Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 116.321
Filtrar
3.
Hum Genomics ; 14(1): 35, 2020 10 02.
Artigo em Inglês | MEDLINE | ID: mdl-33008459

RESUMO

Precision medicine aims to empower clinicians to predict the most appropriate course of action for patients with complex diseases like cancer, diabetes, cardiomyopathy, and COVID-19. With a progressive interpretation of the clinical, molecular, and genomic factors at play in diseases, more effective and personalized medical treatments are anticipated for many disorders. Understanding patient's metabolomics and genetic make-up in conjunction with clinical data will significantly lead to determining predisposition, diagnostic, prognostic, and predictive biomarkers and paths ultimately providing optimal and personalized care for diverse, and targeted chronic and acute diseases. In clinical settings, we need to timely model clinical and multi-omics data to find statistical patterns across millions of features to identify underlying biologic pathways, modifiable risk factors, and actionable information that support early detection and prevention of complex disorders, and development of new therapies for better patient care. It is important to calculate quantitative phenotype measurements, evaluate variants in unique genes and interpret using ACMG guidelines, find frequency of pathogenic and likely pathogenic variants without disease indicators, and observe autosomal recessive carriers with a phenotype manifestation in metabolome. Next, ensuring security to reconcile noise, we need to build and train machine-learning prognostic models to meaningfully process multisource heterogeneous data to identify high-risk rare variants and make medically relevant predictions. The goal, today, is to facilitate implementation of mainstream precision medicine to improve the traditional symptom-driven practice of medicine, and allow earlier interventions using predictive diagnostics and tailoring better-personalized treatments. We strongly recommend automated implementation of cutting-edge technologies, utilizing machine learning (ML) and artificial intelligence (AI) approaches for the multimodal data aggregation, multifactor examination, development of knowledgebase of clinical predictors for decision support, and best strategies for dealing with relevant ethical issues.


Assuntos
Infecções por Coronavirus/genética , Diabetes Mellitus/genética , Neoplasias/genética , Pneumonia Viral/genética , Medicina de Precisão/tendências , Cardiomiopatias , Infecções por Coronavirus/epidemiologia , Análise de Dados , Diabetes Mellitus/epidemiologia , Genômica/tendências , Humanos , Metabolômica/tendências , Neoplasias/epidemiologia , Pandemias , Pneumonia Viral/epidemiologia , Proteômica/tendências
5.
PLoS One ; 15(10): e0240394, 2020.
Artigo em Inglês | MEDLINE | ID: mdl-33031467

RESUMO

BACKGROUND: The SARS-CoV-2 pandemic compounds Mexico's pre-existing challenges: very high levels of both non-communicable diseases (NCD) and social inequity. METHODS AND FINDINGS: Using data from national reporting of SARS-CoV-2 tested individuals, we estimated odds of hospitalization, intubation, and death based on pre-existing non-communicable diseases and socioeconomic indicators. We found that obesity, diabetes, and hypertension are positively associated with the three outcomes in a synergistic manner. The municipal poverty level is also positively associated with hospitalization and death. CONCLUSIONS: Mexico's response to COVID-19 is complicated by a synergistic double challenge: raging NCDs and extreme social inequity. The response to the current pandemic must take both into account both to be effective and to ensure that the burden of COVID-19 not falls disproportionately on those who are already disadvantaged.


Assuntos
Infecções por Coronavirus/epidemiologia , Pneumonia Viral/epidemiologia , Adulto , Fatores Etários , Betacoronavirus/fisiologia , Comorbidade , Infecções por Coronavirus/fisiopatologia , Infecções por Coronavirus/terapia , Complicações do Diabetes , Diabetes Mellitus/fisiopatologia , Feminino , Hospitalização , Humanos , Hipertensão/fisiopatologia , Intubação , Masculino , México/epidemiologia , Pessoa de Meia-Idade , Obesidade/fisiopatologia , Pandemias , Pneumonia Viral/fisiopatologia , Pneumonia Viral/terapia , Pobreza , Fatores Sexuais , Fatores Socioeconômicos
6.
Vestn Oftalmol ; 136(5. Vyp. 2): 155-162, 2020.
Artigo em Russo | MEDLINE | ID: mdl-33063958

RESUMO

Laser corneal confocal microscopy (CCM) is a method of objective visualization of thin corneal nerve fibers (CNF), the structure of which changes in patients with diabetes mellitus (DM). PURPOSE: To conduct comparative analysis of the results of CNF assessment using CCM and other known neurological instrumental techniques as well as evaluate their applicability to the early diagnosis of diabetic polyneuropathy (DPN). MATERIAL AND METHODS: We examined a total of 46 patients (85 eyes) with type 1 DM and either subclinical (24 patients), or clinical-stage DPN (22 patients) and 50 patients (87 eyes) with type 2 DM (subclinical DPN in 27 patients and clinical-stage DPN in 23 patients). The control group consisted of 34 healthy volunteers (68 eyes). All patients underwent standard ophthalmological examination, CCM with nerve tortuosity assessment (including calculation of coefficients of CNF orientation anisotropy, KΔL, and symmetry, Ksym) and interocular asymmetry, electroneuromyography (ENMG), and quantitative sensory testing (QST). RESULTS: Analysis of the CCM results revealed a reliable decrease in the average KΔL values in patients with type 1 and type 2 DM compared with the control group. In the group of patients with type 1 DM and subclinical DPN, correlations were revealed between the CNF tortuosity coefficients and a number of ENMG parameters, such as the M-response amplitude of the peroneal nerve (r=0.73, p≤0.02), M-response amplitude of the tibial nerve (r=0.58, p≤0.01), residual latency (r= -0.62, p≤0.05), and peroneal nerve conduction velocity (r=0.57, p≤0.01). Ksym values correlated with the warm sensitivity threshold (r=0.6, p≤0.008). Among patients with type 2 DM and subclinical DPN, the KΔL coefficient correlated with the peroneal nerve conduction velocity (r=0.46, p≤0.02), M-response amplitude of the tibial nerve (r=0.6, p≤0.04), and residual latency of the peroneal nerve (r=-0.56, p≤0.05). CONCLUSION: The state of thin corneal nerves correlates with functional changes in the peripheral nerves. Pathological changes in CNF in patients with DM can be detected at an early (subclinical) stage of DPN using laser CCM and a program for corneal nerve tortuosity analysis.


Assuntos
Diabetes Mellitus , Neuropatias Diabéticas , Córnea/diagnóstico por imagem , Neuropatias Diabéticas/diagnóstico , Diagnóstico Precoce , Humanos , Microscopia Confocal , Fibras Nervosas
7.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 828-831, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018113

RESUMO

Peripheral vascular flow in response to induced reactive hyperemia of the radial artery is used as a benchmark for non-invasive assessment of the endothelial function. As an alternative to standard modalities, this study investigates the suitability of impedance plethysmography to estimate peripheral vascular flow variations associated with the reactive hyperemia process. Results indicate a consistent variation of bio-impedance during the reactive hyperemia process at higher measurement frequencies and these variations are compatible with a standard tissue impedance model. Further, calculated features of bioimpedance has shown the capability of differentiating healthy and diabetic groups which is useful in estimating the endothelial dysfunction.


Assuntos
Diabetes Mellitus , Hiperemia , Humanos , Hiperemia/diagnóstico , Pletismografia de Impedância , Artéria Radial
8.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 1404-1407, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018252

RESUMO

Diabetic retinopathy (DR) is a progressive eye disease that affects a large portion of working-age adults. DR, which may progress to an irreversible state that causes blindness, can be diagnosed with a comprehensive dilated eye exam. With the eye dilated, the Doctor takes pictures of the inside of the eye via a medical procedure called Fluorescein Angiography, in which a dye is injected into the bloodstream. The dye highlights the blood vessels in the back of the eye so they can be photographed. In addition, the Doctor may request an Optical Coherence Tomography (OCT) exam, by which cross-sectional photos of the retina are produced to measure the thickness of the retina. Early prognostication is vital in treating the disease and preventing it from progressing into advanced irreversible stages. Skilled medical personnel and necessary medical facilities are required to detect DR in its five major stages. In this paper, we propose a diagnostic tool to detect Diabetic retinopathy from fundus images by using an ensemble of multi-inception CNN networks. Our inception block consists of three Convolutional layers with kernel sizes of 3x3, 5x5, and 1x1 that are concatenated deeply and forwarded to the max-pooling layer. We experimentally compare our proposed method with two pre-trained models: VGG16 and GoogleNets. The experiment results show that the proposed method can achieve an accuracy of 93.2% by an ensemble of 10 random networks, compared to 81% obtained with transfer learning based on VGG19.


Assuntos
Diabetes Mellitus , Retinopatia Diabética , Estudos Transversais , Retinopatia Diabética/diagnóstico , Fundo de Olho , Humanos , Redes Neurais de Computação , Tomografia de Coerência Óptica
9.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 1966-1969, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018388

RESUMO

Diabetic retinopathy (DR) is a medical condition due to diabetes mellitus that can damage the patient retina and cause blood leaks. This condition can cause different symptoms from mild vision problems to complete blindness if it is not timely treated. In this work, we propose the use of a deep learning architecture based on a recent convolutional neural network called EfficientNet to detect referable diabetic retinopathy (RDR) and vision-threatening DR. Tests were conducted on two public datasets, EyePACS and APTOS 2019. The obtained results achieve state-of-the-art performance and show that the proposed network leads to higher classification rates, achieving an Area Under Curve (AUC) of 0.984 for RDR and 0.990 for vision-threatening DR on EyePACS dataset. Similar performances are obtained for APTOS 2019 dataset with an AUC of 0.966 and 0.998 for referable and vision-threatening DR, respectively. An explainability algorithm was also developed and shows the efficiency of the proposed approach in detecting DR signs.


Assuntos
Diabetes Mellitus , Retinopatia Diabética , Algoritmos , Área Sob a Curva , Retinopatia Diabética/diagnóstico , Humanos , Redes Neurais de Computação , Retina
10.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 1988-1991, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018393

RESUMO

In this work, we demonstrate a novel approach to assessing the risk of Diabetic Peripheral Neuropathy (DPN) using only the retinal images of the patients. Our methodology consists of convolutional neural network feature extraction, dimensionality reduction and feature selection with random projections, combination of image features to case-level representations, and the training and testing of a support vector machine classifier. Using clinical diagnosis as ground truth for DPN, we achieve an overall accuracy of 89% on a held-out test set, with sensitivity reaching 78% and specificity reaching 95%.


Assuntos
Diabetes Mellitus , Neuropatias Diabéticas , Neuropatias Diabéticas/diagnóstico , Fundo de Olho , Humanos , Aprendizado de Máquina , Fotografação , Medição de Risco
11.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 1992-1995, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018394

RESUMO

Diabetic Retinopathy (DR), the complication leading to vision loss, is generally graded according to the amalgamation of various structural factors in fundus photography such as number of microaneurysms, hemorrhages, vascular abnormalities, etc. To this end, Convolution Neural Network (CNN) with impressively representational power has been exhaustively utilized to address this problem. However, while existing multi-stream networks are costly, the conventional CNNs do not consider multiple levels of semantic context, which suffers from the loss of spatial correlations between the aforementioned DR-related signs. Therefore, this paper proposes a Densely Reversed Attention based CNN (DRAN) to leverage the learnable integration of channel-wise attention at multi-level features in a pretrained network for unambiguously involving spatial representations of important DR-oriented factors. Consequently, the proposed approach gains a quadratic weighted kappa of 85.6% on Kaggle DR detection dataset, which is competitive with the state-of-the-arts.


Assuntos
Diabetes Mellitus , Retinopatia Diabética , Microaneurisma , Atenção , Retinopatia Diabética/diagnóstico , Técnicas de Diagnóstico Oftalmológico , Humanos , Redes Neurais de Computação
13.
Stud Health Technol Inform ; 273: 136-141, 2020 Sep 04.
Artigo em Inglês | MEDLINE | ID: mdl-33087603

RESUMO

Specific predictive models for diabetes polyneuropathy based on screening methods, for example Nerve conduction studies (NCS, can reach up to AUC 65.8 - 84.7 % for the conditional diagnosis of DPN in primary care. Prediction methods that utilize data from personal health records deal with large non-specific datasets with different prediction methods. Li et al. utilized 30 independent variables, which allowed to implement a model with AUC = 0.8863 for a Multilayer perceptron (MLP). Linear regression (LR) based methods produced up to AUC = 0.8 %. This way, modern data mining and computational methods can be effectively adopted in clinical medicine to derive models that use patient-specific information to predict the development of diabetic polyneuropathy, however, there still is a space to improve the efficiency of the predictive models. The goal of this study is the implementation of machine learning methods for early risk identification of diabetes polyneuropathy based on structured electronic medical records. It was demonstrated that the machine learning methods allow to achieve up to 0.7982 precision, 0.8152 recall, 0.8064 f1-score, 0.8261 accuracy, and 0.8988 AUC using the neural network classifier.


Assuntos
Diabetes Mellitus , Aprendizado de Máquina , Humanos , Redes Neurais de Computação , Medição de Risco , Fatores de Risco
14.
Stud Health Technol Inform ; 273: 228-233, 2020 Sep 04.
Artigo em Inglês | MEDLINE | ID: mdl-33087617

RESUMO

Mobile health applications for diabetes are developed like never before and many patients use them for their personalized health needs. With increased use, an increased number of usability evaluations are performed to assure that the applications function as intended. In this review the goal was to determine what usability methods are currently used in the evaluation of mobile health applications for diabetes and how these are used. METHODS: A literature review was conducted to identify applicable studies in the databases ACM Digital Library, Cinahl and Pubmed between the years 2015 and 2020. After the inclusion and exclusion criteria were applied, 32 articles remained that were included in the final review. RESULTS: Most of the studies included one established usability engineering method such as an expert-based and/or user-based method or a validated questionnaire/instrument. Some also included a combination of these. Others used methods of their own design; commonly questionnaires and interviews either on their own or in combination. CONCLUSION: To achieve an adequate level of evidence and quality in the evaluation, it is important that at least one is an established usability engineering method or a validated instrument. This to assure and continue to build the evidence base in this area.


Assuntos
Diabetes Mellitus , Aplicativos Móveis , Telemedicina , Diabetes Mellitus/diagnóstico , Diabetes Mellitus/terapia , Humanos , PubMed , Inquéritos e Questionários
15.
JAMA ; 324(14): 1429-1438, 2020 10 13.
Artigo em Inglês | MEDLINE | ID: mdl-33048153

RESUMO

Importance: The prevalence of leading risk factors for morbidity and mortality in the US significantly varies across regions, states, and neighborhoods, but the extent these differences are associated with a person's place of residence vs the characteristics of the people who live in different places remains unclear. Objective: To estimate the degree to which geographic differences in leading risk factors are associated with a person's place of residence by comparing trends in health outcomes among individuals who moved to different areas or did not move. Design, Setting, and Participants: This retrospective cohort study estimated the association between the differences in the prevalence of uncontrolled chronic conditions across movers' destination and origin zip codes and changes in individuals' likelihood of uncontrolled chronic conditions after moving, adjusting for person-specific fixed effects, the duration of time since the move, and secular trends among movers and those who did not move. Electronic health records from the Veterans Health Administration were analyzed. The primary analysis included 5 342 207 individuals with at least 1 Veterans Health Administration outpatient encounter between 2008 and 2018 who moved zip codes exactly once or never moved. Exposures: The difference in the prevalence of uncontrolled chronic conditions between a person's origin zip code and destination zip code (excluding the individual mover's outcomes). Main Outcomes and Measures: Prevalence of uncontrolled blood pressure (systolic blood pressure level >140 mm Hg or diastolic blood pressure level >90 mm Hg), uncontrolled diabetes (hemoglobin A1c level >8%), obesity (body mass index >30), and depressive symptoms (2-item Patient Health Questionnaire score ≥2) per quarter-year during the 3 years before and the 3 years after individuals moved. Results: The study population included 5 342 207 individuals (mean age, 57.6 [SD, 17.4] years, 93.9% men, 72.5% White individuals, and 12.7% Black individuals), of whom 1 095 608 moved exactly once and 4 246 599 never moved during the study period. Among the movers, the change after moving in the prevalence of uncontrolled blood pressure was 27.5% (95% CI, 23.8%-31.3%) of the between-area difference in the prevalence of uncontrolled blood pressure. Similarly, the change after moving in the prevalence of uncontrolled diabetes was 5.0% (95% CI, 2.7%-7.2%) of the between-area difference in the prevalence of uncontrolled diabetes; the change after moving in the prevalence of obesity was 3.1% (95% CI, 2.0%-4.2%) of the between-area difference in the prevalence of obesity; and the change after moving in the prevalence of depressive symptoms was 15.2% (95% CI, 13.1%-17.2%) of the between-area difference in the prevalence of depressive symptoms. Conclusions and Relevance: In this retrospective cohort study of individuals receiving care at Veterans Health Administration facilities, geographic differences in prevalence were associated with a substantial percentage of the change in individuals' likelihood of poor blood pressure control or depressive symptoms, and a smaller percentage of the change in individuals' likelihood of poor diabetes control and obesity. Further research is needed to understand the source of these associations with a person's place of residence.


Assuntos
Transtorno Depressivo/epidemiologia , Diabetes Mellitus/epidemiologia , Migração Humana/estatística & dados numéricos , Hipertensão/epidemiologia , Obesidade/epidemiologia , Características de Residência/estatística & dados numéricos , Doença Crônica/epidemiologia , Doença Crônica/etnologia , Transtorno Depressivo/etnologia , Diabetes Mellitus/etnologia , Registros Eletrônicos de Saúde/estatística & dados numéricos , Feminino , Geografia Médica , Migração Humana/tendências , Humanos , Hipertensão/etnologia , Masculino , Pessoa de Meia-Idade , Obesidade/etnologia , Prevalência , Estudos Retrospectivos , Fatores de Risco , Fatores de Tempo , Incerteza , Estados Unidos/epidemiologia , Estados Unidos/etnologia , Serviços de Saúde para Veteranos Militares/estatística & dados numéricos
16.
Sci Rep ; 10(1): 16384, 2020 10 02.
Artigo em Inglês | MEDLINE | ID: mdl-33009426

RESUMO

The COVID-19 outbreak is becoming a public health emergency. Data are limited on the clinical characteristics and causes of death. A retrospective analysis of COVID-19 deaths were performed for patients' clinical characteristics, laboratory results, and causes of death. In total, 56 patients (72.7%) of the decedents (male-female ratio 51:26, mean age 71 ± 13, mean survival time 17.4 ± 8.4 days) had comorbidities. Acute respiratory failure (ARF) and sepsis were the main causes of death. Increases in C-reactive protein (CRP), lactate dehydrogenase (LDH), D-dimer and lactic acid and decreases in lymphocytes were common laboratory results. Intergroup analysis showed that (1) most female decedents had cough and diabetes. (2) The proportion of young- and middle-aged deaths was higher than elderly deaths for males, while elderly decedents were more prone to myocardial injury and elevated CRP. (3) CRP and LDH increased and cluster of differentiation (CD) 4+ and CD8+ cells decreased significantly in patients with hypertension. The majority of COVID-19 decedents are male, especially elderly people with comorbidities. The main causes of death are ARF and sepsis. Most female decedents have cough and diabetes. Myocardial injury is common in elderly decedents. Patients with hypertension are prone to an increased inflammatory index, tissue hypoxia and cellular immune injury.


Assuntos
Infecções por Coronavirus/mortalidade , Pneumonia Viral/mortalidade , Sepse/epidemiologia , Síndrome Respiratória Aguda Grave/epidemiologia , Fatores Etários , Idoso , Idoso de 80 Anos ou mais , Proteína C-Reativa/análise , Causas de Morte , China , Comorbidade , Infecções por Coronavirus/sangue , Infecções por Coronavirus/complicações , Infecções por Coronavirus/patologia , Diabetes Mellitus/epidemiologia , Feminino , Produtos de Degradação da Fibrina e do Fibrinogênio/análise , Cardiopatias/epidemiologia , Humanos , L-Lactato Desidrogenase/sangue , Ácido Láctico/sangue , Contagem de Linfócitos , Masculino , Pessoa de Meia-Idade , Pandemias , Pneumonia Viral/sangue , Pneumonia Viral/complicações , Pneumonia Viral/patologia , Sepse/etiologia , Síndrome Respiratória Aguda Grave/etiologia
17.
Medicine (Baltimore) ; 99(40): e22439, 2020 Oct 02.
Artigo em Inglês | MEDLINE | ID: mdl-33019426

RESUMO

BACKGROUND: The mortality rate associated with Covid-19 varies considerably among studies and determinants of this variability are not well characterized. METHODS: A systematic review of peer-reviewed literature published through March 31, 2020 was performed to estimate the mortality rate among hospitalized patients in China with a confirmed diagnosis of Covid-19. Hospital mortality rates were estimated using an inverse variance-weighted random-effects meta-analysis model. Funnel plot symmetry was evaluated for small-study effects, a one-study removed sensitivity analysis assessed the influence of individual studies on the pooled mortality rate, and metaregression assessed the association of potential confounding variables with mortality rates. RESULTS: The review included 16 observational studies involving 1832 hospitalized patients with a diagnosis of Covid-19. The surveillance period among studies ranged from December 16, 2019 to February 23, 2020. The median patient age was 53 years and 53% were males. A total of 38.5% of patients presented with at least 1 comorbidity, most commonly hypertension (24.0%), cardiac disease (15.1%), and diabetes mellitus (14.4%). Fever and cough, reported in 84.8% and 61.7% of patients respectively, were the most common patient symptoms. The pooled mortality rate was 9.9% (95% confidence interval 6.1% to 14.5%). Funnel plot asymmetry was not observed and the meta-analysis results were not substantially influenced by any single study since the pooled mortality rate ranged from 8.9% to 11.1% following iterative removal of one study at a time. Substantial heterogeneity in the mortality rate was identified among studies (I = 87%; P < .001). In a metaregression that included demographics, patient risk factors, and presenting symptoms, only a higher prevalence of diabetes mellitus was associated with a higher mortality rate (P = .03). CONCLUSIONS: In a meta-analysis of hospitalized patients in China with a diagnosis of Covid-19, the mortality rate was 9.9% and a higher diabetes mellitus prevalence was independently associated with a worse prognosis. The independent influence of diabetes mellitus with Covid-19 mortality should be viewed as hypothesis-generating and warrants further study.


Assuntos
Betacoronavirus , Infecções por Coronavirus/mortalidade , Complicações do Diabetes/mortalidade , Diabetes Mellitus/mortalidade , Mortalidade Hospitalar , Pneumonia Viral/mortalidade , Adulto , Idoso , Infecções por Coronavirus/complicações , Infecções por Coronavirus/virologia , Complicações do Diabetes/virologia , Diabetes Mellitus/virologia , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Pandemias , Pneumonia Viral/complicações , Pneumonia Viral/virologia , Prevalência , Fatores de Risco
18.
Med Hypotheses ; 143: 110185, 2020 Oct.
Artigo em Inglês | MEDLINE | ID: mdl-33017914

RESUMO

COVID-19 pandemic is spreading rapidly worldwide, and drug selection can affect the morbidity and mortality of the disease positively or negatively. Alpha-lipoic acid (ALA) is a potent antioxidant and reduces oxidative stress and inhibits activation of nuclear factor-kappa B (NF-kB). ALA reduces ADAM17 activity and ACE2 upregulation. ALA is known to have antiviral effects against some viruses. ALA may show antiviral effect by reducing NF-kB activation and alleviating redox reactions. ALA increases the intracellular glutathione strengthens the human host defense. ALA activates ATP dependent K+ channels (Na+, K+-ATPase). Increased K+ in the cell raises the intracellular pH. As the intracellular pH increases, the entry of the virus into the cell decreases. ALA can increase human host defense against SARS-CoV-2 by increasing intracellular pH. ALA treatment increases antioxidant levels and reduces oxidative stress. Thus, ALA may strengthen the human host defense against SARS-CoV-2 and can play a vital role in the treatment of patients with critically ill COVID-19. It can prevent cell damage by decreasing lactate production in patients with COVID-19. Using ALA with insulin in patients with diabetes can show a synergistic effect against SARS-CoV-2. We think ALA treatment will be beneficial against COVID-19 in patients with diabetes.


Assuntos
Proteína ADAM17/metabolismo , Infecções por Coronavirus/prevenção & controle , Complicações do Diabetes/prevenção & controle , NF-kappa B/metabolismo , Pandemias/prevenção & controle , Peptidil Dipeptidase A/metabolismo , Pneumonia Viral/prevenção & controle , Ácido Tióctico/uso terapêutico , Antioxidantes/uso terapêutico , Betacoronavirus , Infecções por Coronavirus/complicações , Complicações do Diabetes/virologia , Diabetes Mellitus/tratamento farmacológico , Humanos , Concentração de Íons de Hidrogênio , Insulina/metabolismo , Oxirredução , Estresse Oxidativo , Pneumonia Viral/complicações
19.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 1560-1563, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018290

RESUMO

The characteristics of diabetic retinopathy (DR) fundus images generally consist of multiple types of lesions which provided strong evidence for the ophthalmologists to make diagnosis. It is particularly significant to figure out an efficient method to not only accurately classify DR fundus images but also recognize all kinds of lesions on them. In this paper, a deep learning-based multi-label classification model with Gradient-weighted Class Activation Mapping (Grad-CAM) was proposed, which can both make DR classification and automatically locate the regions of different lesions. To reducing laborious annotation work and improve the efficiency of labeling, this paper innovatively considered different types of lesions as different labels for a fundus image so that this paper changed the task of lesion detection into that of image classification. A total of five labels were pre-defined and 3228 fundus images were collected for developing our model. The architecture of deep learning model was designed by ourselves based on ResNet. Through experiments on the test images, this method acquired a sensitive of 93.9% and a specificity of 94.4% on DR classification. Moreover, the corresponding regions of lesions were reasonably outlined on the DR fundus images.


Assuntos
Aprendizado Profundo , Diabetes Mellitus , Retinopatia Diabética , Retinopatia Diabética/diagnóstico por imagem , Fundo de Olho , Humanos , Sensibilidade e Especificidade
20.
Cardiovasc Diabetol ; 19(1): 164, 2020 10 01.
Artigo em Inglês | MEDLINE | ID: mdl-33004045

RESUMO

BACKGROUND: Cardiometabolic disorders may worsen Covid-19 outcomes. We investigated features and Covid-19 outcomes for patients with or without diabetes, and with or without cardiometabolic multimorbidity. METHODS: We collected and compared data retrospectively from patients hospitalized for Covid-19 with and without diabetes, and with and without cardiometabolic multimorbidity (defined as ≥ two of three risk factors of diabetes, hypertension or dyslipidaemia). Multivariate logistic regression was used to assess the risk of the primary composite outcome (any of mechanical ventilation, admission to an intensive care unit [ICU] or death) in patients with diabetes and in those with cardiometabolic multimorbidity, adjusting for confounders. RESULTS: Of 354 patients enrolled, those with diabetes (n = 81), compared with those without diabetes (n = 273), had characteristics associated with the primary composite outcome that included older age, higher prevalence of hypertension and chronic obstructive pulmonary disease (COPD), higher levels of inflammatory markers and a lower PaO2/FIO2 ratio. The risk of the primary composite outcome in the 277 patients who completed the study as of May 15th, 2020, was higher in those with diabetes (Adjusted Odds Ratio (adjOR) 2.04, 95%CI 1.12-3.73, p = 0.020), hypertension (adjOR 2.31, 95%CI: 1.37-3.92, p = 0.002) and COPD (adjOR 2.67, 95%CI 1.23-5.80, p = 0.013). Patients with cardiometabolic multimorbidity were at higher risk compared to patients with no cardiometabolic conditions (adjOR 3.19 95%CI 1.61-6.34, p = 0.001). The risk for patients with a single cardiometabolic risk factor did not differ with that for patients with no cardiometabolic risk factors (adjOR 1.66, 0.90-3.06, adjp = 0.10). CONCLUSIONS: Patients with diabetes hospitalized for Covid-19 present with high-risk features. They are at increased risk of adverse outcomes, likely because diabetes clusters with other cardiometabolic conditions.


Assuntos
Betacoronavirus , Doenças Cardiovasculares/diagnóstico , Doenças Cardiovasculares/epidemiologia , Infecções por Coronavirus/diagnóstico , Infecções por Coronavirus/epidemiologia , Diabetes Mellitus/diagnóstico , Diabetes Mellitus/epidemiologia , Pneumonia Viral/diagnóstico , Pneumonia Viral/epidemiologia , Idoso , Idoso de 80 Anos ou mais , Doenças Cardiovasculares/metabolismo , Infecções por Coronavirus/metabolismo , Diabetes Mellitus/metabolismo , Feminino , Seguimentos , Humanos , Masculino , Doenças Metabólicas/diagnóstico , Doenças Metabólicas/epidemiologia , Doenças Metabólicas/metabolismo , Pessoa de Meia-Idade , Multimorbidade/tendências , Pandemias , Pneumonia Viral/metabolismo , Prognóstico , Estudos Retrospectivos , Fatores de Risco
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA