Explore the vast range of titles available.

The number of publications on deep learning for cancer diagnostics is rapidly increasing, and systems are frequently claimed to perform comparable with or better than clinicians. However, few systems have yet demonstrated real-world medical utility. In this Perspective, we discuss reasons for the moderate progress and describe remedies designed to facilitate transition to the clinic. Recent, presumably influential, deep learning studies in cancer diagnostics, of which the vast majority used images as input to the system, are evaluated to reveal the status of the field. By manipulating real data, we then exemplify that much and varied training data facilitate the generalizability of neural networks and thus the ability to use them clinically. To reduce the risk of biased performance estimation of deep learning systems, we advocate evaluation in external cohorts and strongly advise that the planned analyses, including a predefined primary analysis, are described in a protocol preferentially stored in an online repository. Recommended protocol items should be established for the field, and we present our suggestions.The number of publications on deep learning for cancer diagnostics is rapidly increasing, but clinical translation is slow. This Perspective advocates performance estimation in external cohorts and strongly advises that a primary analysis is predefined in a standardized protocol preferentially stored in an online repository.

Gastric cancer remains a major cause of cancer-related mortality worldwide. The temporal trends for this malignancy, however, are dynamic, and reports from the past decade indicate important declines in some regions and demographic groups, as well as a few notable exceptions in which gastric cancer rates are either stable or increasing. Two main anatomical subtypes of gastric cancer exist, non-cardia and cardia, with different temporal trends and risk factors (such as obesity and reflux for cardia gastric cancer and Helicobacter pylori infection for non-cardia gastric cancer). Shifts in the distribution of anatomical locations have been detected in several high-incidence regions. H. pylori is an important aetiological factor for gastric cancer; importantly, the anticipated long-term findings from studies examining the effect of H. pylori eradication on the risk of (re)developing gastric cancer have emerged in the past few years. In this Review, we highlight the latest trends in incidence and mortality using an evidence-based approach. We make the best possible inferences, including clinical and public health inference, on the basis of the quality of the evidence available, and highlight burning questions as well as gaps in knowledge and public health practice that need to be addressed to reduce gastric cancer burden worldwide.Globally, gastric cancer is a common and highly fatal cancer with two anatomical subtypes, non-cardia and cardia gastric cancer. Helicobacter pylori causes almost 90% of distal gastric cancers worldwide. The authors of this Review summarize the current epidemiology of gastric cancer and the evidence and implications of primary and secondary prevention efforts.

Rheumatoid arthritis (RA) is a systemic autoimmune disease that predominantly affects the joints. The prevalence of RA varies globally, with generally a higher prevalence in industrialized countries, which may be explained by exposures to environmental risk factors, but also by genetic factors, differing demographics and under-reporting in other parts of the world. Over the past three decades, strong trends of the declining severity of RA probably reflect changes in treatment paradigms and overall better management of the disease. Other trends include increasing RA prevalence. Common risk factors for RA include both modifiable lifestyle-associated variables and non-modifiable features, such as genetics and sex. A better understanding of the natural history of RA, and of the factors that contribute to the development of RA in specific populations, might lead to the introduction of specific prevention strategies for this debilitating disease.In this Review, the authors summarize and discuss regional differences in the prevalence and incidence of rheumatoid arthritis (RA), and describe temporal trends associated with the disease as well as evidence related to risk factors.

In countries with a high incidence of tuberculosis, the typical clinical features of Crohn's disease (CD) may be covered up after tuberculosis infection, and the identification of atypical Crohn's disease and intestinal tuberculosis (ITB) is still a dilemma for clinicians. Least absolute shrinkage and selection operator (LASSO) regression has been applied to select variables in disease diagnosis. However, its value in discriminating ITB and atypical Crohn's disease remains unknown. A total of 400 patients were enrolled from January 2014 to January 2019 in second Xiangya hospital Central South University.Among them, 57 indicators including clinical manifestations, laboratory results, endoscopic findings, computed tomography enterography features were collected for further analysis. R software version 3.6.1 (glmnet package) was used to perform the LASSO logistic regression analysis. SPSS 20.0 was used to perform Pearson chi-square test and binary logistic regression analysis. In the variable selection step, LASSO regression and Pearson chi-square test were applied to select the most valuable variables as candidates for further logistic regression analysis. Secondly, variables identified from step 1 were applied to construct binary logistic regression analysis. Receiver operating characteristic (ROC) curve analysis was performed on these models to assess the ability and the optimal cutoff value for diagnosis. The area under the ROC curve (AUC), sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy rate, together with their 95% confidence and intervals (CIs) were calculated. MedCalc software (Version 16.8) was applied to analyze the ROC curves of models. 332 patients were eventually enrolled to build a binary logistic regression model to discriminate CD (including comprehensive CD and tuberculosis infected CD) and ITB. However, we did not get a satisfactory diagnostic value via applying the binary logistic regression model of comprehensive CD and ITB to predict tuberculosis infected CD and ITB (accuracy rate:79.2%VS 65.1%). Therefore, we further established a binary logistic regression model to discriminate atypical CD from ITB, based on Pearsonchi-square test (model1) and LASSO regression (model 2). Model 1 showed 89.9% specificity, 65.9% sensitivity, 88.5% PPV, 68.9% NPV, 76.9% diagnostic accuracy, and an AUC value of 0.811, and model 2 showed 80.6% specificity, 84.4% sensitivity, 82.3% PPV, 82.9% NPV, 82.6% diagnostic accuracy, and an AUC value of 0.887. The comparison of AUCs between model1 and model2 was statistically different (P < 0.05). Tuberculosis infection increases the difficulty of discriminating CD from ITB. LASSO regression showed a more efficient ability than Pearson chi-square test based logistic regression on differential diagnosing atypical CD and ITB.

Over the past several decades, the incidence of early-onset cancers, often defined as cancers diagnosed in adults <50 years of age, in the breast, colorectum, endometrium, oesophagus, extrahepatic bile duct, gallbladder, head and neck, kidney, liver, bone marrow, pancreas, prostate, stomach and thyroid has increased in multiple countries. Increased use of screening programmes has contributed to this phenomenon to a certain extent, although a genuine increase in the incidence of early-onset forms of several cancer types also seems to have emerged. Evidence suggests an aetiological role of risk factor exposures in early life and young adulthood. Since the mid-20th century, substantial multigenerational changes in the exposome have occurred (including changes in diet, lifestyle, obesity, environment and the microbiome, all of which might interact with genomic and/or genetic susceptibilities). However, the effects of individual exposures remain largely unknown. To study early-life exposures and their implications for multiple cancer types will require prospective cohort studies with dedicated biobanking and data collection technologies. Raising awareness among both the public and health-care professionals will also be critical. In this Review, we describe changes in the incidence of early-onset cancers globally and suggest measures that are likely to reduce the burden of cancers and other chronic non-communicable diseases.The incidence of early-onset forms of many cancers (defined as cancers diagnosed in individuals <50 years of age) has increased in a number of countries over the past several decades. The underlying reasons for this apparent increase probably include greater use of screening programmes, but also changing patterns in early-life exposures. In this Review, the authors describe the emerging global increase in the incidence of early-onset cancers and suggest changes that might address this situation.

Anecdotal evidence suggests that Coronavirus disease 2019 (COVID-19), caused by the coronavirus SARS-CoV-2, exhibits differences in morbidity and mortality between sexes. Here, we present a meta-analysis of 3,111,714 reported global cases to demonstrate that, whilst there is no difference in the proportion of males and females with confirmed COVID-19, male patients have almost three times the odds of requiring intensive treatment unit (ITU) admission (OR = 2.84; 95% CI = 2.06, 3.92) and higher odds of death (OR = 1.39; 95% CI = 1.31, 1.47) compared to females. With few exceptions, the sex bias observed in COVID-19 is a worldwide phenomenon. An appreciation of how sex is influencing COVID-19 outcomes will have important implications for clinical management and mitigation strategies for this disease. Anecdotal reports suggest potential severity and outcome differences between sexes following infection by SARS-CoV-2. Here, the authors perform meta-analyses of more than 3 million cases collected from global public data to demonstrate that male patients with COVID-19 are 3 times more likely to require intensive care, and have ~40% higher death rate.

The global prevalence of atrial fibrillation (AF) has increased substantially over the past three decades and is currently approximately 60 million cases. Incident AF and its clinical consequences are largely the result of risk factors that can be modified by lifestyle changes. In this Review, we provide evidence that the lifetime risk of AF is modified not only by sex and race but also through the clinical risk factor and comorbidity burden of individual patients. We begin by summarizing the epidemiology of AF, focusing on non-modifiable and modifiable risk factors, as well as targets and strategies for the primary prevention of AF. Furthermore, we evaluate the role of modifiable risk factors in the secondary prevention of AF as well as the potential effects of risk factor interventions on the frequency and severity of subsequent AF episodes. We end the Review by proposing strategies that require evaluation as well as global policy changes that are needed for the prevention of incident AF and the management of recurrent episodes in patients already affected by AF.The global prevalence of atrial fibrillation (AF) is increasing, largely as a result of a rise in modifiable risk factors. In this Review, Sanders and colleagues summarize the epidemiology of AF and discuss lifestyle changes and risk factor interventions for the primary and secondary prevention of AF.

Globally, ovarian cancer is the eighth most common cancer in women, accounting for an estimated 3.7% of cases and 4.7% of cancer deaths in 2020. Until the early 2000s, age-standardized incidence was highest in northern Europe and North America, but this trend has changed; incidence is now declining in these regions and increasing in parts of eastern Europe and Asia. Ovarian cancer is a very heterogeneous disease and, even among the most common type, namely epithelial ovarian cancer, five major clinically and genetically distinct histotypes exist. Most high-grade serous ovarian carcinomas are now recognized to originate in the fimbrial ends of the fallopian tube. This knowledge has led to more cancers being coded as fallopian tube in origin, which probably explains some of the apparent declines in ovarian cancer incidence, particularly in high-income countries; however, it also suggests that opportunistic salpingectomy offers an important opportunity for prevention. The five histotypes share several reproductive and hormonal risk factors, although differences also exist. In this Review, we summarize the epidemiology of this complex disease, comparing the different histotypes, and consider the potential for prevention. We also discuss how changes in the prevalence of risk and protective factors might have contributed to the observed changes in incidence and what this might mean for incidence in the future.Ovarian cancer, accounting for 4.7% of cancer deaths in women in 2020, remains highly prevalent globally. Nonetheless, owing to changes in environmental exposures, the approach to preventive measures and disease classification, both incidence and mortality have been declining in economically developed countries since the early 2000s. Conversely, parts of Asia and eastern Europe have seen increases in the incidence of ovarian cancer over this period of time. In this Review, the authors summarize the epidemiology of ovarian cancer, including the roles of the various risk factors and the potential for prevention.

Bladder cancer is among the ten most common cancers globally, causes considerable morbidity and mortality and is, therefore, a substantial burden for health-care systems. The incidence of bladder cancer is affected by demographic trends, most notably population growth and ageing, as well as exposure to risk factors, especially tobacco smoking. Consequently, the incidence has not been stable throughout the world over time, nor will it be in the near future. Further primary prevention efforts are of the utmost importance to reduce the medical and financial burden of bladder cancer on populations and health-care systems. Simultaneously, less-invasive and lower-cost approaches for the diagnosis of both primary and recurrent bladder cancers are required to address challenges posed by the increasing shortage of health-care professionals and limited financial resources worldwide. In this regard, urinary biomarkers have demonstrated promising diagnostic accuracy and efficiency. Awareness of the risk factors and symptoms of bladder cancer should also be increased in society, particularly among health-care professionals and high-risk groups. Studies investigating the associations between lifestyle factors and bladder cancer outcomes are scarce and should be a research priority. In this Review, we outline global trends in bladder cancer incidence and mortality, and discuss the main risk factors influencing bladder cancer occurrence and outcomes. We then discuss the implications, challenges and opportunities of these epidemiological trends for public health and clinical practice.Bladder cancer is among the ten most common cancers worldwide and therefore constitutes a substantial health-care burden. This Review summarizes the global trends in bladder cancer incidence and mortality, and describes the main risk factors associated with bladder cancer occurrence and outcomes. The implications, challenges and opportunities of these epidemiological trends for public health and clinical practice are also discussed.

Despite contributing to healthy diets for billions of people, aquatic foods are often undervalued as a nutritional solution because their diversity is often reduced to the protein and energy value of a single food type (‘seafood’ or ‘fish’) 1 , 2 , 3 – 4 . Here we create a cohesive model that unites terrestrial foods with nearly 3,000 taxa of aquatic foods to understand the future impact of aquatic foods on human nutrition. We project two plausible futures to 2030: a baseline scenario with moderate growth in aquatic animal-source food (AASF) production, and a high-production scenario with a 15-million-tonne increased supply of AASFs over the business-as-usual scenario in 2030, driven largely by investment and innovation in aquaculture production. By comparing changes in AASF consumption between the scenarios, we elucidate geographic and demographic vulnerabilities and estimate health impacts from diet-related causes. Globally, we find that a high-production scenario will decrease AASF prices by 26% and increase their consumption, thereby reducing the consumption of red and processed meats that can lead to diet-related non-communicable diseases 5 , 6 while also preventing approximately 166 million cases of inadequate micronutrient intake. This finding provides a broad evidentiary basis for policy makers and development stakeholders to capitalize on the potential of aquatic foods to reduce food and nutrition insecurity and tackle malnutrition in all its forms. Data on the nutrient content of almost 3,000 aquatic animal-source foods is combined with a food-systems model to show that an increase in aquatic-food production could reduce the inadequate intake of most nutrients.