We conducted a systematic review and meta-analysis of the diagnostic performance of current deep learning algorithms for the diagnosis of lung cancer. We searched major databases up to June 2022 to include studies that used artificial intelligence to diagnose lung cancer, using the histopathological analysis of true positive cases as a reference. The quality of the included studies was assessed independently by two authors based on the revised Quality Assessment of Diagnostic Accuracy Studies. Six studies were included in the analysis. The pooled sensitivity and specificity were 0.93 (95% CI 0.85–0.98) and 0.68 (95% CI 0.49–0.84), respectively. Despite the significantly high heterogeneity for sensitivity (I2 = 94%, p < 0.01) and specificity (I2 = 99%, p < 0.01), most of it was attributed to the threshold effect. The pooled SROC curve with a bivariate approach yielded an area under the curve (AUC) of 0.90 (95% CI 0.86 to 0.92). The DOR for the studies was 26.7 (95% CI 19.7–36.2) and heterogeneity was 3% (p = 0.40). In this systematic review and meta-analysis, we found that when using the summary point from the SROC, the pooled sensitivity and specificity of DL algorithms for the diagnosis of lung cancer were 93% and 68%, respectively.
This study showed a high prevalence of obesity in asthmatic patients. Obese and non-obese subjects were similar in regard to asthma severity and level of asthma control. Female sex was associated with obesity in this asthma population.
BACKGROUND: Health-related quality of life (HRQOL) has received much attention in patients with cystic fibrosis (CF). The goal of this study was to evaluate the association between clinical, lung function, sleep quality, and polysomnographic variables with 2 HRQOL questionnaires, the shorterversion World Health Organization Quality of Life (WHOQOL-BREF) and Cystic Fibrosis Quality of Life (CFQOL) questionnaires, in adult subjects with CF. METHODS: In a cross-sectional study, 51 subjects underwent clinical evaluation and overnight polysomnography and answered WHO-QOL-BREF, CFQOL, Pittsburgh Sleep Quality Index, and Epworth Sleepiness Scale questionnaires. In addition, pulmonary function tests, 6-min walk tests, and echocardiography were performed. RESULTS: For WHOQOL-BREF scores, the sleep quality index was associated with the physical domain; the percent-of-predicted 6-min walk distance (6MWD) and sleepiness scale were associated with the psychological domain; the percent-of-predicted FEV 1 and sleep quality index were associated with the social relationship domain; and the sleep quality index was associated with the environment domain. For CFQOL scores, age at diagnosis, clinical score, and sleep quality index were associated with the physical functioning domain; the percent-of-predicted 6MWD and pulmonary arterial systolic pressure were associated with the role domain; sex and sleep quality index were associated with the vitality domain; the apnea-hypopnea index was associated with the emotional functioning domain; sex and body mass index (BMI) were associated with the body image domain; the percent-of-predicted 6MWD and sleep quality index were associated with the health perception domain; age, sex, BMI, and arousal index were associated with the weight domain; age, sex, percent-of-predicted FEV 1 , percent-of-predicted 6MWD, and pulmonary arterial systolic pressure were associated with the respiratory symptom domain; and the clinical score was associated with the digestive symptom domain. CONCLUSIONS: The sleep quality index score, 6MWD, sleepiness scale score, and FEV 1 were predictors of WHOQOL-BREF scores. Age at diagnosis, clinical score, sleep quality score, 6MWD, sex, apnea-hypopnea index, BMI, current age, arousal index, FEV 1 , and pulmonary arterial systolic pressure were predictors of CFQOL scores.
ResumoEste estudo objetivou identificar o perfil antropométrico e bioquímico e analisar a evolução do ganho de peso dos profissionais do Serviço de Nutrição e Dietética (SND) do Hospital de Clínicas de Porto Alegre (HCPA). Estudo de caráter longitudinal retrospectivo, com 190 funcionários. Aplicou-se questionário estruturado e foram realizadas análises bioquímicas e avaliação antropométrica. Observou-se excesso de peso em 60,8% dos funcionários. O ganho de peso encontrou-se associado ao tempo de serviço, turno de trabalho e prática de atividade física. O estudo demonstrou que 1 ano a mais de trabalho esteve associado ao ganho de peso médio de 500 g, o turno de trabalho com ganho de peso médio de 4 kg e a prática de atividade física com perda de peso médio de 3,3 kg. A associação entre ganho de peso, tempo e turno de trabalho em colaboradores de serviços de nutrição remete à necessidade de criação de programas de educação nutricional que promovam hábitos alimentares saudáveis.Palavras-chave: antropometria; categorias de trabalhadores; ganho de peso. AbstractThis study aimed to identify anthropometric and biochemical status and to analyze the weight gain of collaborators of nutrition and dietetics services of Hospital de Clínicas de Porto Alegre (HCPA). This was a retrospective longitudinal study enrolled 190 employees. Nutritional assessment and clinical analysis was measurement. A structured questionnaire was applied all employees. The prevalence of excess weight was 60.8%. Weight gain was significantly associated to length of service, working shift and physical activity. The study showed that an additional year of work was associated with weight gain around 500 g, the shift in average gain of 4 kg and physical activity with average weight loss of 3.3 kg. The association between weight gain, working time and working shift in employees refers to the need to create nutrition intervention program aiming to promote healthy eating habits.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.