检索结果-内蒙古大学图书馆

Supervised Machine Learning-Based decision Support for Signal Validation Classification

drUG SAFETY 2022年第5期45卷 583-596页

作者： Imran, Muhammad Bhatti, Aasia King, david M. Lerch, Magnus dietrich, Juergen doron, Guy Manlik, Katrin Bayer AG Digital Transformat & Informat Technol Pharma Decis Sci & Adv Analyt Med Affairs Pharmacovigilance & Regulatory Affairs Mullerstr 178 D-13353 Berlin Germany Bayer US LLC Pharmaceut Pharmacovigilance Benefit Risk Managem Whippany NJ USA Bayer US LLC Digital Transformat & Informat Technol Pharma Adverse Event Management Morristown NJ USA Lenolution GmbH Berlin Germany Bayer AG Pharmaceut Pharmacovigilance Innovat & Digitaliza Berlin Germany Bayer AG Pharmaceut Pharmacovigilance R&D Data Sci Berlin Germany Bayer AG Pharmaceut Pharmacovigilance Data Sci & Insight G Berlin Germany

Introduction Signal validation in pharmacovigilance is the process of evaluating data to decide whether evidence is sufficient to justify further assessment of a detected signal. during the signal validation process, safety experts in our organization are required to review signals of disproportionate reporting (Sdrs) and classify them into one of six predefined categories. Objective This experiment explored the extent to which predictive machine learning (ML) models can support the decision making of safety experts by accurately identifying the most appropriate predefined signal validation category. Methods We extracted cumulative data for six medicinal products, consisting of historic Sdr validations and Individual Case Safety reports, from the company's safety database for training and testing of the ML model. We implemented a decision tree-based supervised multiclass classifier model termed Gradient Boosted Trees followed by a SHapley Additive exPlanations (SHAP) analysis to mitigate the "black box" effect of the ensemble model by identifying the key predicting features in the model. Following a retrospective analysis, a prospective experiment was conducted to test the model accuracy and user acceptance in a real-life setting. results The prediction accuracy of our ML model ranged from 83 to 86% over 3 months for the six medicinal products. The applicability of the model was confirmed by the company's safety experts. Additionally, the systematic predictions provided valuable information to the safety experts and assisted them in reviewing the Sdrs efficiently and consistently. Conclusions This experiment demonstrated that it is possible to train a multiclass classification model to accurately predict signal validation categories for Sdrs. More importantly, the transparency of the predictions provided by the SHAP analysis led to high acceptance by the safety experts.

关键词：

来源：评论

学校读者我要写书评

暂无评论

New prognostic model for patients with advanced gastric cancer:Fluoropyrimidine/platinum doublet for first-line chemotherapy

引用

World Journal of Gastroenterology 2021年第48期27卷 8357-8369页

作者： dong-Hoe Koo Min-Hee ryu Mi-Yeon Lee Mee-Sun Moon Yoon-Koo Kang Division of Hematology/Oncology Department of Internal MedicineKangbuk Samsung HospitalSungkyunkwan University School of MedicineSeoul 03181South Korea Department of Oncology Asan Medical CenterUniversity of Ulsan College of MedicineSeoul 05505South Korea Division of Biostatistics Department of R&D ManagementKangbuk Samsung HospitalSeoul 03181South Korea

BACKGrOUNd New prognostic factors have been reported in patients with metastatic or recurrent gastric cancer(MrGC),necessitating modifications to the previous prognostic *** To develop a new model,MrGC patients who received fluoropyrimidines/platinum doublet chemotherapy between 2008 and 2015 were *** A total of 1883 patients was divided into a training set(n=937)and an independent validation set(n=946).rESULTS Multivariate analysis showed that the following six factors were associated with poor overall survival(OS)in the training set:Eastern Cooperative Oncology Group performance score≥2 and bone metastasis(2 points each),peritoneal metastasis,high alkaline phosphatase level,low albumin level,and high neutrophil-lymphocyte ratio(1 point each).A prognostic model was developed by stratifying patients into good(0-1 point),moderate(2-3 points),and poor(≥4 points)risk *** the validation set,the median OS of the three risk groups was 15.8,10.1,and 5.7 mo,respectively,and those differences were significant(P<0.001).CONCLUSION We identified six factors readily measured in clinical practice that are predictive of poor prognosis in patients with *** new model is simpler than the old and more easily predicts OS.

关键词： Stomach neoplasms Chemotherapy Prognosis Validation Gastric cancer

来源：评论

学校读者我要写书评

暂无评论

Enhanced Agricultural Methods and Sustainable Farming Through IoT and AI Technology 2

Enhanced Agricultural Methods and Sustainable Farming Throug...

引用

2nd International Conference on Intelligent Cyber Physical Systems and Internet of Things (ICoICI)

作者： Manivannan, K. Gowda, dankan, V Pavan, B. H. V. V. S. r. K. K. Aravindh, S. Nithisha, C. Tanguturi, rama Chaitanya VSB Engn Coll Dept Informat Technol Karur Tamil Nadu India BMS Inst Technol & Management Dept Elect & Commun Engn Bangalore Karnataka India Bonam Venkata Chalamayya Inst Technol & Sci Dept ECE Amalapuram Andhra Pradesh India Vel Tech Rangarajan Dr Sagunthala R&D Inst Sci & Dept Comp Sci & Engn Chennai Tamil Nadu India Mohan Babu Univ Sch Comp Dept Data Sci Tirupati Andhra Pradesh India PACE Inst Technol & Sci Dept Comp Sci & Engn Ongole Andhra Pradesh India

ISBN: (纸本)9798331540661;9798331540678

The combination of IoT and AI technologies in the future promises to disrupt agriculture positively while trying to solve problems affecting the sector through embracing technological advances. The following paper focuses on the development of an IoT and AI framework for enhancing practices in agriculture through real-time control and smart control. Wireless IoT sensors are placed in the farms to monitor important parameters of farms like moisture content, temperature, humidity etc and health of crops. Consequently, data is harvested to assist with accurate irrigation, climatic regulation, and early diagnosis of disease. From the experimental results observed it became clear that resource utilization was boosted by 25% of lesser water usage while crop yields were boosted by as much as 30%. It also early identifies crop diseases, hence cutting crop losses by 15%. Such is crucial to stress that the results obtained reveal the ability of the system to improve the sustainability and productivity of agriculture. Future work will comprise the fine-tuning of the AI model, enhancement of sensors, and their incorporation with other smart technologies besides adapting this strategy for various agricultural conditions, hence the importance of smart solutions in the promotion of eco-friendly farming.

关键词： Internet of Things Artificial Intelligence Sustainable Farming Agriculture Technology Precision Farming Smart Agriculture

来源：评论

学校读者我要写书评

暂无评论

Frequency of weight and body composition increases in advanced non-small cell lung cancer patients during first line therapy

引用

JOUrNAL OF CACHEXIA SArCOPENIA ANd MUSCLE 2024年第6期15卷 2311-2322页

作者： Bonomi, Philip Moudgalya, Hita Gomez, Sandra L. Shah, Palmi Basu, Sanjib Batus, Marta Martinka, Levi B. Abdelkader, Ahmed Tzameli, Iphigenia Cobain, Sonia Collins, Susie Keliher, Edmund J. Breen, danna M. Calle, roberto A. Fidler, Mary Jo Borgia, Jeffrey A. Rush Univ Div Hematol Oncol Med Ctr Chicago IL 60612 USA Rush Univ Med Ctr Dept Anat & Cell Biol Chicago IL 60612 USA Rush Univ Med Ctr Dept Clin Nutr Chicago IL USA Rush Univ Med Ctr Dept Radiol Chicago IL USA Univ Illinois Sch Publ Hlth Biostat Chicago IL USA Pfizer Inc Internal Med Res Unit Cambridge MA USA Pfizer R&D UK Ltd Global Biometr & Data Management Sandwich England Pfizer Inc Early Clin Dev Cambridge MA USA Rush Univ Med Ctr Dept Pathol Chicago IL USA

Background: The primary objective of this study was to assess the frequency of body composition increases and their relationships to changes in body weight in two cohorts of real world, treatment-na & iuml;ve, advanced non-small cell lung cancer (NSCLC) patients. One cohort received the current standard of care (CSOC), which consisted of immunotherapy and newer chemotherapy regimens, and the other cohort was treated with the former standard of care (FSOC), consisting only of older platinum-containing regimens. Methods: CSOC (n = 106) and FSOC (n = 88) cohorts of advanced NSCLC patients were included in this study. Weights were collected at each clinical visit, and body composition analysis from routine chest computed tomography via automated segmentation software assessed at baseline and at 6 and 12 weeks. Standard statistical methods were used to calculate relationships between changes in weight and in body composition. results: The CSOC cohort contained 106 stage IV NSCLC patients treated between 16/12/2014 and 22/10/2020 while the FSOC cohort contained 88 stage III/IV NSCLC patients treated between 16/6/2006 and 18/11/2014. While each cohort exhibited decreases in median weight, body mass index (BMI), mean skeletal muscle index (SMI) and subcutaneous adipose tissue index (SATI) at the 6 and 12 week time points, a subset of patients experienced increases in these parameters. Using a threshold of >= 2.5% increase for weight, BMI, SMI, and SATI at the 12 week time point, both cohorts showed similar (20.5% and 27.3%) increases in these parameters. With a cut point of >= 5% increase at 12 weeks follow-up, 8.0% to 25.0% of the patients gained >= 5% in weight, BMI, SMI and SATI. Comparing these results in each cohort showed no significant differences. Pearson coefficients for weight change related to changes in SMI and SATI at 6 and 12 weeks ranged from 0.31 to 0.58 with all P values <0.02. Pearson coefficients for weight change at 12 weeks related to changes in VATI an

关键词： body composition body weight cancer cachexia chemotherapy immunotherapy non-small cell lung cancer

来源：评论

学校读者我要写书评

暂无评论

Blockchain-based trust mechanism for digital twin empowered Industrial Internet of Things

引用

FUTUrE GENErATION COMPUTEr SYSTEMS-THE INTErNATIONAL JOUrNAL OF ESCIENCE 2023年 141卷 16-27页

作者： Sasikumar, A. Vairavasundaram, Subramaniyaswamy Kotecha, Ketan Indragandhi, V. ravi, Logesh Selvachandran, Ganeshsree Abraham, Ajith Vel Tech Rangarajan Dr Sagunthala R&D Inst Sci & Dept Elect & Commun Engn Chennai Tamil Nadu India SASTRA Sch Comp Thanjavur India Symbiosis Int Symbiosis Ctr Appl Artificial Intelligence Pune Maharashtra India Vellore Inst Technol Sch Elect Engn Vellore Tamil Nadu India Vellore Inst Technol SENSE Chennai Tamil Nadu India UCSI Univ Fac Business & Management Jalan Menara GadingCheras Kuala Lumpur 56000 Malaysia UCSI Univ Inst Actuarial Sci & Data Analyt Jalan Menara GadingCheras Kuala Lumpur 56000 Malaysia Machine Intelligence Res Labs Auburn WA 98071 USA

Emerging technologies such as blockchain and digital twins are essential for the rapid development and employment in Industry 5.0 revolution. With the growing number of industrial IoT nodes, optimizing the network and availing of limited resources to enable secure transmission is difficult. A digital twin is the virtual representation of a physical device that completely depends on sensor data for the critical decision-making simulation process. To this end, we combine a blockchain-based distributed network with a digital twin for the Industrial Internet of Things (IIoT) applications. This paper proposes a blockchain-based Proof of Authority (PoA) trust mechanism to provide high-quality services such as security and data privacy in IIoT. Furthermore, to enhance the authority of decentralized digital twin combined blockchain networks, we introduce a deterministic Pseudo-random Generation (dPrG) to generate a genesis block. To evaluate the trustworthiness of the proposed system, we simulate the blockchain network with a digital twin using IIoT sensor nodes. The simulation result shows that the PoA-based authority master nodes can reduce energy consumption and enhance data security.(c) 2022 Elsevier B.V. All rights reserved.

关键词： digital twin Industry 5 0 Blockchain technology Proof of authority Industrial Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Safety of nivolumab monotherapy in five cancer types: pooled analysis of post-marketing surveillance in Japan

引用

INTErNATIONAL JOUrNAL OF CLINICAL ONCOLOGY 2024年第7期29卷 932-943页

作者： Hiraizumi, Kenji Honda, Chikara Watanabe, Ayu Nakao, Takafumi Midorikawa, Shuichi Abe, Hiromi Matsui, Nobuki Yamamoto, Tsunehisa Sakamoto, Takahiko Ono Pharmaceut Co Ltd Oncol Med Affairs 8-2 Kyutaromachi 1-Chome Chuo Ku Osaka 5418564 Japan Ono Pharmaceut Co Ltd Pharmacovigilance Dept PV Data Strategy 2-1-5 Dosho machiChuo-ku Osaka 5418526 Japan Ono Pharmaceut Co Ltd Safety Management Pharmacovigilance Dept 2-1-5 Dosho MachiChuo Ku Osaka 5418526 Japan Bristol Myers Squibb KK R&D Dept Biometr & Data Sci Otemachi One Tower1-2-1 OtemachiChiyoda ku Tokyo 1000004 Japan Bristol Myers Squibb KK Oncol Med Otemachi One Tower1-2-1 OtemachiChiyoda ku Tokyo 1000004 Japan Bristol Myers Squibb KK Patient Safety Japan Otemachi One Tower1-2-1 OtemachiChiyoda ku Tokyo 1000004 Japan

Background Nivolumab has been approved for treating >= 10 cancer types. However, there is limited information on the incidence of rare, but potentially serious, treatment-related adverse events (TrAEs), as well as notable TrAEs in patients with certain medical disorders or older patients in Japan. Methods We performed pooled analyses of data from published post-marketing surveillance in Japan of nivolumab monotherapy for patients with malignant melanoma, non-small cell lung cancer, renal cell carcinoma, head and neck cancer, and gastric cancer to determine the frequencies of 20 categories of TrAEs of special interest overall and in patient groups with higher perceived safety risks (history of autoimmune disease, interstitial lung disease, tuberculosis, or hepatitis B/C;patients vaccinated during nivolumab treatment;and older patients [>= 75 years]). results The overall population comprised 7421 patients treated with nivolumab. TrAEs were reported in 49.1% of patients, with grade >= 3 TrAEs in 16.7%. Endocrine disorders (14.4%), hepatobiliary disorders (10.9%), and interstitial lung disease (7.0%) were the three most common categories (any grade). The incidences of rare TrAEs with high risk of becoming serious, which occurred in < 1% of patients, were consistent with those in previous reports. The frequencies of TrAEs were not markedly increased in the specified patient groups relative to the overall population. Conclusion To our knowledge, this is the largest study examining the safety of nivolumab-treated patients in real-world clinical practice including rare but potentially serious TrAEs. We found no new signals in the safety of nivolumab among the patient groups relative to the overall population, and no additional safety measures are required in these groups. Trial registration UMIN000048892 (overall analysis), JapicCTI-163272 (melanoma), Japic-163271 (non-small cell lung cancer), JapicCTI-184071 (head and neck cancer), JapicCTI-184070 (gastric cancer), and Jap

关键词： Nivolumab Post-marketing surveillance real-world clinical practice Safety Treatment-related adverse events

来源：评论

学校读者我要写书评

暂无评论

引用

20th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2021

作者： du, Yali Liu, Bo Moens, Vincent Liu, Ziqi ren, Zhicheng Wang, Jun Chen, Xu Zhang, Haifeng University College London Institute of Automation Chinese Academy of Sciences Huawei R&D UK University of California Los Angeles United States Beijing Key Laboratory of Big Data Management and Analysis Methods GSAI Renmin University of China

ISBN: (纸本)9781713832621

Communication improves the efficiency and convergence of multiagent learning. Existing study of agent communication has been limited on predefined fixed connections. While an attention mechanism exists and is useful for scheduling the communication between agents, it, however, largely ignores the dynamical nature of communication and thus the correlation between agents' connections. In this work, we adopt a normalizing flow to encode correlation between agents interactions. The dynamical communication topology is directly learned by maximizing the agent rewards. In our end-to-end formulation, the communication structure is learned by considering it as a hidden dynamical variable. We realize centralized training of critics and graph reasoning policy, and decentralized execution from local observation and message that are received through the learned dynamical communication topology. Experiments on cooperative navigation in the particle world and adaptive traffic control tasks demonstrate the effectiveness of our method. © 2021 International Foundation for Autonomous Agents and Multiagent Systems (***). All rights reserved.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Predicting study duration in clinical trials with a time-to-event endpoint

引用

STATISTICS IN MEdICINE 2021年第10期40卷 2413-2421页

作者： Machida, ryunosuke Fujii, Yosuke Sozu, Takashi Tokyo Univ Sci Dept Informat & Comp Technol Grad Sch Engn Tokyo Japan Natl Canc Ctr Ctr Res Adm & Support Biostat Div Tokyo Japan Pfizer R&D Japan GK Biometr & Data Management Tokyo Japan Tokyo Univ Sci Fac Engn Dept Informat & Comp Technol Tokyo Japan

In event-driven clinical trials comparing the survival functions of two groups, the number of events required to achieve the desired power is usually calculated using the Freedman formula or the Schoenfeld formula. Then, the sample size and the study duration derived from the required number of events are considered;however, their combination is not uniquely determined. In practice, various combinations are examined considering the enrollment speed, study duration, and the cost of enrollment. However, effective methods for visually representing their relationships and evaluating the uncertainty in study duration are insufficient. We developed a graphical approach for examining the relationship between sample size and study duration. To evaluate the uncertainty in study duration under a given sample size, we also derived the probability density function of the study duration and a method for updating the probability density function according to the observed number of events (ie, information time). The proposed methods are expected to improve the operation and management of clinical trials with a time-to-event endpoint.

关键词： clinical trial prediction sample size study duration time‐ to‐ event

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Blockchain Framework for Secure, Scalable, and Energy-Efficient digital Identity management with Token-based Selective disclosure 3

A Hybrid Blockchain Framework for Secure, Scalable, and Ener...

引用

3rd International Conference on Electronics and renewable Systems, ICEArS 2025

作者： Velmurugan, M. Shinzeer, C.K. Maya, G. ramya, r. Kanimozhi, r. Lathif, Syed Ismail Abdul Vel Tech Rangarajan Dr Sagunthala R&d Institute of Science And Technology Department Of Computer Science & Engineering Chennai600 062 India Lovely Professional University Department of School of Computer Applications Punjab Phagwara144411 India Srm Institute of Science and Technology Faculty of Management Kattankulathur603 203 India K.Ramakrishnan College of Engineering Department of Electronics and Communication Engineering Samayapuram621112 India Muthayammal Engineering College Computer Science and Engineering Rasipuram637408 India Srm Institute of Science and Technology Department of Data Science and Business Systems Chennai603203 India

ISBN: (纸本)9798331509675

data breaches, identity theft, and the lack of user control within traditional digital identity management systems, it begs a more secure and decentralized alternative. In this study we propose a blockchain based digital identity management framework that implements privacy, security and transparency by employing distributed ledger technology. To provide tamper proof identity storage and automated verification, the proposed model uses cryptographic hashing and smart contracts. The use of a novel token-based access mechanism enables users to safely share their identity data with third parties, while keeping sensitive information out of sight. Security metrics are enhanced by 30% for data integrity with 45% reduction in unauthorized access attempts all through simulations. The framework also achieves improved efficiency reducing identity verification time by 40 percent compared to traditional systems. It offers a promising approach to address important vulnerabilities in centralized identity management in line with the development of marketable and user-friendly digital identity solutions. © 2025 IEEE.

关键词： data integrity

来源：评论

学校读者我要写书评

暂无评论

Projection of fuel cell electric vehicle demand reflecting the feedback effects between market conditions and market share affected by spatial factors

引用

ENErGY POLICY 2023年 173卷

作者： Ko, Sungmin Shin, Jungwoo Sci & Technol Policy Inst STEPI R&D Financial Project Evaluat Ctr A 3F Sejong Natl Res Complex370 Sicheong daero Sejong 30147 South Korea Kyung Hee Univ Dept Ind & Management Syst Engn Dept Big Data Analyt 1732 Deogyeong daero Yongin 17104 Gyeonggi South Korea

The Korean government has planned policies to increase the penetration rate of fuel cell electric vehicles (FCEVs). Policy intervention has a positive effect on FCEV diffusion. Infrastructure distribution plays a significant role in accelerating penetration rate at the early stage of the market. Although inevitably differences exist in the accessibility of hydrogen refueling stations (HrSs) by region due to various constraints, few studies have considered accessibility in detail. This study analyzes how policies that vary depending on time and space, including infrastructure distribution, impact demand for FCEVs. A multistage structure is employed in the analysis to reflect the influence of spatial factors. Vehicle preference is analyzed through a discrete choice experiment at the first stage. The second stage solves the location problem and predicts the market share of FCEVs by reflecting the feedback effect between FCEVs' market share and the accessibility of HrSs through a loop structure. The results indicate that improving access to HrSs positively affects the initial stage of the market;however, after accessibility reaches a certain level, it no longer affects the market share. The subsidies for hydrogen refueling costs bring a relatively rapid change to the gradually increasing penetration rate of FCEVs.

关键词： Consumer preference demand forecasting discrete choice experiment Fuel cell electric vehicle Infrastructure distribution Location optimization

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：