检索结果-内蒙古大学图书馆

Developing an ICD-10 coding Assistant: Pilot Study Using RoBERTa and GPT-4 for Term Extraction and Description- Based Code Selection

引用

JMIR FORMATIVE RESEARCH 2025年 9卷 e60095页

作者： Puts, Sander Zegers, Catharina M. L. Dekker, Andre Bermejo, Inigo Maastricht Univ GROW Res Inst Oncol & Reprod Med Ctr Dept Radiat Oncol Maastro POB 616 NL-6200 MD Maastricht Netherlands Hasselt Univ Data Sci Inst DSI Hasselt Belgium

Background: The International Classification of Diseases (ICD), developed by the World Health Organization, standardizes health condition coding to support health care policy, research, and billing, but artificial intelligence automation, while promising, still underperforms compared with human accuracy and lacks the explainability needed for adoption in medical settings. Objective: The potential of large language models for assisting medical coders in the ICD-10 coding was explored through the development of a computer-assisted coding system. This study aimed to augment human coding by initially identifying lead terms and using retrieval-augmented generation (RAG)-based methods for computer-assisted coding enhancement. Methods: The explainability dataset from the CodiEsp challenge (CodiEsp-X) was used, featuring 1000 Spanish clinical cases annotated with ICD-10 codes. A new dataset, CodiEsp-X-lead, was generated using GPT-4 to replace full-textual evidence annotations with lead term annotations. A Robustly Optimized BERT (Bidirectional Encoder Representations from Transformers) Pretraining Approach transformer model was fine-tuned for named entity recognition to extract lead terms. GPT-4 was subsequently employed to generate code descriptions from the extracted textual evidence. Using a RAG approach, ICD codes were assigned to the lead terms by querying a vector database of ICD code descriptions with OpenAI's text-embedding-ada-002 model. Results: The fine-tuned Robustly Optimized BERT Pretraining Approach achieved an overall F1-score of 0.80 for ICD lead term extraction on the new CodiEsp-X-lead dataset. GPT-4-generated code descriptions reduced retrieval failures in the RAG approach by approximately 5% for both diagnoses and procedures. However, the overall explainability F1-score for the CodiEsp-X task was limited to 0.305, significantly lower than the state-of-the-art F1-score of 0.633. The diminished performance was partly due to the reliance on code descripti

关键词： International Classification of Diseases ICD-10 computer-assisted-coding GPT-4 coding term extraction code analysis computer assisted coding transformer model artificial intelligence AI automation retrieval-augmented generation RAG large language model LLM Bidirectional Encoder Representations from Transformers Robustly Optimized BERT Pretraining Approach RoBERTa named entity recognition NER

来源：评论

学校读者我要写书评

暂无评论

Scaffolding coding Instruction Through Literacy via the Compose and Code Digital Platform and Curriculum

引用

JOURNAL OF COMPUTER ASSISTED LEARNING 2025年第1期41卷

作者： Hutchison, Amy Si, Qi Colwell, Jamie Kaya, Erdogan Jakeway, Eileen Miller, Brittany Gutierrez, Kristie Regan, Kelly Evmenova, Anna Univ Alabama Dept Curriculum & Instruct Tuscaloosa AL 35487 USA Utah State Univ Sch Teacher Educ & Leadership Logan UT USA Old Dominion Univ Dept Teaching & Learning Norfolk VA USA George Mason Univ Coll Educ & Human Dev Fairfax VA USA

BackgroundIn recent years, computer science education has emerged as a necessary part of school curricula for students of all ages. With such momentum in this direction, it is essential that program designers, educators, and researchers ensure that computer science education is designed to be inclusive, effective, and engaging for all ***, this paper reports on the design and implementation of an inclusive digital learning platform and accompanying curriculum for scaffolding and integrating coding into writing instruction for elementary-aged students (approximately ages 9-12). In this paper, we report on teachers' uses of the Compose and Code (CoCo) platform and curriculum, how students used its features, and its influence on students' computational thinking skills and attitudes about *** analysed in this mixed-methods study come from 11 teachers and 595 students in Grades 3-6. Data sources included teacher reflections and interviews, an assessment of computational thinking for students, and a coding attitudes survey for students. Quantitative data were analysed descriptively and using paired sample t-tests. Qualitative data were analysed inductively using open coding to determine emergent *** and ConclusionFindings indicate that (1) a majority of students effectively used the CoCo platform to plan their work and code in Scratch, with a smaller percentage using the self-evaluation and self-monitoring features, (2) teachers indicated overall positive perceptions of the CoCo platform and curriculum, with strong support for using it in the future, (3) students' computational thinking skills improved over the course of the project, with results indicating a large effect size (g = 1.24), and (4) student attitudinal results were mixed, providing insights to the barriers that students face when learning to code. Overall, this study indicates that the CoCo platform and curriculum show promise as a scaffolded, structured

关键词： coding computer science education digital learning writing

来源：评论

学校读者我要写书评

暂无评论

The importance of coding and translation between programming languages in sequential activities of pre-service teachers: an approach

引用

EDUCATION AND INFORMATION TECHNOLOGIES 2025年第6期30卷 6925-6949页

作者： Berciano, Ainhoa Cuida, Astrid Novo, Maria-Luisa Univ Basque Country UPV EHU Dept Didact Math Expt & Social Sci Leioa Spain Univ Valladolid UVa Dept Didact Expt Social Sci & Math Valladolid Spain

In the last two decades, computational thinking has gained wide relevance in international educational systems. The inclusion of this new type of thinking poses educational challenges with some underlying research questions that need to be answered to meet these challenges with quality. Thus, this study focuses on analyzing the difficulties that teachers in initial training experience have, when carrying out translation tasks of programming languages used by certain educational robots, in this case, the Cubetto. For this purpose, a specific learning sequence has been designed to work with different programming languages (Cubetto, Bee-Bot, Scratch) and natural language. The work of early childhood and elementary trainee teachers in these tasks has been analyzed using a descriptive approach. The main results are: (1) some of the difficulties encountered are clearly caused by the Cubetto hardware (regardless of the language to which it is translated) and (2) the designed learning sequence has enabled coding skills to be improved remarkably. We conclude that translation tasks between programming languages are necessary in initial teacher training to improve their ability programming and their computational thinking, and for them to be able to detect the disadvantages and benefits of educational robots in their transposition to the classroom.

关键词： coding Computational thinking Pre-service teachers Early childhood and primary education

来源：评论

学校读者我要写书评

暂无评论

Incorporating coding into the Classroom: An Important Component of Modern Bioinformatics Instruction

引用

Journal of College Science Teaching 2025年第1期54卷 69-77页

作者： Orench-Rivera, Nichole Bednarski, April Craig, Paul Talbot, Austin School of Health Sciences Lasell University Auburndale MA United States Washington University in St. Louis St. Louis MO United States School of Chemistry & Materials Science Rochester Institute of Technology Rochester NY United States Pillar Diagnostics Natick MA United States

Advancements in computation and machine learning have revolutionized science, enabling researchers to address once insurmountable challenges. Bioinformatics, a field that heavily relies on computer-driven analysis of biological data, has greatly benefited from these developments. However, traditional bioinformatics instruction frequently lacks the necessary coding skills. This article explores the transformation of a bioinformatics course in which feedback from students revealed limitations in traditional web application interfaces and the absence of coding automated pipelines for real-world applications. To address these shortcomings, the authors redesigned the project to incorporate computer programming using Google Colaboratory, where students access databases and websites by coding. The curriculum outlined the integration of modern programming skills with essential bioinformatics concepts. This article evaluates the effectiveness of this redesign by analyzing a self-response survey completed by course participants. Results show a positive impact on students’ perception of science and scientific research. Bayesian statistical analysis reveals that the programming component significantly predicts students’ career clarity in science and their pursuit of graduate education. Integrating coding exercises in bioinformatics education enhances students’ preparedness for real-world applications. The freely available GitHub repository will facilitate adoption. By embracing computational tools, students can become adept researchers capable of tackling complex biological questions. © 2024 National Science Teaching Association.

关键词： Bioinformatics Biological databases coding Genetics Google colab Laboratory exercise Python

来源：评论

学校读者我要写书评

暂无评论

Cracking the code: Linking good modeling and coding practices for new ecological modelers

引用

ECOLOGICAL MODELLING 2025年 499卷

作者： Swannack, Todd M. Cushway, Kiara C. Carrillo, Carra C. Calvo, Clementina Determan, Kierra R. Mierzejewski, Caroline M. Quintana, Vanessa M. Riggins, Christopher L. Sams, Miranda D. Wadsworth, Waverly E. US Army Engineer Res & Dev Ctr Vicksburg MS 39180 USA Texas State Univ San Marcos Dept Biol San Marcos TX 78666 USA UIC Govt Serv Bowhead Family Co Springfield VA 22150 USA Univ Maine Orono ME USA Oak Ridge Inst Sci Educ Nashville TN USA

Good modeling practices are essential for producing reliable and reproducible ecological models. Inherent to good modeling practices are fundamental coding and documentation skills, which not only implement the desired modeling capabilities but also clearly outline the goals, methods, and components of a model that are necessary to reproduce the desired results. One of the largest challenges for new ecological modelers can be implementing a model into computer code. In fact, coding represents a significant barrier for entry into ecological modeling, since most ecologists have not had formal training in computer science or software development. While software packages do exist that facilitate model development, we have observed that newer modelers still struggle with developing good coding practice throughout the modeling process. During a series of agent-based modeling short-courses and full semester graduate courses, both taught in NetLogo, we identified some common challenges encountered by graduate students and environmental professionals as they learn to code an ecological model, many for the first time. We were able to categorize and provide examples of the main challenges and obstacles, which fell into three main groups that follow the steps of good modeling practice: problem scoping and conceptualization, formulation, and evaluation. We then provide guidance on how to overcome these obstacles while developing good coding and modeling practices that will result in more scientifically defensible models.

关键词： coding Good practice Model development Documentation Evaluation

来源：评论

学校读者我要写书评

暂无评论

AABC: A Tool for Assessing Arduino Basic coding Skills

引用

COMPUTER APPLICATIONS IN ENGINEERING EDUCATION 2025年第3期33卷

作者： Tselegkaridis, Sokratis Sapounidis, Theodosios Tokatlidis, Christos Rapti, Sophia Papakostas, Dimitrios Aristotle Univ Thessaloniki AUTH Sch Philosophy & Educ Dept Educ Thessaloniki Greece Int Hellen Univ IHU Dept Informat & Elect Engn Thessaloniki Greece

In recent years, coding has become a useful component of education at all levels, leading to the emergence of various programmable devices and platforms, such as Arduino. These tools offer students opportunities to enhance their coding skills through hands-on experiences or graphical simulations. However, the literature lacks a comprehensive instrument for evaluating code skills via such technologies. To address this gap, this study introduces the "Assessing Arduino Basics in coding" (AABC) tool. This tool was validated and refined with 151 university students, who completed three experimental exercises followed by coding-related questions. Students were divided into two groups. The first group implemented the experiments with physical-tangible boards, while the second used graphical interfaces in a virtual environment. The analysis of questionnaire scores underwent four steps. Initially, Item Response Theory was employed to discard questions resulting in unscaled scores. Subsequently, Exploratory Factor Analysis identified three factors corresponding to the three exercises. Additionally, Confirmatory Factor Analysis confirmed the questionnaire's structure, indicating high reliability (chi(2)[74] = 74.5, p = 0.463, CFI = 0.995, TLI = 0.994, RMSEA = 0.00612, SRMR = 0.0625). Lastly, measurement invariance testing demonstrated that AABC is unaffected by the user interface, suggesting its usability for evaluating Arduino coding skills regardless of the interface used. Overall, the AABC tool provides a reliable method for evaluating coding skills in basic Arduino circuits, contributing to advancements in coding education.

关键词： Arduino assessing tool coding factor analysis Item Response Theory

来源：评论

学校读者我要写书评

暂无评论

coding with a transdisciplinary team - A project exploring unhealthy urban development

引用

AREA 2025年第0期

作者： Barnfield, Andrew Bates, Geoff Univ East London Sch Hlth Sport & Biosci Stratford CampusWater Lane London E15 4LZ England Univ Bath Inst Policy Res Bath England

We are a geographer and a public policy researcher who share an interest in public health. In this paper we will explore coding in thematic analysis in a transdisciplinary qualitative study. We begin by introducing a moment from our 16-week coding phase to identify the challenges in working across disciplines on qualitative analysis. Transdisciplinary research is about meeting in space and time - between disciplines and ideas, currents of thought - and producing something greater than the sum of its parts. It creates challenges for producing good quality research while maintaining team cohesion. In discussing our coding practices and procedures, we highlight how paying attention to team dynamics and atmosphere creation is fundamental for working in large groups.

关键词： coding dynamics methods teamwork transdisciplinary

来源：评论

学校读者我要写书评

暂无评论

Challenges to reliable ICD-10 coding of child maltreatment: A qualitative interview study of healthcare professionals in German and Swedish hospitals

引用

CHILD ABUSE & NEGLECT 2025年 164卷 107446-107446页

作者： Walter, Teresa Korhonen, Laura Otterman, Gabriel van Agthoven, Godfried Jud, Andreas Univ Hosp Ulm Dept Child & Adolescent Psychiat Psychotherapy Ulm Germany Linkoping Univ Barnafrid Linkoping Sweden Linkoping Univ Dept Biomed & Clin Sci Linkoping Sweden Linkoping Univ Dept Child & Adolescent Psychiat Linkoping Sweden Linkoping Univ Dept Biomed & Clin Sci Linkoping Sweden Uppsala Univ Childrens Hosp Uppsala Sweden Skaraborgs Hosp Dept Res Dev & Innovat Dept Pediat Skovde Region Vastra G Sweden Child Protect Team Vastra Gotalandsreg Regionhalsan Gothenburg Region Vastra G Sweden Competence Ctr Child Abuse & Neglect com can Ulm Germany Zurich Univ Appl Sci Sch Social Work Zurich Switzerland

Background: Child maltreatment (CM) is a major public health issue. Data collection, analysis, and reporting are widely recognized as key components in developing policies and programs aimed at preventing child maltreatment. Unfortunately, CM is significantly under-coded by healthcare professionals (HCPs) in hospitals. Due to a lack of studies, causes of this under-coding are not fully understood. Objective: The aim was to identify and understand challenging factors leading to under-coding of CM in hospitals in Germany and Sweden. Participants and setting: The sample includes 28 HCPs from different professional groups involved in coding-process: pediatricians (n = 14), child psychiatrists (n = 6), pediatric surgeons (n = 4), medical coding professionals (n = 3), and child protection coordinators (n = 1). Nineteen identified as female and 9 as male;age ranged from 24 to 65. Methods: The transcripts of the semi-structured interviews have been coded and analyzed using the thematic analysis approach of Braun & Clarke. Results: In this study, four major themes were identified influencing child maltreatment coding practices on multiple levels. (1) The Impact of Systemic Frameworks, describing systemic factors, such as legal requirements and lack of mandatory education;(2) The Role of Organizational Culture and Structures, describing attitude of the clinic, transparency, and shortcomings in quality control;(3) Interpersonal Dynamics of Multidisciplinary Cooperation and Communication;and (4) Intrapersonal Barriers: Knowledge, Uncertainty, and Emotional Burdens. Conclusion: Identified themes significantly influence HCPs coding practices. Addressing these multifaceted challenges requires comprehensive educational programs, improved organizational support, and systemic changes to counteract the under-coding of CM in hospitals.

关键词： coding Child maltreatment ICD Hospitals Healthcare professionals

来源：评论

学校读者我要写书评

暂无评论

Making sense of non-comprehension issues while listening: A data-based coding scheme

引用

Research Methods in Applied Linguistics 2025年第1期4卷

作者： Siegel, Joseph Kuteeva, Maria Siegel, Aki Department of English Stockholm University Frescativägen Stockholm 114 19 Sweden

Listening has been a notoriously challenging language skill to research due to its ephemeral nature and the complex, dynamic and individualized operations that contribute to comprehension. Based on empirical data analysis using the idiodynamic method for research in applied linguistics, this paper presents a scheme for coding listening comprehension issues as expressed by students who attended an English medium instruction (EMI) lecture. The coding scheme consists of five broader conceptual categories (top-down, bottom-up, affective, multimodal, and environmental) that are further divided into specific codes used to classify data. The paper describes the emergence of these five categories and the codes subsumed within them, including illustrative data samples and discussion of the coding process. By combining theoretical and practical insights on the listening process with the idiodynamic method, the paper seeks to articulate challenges L2 listeners face and provides a fine-grained analysis tool for researchers working in this area. © 2025 The Author(s)

关键词： coding Idiodynamic method Lecture listening Listening comprehension Qualitative data

来源：评论

学校读者我要写书评

暂无评论

No more NVivo! Dealing with coding frustrations in a study of contemporary Cambodian dance

引用

AREA 2025年第0期

作者： Rogers, Amanda Swansea Univ Dept Geog Singleton Pk Swansea SA2 8PP Wales

This paper offers a short reflection on the analytical practice of coding a large number of interviews as part of a long-term research project on the relationship between contemporary dance and national identity in Cambodia. It probes some of the assumptions that we make about 'coding' interviews and how we do it, particularly the idea of seemingly neat, sequential ordering of analytical steps, as well as when the moment of analysis occurs. Rather than present a conventional account of how coding works, I share instead some of my frustrations with the practice and how the difficult-and at times boring and overwhelming-work of coding affects how we understand its analytical possibilities. In so doing, I highlight that we should not assume that coding is easy or the obvious thing to do, regardless of the specificities and demands of our research projects.

关键词： analysis coding dance interviews NVivo

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：