Search

Federated learning enables multiple nodes to perform local computations and collaborate to complete machine learning tasks without centralizing private data of nodes. However, the frequent model gradients upload/download operations required by the framework result in high communication costs, which have become the main bottleneck for federated learning as deep models scale up, hindering its performance. In this paper, we propose a two-layer accumulated quantized compression algorithm (TLAQC) that effectively reduces the communication cost of federated learning. TLAQC achieves this by reducing both the cost of individual communication and the number of global communication rounds. TLAQC introduces a revised quantization method called RQSGD, which employs zero-value correction to mitigate ineffective quantization phenomena and minimize average quantization errors. Additionally, TLAQC reduces the frequency of gradient information uploads through an adaptive threshold and parameter self-inspection mechanism, further reducing communication costs. It also accumulates quantization errors and retained weight deltas to compensate for gradient knowledge loss. Through quantization correction and two-layer accumulation, TLAQC significantly reduces precision loss caused by communication compression. Experimental results demonstrate that RQSGD achieves an incidence of ineffective quantization as low as 0.003% and reduces the average quantization error to 1.6 × 10 - 5 . Compared to full-precision FedAVG, TLAQC compresses uploaded traffic to only 6.73% while increasing accuracy by 1.25%. [ABSTRACT FROM AUTHOR]

A promising way to uncover the genetic architectures underlying complex traits may lie in the ability to recognize the genetic variants and expression transcripts that are responsible for the traits' inheritance. However, statistical methods capable of investigating the association between the inheritance of a quantitative trait and expression transcripts are still limited. In this study, we described a two-step approach that we developed to evaluate the contribution of expression transcripts to the inheritance of a complex trait. First, a mixed linear model approach was applied to detect significant trait-associated differentially expressed transcripts. Then, conditional analysis were used to predict the contribution of the differentially expressed genes to a target trait. Diallel cross data of cotton was used to test the application of the approach. We proposed that the detected differentially expressed transcripts with a strong impact on the target trait could be used as intermediates for screening lines to improve the traits in plant and animal breeding programs. It can benefit the discovery of the genetic mechanisms underlying complex traits. [ABSTRACT FROM AUTHOR]

Objective: Predicting the risk of falls in advance can benefit the quality of care and potentially reduce mortality and morbidity in the older population. The aim of this study was to construct and validate an electronic health record-based fall risk predictive tool to identify elders at a higher risk of falls.Methods: The one-year fall prediction model was developed using the machine-learning-based algorithm, XGBoost, and tested on an independent validation cohort. The data were collected from electronic health records (EHR) of Maine from 2016 to 2018, comprising 265,225 older patients (≥65 years of age).Results: This model attained a validated C-statistic of 0.807, where 50 % of the identified high-risk true positives were confirmed to fall during the first 94 days of next year. The model also captured in advance 58.01 % and 54.93 % of falls that happened within the first 30 and 30-60 days of next year. The identified high-risk patients of fall showed conditions of severe disease comorbidities, an enrichment of fall-increasing cardiovascular and mental medication prescriptions and increased historical clinical utilization, revealing the complexity of the underlying fall etiology. The XGBoost algorithm captured 157 impactful predictors into the final predictive model, where cognitive disorders, abnormalities of gait and balance, Parkinson's disease, fall history and osteoporosis were identified as the top-5 strongest predictors of the future fall event.Conclusions: By using the EHR data, this risk assessment tool attained an improved discriminative ability and can be immediately deployed in the health system to provide automatic early warnings to older adults with increased fall risk and identify their personalized risk factors to facilitate customized fall interventions. [ABSTRACT FROM AUTHOR]

Background: Allergic rhinitis is a common health concern that affects quality of life. This study aims to examine the online search trends of allergic rhinitis in China before and after the COVID-19 epidemic and to explore the association between the daily air quality and online search volumes of allergic rhinitis in Beijing. Methods: We extracted the online search data of allergic rhinitis-related keywords from the Baidu index database from January 23, 2017 to June 23, 2022. We analyzed and compared the temporal distribution of online search behaviors across different themes of allergic rhinitis before and after the COVID-19 pandemic in mainland China, using the Baidu search index (BSI). We also obtained the air quality index (AQI) data in Beijing and assessed its correlation with daily BSIs of allergic rhinitis. Results: The online search for allergic rhinitis in China showed significant seasonal variations, with two peaks each year in spring from March to May and autumn from August and October. The BSI of total allergic rhinitis-related searches increased gradually from 2017 to 2019, reaching a peak in April 2019, and declined after the COVID-19 pandemic, especially in the first half of 2020. The BSI for all allergic rhinitis themes was significantly lower after the COVID-19 pandemic than before (all p values < 0.05). The results also revealed that, in Beijing, there was a significant negative association between daily BSI and AQI for each allergic rhinitis theme during the original variant strain epidemic period and a significant positive correlation during the Omicron variant period. Conclusion: Both air quality and the interventions used for COVID-19 pandemic, including national and local quarantines and mask wearing behaviors, may have affected the incidence and public concern about allergic rhinitis in China. The online search trends can serve as a valuable tool for tracking real-time public concerns about allergic rhinitis. By complementing traditional disease monitoring systems of health departments, these search trends can also offer insights into the patterns of disease outbreaks. Additionally, they can provide references and suggestions regarding the public's knowledge demands related to allergic rhinitis, which can further be instrumental in developing targeted strategies to enhance population-based disease education on allergic diseases. [ABSTRACT FROM AUTHOR]

Background: Pulmonary rehabilitation (PR) has been recognized to be an effective therapy for chronic obstructive pulmonary disease (COPD). However, in China, the application of PR interventions is still less promoted. Therefore, this cross-sectional study aimed to understand COPD patients' intention to receive PR, capture the potential personal, social and environmental barriers preventing their willingness of receiving PR, and eventually identify demanding PR services with the highest priority from patients' point of view. Methods: In total 237 COPD patients were recruited from 8 health care facilities in Zhejiang, China. A self-designed questionnaire was applied to investigate patients' intention to participate in PR and potentially associated factors, including personal dimension such as personal awareness, demographic factors, COPD status and health-related literacy/behaviors, as well as social policies and perceived environmental barriers. The demand questionnaire of PR interventions based on the Kano model was further adopted. Results: Among the 237 COPD patients, 75.1% of COPD patients were willing to participate in PR interventions, while only 62.9% of the investigated patients had heard of PR interventions. Over 90% of patients believed that the cost of PR services and the ratio of medical insurance reimbursement were potential obstacles hindering them from accepting PR services. The multiple linear regression analysis indicated that the PR skills of medical staff, knowledge promotion and public education levels of PR in the community, patients' transportation concerns and degree of support from family and friends were significantly associated with willingness of participation in PR interventions. By using the Kano model, the top 9 most-requisite PR services (i.e., one-dimensional qualities) were identified from patients' point of view, which are mainly diet guidance, education interventions, psychological interventions and lower limb exercise interventions. Subgroup analysis also revealed that patients' demographics, such as breathlessness level, age, education and income levels, could influence their choice of priorities for PR services, especially services related to exercise interventions, respiratory muscle training, oxygen therapy and expectoration. Conclusions: This study suggested that PR-related knowledge education among patients and their family, as well as providing basic package of PR services with the most-requisite PR items to COPD patients, were considerable approaches to promote PR attendance in the future. [ABSTRACT FROM AUTHOR]

Translation studies have been initiated to assess the combined effect of genetic loci from recently accomplished genome-wide association studies and the existing risk factors for early disease prediction. We propose a bagging optimal receiver operating characteristic (ROC) curve method to facilitate this research. Through simulation and real data application, we compared the new method with the commonly used allele counting method and logistic regression, and found that the new method yields a better performance. The new method was applied on the Wellcome Trust data set to form a predictive genetic test for rheumatoid arthritis. The formed test reached an area under the curve (AUC) value of 0.7. [ABSTRACT FROM AUTHOR]

Genetic association studies using high-throughput genotyping and sequencing technologies have identified a large number of genetic variants associated with complex human diseases. These findings have provided an unprecedented opportunity to identify individuals in the population at high risk for disease who carry causal genetic mutations and hold great promise for early intervention and individualized medicine. While interest is high in building risk prediction models based on recent genetic findings, it is crucial to have appropriate statistical measurements to assess the performance of a genetic risk prediction model. Predictiveness curves were recently proposed as a graphic tool for evaluating a risk prediction model on the basis of a single continuous biomarker. The curve evaluates a risk prediction model for classification performance as well as its usefulness when applied to a population. In this article, we extend the predictiveness curve to measure the collective contribution of multiple genetic variants. We further propose a nonparametric, U-statistics-based measurement, referred to as the U-Index, to quantify the performance of a multi-locus predictiveness curve. In particular, a global U-Index and a partial U-Index can be used in the general population and a subpopulation of particular clinical interest, respectively. Through simulation studies, we demonstrate that the proposed U-Index has advantages over several existing summary statistics under various disease models. We also show that the partial U-Index can have its own uniqueness when rare variants have a substantial contribution to disease risk. Finally, we use the proposed predictiveness curve and its corresponding U-Index to evaluate the performance of a genetic risk prediction model for nicotine dependence. [ABSTRACT FROM AUTHOR]

The Attabad landslide dam caused significant property losses and many human casualties in Pakistan, and also greatly affected the operation of the China-Pakistan Karakoram Highway (KKH). This paper discusses the risk of dam breach and hazards to the KKH project construction site following a dam breach. The paper examines the following three topics. (1) The geomorphologic dimensionless blockage index (DBI) and the analogy method were used to analyze the stability of the Attabad landslide dam. The long-term behaviors of landslide dams downstream of the Attabad landslide dam indicate that the risk of a dam breach exists, but the probability of a total dam failure is low. (2) The peak discharge of a potential breach of the Attabad landslide dam was calculated for scenarios in which 1/4, 1/3, 1/2, and total failure of the dam was breached. The potential breach discharge decreases with the downstream distance. (3) The potential impacts of the landslide dam breach on the KKH project construction site were analyzed. Based on the composition of the landslide dam, the probability of a 1/3 dam breach is high. To ensure the safety of downstream areas, disaster preparedness plans that correspond to the 1/2 dam breach scenario should be developed. Based on experience in addressing the landslide dam that was caused by the Wenchuan Earthquake, artificial controlled drainage measures are suggested and provide a technical reference for addressing the Attabad landslide dam and achieving recovery and normal operation of KKH. [ABSTRACT FROM AUTHOR]