Showing papers by "University of Sydney published in 2019"

Canagliflozin and Renal Outcomes in Type 2 Diabetes and Nephropathy

Abstract: Background Type 2 diabetes mellitus is the leading cause of kidney failure worldwide, but few effective long-term treatments are available. In cardiovascular trials of inhibitors of sodium...

Haemodynamic definitions and updated clinical classification of pulmonary hypertension.

Abstract: Since the 1st World Symposium on Pulmonary Hypertension (WSPH) in 1973, pulmonary hypertension (PH) has been arbitrarily defined as mean pulmonary arterial pressure (mPAP) ≥25 mmHg at rest, measured by right heart catheterisation. Recent data from normal subjects has shown that normal mPAP was 14.0±3.3 mmHg. Two standard deviations above this mean value would suggest mPAP >20 mmHg as above the upper limit of normal (above the 97.5th percentile). This definition is no longer arbitrary, but based on a scientific approach. However, this abnormal elevation of mPAP is not sufficient to define pulmonary vascular disease as it can be due to an increase in cardiac output or pulmonary arterial wedge pressure. Thus, this 6th WSPH Task Force proposes to include pulmonary vascular resistance ≥3 Wood Units in the definition of all forms of pre-capillary PH associated with mPAP >20 mmHg. Prospective trials are required to determine whether this PH population might benefit from specific management. Regarding clinical classification, the main Task Force changes were the inclusion in group 1 of a subgroup “pulmonary arterial hypertension (PAH) long-term responders to calcium channel blockers”, due to the specific prognostic and management of these patients, and a subgroup “PAH with overt features of venous/capillaries (pulmonary veno-occlusive disease/pulmonary capillary haemangiomatosis) involvement”, due to evidence suggesting a continuum between arterial, capillary and vein involvement in PAH.

Clinical Targets for Continuous Glucose Monitoring Data Interpretation: Recommendations From the International Consensus on Time in Range

Abstract: Improvements in sensor accuracy, greater convenience and ease of use, and expanding reimbursement have led to growing adoption of continuous glucose monitoring (CGM). However, successful utilization of CGM technology in routine clinical practice remains relatively low. This may be due in part to the lack of clear and agreed-upon glycemic targets that both diabetes teams and people with diabetes can work toward. Although unified recommendations for use of key CGM metrics have been established in three separate peer-reviewed articles, formal adoption by diabetes professional organizations and guidance in the practical application of these metrics in clinical practice have been lacking. In February 2019, the Advanced Technologies & Treatments for Diabetes (ATTD) Congress convened an international panel of physicians, researchers, and individuals with diabetes who are expert in CGM technologies to address this issue. This article summarizes the ATTD consensus recommendations for relevant aspects of CGM data utilization and reporting among the various diabetes populations.

Short-Term Residential Load Forecasting Based on LSTM Recurrent Neural Network

Abstract: As the power system is facing a transition toward a more intelligent, flexible, and interactive system with higher penetration of renewable energy generation, load forecasting, especially short-term load forecasting for individual electric customers plays an increasingly essential role in the future grid planning and operation. Other than aggregated residential load in a large scale, forecasting an electric load of a single energy user is fairly challenging due to the high volatility and uncertainty involved. In this paper, we propose a long short-term memory (LSTM) recurrent neural network-based framework, which is the latest and one of the most popular techniques of deep learning, to tackle this tricky issue. The proposed framework is tested on a publicly available set of real residential smart meter data, of which the performance is comprehensively compared to various benchmarks including the state-of-the-arts in the field of load forecasting. As a result, the proposed LSTM approach outperforms the other listed rival algorithms in the task of short-term load forecasting for individual residential households.

Chronic pain as a symptom or a disease: the IASP Classification of Chronic Pain for the International Classification of Diseases (ICD-11).

Abstract: Chronic pain is a major source of suffering. It interferes with daily functioning and often is accompanied by distress. Yet, in the International Classification of Diseases, chronic pain diagnoses are not represented systematically. The lack of appropriate codes renders accurate epidemiological investigations difficult and impedes health policy decisions regarding chronic pain such as adequate financing of access to multimodal pain management. In cooperation with the WHO, an IASP Working Group has developed a classification system that is applicable in a wide range of contexts, including pain medicine, primary care, and low-resource environments. Chronic pain is defined as pain that persists or recurs for more than 3 months. In chronic pain syndromes, pain can be the sole or a leading complaint and requires special treatment and care. In conditions such as fibromyalgia or nonspecific low-back pain, chronic pain may be conceived as a disease in its own right; in our proposal, we call this subgroup "chronic primary pain." In 6 other subgroups, pain is secondary to an underlying disease: chronic cancer-related pain, chronic neuropathic pain, chronic secondary visceral pain, chronic posttraumatic and postsurgical pain, chronic secondary headache and orofacial pain, and chronic secondary musculoskeletal pain. These conditions are summarized as "chronic secondary pain" where pain may at least initially be conceived as a symptom. Implementation of these codes in the upcoming 11th edition of International Classification of Diseases will lead to improved classification and diagnostic coding, thereby advancing the recognition of chronic pain as a health condition in its own right.

Libra R-CNN: Towards Balanced Learning for Object Detection

Abstract: Compared with model architectures, the training process, which is also crucial to the success of detectors, has received relatively less attention in object detection. In this work, we carefully revisit the standard training practice of detectors, and find that the detection performance is often limited by the imbalance during the training process, which generally consists in three levels - sample level, feature level, and objective level. To mitigate the adverse effects caused thereby, we propose Libra R-CNN, a simple but effective framework towards balanced learning for object detection. It integrates three novel components: IoU-balanced sampling, balanced feature pyramid, and balanced L1 loss, respectively for reducing the imbalance at sample, feature, and objective level. Benefitted from the overall balanced design, Libra R-CNN significantly improves the detection performance. Without bells and whistles, it achieves 2.5 points and 2.0 points higher Average Precision (AP) than FPN Faster R-CNN and RetinaNet respectively on MSCOCO.

Genome-wide gene-based analyses of weight loss interventions identify a potential role for NKX6.3 in metabolism.

Abstract: Hundreds of genetic variants have been associated with Body Mass Index (BMI) through genome-wide association studies (GWAS) using observational cohorts. However, the genetic contribution to efficient weight loss in response to dietary intervention remains unknown. We perform a GWAS in two large low-caloric diet intervention cohorts of obese participants. Two loci close to NKX6.3/MIR486 and RBSG4 are identified in the Canadian discovery cohort (n = 1166) and replicated in the DiOGenes cohort (n = 789). Modulation of HGTX (NKX6.3 ortholog) levels in Drosophila melanogaster leads to significantly altered triglyceride levels. Additional tissue-specific experiments demonstrate an action through the oenocytes, fly hepatocyte-like cells that regulate lipid metabolism. Our results identify genetic variants associated with the efficacy of weight loss in obese subjects and identify a role for NKX6.3 in lipid metabolism, and thereby possibly weight control. Individuals show large variability in their capacity to lose weight and maintain this weight. Here, the authors perform GWAS in two weight loss intervention cohorts and identify two genetic loci associated with weight loss that are taken forward for Bayesian fine-mapping and functional assessment in flies.

Energy Minimization for Wireless Communication With Rotary-Wing UAV

Abstract: This paper studies unmanned aerial vehicle (UAV)-enabled wireless communication, where a rotary-wing UAV is dispatched to communicate with multiple ground nodes (GNs). We aim to minimize the total UAV energy consumption, including both propulsion energy and communication related energy, while satisfying the communication throughput requirement of each GN. To this end, we first derive a closed-form propulsion power consumption model for rotary-wing UAVs, and then formulate the energy minimization problem by jointly optimizing the UAV trajectory and communication time allocation among GNs, as well as the total mission completion time. The problem is difficult to be optimally solved, as it is non-convex and involves infinitely many variables over time. To tackle this problem, we first consider the simple fly-hover-communicate design, where the UAV successively visits a set of hovering locations and communicates with one corresponding GN while hovering at each location. For this design, we propose an efficient algorithm to optimize the hovering locations and durations, as well as the flying trajectory connecting these hovering locations, by leveraging the travelling salesman problem with neighborhood and convex optimization techniques. Next, we consider the general case, where the UAV also communicates while flying. We propose a new path discretization method to transform the original problem into a discretized equivalent with a finite number of optimization variables, for which we obtain a high-quality suboptimal solution by applying the successive convex approximation technique. The numerical results show that the proposed designs significantly outperform the benchmark schemes.

Updated Analysis of KEYNOTE-024: Pembrolizumab Versus Platinum-Based Chemotherapy for Advanced Non–Small-Cell Lung Cancer With PD-L1 Tumor Proportion Score of 50% or Greater

Abstract: PurposeIn the randomized, open-label, phase III KEYNOTE-024 study, pembrolizumab significantly improved progression-free survival and overall survival (OS) compared with platinum-based chemotherapy in patients with previously untreated advanced non–small-cell lung cancer (NSCLC) with a programmed death ligand 1 tumor proportion score of 50% or greater and without EGFR/ALK aberrations. We report an updated OS and tolerability analysis, including analyses adjusting for potential bias introduced by crossover from chemotherapy to pembrolizumab.Patients and MethodsPatients were randomly assigned to pembrolizumab 200 mg every 3 weeks (for up to 2 years) or investigator’s choice of platinum-based chemotherapy (four to six cycles). Patients assigned to chemotherapy could cross over to pembrolizumab upon meeting eligibility criteria. The primary end point was progression-free survival; OS was an important key secondary end point. Crossover adjustment analysis was done using the following three methods: simplified ...

Scientists' Warning to Humanity: Microorganisms and Climate Change

Abstract: In the Anthropocene, in which we now live, climate change is impacting most life on Earth. Microorganisms support the existence of all higher trophic life forms. To understand how humans and other life forms on Earth (including those we are yet to discover) can withstand anthropogenic climate change, it is vital to incorporate knowledge of the microbial 'unseen majority'. We must learn not just how microorganisms affect climate change (including production and consumption of greenhouse gases) but also how they will be affected by climate change and other human activities. This Consensus Statement documents the central role and global importance of microorganisms in climate change biology. It also puts humanity on notice that the impact of climate change will depend heavily on responses of microorganisms, which are essential for achieving an environmentally sustainable future.

Benchmarking Single-Image Dehazing and Beyond

Abstract: We present a comprehensive study and evaluation of existing single-image dehazing algorithms, using a new large-scale benchmark consisting of both synthetic and real-world hazy images, called REalistic Single-Image DEhazing (RESIDE). RESIDE highlights diverse data sources and image contents, and is divided into five subsets, each serving different training or evaluation purposes. We further provide a rich variety of criteria for dehazing algorithm evaluation, ranging from full-reference metrics to no-reference metrics and to subjective evaluation, and the novel task-driven evaluation. Experiments on RESIDE shed light on the comparisons and limitations of the state-of-the-art dehazing algorithms, and suggest promising future directions.

Enzalutamide with Standard First-Line Therapy in Metastatic Prostate Cancer

Abstract: Background Enzalutamide, an androgen-receptor inhibitor, has been associated with improved overall survival in men with castration-resistant prostate cancer. It is not known whether adding enzalutamide to testosterone suppression, with or without early docetaxel, will improve survival in men with metastatic, hormone-sensitive prostate cancer. Methods In this open-label, randomized, phase 3 trial, we assigned patients to receive testosterone suppression plus either open-label enzalutamide or a standard nonsteroidal antiandrogen therapy (standard-care group). The primary end point was overall survival. Secondary end points included progression-free survival as determined by the prostate-specific antigen (PSA) level, clinical progression-free survival, and adverse events. Results A total of 1125 men underwent randomization; the median follow-up was 34 months. There were 102 deaths in the enzalutamide group and 143 deaths in the standard-care group (hazard ratio, 0.67; 95% confidence interval [CI], 0.52 to 0.86; P = 0.002). Kaplan-Meier estimates of overall survival at 3 years were 80% (based on 94 events) in the enzalutamide group and 72% (based on 130 events) in the standard-care group. Better results with enzalutamide were also seen in PSA progression-free survival (174 and 333 events, respectively; hazard ratio, 0.39; P Conclusions Enzalutamide was associated with significantly longer progression-free and overall survival than standard care in men with metastatic, hormone-sensitive prostate cancer receiving testosterone suppression. The enzalutamide group had a higher incidence of seizures and other toxic effects, especially among those treated with early docetaxel. (Funded by Astellas Scientific and Medical Affairs and others; ENZAMET (ANZUP 1304) ANZCTR number, ACTRN12614000110684; ClinicalTrials.gov number, NCT02446405; and EU Clinical Trials Register number, 2014-003190-42.).

Global guideline for the diagnosis and management of mucormycosis: an initiative of the European Confederation of Medical Mycology in cooperation with the Mycoses Study Group Education and Research Consortium

Abstract: Mucormycosis is a difficult to diagnose rare disease with high morbidity and mortality. Diagnosis is often delayed, and disease tends to progress rapidly. Urgent surgical and medical intervention is lifesaving. Guidance on the complex multidisciplinary management has potential to improve prognosis, but approaches differ between health-care settings. From January, 2018, authors from 33 countries in all United Nations regions analysed the published evidence on mucormycosis management and provided consensus recommendations addressing differences between the regions of the world as part of the "One World One Guideline" initiative of the European Confederation of Medical Mycology (ECMM). Diagnostic management does not differ greatly between world regions. Upon suspicion of mucormycosis appropriate imaging is strongly recommended to document extent of disease and is followed by strongly recommended surgical intervention. First-line treatment with high-dose liposomal amphotericin B is strongly recommended, while intravenous isavuconazole and intravenous or delayed release tablet posaconazole are recommended with moderate strength. Both triazoles are strongly recommended salvage treatments. Amphotericin B deoxycholate is recommended against, because of substantial toxicity, but may be the only option in resource limited settings. Management of mucormycosis depends on recognising disease patterns and on early diagnosis. Limited availability of contemporary treatments burdens patients in low and middle income settings. Areas of uncertainty were identified and future research directions specified.

Limbic-predominant age-related TDP-43 encephalopathy (LATE): consensus working group report.

Abstract: We describe a recently recognized disease entity, limbic-predominant age-related TDP-43 encephalopathy (LATE). LATE neuropathological change (LATE-NC) is defined by a stereotypical TDP-43 proteinopathy in older adults, with or without coexisting hippocampal sclerosis pathology. LATE-NC is a common TDP-43 proteinopathy, associated with an amnestic dementia syndrome that mimicked Alzheimer's-type dementia in retrospective autopsy studies. LATE is distinguished from frontotemporal lobar degeneration with TDP-43 pathology based on its epidemiology (LATE generally affects older subjects), and relatively restricted neuroanatomical distribution of TDP-43 proteinopathy. In community-based autopsy cohorts, ∼25% of brains had sufficient burden of LATE-NC to be associated with discernible cognitive impairment. Many subjects with LATE-NC have comorbid brain pathologies, often including amyloid-β plaques and tauopathy. Given that the 'oldest-old' are at greatest risk for LATE-NC, and subjects of advanced age constitute a rapidly growing demographic group in many countries, LATE has an expanding but under-recognized impact on public health. For these reasons, a working group was convened to develop diagnostic criteria for LATE, aiming both to stimulate research and to promote awareness of this pathway to dementia. We report consensus-based recommendations including guidelines for diagnosis and staging of LATE-NC. For routine autopsy workup of LATE-NC, an anatomically-based preliminary staging scheme is proposed with TDP-43 immunohistochemistry on tissue from three brain areas, reflecting a hierarchical pattern of brain involvement: amygdala, hippocampus, and middle frontal gyrus. LATE-NC appears to affect the medial temporal lobe structures preferentially, but other areas also are impacted. Neuroimaging studies demonstrated that subjects with LATE-NC also had atrophy in the medial temporal lobes, frontal cortex, and other brain regions. Genetic studies have thus far indicated five genes with risk alleles for LATE-NC: GRN, TMEM106B, ABCC9, KCNMB2, and APOE. The discovery of these genetic risk variants indicate that LATE shares pathogenetic mechanisms with both frontotemporal lobar degeneration and Alzheimer's disease, but also suggests disease-specific underlying mechanisms. Large gaps remain in our understanding of LATE. For advances in prevention, diagnosis, and treatment, there is an urgent need for research focused on LATE, including in vitro and animal models. An obstacle to clinical progress is lack of diagnostic tools, such as biofluid or neuroimaging biomarkers, for ante-mortem detection of LATE. Development of a disease biomarker would augment observational studies seeking to further define the risk factors, natural history, and clinical features of LATE, as well as eventual subject recruitment for targeted therapies in clinical trials.

Federated Learning over Wireless Networks: Optimization Model Design and Analysis

Abstract: There is an increasing interest in a new machine learning technique called Federated Learning, in which the model training is distributed over mobile user equipments (UEs), and each UE contributes to the learning model by independently computing the gradient based on its local training data. Federated Learning has several benefits of data privacy and potentially a large amount of UE participants with modern powerful processors and low-delay mobile-edge networks. While most of the existing work focused on designing learning algorithms with provable convergence time, other issues such as uncertainty of wireless channels and UEs with heterogeneous power constraints and local data size, are under-explored. These issues especially affect to various trade-offs: (i) between computation and communication latencies determined by learning accuracy level, and thus (ii) between the Federated Learning time and UE energy consumption. We fill this gap by formulating a Federated Learning over wireless network as an optimization problem FEDL that captures both trade-offs. Even though FEDL is non-convex, we exploit the problem structure to decompose and transform it to three convex sub-problems. We also obtain the globally optimal solution by charactering the closed-form solutions to all sub-problems, which give qualitative insights to problem design via the obtained optimal FEDL learning time, accuracy level, and UE energy cost. Our theoretical analysis is also illustrated by extensive numerical results.

Hybrid Task Cascade for Instance Segmentation

Abstract: Cascade is a classic yet powerful architecture that has boosted performance on various tasks. However, how to introduce cascade to instance segmentation remains an open question. A simple combination of Cascade R-CNN and Mask R-CNN only brings limited gain. In exploring a more effective approach, we find that the key to a successful instance segmentation cascade is to fully leverage the reciprocal relationship between detection and segmentation. In this work, we propose a new framework, Hybrid Task Cascade (HTC), which differs in two important aspects: (1) instead of performing cascaded refinement on these two tasks separately, it interweaves them for a joint multi-stage processing; (2) it adopts a fully convolutional branch to provide spatial context, which can help distinguishing hard foreground from cluttered background. Overall, this framework can learn more discriminative features progressively while integrating complementary features together in each stage. Without bells and whistles, a single HTC obtains 38.4% and 1.5% improvement over a strong Cascade Mask R-CNN baseline on MSCOCO dataset. Moreover, our overall system achieves 48.6 mask AP on the test-challenge split, ranking 1st in the COCO 2018 Challenge Object Detection Task. Code is available at https://github.com/open-mmlab/mmdetection.

Pembrolizumab versus ipilimumab in advanced melanoma (KEYNOTE-006): post-hoc 5-year results from an open-label, multicentre, randomised, controlled, phase 3 study

Abstract: Summary Background Pembrolizumab improved progression-free survival and overall survival versus ipilimumab in patients with advanced melanoma and is now a standard of care in the first-line setting. However, the optimal duration of anti-PD-1 administration is unknown. We present results from 5 years of follow-up of patients in KEYNOTE-006. Methods KEYNOTE-006 was an open-label, multicentre, randomised, controlled, phase 3 study done at 87 academic institutions, hospitals, and cancer centres in 16 countries. Patients aged at least 18 years with Eastern Cooperative Oncology Group performance status of 0 or 1, ipilimumab-naive histologically confirmed advanced melanoma with known BRAFV600 status and up to one previous systemic therapy were randomly assigned (1:1:1) to intravenous pembrolizumab 10 mg/kg every 2 weeks or every 3 weeks or four doses of intravenous ipilimumab 3 mg/kg every 3 weeks. Treatments were assigned using a centralised, computer-generated allocation schedule with blocked randomisation within strata. Exploratory combination of data from the two pembrolizumab dosing regimen groups was not protocol-specified. Pembrolizumab treatment continued for up to 24 months. Eligible patients who discontinued pembrolizumab with stable disease or better after receiving at least 24 months of pembrolizumab or discontinued with complete response after at least 6 months of pembrolizumab and then progressed could receive an additional 17 cycles of pembrolizumab. Co-primary endpoints were overall survival and progression-free survival. Efficacy was analysed in all randomly assigned patients, and safety was analysed in all randomly assigned patients who received at least one dose of study treatment. Exploratory assessment of efficacy and safety at 5 years' follow-up was not specified in the protocol. Data cutoff for this analysis was Dec 3, 2018. Recruitment is closed; the study is ongoing. This study is registered with ClinicalTrials.gov, number NCT01866319. Findings Between Sept 18, 2013, and March 3, 2014, 834 patients were enrolled and randomly assigned to receive pembrolizumab (every 2 weeks, n=279; every 3 weeks, n=277), or ipilimumab (n=278). After a median follow-up of 57·7 months (IQR 56·7–59·2) in surviving patients, median overall survival was 32·7 months (95% CI 24·5–41·6) in the combined pembrolizumab groups and 15·9 months (13·3–22·0) in the ipilimumab group (hazard ratio [HR] 0·73, 95% CI 0·61–0·88, p=0·00049). Median progression-free survival was 8·4 months (95% CI 6·6–11·3) in the combined pembrolizumab groups versus 3·4 months (2·9–4·2) in the ipilimumab group (HR 0·57, 95% CI 0·48–0·67, p Interpretation Pembrolizumab continued to show superiority over ipilimumab after almost 5 years of follow-up. These results provide further support for use of pembrolizumab in patients with advanced melanoma. Funding Merck Sharp & Dohme.

Guidelines for the use of flow cytometry and cell sorting in immunological studies (second edition)

Abstract: These guidelines are a consensus work of a considerable number of members of the immunology and flow cytometry community. They provide the theory and key practical aspects of flow cytometry enabling immunologists to avoid the common errors that often undermine immunological data. Notably, there are comprehensive sections of all major immune cell types with helpful Tables detailing phenotypes in murine and human cells. The latest flow cytometry techniques and applications are also described, featuring examples of the data that can be generated and, importantly, how the data can be analysed. Furthermore, there are sections detailing tips, tricks and pitfalls to avoid, all written and peer-reviewed by leading experts in the field, making this an essential research companion.

Global, regional and national burden of osteoarthritis 1990-2017: A systematic analysis of the Global Burden of Disease Study 2017

Abstract: Objectives To report the level and trends of prevalence, incidence and years lived with disability (YLDs) for osteoarthritis (OA) in 195 countries and territories from 1990 to 2017 by age, sex and Socio-demographic index (SDI; a composite of sociodemographic factors). Methods Publicly available modelled data from the Global Burden of Diseases, Injuries, and Risk Factors Study (GBD) 2017 were used. The burden of OA was estimated for 195 countries and territories from 1990 to 2017, through a systematic analysis of prevalence and incidence modelled data using the methods reported in the GBD 2017 Study. All estimates were presented as counts and age-standardised rates per 100 000 population, with uncertainty intervals (UIs). Results Globally, the age-standardised point prevalence and annual incidence rate of OA in 2017 were 3754.2 (95% UI 3389.4 to 4187.6) and 181.2 (95% UI 162.6 to 202.4) per 100 000, an increase of 9.3% (95% UI 8% to 10.7%) and 8.2% (95% UI 7.1% to 9.4%) from 1990, respectively. In addition, global age-standardised YLD rate in 2017 was 118.8 (95% UI 59.5 to 236.2), an increase of 9.6% (95% UI 8.3% to 11.1%) from 1990. The global prevalence was higher in women and increased with age, peaking at the >95 age group among women and men in 2017. Generally, a positive association was found between the age-standardised YLD rate and SDI at the regional and national levels. Age-standardised prevalence of OA in 2017 ranged from 2090.3 to 6128.1 cases per 100 000 population. United States (6128.1 (95% UI 5729.3 to 6582.9)), American Samoa (5281 (95% UI 4688 to 5965.9)) and Kuwait (5234.6 (95% UI 4643.2 to 5953.6)) had the three highest levels of age-standardised prevalence. Oman (29.6% (95% UI 24.8% to 34.9%)), Equatorial Guinea (28.6% (95% UI 24.4% to 33.7%)) and the United States 23.2% (95% UI 16.4% to 30.5%)) showed the highest increase in the age-standardised prevalence during 1990–2017. Conclusions OA is a major public health challenge. While there is remarkable international variation in the prevalence, incidence and YLDs due to OA, the burden is increasing in most countries. It is expected to continue with increased life expectancy and ageing of the global population. Improving population and policy maker awareness of risk factors, including overweight and injury, and the importance and benefits of management of OA, together with providing health services for an increasing number of people living with OA, are recommended for management of the future burden of this condition.

GhostNet: More Features from Cheap Operations

Abstract: Deploying convolutional neural networks (CNNs) on embedded devices is difficult due to the limited memory and computation resources. The redundancy in feature maps is an important characteristic of those successful CNNs, but has rarely been investigated in neural architecture design. This paper proposes a novel Ghost module to generate more feature maps from cheap operations. Based on a set of intrinsic feature maps, we apply a series of linear transformations with cheap cost to generate many ghost feature maps that could fully reveal information underlying intrinsic features. The proposed Ghost module can be taken as a plug-and-play component to upgrade existing convolutional neural networks. Ghost bottlenecks are designed to stack Ghost modules, and then the lightweight GhostNet can be easily established. Experiments conducted on benchmarks demonstrate that the proposed Ghost module is an impressive alternative of convolution layers in baseline models, and our GhostNet can achieve higher recognition performance (e.g. $75.7\%$ top-1 accuracy) than MobileNetV3 with similar computational cost on the ImageNet ILSVRC-2012 classification dataset. Code is available at this https URL

Polygenic Risk Scores for Prediction of Breast Cancer and Breast Cancer Subtypes

Abstract: Stratification of women according to their risk of breast cancer based on polygenic risk scores (PRSs) could improve screening and prevention strategies. Our aim was to develop PRSs, optimized for prediction of estrogen receptor (ER)-specific disease, from the largest available genome-wide association dataset and to empirically validate the PRSs in prospective studies. The development dataset comprised 94,075 case subjects and 75,017 control subjects of European ancestry from 69 studies, divided into training and validation sets. Samples were genotyped using genome-wide arrays, and single-nucleotide polymorphisms (SNPs) were selected by stepwise regression or lasso penalized regression. The best performing PRSs were validated in an independent test set comprising 11,428 case subjects and 18,323 control subjects from 10 prospective studies and 190,040 women from UK Biobank (3,215 incident breast cancers). For the best PRSs (313 SNPs), the odds ratio for overall disease per 1 standard deviation in ten prospective studies was 1.61 (95%CI: 1.57-1.65) with area under receiver-operator curve (AUC) = 0.630 (95%CI: 0.628-0.651). The lifetime risk of overall breast cancer in the top centile of the PRSs was 32.6%. Compared with women in the middle quintile, those in the highest 1% of risk had 4.37- and 2.78-fold risks, and those in the lowest 1% of risk had 0.16- and 0.27-fold risks, of developing ER-positive and ER-negative disease, respectively. Goodness-of-fit tests indicated that this PRS was well calibrated and predicts disease risk accurately in the tails of the distribution. This PRS is a powerful and reliable predictor of breast cancer risk that may improve breast cancer prevention programs.

Five-Year Overall Survival for Patients With Advanced Non-Small-Cell Lung Cancer Treated With Pembrolizumab: Results From the Phase I KEYNOTE-001 Study

Abstract: PURPOSEPembrolizumab monotherapy has demonstrated durable antitumor activity in advanced programmed death ligand 1 (PD-L1)–expressing non‒small-cell lung cancer (NSCLC). We report 5-year outcomes f...

World Scientists’ Warning of a Climate Emergency

Abstract: 1 Department of Forest Ecosystems and Society, Oregon State University, Corvallis, OR 97331, USA 2 School of Life and Environmental Sciences, The University of Sydney, Sydney, NSW 2006, Australia 3 Conservation Biology Institute, 136 SW Washington Avenue, Suite 202, Corvallis, OR 97333, USA 4 African Climate and Development Initiative, University of Cape Town, Cape Town, 7700, South Africa. 5 The Fletcher School and Global Development and Environment Institute, Tufts University, Medford, MA, USA

Comparing different supervised machine learning algorithms for disease prediction

Abstract: Supervised machine learning algorithms have been a dominant method in the data mining field. Disease prediction using health data has recently shown a potential application area for these methods. This study aims to identify the key trends among different types of supervised machine learning algorithms, and their performance and usage for disease risk prediction. In this study, extensive research efforts were made to identify those studies that applied more than one supervised machine learning algorithm on single disease prediction. Two databases (i.e., Scopus and PubMed) were searched for different types of search items. Thus, we selected 48 articles in total for the comparison among variants supervised machine learning algorithms for disease prediction. We found that the Support Vector Machine (SVM) algorithm is applied most frequently (in 29 studies) followed by the Naive Bayes algorithm (in 23 studies). However, the Random Forest (RF) algorithm showed superior accuracy comparatively. Of the 17 studies where it was applied, RF showed the highest accuracy in 9 of them, i.e., 53%. This was followed by SVM which topped in 41% of the studies it was considered. This study provides a wide overview of the relative performance of different variants of supervised machine learning algorithms for disease prediction. This important information of relative performance can be used to aid researchers in the selection of an appropriate supervised machine learning algorithm for their studies.