Search

Your search keyword '"Qi, Pi"' showing total 13 results
Start Over Author "Qi, Pi" Publication Year Range Last 10 years
13 results on '"Qi, Pi"'

1. Increased antipsychotic drug concentration in hospitalized patients with mental disorders following COVID-19 infection: a call for attention

Author

Rui Yang, Jin-Ling Wan, Chen-Qi Pi, Tian-Hui Wang, Xue-Quan Zhu, and Shuang-Jiang Zhou

Subjects
coronavirus disease-2019, antipsychotic concentration, mental disorder, therapeutic drug monitoring, clozapine, Psychiatry, RC435-571
Abstract

PurposeExamine the alterations in antipsychotic concentrations following coronavirus disease-2019 (COVID-19) infection among hospitalized patients with mental disorders and conduct an analysis of the factors influencing these changes.MethodsData were collected from inpatients at Beijing Huilongguan Hospital between December 12, 2022, and January 11, 2023, pre- and post-COVID-19. Based on the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition, 329 inpatients with mental disorders were included (3 with incomplete data excluded). Primary outcomes assessed changes in antipsychotic concentrations pre- and post-COVID-19, while secondary outcomes examined factors linked to concentration increases and antipsychotic dose adjustments.ResultsClozapine (P < 0.001), aripiprazole (P < 0.001), quetiapine (P = 0.005), olanzapine (P < 0.001), risperidone (P < 0.001), and paliperidone (P < 0.001) concentrations increased post-COVID-19 in patients with mental disorders. Notably, clozapine concentration surpassing pre-infection levels was highest. Clozapine users were more likely to adjust their dose (50.4%) compared to olanzapine (17.5%) and other antipsychotics. Moreover, traditional Chinese patent medicines and antibiotics during COVID-19 infection were associated with antipsychotic reduction or withdrawal (OR = 2.06, P = 0.0247; OR = 7.53, P = 0.0024, respectively).ConclusionAntipsychotic concentrations in hospitalized patients with mental disorders increased after COVID-19 infection, that may be related not only to COVID-19, but also to the use of Chinese patent medicines during infection. The pre-infection concentration and types of antipsychotics, patient’s gender, and combination of traditional Chinese medicine or antibiotics, were factors found to correlate with increased drug concentrations and necessitate dose adjustments.

Published
2024
Full Text
View/download PDF

2. Search-based User Interest Modeling with Lifelong Sequential Behavior Data for Click-Through Rate Prediction

Author

Qi, Pi, Zhu, Xiaoqiang, Zhou, Guorui, Zhang, Yujing, Wang, Zhe, Ren, Lejian, Fan, Ying, and Gai, Kun

Subjects
Computer Science - Information Retrieval, Statistics - Machine Learning, Machine Learning (stat.ML), Information Retrieval (cs.IR), Machine Learning (cs.LG), I.2.6
Abstract

Rich user behavior data has been proven to be of great value for click-through rate prediction tasks, especially in industrial applications such as recommender systems and online advertising. Both industry and academy have paid much attention to this topic and propose different approaches to modeling with long sequential user behavior data. Among them, memory network based model MIMN proposed by Alibaba, achieves SOTA with the co-design of both learning algorithm and serving system. MIMN is the first industrial solution that can model sequential user behavior data with length scaling up to 1000. However, MIMN fails to precisely capture user interests given a specific candidate item when the length of user behavior sequence increases further, say, by 10 times or more. This challenge exists widely in previously proposed approaches. In this paper, we tackle this problem by designing a new modeling paradigm, which we name as Search-based Interest Model (SIM). SIM extracts user interests with two cascaded search units: (i) General Search Unit acts as a general search from the raw and arbitrary long sequential behavior data, with query information from candidate item, and gets a Sub user Behavior Sequence which is relevant to candidate item; (ii) Exact Search Unit models the precise relationship between candidate item and SBS. This cascaded search paradigm enables SIM with a better ability to model lifelong sequential behavior data in both scalability and accuracy. Apart from the learning algorithm, we also introduce our hands-on experience on how to implement SIM in large scale industrial systems. Since 2019, SIM has been deployed in the display advertising system in Alibaba, bringing 7.1\% CTR and 4.4\% RPM lift, which is significant to the business. Serving the main traffic in our real system now, SIM models user behavior data with maximum length reaching up to 54000, pushing SOTA to 54x.

Published
2020

4. Spatial-temporal analysis of pulmonary tuberculosis in Hubei Province, China, 2011-2021.

Author

Yu Zhang, Jianjun Ye, Shuangyi Hou, Xingxing Lu, Chengfeng Yang, Qi Pi, Mengxian Zhang, Xun Liu, Qin Da, and Liping Zhou

Subjects
Medicine, Science
Abstract

BackgroundPulmonary tuberculosis (PTB) is an infectious disease of major public health problem, China is one of the PTB high burden counties in the word. Hubei is one of the provinces having the highest notification rate of tuberculosis in China. This study analyzed the temporal and spatial distribution characteristics of PTB in Hubei province for targeted intervention on TB epidemics.MethodsThe data on PTB cases were extracted from the National Tuberculosis Information Management System correspond to population in 103 counties of Hubei Province from 2011 to 2021. The effect of PTB control was measured by variation trend of bacteriologically confirmed PTB notification rate and total PTB notification rate. Time series, spatial autonomic correlation and spatial-temporal scanning methods were used to identify the temporal trends and spatial patterns at county level of Hubei.ResultsA total of 436,955 cases were included in this study. The total PTB notification rate decreased significantly from 81.66 per 100,000 population in 2011 to 52.25 per 100,000 population in 2021. The peak of PTB notification occurred in late spring and early summer annually. This disease was spatially clustering with Global Moran's I values ranged from 0.34 to 0.63 (P< 0.01). Local spatial autocorrelation analysis indicated that the hot spots are mainly distributed in the southwest and southeast of Hubei Province. Using the SaTScan 10.0.2 software, results from the staged spatial-temporal analysis identified sixteen clusters.ConclusionsThis study identified seasonal patterns and spatial-temporal clusters of PTB cases in Hubei province. High-risk areas in southwestern Hubei still exist, and need to focus on and take targeted control and prevention measures.

Published
2023
Full Text
View/download PDF

10. Comparison of Cerebrospinal Fluid Cellular Analysis by Optical Microscopy and Sysmex XN 9000.

Author

Xiu-Qin Ren, Xi Jiang, Ying-Qi Pi, Zhi-Kun Wu, Hong-bo Jiang, and Hua-Cheng Wang

Subjects
CEREBROSPINAL fluid examination, MICROSCOPY, MENINGES, MENINGEAL cancer, CEREBROSPINAL fluid, CELL separation, SUBARACHNOID hemorrhage
Abstract

Background: This study was designed to compare the body fluid module of Sysmex XN9000 (XN-BF) with optical microscopy (OM) for cerebrospinal fluid (CSF) analysis after two-step cell slide centrifuge (TSCSC), defining the best procedure for CSF optical microscopy analysis. Methods: Items of RBC, WBC enumeration and differentiation were observed. The cell count and morphologic evaluation of the cellular composition by OM was carried out both with and without two-step cell slide centrifuge (TSCSC) and were compared the data with XN-BF. Results: There were 69.98 ± 4.94 RBC and 36.98 ± 3.39 WBC in one OSCSC microscopic field whereas there were 96.35 ± 5.41 RBC and 66.15 ± 4.85 WBC in one TSCSC microscopic field in the same sample (*200). There was a statistical difference between those two methods (p = 0.000). Excellent correlation was found between total cell count with both OM and XN-BF. The R2 value for RBC and WBC counts were 0.99 and 0.96, respectively. For WBC differential, the R2 values were 0.98 for PMN and 0.70 for MN. Correlation of MN was poorer than PMN. As far as the tumor cell, phagocyte, and plasma cell with high fluorescence were concerned, OM were not consistent with XN-BF. Conclusions: The TSCSC procedure contributes to the separation of cells and other ingredients. XN-BF displays excellent performance at RBC and WBC cell count except for mononuclear cells, tumor cells, phagocytes, and leukemia cells. which makes it just a practical alternative to total cell (WBC, RBC) count for CSF samples. Detailed morphologic workup of CSF samples is mandated in all cases with meningoencephalitis, elevated cell count, subarachnoid hemorrhage and meningeal carcinomatosis, the TSCSC procedure is recommended. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

11. Practice on Long Sequential User Behavior Modeling for Click-Through Rate Prediction

Author

Kun Gai, Qi Pi, Xiaoqiang Zhu, Weijie Bian, and Guorui Zhou

Subjects
FOS: Computer and information sciences, Event (computing), business.industry, Computer science, Display advertising, Deep learning, Distributed computing, 02 engineering and technology, Recommender system, Click-through rate, Online advertising, Computer Science - Information Retrieval, Task (computing), 020204 information systems, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, State (computer science), Artificial intelligence, business, Information Retrieval (cs.IR)
Abstract

Click-through rate (CTR) prediction is critical for industrial applications such as recommender system and online advertising. Practically, it plays an important role for CTR modeling in these applications by mining user interest from rich historical behavior data. Driven by the development of deep learning, deep CTR models with ingeniously designed architecture for user interest modeling have been proposed, bringing remarkable improvement of model performance over offline metric.However, great efforts are needed to deploy these complex models to online serving system for realtime inference, facing massive traffic request. Things turn to be more difficult when it comes to long sequential user behavior data, as the system latency and storage cost increase approximately linearly with the length of user behavior sequence. In this paper, we face directly the challenge of long sequential user behavior modeling and introduce our hands-on practice with the co-design of machine learning algorithm and online serving system for CTR prediction task. Theoretically, the co-design solution of UIC and MIMN enables us to handle the user interest modeling with unlimited length of sequential behavior data. Comparison between model performance and system efficiency proves the effectiveness of proposed solution. To our knowledge, this is one of the first industrial solutions that are capable of handling long sequential user behavior data with length scaling up to thousands. It now has been deployed in the display advertising system in Alibaba., 9 pages. Accepted by KDD 2019

Published
2019

12. Deep Interest Evolution Network for Click-Through Rate Prediction

Author

Qi Pi, Xiaoqiang Zhu, Guorui Zhou, Weijie Bian, Chang Zhou, Na Mou, Kun Gai, and Ying Fan

Subjects
FOS: Computer and information sciences, Sequence, Computer Science - Machine Learning, Process (engineering), Computer science, I.2.6, Machine Learning (stat.ML), 02 engineering and technology, General Medicine, computer.software_genre, Click-through rate, Machine Learning (cs.LG), Computer Science - Information Retrieval, Core (game theory), Statistics - Machine Learning, 020204 information systems, 0202 electrical engineering, electronic engineering, information engineering, Changing trend, 020201 artificial intelligence & image processing, Data mining, Layer (object-oriented design), Representation (mathematics), computer, Information Retrieval (cs.IR)
Abstract

Click-through rate~(CTR) prediction, whose goal is to estimate the probability of the user clicks, has become one of the core tasks in advertising systems. For CTR prediction model, it is necessary to capture the latent user interest behind the user behavior data. Besides, considering the changing of the external environment and the internal cognition, user interest evolves over time dynamically. There are several CTR prediction methods for interest modeling, while most of them regard the representation of behavior as the interest directly, and lack specially modeling for latent interest behind the concrete behavior. Moreover, few work consider the changing trend of interest. In this paper, we propose a novel model, named Deep Interest Evolution Network~(DIEN), for CTR prediction. Specifically, we design interest extractor layer to capture temporal interests from history behavior sequence. At this layer, we introduce an auxiliary loss to supervise interest extracting at each step. As user interests are diverse, especially in the e-commerce system, we propose interest evolving layer to capture interest evolving process that is relative to the target item. At interest evolving layer, attention mechanism is embedded into the sequential structure novelly, and the effects of relative interests are strengthened during interest evolution. In the experiments on both public and industrial datasets, DIEN significantly outperforms the state-of-the-art solutions. Notably, DIEN has been deployed in the display advertisement system of Taobao, and obtained 20.7\% improvement on CTR., 9 pages. Accepted by AAAI 2019

Published
2018

13. CAPred: A Prediction Model for Timely QoS

Author

Qi Pi, Yao Zhao, Chengduo Luo, and Danfeng Yan

Subjects
Computer science, Reliability (computer networking), media_common.quotation_subject, Distributed computing, Quality of service, Preemption, Mobile QoS, computer.software_genre, Data modeling, Key (cryptography), Quality (business), Data mining, Web service, computer, media_common
Abstract

With the rapidly growing number of Web services, how to identify high quality Web services becomes a hot research topic. User-side QoS evaluation on Web services is a key measurement to choose the optimal Web service from a set of Web services with similar functions. The user-side QoS data is acquired through the invocation of services from different locations. However, in real world, the QoS data of Web services is sparse and not timely. Though there are already a lot of research works on the sparsity and timeliness of QoS data respectively, it's still a lack of a prediction model which can combine both of these features. In order to solve this challenging problem, we put forward a novel model, called CAPred, to provide timely QoS prediction. Our model cut the historical QoS data into several time slices. Each time slice is a 2-dimension matrix. CAPred firstly processes every time slice to fill the empty part of the matrix, then utilizes all of the historical data to predict current QoS values of Web services. And at last we demonstrate two applications, those are recommendation and selection, which utilize the QoS prediction results of our model. The experimental results indicate the high feasibility and efficiency of our model.

Published
2015
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results