RESUMO
Background: In 2020, our center established a Tanner-Whitehouse 3 (TW3) artificial intelligence (AI) system using a convolutional neural network (CNN), which was built upon 9059 radiographs. However, the system, upon which our study is based, lacked a gold standard for comparison and had not undergone thorough evaluation in different working environments. Methods: To further verify the applicability of the AI system in clinical bone age assessment (BAA) and to enhance the accuracy and homogeneity of BAA, a prospective multi-center validation was conducted. This study utilized 744 left-hand radiographs of patients, ranging from 1 to 20 years of age, with 378 boys and 366 girls. These radiographs were obtained from nine different children's hospitals between August and December 2020. The BAAs were performed using the TW3 AI system and were also reviewed by experienced reviewers. Bone age accuracy within 1 year, root mean square error (RMSE), and mean absolute error (MAE) were statistically calculated to evaluate the accuracy. Kappa test and Bland-Altman (B-A) plot were conducted to measure the diagnostic consistency. Results: The system exhibited a high level of performance, producing results that closely aligned with those of the reviewers. It achieved a RMSE of 0.52 years and an accuracy of 94.55% for the radius, ulna, and short bones series. When assessing the carpal series of bones, the system achieved a RMSE of 0.85 years and an accuracy of 80.38%. Overall, the system displayed satisfactory accuracy and RMSE, particularly in patients over 7 years old. The system excelled in evaluating the carpal bone age of patients aged 1-6. Both the Kappa test and B-A plot demonstrated substantial consistency between the system and the reviewers, although the model encountered challenges in consistently distinguishing specific bones, such as the capitate. Furthermore, the system's performance proved acceptable across different genders and age groups, as well as radiography instruments. Conclusions: In this multi-center validation, the system showcased its potential to enhance the efficiency and consistency of healthy delivery, ultimately resulting in improved patient outcomes and reduced healthcare costs.
RESUMO
Background: The global burden of digestive diseases has been rising in the last 30 years. The rates and trends of incidence, deaths, and disability-adjusted life-years (DALYs) for digestive diseases need to be investigated. Methods: We extracted the data on overall digestive diseases and by cause between 1990-2019 from the Global Burden of Diseases 2019 website, including the absolute number and the corresponding age-standardized rates of incidence (ASIR), deaths (ASDR), and DALYs (ASDALYs). Results: Globally, the incident cases, deaths, and DALYs of digestive diseases in 2019 increased by 74.44, 37.85, and 23.46%, respectively, compared with that in 1990, with an increasing ASIR of 0.09%, as well as decreasing ASDR and ASDALYs of 1.38 and 1.32% annually. The sociodemographic index (SDI) of overall digestive diseases showed a slight increase in ASIR from low to middle-low regions. The downtrend in ASDR and ASDALYs was found in all SDI regions. The burden of incidence was higher in females, while the burden of deaths and DALYs was higher in males for the overall digestive diseases and most causes. The estimated annual percentage changes were significantly associated with the baseline ASIR, ASDR, and ASDALYs for the overall digestive diseases, and the negative correlations between ASDR, ASDALYs, and human development index both in 1990 (R = -0.68, R = -0.69) and 2019 (R = -0.71, R = -0.73) were noticed. Conclusion: The findings indicate that digestive diseases remain a significant public health burden, with substantial variation across countries, sexes, and age groups. Therefore, implementing age, gender, and country-specific policies for early screening and targeted interventions could significantly reduce the global burden of digestive diseases.
Assuntos
Carga Global da Doença , Políticas , Feminino , Humanos , Masculino , Saúde PúblicaRESUMO
OBJECTIVES: The global burden of heart disease is severe and increasing in the coming years. This study aims to analyze the global burden of heart disease. STUDY DESIGN: Rheumatic heart disease (RHD), ischemic heart disease (IHD), hypertensive heart disease (HHD), and non-rheumatic valvular heart disease (NRVHD) were selected and analyzed from the Global Burden of Disease Study 2019. METHODS: The prevalence, deaths, disability-adjusted life years and their corresponding age-standardized rates were obtained from the Global Burden of Disease Study 2019. In addition, estimated annual percentage change was calculated to better assess epidemiological trends. In addition, we performed an age-period-cohort analysis using the Nordpred package in R program to predict death trends over the next 20 years. RESULTS: Globally, the prevalence of four heart diseases (RHD, IHD, HHD, and NRVHD) increased by 70.5%, 103.5%, 137.9%, and 110.0% compared with 1990, respectively. The deaths cases of RHD decreased by 15.6%, whereas IHD, HHD, and NRVHD increased by 60.4%, 76.6%, and 110.6%. Compared with absolute values, their corresponding age-standardized rates only showed a slight increase trend or even decreased in some areas with high sociodemographic index. In the next 20 years, the absolute values of deaths will continue to increase, whereas their age-standardized rates of deaths will flatten out. CONCLUSIONS: Globally, the absolute values of heart disease have increased over the past 30 years and will continue to increase over the next 20 years. Targeted prevention and control strategies and measures need to be developed and improved to reduce this burden.
Assuntos
Isquemia Miocárdica , Cardiopatia Reumática , Humanos , Adulto Jovem , Adulto , Carga Global da Doença , Anos de Vida Ajustados por Qualidade de Vida , Saúde Global , Isquemia Miocárdica/epidemiologia , Cardiopatia Reumática/epidemiologiaRESUMO
BACKGROUND: Smoke-free policies have led to a decline in smoking prevalence. Nevertheless, as the global population grows, more non-smokers are exposed to second-hand smoke (SHS) hazards. Mitigating SHS hazards requires a systematic analysis of the global disease burden attributable to SHS. METHODS: Data on SHS was extracted from the Global Burden of Disease Study 2019. First, we measured the disease burden of SHS by the number of cases and age-standardized rates of deaths, disability-adjusted life years (DALYs), years lived with disability (YLDs), and years of life lost (YLLs) from 1990 to 2019. Second, trends in the disease burden of SHS in different periods were estimated based on the annual percentage change (APC) by joinpoint regression analysis. Finally, using histogram plots, world maps, Pearson correlation analysis, and population attributable fraction (PAF), we conducted a stratified analysis of SHS exposure by sex, age, geographic location, sociodemographic index (SDI) level, and disease. RESULTS: The number of deaths caused by SHS remained stable between 1990 and 2019, and the number of YLDs more than doubled in three decades. In contrast, the number of DALYs and YLLs caused by SHS decreased. The declining trend in deaths (APCâ¯=â¯-1.42â¯% [95â¯% UI -1.79â¯%, -1.05â¯%]), DALYs (APCâ¯=â¯-1.91â¯% [95â¯% UI -2.15â¯%, -1.67â¯%]), and YLLs (APCâ¯=â¯-1.28â¯% [95â¯% UI -1.93â¯%, -0.64â¯%]) had slowed down in recent years, while SHS-related YLDs were still increasing (APCâ¯=â¯1.84â¯% [95â¯% UI 0.74â¯%, 2.96â¯%]). From 2010 to 2019, we found that SHS exposure increased the risk of tracheal, bronchus, and lung cancer (PAF increased by 11.75â¯%), breast cancer (PAF increased by 5.36â¯%), diabetes mellitus (PAF increased by 8.24â¯%), and ischemic heart disease (PAF increased by 4.46â¯%). In addition, the disease burden caused by SHS was highest in middle SDI and low-middle SDI countries. CONCLUSION: The global disease burden attributable to SHS is still severe, and policymakers need to implement more effective measures to reduce the harm of SHS.