcinoma de Pulmão , Neoplasias Pulmonares , Humanos , Linfócitos T CD8-Positivos , Cisteína , Prognóstico , Adenocarcinoma de Pulmão/genética , Neoplasias Pulmonares/genética , RNA Mensageiro/genética , Biomarcadores , Biomarcadores Tumorais/genética , Microambiente Tumoral , Antígenos B7 , Monoacilglicerol Lipases , Serina ProteasesRESUMO
Cardiovascular diseases have become one of the most prevalent threats to human health throughout the world. As a noninvasive assistant diagnostic tool, the heart sound detection techniques play an important role in the prediction of cardiovascular diseases. In this paper, the latest development of the computer-aided heart sound detection techniques over the last five years has been reviewed. There are mainly the following aspects: the theories of heart sounds and the relationship between heart sounds and cardiovascular diseases; the key technologies used in the processing and analysis of heart sound signals, including denoising, segmentation, feature extraction and classification; with emphasis, the applications of deep learning algorithm in heart sound processing. In the end, some areas for future research in computer-aided heart sound detection techniques are explored, hoping to provide reference to the prediction of cardiovascular diseases.
Assuntos
Doenças Cardiovasculares/diagnóstico , Auscultação Cardíaca , Ruídos Cardíacos/fisiologia , Processamento de Sinais Assistido por Computador , Algoritmos , Aprendizado Profundo , Auscultação Cardíaca/classificação , Auscultação Cardíaca/métodos , HumanosRESUMO
PURPOSE: Exosomes contain abundant circRNAs and are determined to be involved in the pathogenesis of lung adenocarcinoma (LUAD). Thus, our study aimed to explore new circRNAs in plasma exosomes that could be involved in such pathogenesis. PATIENTS AND METHODS: High-throughput sequencing was used in identifying the alterations in exosomal circRNA expression. Gene ontology functional analysis (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analysis were performed to determine the significant functions and pathways associated with differentially expressed circRNAs. TargetScan and miRanda were used to predict circRNA-targeted microRNAs and mRNAs. CircRNA expression profiles were then validated by quantitative reverse-transcription polymerase chain reaction (qRT-PCR). Wound healing and Transwell assays were performed to determine the roles of has_circ_0102537 in LUAD progression. RESULTS: We identified six significantly upregulated and 214 significantly downregulated circRNAs. GO and KEGG pathway analysis suggested that the differentially expressed circRNAs are involved in the occurrence and development of LUAD. A circRNA-miRNA-mRNA meshwork was established to predict the potential interactions among these RNAs. The circRNA expression profile was then subjected to qRT-PCR for validation. We identified hsa_circ_0102537 to be downregulated in both LUAD plasma exosomes and tissues. GO, KEGG pathway analysis, circRNA-miRNA-mRNA meshwork, and further experiments suggest that hsa_circ_0102537 could be involved in LUAD progression. CONCLUSION: Our study explored a large number of circRNAs that may be involved in the LUAD pathogenesis, thereby supporting the need for further research on both diagnosis biomarkers and the potential intervention therapeutic targets.
RESUMO
INTRODUCTION: The benefits of cardiac rehabilitation (CR) on the reduction of cardiac and all-cause mortality are well documented. However, adherence remains suboptimal in China. It is clear that traditional CR does not meet the needs of many eligible patients and innovation is required to improve its application. Home-based CR (HBCR) is a cost-effective method that may be a valuable alternative for many individuals in China. In HBCR, it is often difficult to maintain an exercise intensity that is both effective and within safe limits, factors that are essential for patient safety. Mobile health interventions have the potential to overcome these obstacles and may be efficacious in improving adherence. The purpose of this study is to evaluate whether an Intelligent Exercise Rehabilitation Management System (IERMS)-based HBCR could improve adherence to CR and to assess the effects on exercise capacity, mental health, self-efficacy, quality of life and lifestyle-related risk factors. METHODS AND ANALYSIS: We propose a single-blinded, two-arm, randomised controlled crossover study of 70 patients with coronary heart disease (CHD). Participants will be randomly assigned in a 1:1 ratio to one of the two groups. Patients in group 1 will receive the IERMS intervention together with usual care for the first 6 weeks and usual care for the last 6 weeks, while patients assigned to group 2 will receive usual care for the first 6 weeks and will use IERMS in the last 6 weeks. The primary outcome is adherence to the programme and secondary outcomes include exercise capacity, psychological well-being, quality of life, self-efficacy and lifestyle-related risk factors. All secondary outcomes will be measured at baseline, 6 weeks and 12 weeks. ETHICS AND DISSEMINATION: This study has been approved by the Human Research Ethics Committee of the School of Nursing, Jilin University (HREC 2019120901). The results will be published in peer-reviewed journals and at conferences. TRIAL REGISTRATION NUMBER: ChiCTR1900028182; Pre-results.
Assuntos
Reabilitação Cardíaca/métodos , Doença das Coronárias/reabilitação , Terapia por Exercício/métodos , Cooperação do Paciente , Estudos Cross-Over , Humanos , Ensaios Clínicos Controlados Aleatórios como Assunto , Projetos de PesquisaRESUMO
BACKGROUND AND AIM: Several studies have identified that obesity and being overweight can increase the risk of developing myocardial infarction (MI). However, the predictive value of the central obesity index, that is, the waist-hip ratio (WHR), regarding MI risk remains unclear. This study aimed to provide a systematic review and meta-analysis of WHR as a predictor of MI incidence. METHODS: This study used relevant keywords and MeSH terms to identify studies of MI risk and WHR from PubMed, Web of Science, Embase, and Cochrane databases in November 2017. RESULTS: We conducted a meta-analysis of 12 case-control studies in 14 eligible trials and further explored whether the predictive value of WHR on MI risk varies according to sex. The results showed that a high WHR increased MI risk (pooled odds ratio [OR] 2.62, 95% confidence interval [CI] 2.02-3.39, Pâ<â0.00001) and that elevated WHR is more strongly predictive of MI in women than in men (pooled OR 4.63, 95% CI 3.28-6.53 in women; pooled OR 2.71, 95% CI 2.15-3.41 in men). CONCLUSIONS: MI is significantly associated with increased WHR, with a stronger association among women.
Assuntos
Infarto do Miocárdio/epidemiologia , Obesidade Abdominal/epidemiologia , Relação Cintura-Quadril , Comorbidade , Feminino , Humanos , Masculino , Fatores de Risco , Distribuição por SexoRESUMO
The noninvasive peripheral oxygen saturation (SpO2) and the pulse rate can be extracted from photoplethysmography (PPG) signals. However, the accuracy of the extraction is directly affected by the quality of the signal obtained and the peak of the signal identified; therefore, a hybrid wavelet-based method is proposed in this study. Firstly, we suppressed the partial motion artifacts and corrected the baseline drift by using a wavelet method based on the principle of wavelet multiresolution. And then, we designed a quadratic spline wavelet modulus maximum algorithm to identify the PPG peaks automatically. To evaluate this hybrid method, a reflective pulse oximeter was used to acquire ten subjects' PPG signals under sitting, raising hand, and gently walking postures, and the peak recognition results on the raw signal and on the corrected signal were compared, respectively. The results showed that the hybrid method not only corrected the morphologies of the signal well but also optimized the peaks identification quality, subsequently elevating the measurement accuracy of SpO2 and the pulse rate. As a result, our hybrid wavelet-based method profoundly optimized the evaluation of respiratory function and heart rate variability analysis.
Assuntos
Oximetria/métodos , Fotopletismografia/métodos , Processamento de Sinais Assistido por Computador , Análise de Ondaletas , Adulto , Algoritmos , Artefatos , Feminino , Frequência Cardíaca/fisiologia , Humanos , Masculino , Pessoa de Meia-Idade , Movimento (Física) , RespiraçãoAssuntos
Erros de Diagnóstico , Hemangioendotelioma Epitelioide/diagnóstico , Cuidados Intraoperatórios/efeitos adversos , Neoplasias Pulmonares/diagnóstico , Pulmão/patologia , Diagnóstico Diferencial , Feminino , Hemangioendotelioma Epitelioide/patologia , Hemangioendotelioma Epitelioide/terapia , Humanos , Pulmão/irrigação sanguínea , Pulmão/diagnóstico por imagem , Pulmão/cirurgia , Neoplasias Pulmonares/patologia , Neoplasias Pulmonares/terapia , Pessoa de Meia-Idade , Metástase Neoplásica/diagnóstico , Pneumonectomia , Tomografia Computadorizada por Raios X , Conduta ExpectanteRESUMO
Reoperation as a result of increased intracranial pressure (ICP) associated with cyst formation in an intracranial tumor resection cavity is a rare clinical condition. We report two cases of reoperation as a result of raised ICP associated with cyst formation in the tumor resection cavity, one arising after glioma resection and the other after meningioma resection. In both cases, a "valve"-like structure was noted intraoperatively in the roof region of the tumor resection cavity. Surgical resection of the "valve"-like structure led to slow regression over several months after the reoperation rather than to immediate disappearance of the cyst. Both cases illustrate that the "valve"-like structure formed in the roof region of the tumor resection cavity may be responsible for cyst formation. Surgical resection of it provides good long-term outcomes in such patients though short-term outcomes are unsatisfactory; we speculate that if the resection of the cortical tissue around the "valve"-like structure is enough wide, its return may be avoided.