检索结果-内蒙古大学图书馆

Detection of adverse drug reactions: evaluation of an automatic data processing applied in oncology performed in the French Diagnosis Related Groups database

引用

FUNDAMENTAL & CLINICAL PHARMACOLOGY 2018年第2期32卷 227-233页

作者： Quillet, Alexandre Colin, Olivier Bourgeois, Nicolas Favreliere, Sylvie Ferru, Aurelie Boinot, Laurence Lafay-Chebassier, Claire Perault-Pochat, Marie-Christine CHU Poitiers Serv Pharmacol Clin & Vigilances 2 Rue Mil F-86021 Poitiers France CHU Poitiers Serv Neurol 2 Rue Mil F-86021 Poitiers France CHU Poitiers Serv Oncol Med 2 Rue Mil F-86021 Poitiers France CHU Poitiers Serv Informat Med 2 Rue Mil F-86021 Poitiers France CHU Poitiers INSERM CIC 1402 2 Rue Mil F-86021 Poitiers France

The aim of this study was to assess an automated detection method of serious adverse reactions induced by oral targeted therapy (OTT) in patients with cancer, performed in the French Diagnosis Related Groups (DRG) database. Patients with cancer of the Poitiers hospital who started an OTT between 2014 and 2015 were included. This study focused on adverse drug reaction which required inpatient hospitalization (ADR(h)). All diagnoses coded in the DRG database for hospital stays that occurred within 3 months after OTT initiation were collected (potential ADR(h)). Filters (exclusion criteria) were automatically applied on potential ADR(h) to exclude diagnoses that were not adverse drug reactions (false positives). A pharmacovigilance review was carried out to identify ADR(h) in the medical records (reported ADR(h)). The sensitivity and specificity of the detection method were estimated for each filter combinations by comparison between potential and reported ADR(h). This study included 129 patients. The medical records review led to identify 19 ADR(h) (all coded in the DRG database) in 14 patients. To maintain a 100% sensitivity of the method detection, the best specificity obtained was 58.3% (95% IC: [55.2-61.4]).The use of restrictive filters (drug' in the diagnostic label, specific diagnosis code for adverse cancer drug reaction) resulted in a 97.8% specificity (95% IC: [96.6-98.5]) with a 38.2% sensitivity (95% IC: [23.9-55.0]). Our method has detected the third of ADR(h) with an excellent specificity. Complementary experimentations in pharmacovigilance centers are necessary to evaluate the interest of this tool in routine in addition to spontaneous reporting.

关键词： neoplasms molecular targeted therapy pharmacovigilance automatic data processing Diagnosis Related Groups-based information system adverse drug reactions

来源：评论

学校读者我要写书评

暂无评论

Adaptive Deep Learning System for Investigating General data

引用

CYBERNETICS AND SYSTEMS ANALYSIS 2023年第5期59卷 704-712页

作者： Dovgyi, S. Zoziuk, M. Koroliouk, D. Natl Acad Sci Ukraine Inst Telecommun & Global Informat Space Kiev Ukraine Natl Tech Univ Ukraine Igor Sikorsky Kyiv Polytech Inst Kiev Ukraine Natl Tech Univ Ukraine Igor Sikorsky Kyiv Polytech Inst Inst Math Inst Telecommun & Global Informat SpaceNatl Acad Kiev Ukraine Univ Roma Tor Vergata UNESCO Interdisciplinary Chair Biotechnol & Bioet Lab Digital Innovat Rome Italy

The paper presents an approach to analyzing large amounts of data lacking a clear relationship. The approach serves to identify at least some relationship between the data and determine the degree of that interconnection when such a relationship is detected. The authors have demonstrated the possibility of automatic data processing and automatic adjustment of deep learning system parameters to create a deep learning platform during data parameter analysis. The paper describes how this system will cater to the needs of professionals in other fields who have never directly utilized deep learning systems. Based on the well-known MNIST dataset, the authors have determined that using specific parameters of this data, one can identify their influence on the prediction accuracy of deep learning system.

关键词： neural network automatic data processing sampling informativeness prediction system processing methods

来源：评论

学校读者我要写书评

暂无评论

Microtomography to traditional dental radiograph: projecting 3-dimensional initial proximal caries lesion annotations for enhanced radiographic delineation

引用

DENTOMAXILLOFACIAL RADIOLOGY 2025年第4期54卷 320–328页

作者： Gonzalez-Valenzuela, Ricardo E. Vu, Quoc T. D. Mettes, Pascal Loos, Bruno G. Marquering, Henk Berkhout, Erwin Univ Amsterdam Acad Ctr Dent Amsterdam ACTA Dept Oral Radiol NL-1182 DB Amsterdam Netherlands Vrije Univ Amsterdam NL-1182 DB Amsterdam Netherlands Acad Med Ctr Univ Amsterdam AMC Dept Biomed Engn & Phys NL-1105 AZ Amsterdam Netherlands Univ Amsterdam Informat Inst VISlab NL-1098 XH Amsterdam Netherlands Univ Amsterdam Acad Ctr Dent Amsterdam ACTA Dept Periodontol NL-1182 DB Amsterdam Netherlands Acad Med Ctr Univ Amsterdam AMC Dept Radiol & Nucl Med NL-1105 AZ Amsterdam Netherlands

Objectives This study was undertaken to generate high-quality radiographic annotations of initial proximal carious lesions based on micro-CT scans. Specifically, we projected manually and automatically acquired annotations of micro-CT scans onto corresponding traditional dental *** We utilized the Diagnostic Insights for Radiographic Early-caries with micro-CT (ACTA-DIRECT) dataset of manually annotated initial proximal carious lesions in micro-CT scans and radiographs, the former serving as reference-standard. Production of high-quality radiographic annotations entailed the following: (1) acquiring a reference-standard (for a semi-automated approach) or generating a fully automated micro-CT-based annotation (for a fully automated approach);(2) simulating the corresponding radiograph by projecting the micro-CT scan to find the suitable projection parameters;and (3) superimposing micro-CT-based caries annotations onto radiographs, using identical projection parameters. To evaluate the subsequent accuracy of the annotations on radiograph, we assessed the sensitivity, specificity, and International Caries Classification and Management System (ICCMS) staging of micro-CT-based automated annotations. Projection accuracy was qualitatively *** Micro-CT-based automated annotations outperformed conventional annotations achieving a sensitivity of 50% (95% CI: 42%-59%) compared to 42% (95% CI: 34%-51%) and specificity of 99% (95% CI: 96%-100%) compared to 92% (95% CI: 87%-94%). Among correctly identified micro-CT-based automated annotations, 94% (61/65) were also accurately classified;and 80% of micro-CT projections were ranked as suitably similar to corresponding *** Micro-CT imaging offers resource-rich depictions, enabling more accurate annotations than those achievable through conventional means. By projecting micro-CT-based annotations of initial proximal caries onto radiographs, some limitations of the conventional radiograph

关键词： radiography micro-CT scans carious lesions data annotation automatic data processing

来源：评论

学校读者我要写书评

暂无评论

Comparing Manual and automatic Artifact Detection in Sleep EEG Recordings

引用

PSYCHOPHYSIOLOGY 2025年第2期62卷 e70016页

作者： Ujma, Peter P. Dresler, Martin Bodizs, Robert Semmelweis Univ Inst Behav Sci Budapest Hungary Radboud Univ Nijmegen Med Ctr Donders Inst Nijmegen Netherlands

Sleep electroencephalogram (EEG) recordings can be contaminated by artifacts. Visual and automatic methods have been developed to mark such erroneous segments of EEG data. Here, we systematically explored the effect of artifacts on the sleep EEG power spectrum density (PSD), and we compared gold-standard visual detections to a simple automatic detector using Hjorth parameters to identify artifacts. We found that most distortions in the all-night average PSD occur because of a small minority of highly anomalous artifacts, which mainly affect the beta and gamma frequency ranges and NREM delta. Visual and automatic detections only showed moderate agreement in which data segments are artifactual. However, the resulting all-night average PSD is highly similar across all methods, and PSDs calculated with all methods successfully recover the known correlations of PSD with age and sex. No parameter settings of the automatic detector clearly outperformed others. Additionally, we showed that accurate average PSD estimates can be recovered from just a fraction of available data epochs. Our results suggest that artifacts represent a minor and easily solvable problem in sleep EEG recordings. Most visually identified artifacts do not seriously distort estimates of mid-frequency activity in the sleep EEG spectrum, and distortions to low and high frequencies can be eliminated using a simple automatic detection method nearly as well as with visual detections. These findings show that the visual inspection of EEG data is not necessary to eliminate the effects of artifacts, which is encouraging for the expected performance of automatic preprocessing in large sleep EEG databases.

关键词： artifacts automatic data processing data quality EEG sleep

来源：评论

学校读者我要写书评

暂无评论

A New Fine Detection Approach for Explosion Cracks Based on Distributed Fiber Optic Sensing and Deep Learning

引用

ROCK MECHANICS AND ROCK ENGINEERING 2025年 1-16页

作者： Li, Jin Yang, Renshu Yang, Liyun Zuo, Jinjing Zhang, Xiang You, Yuanyuan Kang, Yiqiang China Univ Min & Technol Beijing Sch Mech & Civil Engn Beijing 10083 Peoples R China Univ Sci & Technol Beijing Sch Civil & Resource Engn Beijing 100083 Peoples R China Univ Sci & Technol Beijing Sch Mech Engn Beijing 100083 Peoples R China

The formation and propagation of fracture fields under explosive loading significantly influence rock rupture morphology and blasting effectiveness. However, the transient nature of the explosive event and the complex coupling of blast-induced stresses pose considerable challenges in accurately monitoring crack propagation during experimental investigations. This study introduces, for the first time, an innovative approach for precise detection of explosion-induced cracks using Distributed Fiber Optic Sensing (DFOS) integrated with deep learning techniques. Initially, the feasibility of DFOS for monitoring crack propagation under explosive loading is validated. Subsequently, millimeter-level precision in tracking crack extension paths is achieved through polar coordinate transformation and color mapping techniques. A novel strain profile image generation approach is also developed to facilitate the visual representation of DFOS strain data. The spatial distribution of cracks is successfully identified using the YOLOv5 deep learning model, achieving precision, recall, and F1 scores of 0.927, 0.933, and 0.930, respectively, demonstrating the high efficacy of the proposed detection method. This approach eliminates the need for traditional visual imaging and presents a pioneering solution for detecting internal fracture fields induced by explosions.

关键词： Blasting Distributed fiber optics Crack detection Deep learning automatic data processing

来源：评论

学校读者我要写书评

暂无评论

Can ChatGPT4-vision identify radiologic progression of multiple sclerosis on brain MRI?

引用

EUROPEAN RADIOLOGY EXPERIMENTAL 2025年第1期9卷 1-9页

作者： Kelly, Brendan S. Duignan, Sophie Mathur, Prateek Dillon, Henry Lee, Edward H. Yeom, Kristen W. Keane, Pearse A. Lawlor, Aonghus Killeen, Ronan P. St Vincents Univ Hosp Dublin Ireland UCD Insight Ctr Data Analyt Dublin Ireland Irish Clin Acad Training Wellcome Trust HRB Dublin Ireland Univ Coll Dublin Sch Med Dublin Ireland Lucille Packard Childrens Hosp Stanford Stanford CA USA UCL London England

BackgroundThe large language model ChatGPT can now accept image input with the GPT4-vision (GPT4V) version. We aimed to compare the performance of GPT4V to pretrained U-Net and vision transformer (ViT) models for the identification of the progression of multiple sclerosis (MS) on magnetic resonance imaging (MRI).MethodsPaired coregistered MR images with and without progression were provided as input to ChatGPT4V in a zero-shot experiment to identify radiologic progression. Its performance was compared to pretrained U-Net and ViT models. Accuracy was the primary evaluation metric and 95% confidence interval (CIs) were calculated by bootstrapping. We included 170 patients with MS (50 males, 120 females), aged 21-74 years (mean 42.3), imaged at a single institution from 2019 to 2021, each with 2-5 MRI studies (496 in total).ResultsOne hundred seventy patients were included, 110 for training, 30 for tuning, and 30 for testing;100 unseen paired images were randomly selected from the test set for evaluation. Both U-Net and ViT had 94% (95% CI: 89-98%) accuracy while GPT4V had 85% (77-91%). GPT4V gave cautious nonanswers in six cases. GPT4V had precision (specificity), recall (sensitivity), and F1 score of 89% (75-93%), 92% (82-98%), 91 (82-97%) compared to 100% (100-100%), 88 (78-96%), and 0.94 (88-98%) for U-Net and 94% (87-100%), 94 (88-100%), and 94 (89-98%) for *** performance of GPT4V combined with its accessibility suggests has the potential to impact AI radiology research. However, misclassified cases and overly cautious non-answers confirm that it is not yet ready for clinical *** statementGPT4V can identify the radiologic progression of MS in a simplified experimental setting. However, GPT4V is not a medical device, and its widespread availability highlights the need for caution and education for lay users, especially those with limited access to expert *** PointsWithout fine-tuning or the need for prior coding experience, GPT4V

关键词： Artificial intelligence automatic data processing Brain Disease progression Multiple sclerosis

来源：评论

学校读者我要写书评

暂无评论

Digitalization and artificial intelligence in radiation oncology

引用

Best Practice Onkologie 2024年第7-8期19卷 288-295页

作者： El Shafie, Rami A. Janssen, Stefan Braulke, Friederike Rieken, Stefan Grohmann, Maximilian Klinik für Strahlentherapie und Radioonkologie Universitätsmedizin Göttingen (UMG) Georg-August-Universität Robert-Koch-Straße 40 Göttingen 37075 Germany Klinik für Strahlentherapie Universität zu Lübeck Lübeck Germany Gemeinschaftspraxis für Strahlentherapie und Radioonkologie (GSR) Hannover Germany UniversitätsKrebszentrum G-CCC Universitätsmedizin Göttingen (UMG) Göttingen Germany Strahlentherapie und Radioonkologie Universitätsklinikum Hamburg Eppendorf (UKE) Hamburg Germany AG Digitalisierung Deutsche Gesellschaft für Radioonkologie (DEGRO) Berlin Germany

Neuronal networks enable flexible and adaptable information processing. This renders them particularly suitable for complex tasks such as image recognition or prognostic modeling. Via application of these concepts, artificial intelligence (AI) can contribute to more precise diagnoses, creation of individualized treatment plans, and improvement of therapeutic efficiency. The use of AI in diagnostic imaging to detect lung nodules is a promising approach, as is its application in lung cancer screening. Alongside prediction of the probability of adverse events, AI is also of interest for prediction of the response to radiotherapy and during follow-up. For example, during individualized treatment follow-up of patients with lung cancer, use of a web-based application with an integrated risk evaluation algorithm based on weekly recording of symptoms by the patients was shown to be superior to non-individualized follow-up, as longer overall survival was achieved due to early detection of recurrence and the overall clinical condition of patients was improved. © The Author(s), under exclusive licence to Springer Medizin Verlag GmbH, ein Teil von Springer Nature 2024.

关键词： automatic data processing Diagnostic screening programs Machine learning Neural networks (computer) Radiomics

来源：评论

学校读者我要写书评

暂无评论

A BIM-Based Coordination Support System for Emergency Response

引用

IEEE ACCESS 2021年 9卷 68814-68825页

作者： Feng, Yanxiao Wang, Julian Fan, Howard Hu, Yuqing Penn State Univ Dept Architectural Engn University Pk PA 16802 USA Univ Cincinnati Dept Elect Engn & Comp Engn Cincinnati OH 45211 USA

In fire emergencies, timely communication with on-site coordinators and accurate localization of first responders facilitates effective task assignment and resource allocation in harsh, low-visibility environments. Building information modeling (BIM) is widely accepted in the architecture, engineering, and construction industries as a central repository of building information. It could provide both the geometric building data and semantic information;however, the convenient linkage and integration with indoor location technologies for emergency purposes have not been addressed according to the authors' knowledge. A stand-alone BIM-based indoor location (BIMIL) framework and portal were designed and tested to enable the automatic extraction, transformation, and visualization of BIM-related data for public safety purposes in this study. Based on current information technology, this research reduces the gap in cross-application by supporting indoor location to overcome the primary shortcoming of existing indoor building models. Eliminating the need for specific software and skill in data processing, this portal will support on-site coordinators' importation of BIM files, allowing them to convert those files into processed and visualized indoor information containing key yet simplified geometric building data and essential emergency-related information such as fire rating hours, egresses, and hazardous materials. Additionally, the indoor location data can be integrated into a generalized 3D building model to support decision-making activities and management tasks in the field.

关键词： Buildings Emergency services Three-dimensional displays Task analysis Solid modeling Semantics Location awareness BIM on-site coordination indoor location automatic data processing user graphic interface

来源：评论

学校读者我要写书评

暂无评论

automatic Control of Prosthetic Socket Size for People WithTranstibial Amputation: Implementation and Evaluation

引用

IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING 2021年第1期68卷 36-46页

作者： Weathersby, Ethan J. Garbini, Joseph L. Larsen, Brian G. McLean, Jake B. Vamos, Andrew C. Sanders, Joan E. Univ Washington Dept Bioengn Seattle WA 98195 USA Univ Washington Dept Mech Engn Seattle WA 98195 USA Boeing Co Seattle WA 29208 USA

Objective: The purpose was to design, implement, and test a control system for a motor-actuated, cable-panel prosthetic socket that automatically maintains socket fit by continuous adjustment of the socket size. Methods: Sockets with motor-driven adjustable panels were fabricated for participants with transtibial amputation. A proportional-integral control system was implemented to adjust socket size based on Socket Fit Metric (SFM) data collected by an inductive sensor embedded within the socket wall. The sensed distance was representative of limb-to-socket distance. Testing was conducted with participants walking on a treadmill to characterize the system's capability to maintain a set point and to respond to a change in the set point. Results: Test results from 10 participants with transtibial amputation showed that the Integral of Absolute Error (IAE) to maintain a set point ranged from 0.001 to 0.046 mm with a median of 0.003 mm. When the set point was changed, IAE errors ranged from 0.001 to 0.005 mm, with a median of 0.003 mm. An IAE of 0.003 mm corresponded to approximately a 0.08% socket volume error, which was considered clinically acceptable. Conclusion: The capability of the control system to maintain and respond to a change in set point indicates that it is ready for evaluation outside of the laboratory. Significance: Integration of the developed control system into everyday prostheses may improve quality of life of prosthesis users by relieving them of the burden of continually adjusting socket size to maintain fit.

关键词： Sockets Prosthetics Control systems Testing Legged locomotion Atmospheric measurements Particle measurements Amputee prosthesis residual limb volume accommodation PI controller automated socket adjustment prosthesis fitting amputation microcomputer automatic data processing

来源：评论

学校读者我要写书评

暂无评论

automatic processing of Intensives at GSFC VLBI Analysis Center

Automatic Processing of Intensives at GSFC VLBI Analysis Cen...

引用

作者： Bolotin, S Baver, K Berube, M National Aeronautics and Space Administration Washington DC. Geospatial Information Authority of Japan Tsukuba Japan NVI INC

VLBI Intensive (INT) sessions are conducted to determine the change in Earth rotation, which is measured as a correction to UT1. This correction varies unpredictably over time. Because UT1 is used in precise navigation, particularly GNSS, rapid turnaround is very important. The decrease of time elapsed from observations to obtained results can be shortened with the automatic data processing of new INT sessions at the analysis stage.

关键词： Space geodesy automatic data processing Ut1 determination Vlbi

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：