检索结果-内蒙古大学图书馆

Automatic International Classification of Diseases coding system: Deep Contextualized Language Model With Rule-Based Approaches

引用

JMIR MEDICAL INFORMATICS 2022年第6期10卷 e37557页

作者： Chen, Pei-Fu Chen, Kuan-Chih Liao, Wei-Chih Lai, Feipei He, Tai-Liang Lin, Sheng-Che Chen, Wei-Jen Yang, Chi-Yu Lin, Yu-Cheng Tsai, I-Chang Chiu, Chi-Hao Chang, Shu-Chih Hung, Fang-Ming Natl Taiwan Univ Grad Inst Biomed Elect & Bioinformat Taipei Taiwan Far Eastern Mem Hosp Dept Anesthesiol New Taipei Taiwan Far Eastern Mem Hosp Dept Internal Med New Taipei Taiwan Natl Taiwan Univ Dept Comp Sci & Informat Engn Taipei Taiwan Natl Taiwan Univ Dept Elect Engn Taipei Taiwan Far Eastern Mem Hosp Dept Informat Technol New Taipei Taiwan Far Eastern Mem Hosp Cardiovasc Ctr Sect Cardiovasc Med New Taipei Taiwan Far Eastern Mem Hosp Dept Pediat New Taipei Taiwan Oriental Inst Technol Dept Healthcare Adm New Taipei Taiwan Far Eastern Mem Hosp Artificial Intelligence Ctr New Taipei Taiwan Far Eastern Mem Hosp Dept Med Affairs Sect Hlth Insurance New Taipei Taiwan Far Eastern Mem Hosp Med Records Dept New Taipei Taiwan Far Eastern Mem Hosp Dept Med Affairs 21Sec 2Nanya S Rd New Taipei 220216 Taiwan Far Eastern Mem Hosp Dept Surg Intens Care Unit New Taipei Taiwan

Background: The tenth revision of the International Classification of Diseases (ICD-10) is widely used for epidemiological research and health management. The clinical modification (CM) and procedure coding system (PCS) of ICD-10 were developed to describe more clinical details with increasing diagnosis and procedure codes and applied in disease-related groups for reimbursement. The expansion of codes made the coding time-consuming and less accurate. The state-of-the-art model using deep contextual word embeddings was used for automatic multilabel text classification of ICD-10. In addition to input discharge diagnoses (DD), the performance can be improved by appropriate preprocessing methods for the text from other document types, such as medical history, comorbidity and complication, surgical method, and special examination. Objective: This study aims to establish a contextual language model with rule-based preprocessing methods to develop the model for ICD-10 multilabel classification. Methods: We retrieved electronic health records from a medical center. We first compared different word embedding methods. Second, we compared the preprocessing methods using the best-performing embeddings. We compared biomedical bidirectional encoder representations from transformers (BioBERT), clinical generalized autoregressive pretraining for language understanding (Clinical XLNet), label tree-based attention-aware deep model for high-performance extreme multilabel text classification (AttentionXLM), and word-to-vector (Word2Vec) to predict ICD-10-CM. To compare different preprocessing methods for ICD-10-CM, we included DD, medical history, and comorbidity and complication as inputs. We compared the performance of ICD-10-CM prediction using different preprocesses, including definition training, external cause code removal, number conversion, and combination code filtering. For the ICD-10 PCS, the model was trained using different combinations of DD, surgical method, and key word

关键词： deep learning International Classification of Diseases medical records multilabel text classification natural language processing coding system algorithm electronic health record data mining

来源：评论

学校读者我要写书评

暂无评论

A coding Support system for the ICD-9-CM standard 2

A Coding Support System for the ICD-9-CM standard

引用

IEEE International Conference on Healthcare Informatics (ICHI)

作者： Chiaravalloti, Maria Teresa Guarasci, Roberto Lagani, Vincenzo Pasceri, Erika Trunfio, Roberto ICAR CNR Arcavacata Di Rende CS Italy DiLISE Univ Calabria Arcavacata Di Rende CS Italy FORTH Iraklion Crete Greece

ISBN: (纸本)9781479957019

The 9th revision of the International Classification of Diseases (as modified in the United States, also known as ICD-9-CM) is one of the most widely used classification system for clinical problems and procedures. Electronic health record systems usually require physicians to encode diagnoses or medical procedures through appropriate ICD-9-CM codes. Since ICD-9-CM is constituted by more than 13,000 diagnosis and 3,500 procedure codes, clearly the coding procedure is a nontrivial task. In this paper we present a coding support system for assisting physicians in the assignment of ICD-9-CM codes. The proposed system is based on tools for natural language processing and text-searches on knowledge bases. It analyzes a short medical text and then returns the list of ICD-9-CM codes that are most likely to be associated with the given text. A set of numerical experiments were carried out in order to assess the reliability and quality of the proposed support system. The results of the experiments show that the support system has an accuracy of 92%, largely improving physicians' average performances.

关键词： ICD-9-CM healthcare decision support tool coding system knowledge base natural language processing

来源：评论

学校读者我要写书评

暂无评论

Presentation of the coding and Assessment system for Narratives of Trauma (CASNOT): Application in Spanish Battered Women and Preliminary Analyses

引用

SPANISH JOURNAL OF PSYCHOLOGY 2017年 20卷 E33-E33页

作者： Fernandez-Lansac, Violeta Crespo, Maria Univ Complutense Madrid Spain

This study introduces a new coding system, the coding and Assessment system for Narratives of Trauma (CASNOT), to analyse several language domains in narratives of autobiographical memories, especially in trauma narratives. The development of the coding system is described. It was applied to assess positive and traumatic/negative narratives in 50 battered women (trauma-exposed group) and 50 nontrauma-exposed women (control group). Three blind raters coded each narrative. Inter-rater reliability analyses were conducted for the CASNOT language categories (multirater K-free coefficients) and dimensions (intraclass correlation coefficients). High levels of inter-rater agreement were found for most of the language domains. Categories that did not reach the expected reliability were mainly those related to cognitive processes, which reflects difficulties in operationalizing constructs such as lack of control or helplessness, control or planning, and rationalization or memory elaboration. Applications and limitations of the CASNOT are discussed to enhance narrative measures for autobiographical memories.

关键词： autobiographical memory coding system judge-based thematic content analyses language domain traumatic narrative

来源：评论

学校读者我要写书评

暂无评论

system FOR coding PLANT SPECIES FOR DATA-PROCESSING IN PHYTOSOCIOLOGY

引用

VEGETATIO 1976年第1期33卷 23-32页

作者： PIGNATTI, S UNIV TRIESTE IST & ORTO BOT I-34100 TRIESTE ITALY

A system for coding plant species is described. The system is in use in the project Data-Processing in phytosociology. The code consists of 7 digits, 4 for the genus and 3 for the species. The genus code is derived from Dalla Torre and Harms, with ad hoc numbers for Pteridophyta, Bryophyta and Lichenes. Species codes are established according to Flora Europaea, Volumes I-III, and for species not treated there according to an alphabetical list of species based on SW European floras, completed with ad hoc data for other parts of Europe. About 9000 species names have been coded at Trieste [Italy]. The coding system is compared with the systems of Ehrendorfer, Flora Europaea, alphabetic systems and Gould''s international plant index. Problems of nomenclatural changes and species concepts and their bearing on the code are discussed.

关键词： coding system Data-Processing Nomenclature Phytosociology Plant species

来源：评论

学校读者我要写书评

暂无评论

Power and exponential sums for generalized coding systems by a measure theoretic approach

引用

THEORETICAL COMPUTER SCIENCE 2015年 592卷 23-38页

作者： Kamiya, Yuichi Okada, Tatsuya Sekiguchi, Takeshi Shiota, Yasunobu Daito Bunka Univ Fac Econ Saitama 3558501 Japan Fukushima Med Univ Dept Nat Sci Fukushima 9601295 Japan Tohoku Gakuin Univ Fac Liberal Arts & Sci Dept Infomat Sci Sendai Miyagi 9813193 Japan

A measure theoretic approach to study the power and the exponential sums for the usual coding system has been developed since the 1990s. In this paper, we first introduce a new coding system, and then give explicit formulas for the power and the exponential sums for the coding system by the measure theoretic approach. An expression for the power sum using the generalized Takagi function will also be given. (C) 2015 Elsevier B.V. All rights reserved.

关键词： Power sum Exponential sum Paperfolding sequence coding system Probability measure Takagi function

来源：评论

学校读者我要写书评

暂无评论

Classification and coding systems for platelet-rich plasma (PRP): a peek into the history

引用

EXPERT OPINION ON BIOLOGICAL THERAPY 2021年第2期21卷 121-123页

作者： Sharun, Khan Pawde, Abhijit M. Amarpal Indian Vet Res Inst ICAR Div Surg Bareilly Uttar Pradesh India

Click to increase image sizeClick to decrease image size

关键词： Platelet rich plasma characterization classification composition coding system variables

来源：评论

学校读者我要写书评

暂无评论

What is the value of pain therapy in the German refined diagnosis-related-groups system?

引用

ANAESTHESIST 2006年第3期55卷 325-330页

作者： Meissner, W Thoma, R Bauer, M Univ Jena Klin Anasthesiol & Intens Therapie D-07740 Jena Germany Krankenhaus Missions Benediktinerinnen Schmerzzentrum Tutzing Germany Univ Kiel Klinikum Schleswig Holstein Klin Anaesthesiol & Operat Intensivmed Kiel Germany

The German refined diagnosis-related-groups (G-DRG) system was introduced on 1st January 2003, initially on a voluntary basis and on I st January 2004 the use of a G-DRG costing for stationary hospital treatment became obligatory. The possibility of a description of acute and chronic pain therapy in the G-DRG system was initially rudimentary and not logically planned and also a fair allotment of proceeds according to resources was not possible. By further development of the G-DRG system, pain therapeutic treatment could be improved in some areas, but in others it still remains unsatisfactory. This article offers a summary of the underlying systematics of the G-DRG system and consideration of chronic and current pain therapy in the GDRG system 2006. In addition to information on currently available possibilities of a pain therapeutical coding in conformation with the G-DRG system, the tasks which are still outstanding will be outlined.

关键词： German refined diagnosis-related-groups chronic pain therapy current pain therapy coding system

来源：评论

学校读者我要写书评

暂无评论

Recombinant Chinese Pinyin system for efficient processing of information in Chinese

引用

COMPUTER STANDARDS & INTERFACES 1998年第1期20卷 25-29页

作者： Tong, H Jin, L Argonne Natl Lab BioCARS Argonne IL 60439 USA

An enhanced Pinyin (Chinese phonetic symbol) coding system has been developed for creating a novel Romanized version of the Chinese language. The homophonic problem associated with inputting Chinese characters to computers has been solved by the addition of a suffix to the conventional Pinyin of individual Chinese characters as well as multisyllable words/phrases. The suffix for the Pinyin of a Chinese character comprises a combination of a tone symbol and a single letter index that is mostly designated as the first letter of an English word giving an appropriate translation. For multisyllable Chinese words, the suffix consists only of a single letter that indicates either the tone of the last Chinese character or the first letter of an English translation. The resulting set of Romanized Chinese notations, christened 'Chinish', make it possible to input Chinese characters as efficiently as English words. It is proposed that Chinish be used as a replacement for the current Pinyin system as a standard interface between Chinese speaking users and computers. (C) 1998 Elsevier Science B.V. All rights reserved.

关键词： Chinese Pinyin system Chinish coding system information processing

来源：评论

学校读者我要写书评

暂无评论

The necessity to develop a national classification system for Iranian traditional medicine

引用

HEALTH INFORMATION MANAGEMENT JOURNAL 2021年第3期50卷 128-139页

作者： Safdari, Reza Rezaeizadeh, Hossein Arji, Goli Abbassian, Alireza Mokhtaran, Mehrshad Dehghan, Reza Shekalyou, Sara Univ Tehran Med Sci Tehran Iran Saveh Univ Med Sci Markazi Iran

Background: Classification of disease and interventions in traditional medicine (TM) is necessary for standardised coding of information. Currently, in Iran, there is no standard electronic classification system for disease and interventions in TM. Objective: The current study aimed to develop a national framework for the classification of disease and intervention in Persian medicine based on expert opinion. Method: A descriptive cross-sectional study was carried out in 2018. The existing systems for the classification of disease and interventions in TM were reviewed in detail, and some of the structural and content characteristics were extracted for the development of the classification of Iranian traditional medicine. Based on these features, a self-administered questionnaire was developed. Study participants (25) were experts in the field of Persian medicine and health information management in Tehran medical universities. Results: Main axes for the classification of disease and interventions were determined. The most important applications of the classification system were related to clinical coding, policymaking, reporting of mortality and morbidity data, cost analysis and determining the quality indicators. Half of the participants (50%) stated that the classification system should be designed by maintaining the main axis of the World Health Organization classification system and changing the subgroups if necessary. A computer-assisted coding system for TM was proposed for the current study. Conclusion: Development of this classification system will provide nationally comparable data that can be widely used by governments, national organisations and academic researchers.

关键词： classification traditional medicine disease classification coding system health information management

来源：评论

学校读者我要写书评

暂无评论

The revised NEUROGES-ELAN system: An objective and reliable interdisciplinary analysis tool for nonverbal behavior and gesture

引用

BEHAVIOR RESEARCH METHODS 2016年第3期48卷 973-993页

作者： Lausberg, Hedda Sloetjes, Han German Sport Univ Cologne Dept Neurol Psychosomat Med & Psychiat Spottpk Mungersdorf 6 D-50939 Cologne Germany Max Planck Inst Psycholinguist Language Arch Wundtlaan 1 NL-6525 XD Nijmegen Netherlands

As visual media spread to all domains of public and scientific life, nonverbal behavior is taking its place as an important form of communication alongside the written and spoken word. An objective and reliable method of analysis for hand movement behavior and gesture is therefore currently required in various scientific disciplines, including psychology, medicine, linguistics, anthropology, sociology, and computer science. However, no adequate common methodological standards have been developed thus far. Many behavioral gesture-coding systems lack objectivity and reliability, and automated methods that register specific movement parameters often fail to show validity with regard to psychological and social functions. To address these deficits, we have combined two methods, an elaborated behavioral coding system and an annotation tool for video and audio data. The NEUROGES-ELAN system is an effective and user-friendly research tool for the analysis of hand movement behavior, including gesture, self-touch, shifts, and actions. Since its first publication in 2009 in Behavior Research Methods, the tool has been used in interdisciplinary research projects to analyze a total of 467 individuals from different cultures, including subjects with mental disease and brain damage. Partly on the basis of new insights from these studies, the system has been revised methodologically and conceptually. The article presents the revised version of the system, including a detailed study of reliability. The improved reproducibility of the revised version makes NEUROGES-ELAN a suitable system for basic empirical research into the relation between hand movement behavior and gesture and cognitive, emotional, and interactive processes and for the development of automated movement behavior recognition methods.

关键词： Nonverbal behavior Gesture Annotation coding system Analysis tool Reliability

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：