A multi-institutional retrospective study of hyperthermic plus intravesical chemotherapy versus intravesical chemotherapy treatment alone in intermediate and high risk nonmuscle-invasive bladder cancer

Objective:To compare the efficacy and safety of hyperthermic intravesical chemotherapy(HIVEC)and intravesical chemotherapy(IVEC)in patients with intermediate and high risk nonmuscle-invasive bladder cancer(NMIBC)after transurethral resection.Methods:We included 560 patients diagnosed with primary or recurrent NMIBC between April 2009 and December 2015 at 1 of 6 tertiary centers.We matched 364 intermediate or high risk cases and divided them into 2 groups:the HIVEC+IVEC group[chemohyperthermia(CHT)composed of 3 consecutive sessions followed by intravesical instillation without hyperthermia]and the IVEC group(intravesical instillation without hyperthermia).The data were recorded in the database.The primary endpoint was 2-year recurrence-free survival(RFS)in all NMIBC patients(n=364),whereas the secondary endpoints were the assessment of radical cystectomy(RC)and 5-year overall survival(OS).Results:There was a significant difference in the 2-year RFS between the two groups in all patients(n=364;HIVEC+IVEC:82.42%vs.IVEC:74.18%,P=0.038).Compared with the IVEC group,the HIVEC+IVEC group had a lower incidence of RC(P=0.0274).However,the 5-year OS was the same between the 2 groups(P=0.1434).Adverse events(AEs)occurred in 32.7%of all patients,but none of the events was serious(grades 3–4).No difference in the incidence or severity of AEs between each treatment modality was observed.Conclusions:This retrospective study showed that HIVEC+IVEC had a higher 2-year RFS and a lower incidence of RC than IVEC therapy in intermediate and high risk NMIBC patients.Both treatments were well-tolerated in a similar manner.

Multi-Modal Military Event Extraction Based on Knowledge Fusion

Event extraction stands as a significant endeavor within the realm of information extraction,aspiring to automatically extract structured event information from vast volumes of unstructured text.Extracting event elements from multi-modal data remains a challenging task due to the presence of a large number of images and overlapping event elements in the data.Although researchers have proposed various methods to accomplish this task,most existing event extraction models cannot address these challenges because they are only applicable to text scenarios.To solve the above issues,this paper proposes a multi-modal event extraction method based on knowledge fusion.Specifically,for event-type recognition,we use a meticulous pipeline approach that integrates multiple pre-trained models.This approach enables a more comprehensive capture of the multidimensional event semantic features present in military texts,thereby enhancing the interconnectedness of information between trigger words and events.For event element extraction,we propose a method for constructing a priori templates that combine event types with corresponding trigger words.This approach facilitates the acquisition of fine-grained input samples containing event trigger words,thus enabling the model to understand the semantic relationships between elements in greater depth.Furthermore,a fusion method for spatial mapping of textual event elements and image elements is proposed to reduce the category number overload and effectively achieve multi-modal knowledge fusion.The experimental results based on the CCKS 2022 dataset show that our method has achieved competitive results,with a comprehensive evaluation value F1-score of 53.4%for the model.These results validate the effectiveness of our method in extracting event elements from multi-modal data.

Classification of Acupuncture Points Based on the Bert Model*

In this paper, we explore the multi-classification problem of acupuncture acupoints based on Bert model, i.e., we try to recommend the best main acupuncture point for treating the disease by classifying and predicting the main acupuncture point for the disease, and further explore its acupuncture point grouping to provide the medical practitioner with the optimal solution for treating the disease and improving the clinical decision-making ability. The Bert-Chinese-Acupoint model was constructed by retraining on the basis of the Bert model, and the semantic features in terms of acupuncture points were added to the acupuncture point corpus in the fine-tuning process to increase the semantic features in terms of acupuncture points, and compared with the machine learning method. The results show that the Bert-Chinese Acupoint model proposed in this paper has a 3% improvement in accuracy compared to the best performing model in the machine learning approach.

Optimized segmented regression models for the transition period of intervention effects

Background The interrupted time series(ITS)design is a widely used approach to examine the effects of interventions.However,the classic segmented regression(CSR)method,the most popular statistical technique for analyzing ITS data,may not be adequate when there is a transitional period between the pre-and post-intervention phases.Methods To address this issue and better capture the distribution patterns of intervention effects during the transition period,we propose using different cumulative distribution functions in the CSR model and developing corresponding optimized segmented regression(OSR)models.This study illustrates the application of OSR models to estimate the long-term impact of a national free delivery service policy intervention in Ethiopia.Results Regardless of the choice of transition length(L)and distribution patterns of intervention effects,the OSR models outperformed the CSR model in terms of mean square error(MSE),indicating the existence of a transition period and the validity of our model’s assumptions.However,the estimates of long-term impacts using OSR models are sensitive to the selection of L,highlighting the importance of reasonable parameter specification.We propose a data-driven approach to select the transition period length to address this issue.Conclusions Overall,our OSR models provide a powerful tool for modeling intervention effects during the transition period,with a superior model fit and more accurate estimates of long-term impacts.Our study highlights the importance of appropriate statistical methods for analyzing ITS data and provides a useful framework for future research.

Privacy-Preserving Task Assignment in Spatial Crowdsourcing

With the progress of mobile devices and wireless networks, spatial crowdsourcing （SC） is emerging as a promising approach for problem solving. In SC, spatial tasks are assigned to and performed by a set of human workers. To enable effective task assignment, however, both workers and task requesters are required to disclose their locations to untrusted SC systems. In this paper, we study the problem of assigning workers to tasks in a way that location privacy for both workers and task requesters is preserved. We first combine the Paillier cryptosystem with Yao＆#39;s garbled circuits to construct a secure protocol that assigns the nearest worker to a task. Considering that this protocol cannot scale to a large number of workers, we then make use of Geohash, a hierarchical spatial index to design a more efficient protocol that can securely find approximate nearest workers. We theoretically show that these two protocols are secure against semi-honest adversaries. Through extensive experiments on two real-world datasets, we demonstrate the efficiency and effectiveness of our protocols.

Combat data shift in few-shot learning with knowledge graph

Many few-shot learning approaches have been designed under the meta-learning framework, which learns from a variety of learning tasks and generalizes to new tasks. These meta-learning approaches achieve the expected performance in the scenario where all samples are drawn from the same distributions (i.i.d. observations). However, in real-world applications, few-shot learning paradigm often suffers from data shift, i.e., samples in different tasks, even in the same task, could be drawn from various data distributions. Most existing few-shot learning approaches are not designed with the consideration of data shift, and thus show downgraded performance when data distribution shifts. However, it is non-trivial to address the data shift problem in few-shot learning, due to the limited number of labeled samples in each task. Targeting at addressing this problem, we propose a novel metric-based meta-learning framework to extract task-specific representations and task-shared representations with the help of knowledge graph. The data shift within/between tasks can thus be combated by the combination of task-shared and task-specific representations. The proposed model is evaluated on popular benchmarks and two constructed new challenging datasets. The evaluation results demonstrate its remarkable performance.