Stages Of Model Development Research Articles

Artificial intelligence’s current involvement in urology and future implementation in clinical environments

Artificial intelligence (AI) is a set of computational methods that interprets the data given, uncovers the underlying patterns associated with the complexity of data, and provides the prediction of outcomes that have become increasingly relevant in urology. The current application of AI in urology predominately focuses on disease diagnosis and risk factor analysis in urologic oncology and male infertility. While many candidate models have been proposed in the literature, efforts to construct clinically meaningful data by incorporating patient-specific and multidisciplinary approaches should be carried out to improve the clinical applicability of AI in driving personalised treatment planning and disease prognosis. Looking forward, AI has the potential to drive targeted training in urology, from surgical techniques to patient-specific surgical procedure simulation, in combination with other technologies such as augmented reality. In order to achieve this, patient involvement should be considered in the model development stage, which also addresses issues surrounding the ethical deployment of AI in the clinical environment. It is possible to see AI playing a collaborative role with surgeons in improving clinical efficiency in the future. Level of evidence: Not Applicable

Co‐Creation of Societal Benefits Through Human‐Centered Design and Management of Dynamic Capabilities in Oyster Farm Communities

ABSTRACTThis paper explores how business reconciles the perceived conflicting demands of social and profit logic to deliver value to shareholders and the wider community it serves. Through a human‐centered design lens, the paper identifies co‐creation as pivotal in the design of the business model that delivers social and economic value. Empirical data from an aquaculture SME case study was collected and analyzed to comprehend the role of social good in the development of the business model. The results demonstrate that societal improvements can be achieved when concurrently considered and designed into each stage of the business model development. The findings reveal that technology when deployed within the context of economic and societal improvements has the potential to support businesses in organizing services that deliver economic, societal, and environmental benefits. Replicating this approach requires organizations to develop a deep understanding of the social context that their customers operate within.

CALIFRAME: a proposed method of calibrating reporting guidelines with FAIR principles to foster reproducibility of AI research in medicine.

Procedural and reporting guidelines are crucial in framing scientific practices and communications among researchers and the broader community. These guidelines aim to ensure transparency, reproducibility, and reliability in scientific research. Despite several methodological frameworks proposed by various initiatives to foster reproducibility, challenges such as data leakage and reproducibility remain prevalent. Recent studies have highlighted the transformative potential of incorporating the FAIR (Findable, Accessible, Interoperable, and Reusable) principles into workflows, particularly in contexts like software and machine learning model development, to promote open science. This study aims to introduce a comprehensive framework, designed to calibrate existing reporting guidelines against the FAIR principles. The goal is to enhance reproducibility and promote open science by integrating these principles into the scientific reporting process. We employed the "Best fit" framework synthesis approach which involves systematically reviewing and synthesizing existing frameworks and guidelines to identify best practices and gaps. We then proposed a series of defined workflows to align reporting guidelines with FAIR principles. A use case was developed to demonstrate the practical application of the framework. The integration of FAIR principles with established reporting guidelines through the framework effectively bridges the gap between FAIR metrics and traditional reporting standards. The framework provides a structured approach to enhance the findability, accessibility, interoperability, and reusability of scientific data and outputs. The use case demonstrated the practical benefits of the framework, showing improved data management and reporting practices. The framework addresses critical challenges in scientific research, such as data leakage and reproducibility issues. By embedding FAIR principles into reporting guidelines, the framework ensures that scientific outputs are more transparent, reliable, and reusable. This integration not only benefits researchers by improving data management practices but also enhances the overall scientific process by promoting open science and collaboration. The proposed framework successfully combines FAIR principles with reporting guidelines, offering a robust solution to enhance reproducibility and open science. This framework can be applied across various contexts, including software and machine learning model development stages, to foster a more transparent and collaborative scientific environment.

Application of Mind Map and TRIZ to an Advanced Air Mobility System for Post-Disaster Response

In this article, an Advanced Air Mobility (AAM) platform focused on search and rescue applications is discussed and analyzed from a systems thinking perspective. By applying two systems thinking tools, namely Mind Map and TRIZ, the strong interactions within the constituent parts that make up the system’s whole are examined with the aim of providing a comprehensive roadmap for a proposed Advanced Air Mobility Post-Disaster Response (AAMPDR) system. Furthermore, two problems are discussed to demonstrate the application of the TRIZ technique. The first is in regards to a clause in the AGL rule that could present operational risks to the AAM’s airframe, while the second relates to a potential conflict ensuing from the advent of the 5G C-band and its effect on the AAM altimetry. The resulting solutions to resolve these conflicts using this same technique are also discussed, firstly by taking into account the mean sea/water level as a reference for vertical height within the provisions of the Federal Aviation Regulation requirements, and secondly by applying segmentation of the mission profile as well as a multi-stage frequency designation for each segment depending on a threshold vertical distance. Finally, this study demonstrated that Mind Map and TRIZ can be effective techniques in the early stages of conceptual model development for an AAM system applied to post–disaster response. Furthermore, that the contradictions tool of TRIZ can also be utilized in resolving those potential conflicts identified in relation to the system of interest. To this end, this paper proposes the amendment of the current Part 107 rule to include the term Above Mean Sea (or Water) Level (AMS/WL), a critical yet missing piece of the system requirements that engineers should take into account in future AAM system designs.

Supporting long-term condition management: a workflow framework for the co-development and operationalization of machine learning models using electronic health record data insights.

The prevalence of long-term conditions such as cardiovascular disease, chronic obstructive pulmonary disease (COPD), asthma, and diabetes mellitus is rising. These conditions are leading sources of premature mortality, hospital admission, and healthcare expenditure. Machine learning approaches to improve the management of these conditions have been widely explored, with data-driven insights demonstrating the potential to support earlier diagnosis, triage, and treatment selection. The translation of this research into tools used in live clinical practice has however been limited, with many projects lacking clinical involvement and planning beyond the initial model development stage. To support the move toward a more coordinated and collaborative working process from concept to investigative use in a live clinical environment, we present a multistage workflow framework for the co-development and operationalization of machine learning models which use routine clinical data derived from electronic health records. The approach outlined in this framework has been informed by our multidisciplinary team's experience of co-developing and operationalizing risk prediction models for COPD within NHS Greater Glasgow & Clyde. In this paper, we provide a detailed overview of this framework, alongside a description of the development and operationalization of two of these risk-prediction models as case studies of this approach.

Bias in medical AI: Implications for clinical decision-making.

Biases in medical artificial intelligence (AI) arise and compound throughout the AI lifecycle. These biases can have significant clinical consequences, especially in applications that involve clinical decision-making. Left unaddressed, biased medical AI can lead to substandard clinical decisions and the perpetuation and exacerbation of longstanding healthcare disparities. We discuss potential biases that can arise at different stages in the AI development pipeline and how they can affect AI algorithms and clinical decision-making. Bias can occur in data features and labels, model development and evaluation, deployment, and publication. Insufficient sample sizes for certain patient groups can result in suboptimal performance, algorithm underestimation, and clinically unmeaningful predictions. Missing patient findings can also produce biased model behavior, including capturable but nonrandomly missing data, such as diagnosis codes, and data that is not usually or not easily captured, such as social determinants of health. Expertly annotated labels used to train supervised learning models may reflect implicit cognitive biases or substandard care practices. Overreliance on performance metrics during model development may obscure bias and diminish a model's clinical utility. When applied to data outside the training cohort, model performance can deteriorate from previous validation and can do so differentially across subgroups. How end users interact with deployed solutions can introduce bias. Finally, where models are developed and published, and by whom, impacts the trajectories and priorities of future medical AI development. Solutions to mitigate bias must be implemented with care, which include the collection of large and diverse data sets, statistical debiasing methods, thorough model evaluation, emphasis on model interpretability, and standardized bias reporting and transparency requirements. Prior to real-world implementation in clinical settings, rigorous validation through clinical trials is critical to demonstrate unbiased application. Addressing biases across model development stages is crucial for ensuring all patients benefit equitably from the future of medical AI.

SoUnD Framework: Analyzing (So)cial Representation in (Un)structured (D)ata

Decisions about how to responsibly collect, use and document data often rely upon understanding how people are represented in data. Yet, the unlabeled nature and scale of data used in foundation model development poses a direct challenge to systematic analyses of downstream risks, such as representational harms. We provide a framework designed to help RAI practitioners more easily plan and structure analyses of how people are represented in unstructured data and identify downstream risks. The framework is organized into groups of analyses that map to 3 basic questions: 1) Who is represented in the data, 2) What content is in the data, and 3) How are the two associated. We use the framework to analyze human representation in two commonly used datasets: the Common Crawl web corpus (C4) of 356 billion tokens, and the LAION-400M dataset of 400 million text-image pairs, both developed in the English language. We illustrate how the framework informs action steps for hypothetical teams faced with data use, development, and documentation decisions. Ultimately, the framework structures human representation analyses and maps out analysis planning considerations, goals, and risk mitigation actions at different stages of dataset and model development.

Framework for developing entrepreneurial business models: Theory and practical application

A framework for developing entrepreneurial business models is crucial for guiding entrepreneurs from conceptualization to practical application in a dynamic market environment. This review outlines a comprehensive framework that integrates theoretical concepts with practical approaches to help entrepreneurs create robust and adaptable business models. The framework is grounded in a synthesis of contemporary entrepreneurship theories and practical insights drawn from case studies of successful ventures. It begins with a theoretical exploration of foundational business model components, including value proposition, customer segments, revenue streams, and cost structures. By leveraging established models such as the Business Model Canvas and the Lean Startup methodology, the framework provides a structured approach for entrepreneurs to design and validate their business models. A key component of the framework is its emphasis on iterative development and validation. Entrepreneurs are encouraged to employ lean principles, such as rapid prototyping and customer feedback loops, to refine their business models. This iterative process helps in adapting to market changes and customer needs, reducing risk, and improving the likelihood of success. The framework also incorporates strategic analysis tools to evaluate market opportunities, competitive landscape, and potential challenges. Practical application is emphasized through detailed guidelines and tools for each stage of business model development. This includes methodologies for conducting market research, identifying key resources and partnerships, and establishing operational processes. Additionally, the framework addresses the importance of financial planning and risk management, offering practical advice on funding strategies and contingency planning. The paper also highlights the significance of contextual factors, such as industry trends, regulatory environment, and technological advancements, in shaping business models. By incorporating these elements, the framework provides a holistic approach to entrepreneurial business model development. In conclusion, the proposed framework serves as a valuable guide for entrepreneurs seeking to develop and implement effective business models. It combines theoretical insights with practical tools and strategies, enabling entrepreneurs to navigate the complexities of the business landscape and achieve sustainable success. This approach not only enhances the strategic planning process but also fosters innovation and adaptability in an ever-evolving market environment.

Review of multimodal machine learning approaches in healthcare

Machine learning methods in healthcare have traditionally focused on using data from a single modality, limiting their ability to effectively replicate the clinical practice of integrating multiple sources of information for improved decision making. Clinicians typically rely on a variety of data sources including patients’ demographic information, laboratory data, vital signs and various imaging data modalities to make informed decisions and contextualise their findings. Recent advances in machine learning have facilitated the more efficient incorporation of multimodal data, resulting in applications that better represent the clinician’s approach. Here, we provide an overview of multimodal machine learning approaches in healthcare, encompassing various data modalities commonly used in clinical diagnoses, such as imaging, text, time series and tabular data. We discuss key stages of model development, including pre-training, fine-tuning and evaluation. Additionally, we explore common data fusion approaches used in modelling, highlighting their advantages and performance challenges. An overview is provided of 17 multimodal clinical datasets with detailed description of the specific data modalities used in each dataset. Over 50 studies have been reviewed, with a predominant focus on the integration of imaging and tabular data. While multimodal techniques have shown potential in improving predictive accuracy across many healthcare areas, our review highlights that the effectiveness of a method is contingent upon the specific data and task at hand.

Development of Guided Inquiry Learning Model Based on Educational Games to Improve Elementary Students' Science Process Skills

This research aims to develop a Guided Inquiry Learning Model Based on Educational Games, presented in a book format and supported by educational games accessible via Canva and Wordwall platforms. The model is designed to be valid, practical, and effective in enhancing elementary school students' science process skills. This study uses a Research and Development (R&D) approach, adapting the Plomp model's development stages: initial investigation, design, realization, testing, evaluation, revision, and implementation. The subjects are fifth-grade students from UPT SD Negeri 214, UPT SD Negeri 99, and UPT SD Negeri 101 in Pinrang Regency. Research instruments include validation sheets, observation sheets, questionnaires, and evaluation sheets. The study produces an Inquiry-Based Educational Game (IGE) textbook and learning tools, such as lesson plans (RPP), student worksheets (LKPD), and educational games. The findings reveal a strong need among teachers and students for a learning model that enhances science process skills. The developed IGE model comprises syntax, social system, reaction principles, support system, instructional impact, and accompanying impact. The syntax includes Activation, Playing, Exploring, and Wrap-Up phases. The IGE model meets the criteria for validity and practicality, receiving high validation ratings. The model effectively enhances students' science process skills, as shown by significant improvements in student performance. The IGE model and its learning tools are deemed highly practical, based on feedback from students and teachers.

Meta-Regulation: An ideal alternative to the primary responsibility as the regulatory model of generative AI in China

Generative AI with stronger responsiveness and emergent abilities has triggered a global boom and is facing challenges such as data compliance risks during the pretraining process and risks of generating fake information, which has raised concerns among global regulatory authorities. The European Union, United States, United Kingdom, and other countries and regions are gradually establishing risk-based, scenario-based, and outcome-based governance models for generative AI. China recently introduced new regulations for the management of generative AI, which adopt a governance model focusing on generative AI service providers. It suggests that China is continuing the principle of primary responsibility in Internet governance, which encompasses legal responsibility, contractual obligations, and ethical responsibility. However, the governance model based on primary responsibility emphasizes the accountability of generative AI model service providers, with relatively limited regulation on other important entities such as users and large-scale dissemination platforms, which may not be conducive to achieving China's regulatory goals for the AI industry. In comparison, the Meta-Regulation model could be an ideal alternative for China. As a classic theory explaining the public-private relationship, the ‘Meta-Regulation’ aligns with the generative AI governance requirements. Based on the Meta-Regulation theory, the governance of generative AI in China should move towards a direction of emphasizing safety, transparency, collaborative governance, and accountability. In line with this, it is necessary to include users and large-scale dissemination platforms within the regulatory scope and establish overarching governance objectives that ensure the responsible distribution of duties among stakeholders, with regulatory authorities assuming ultimate oversight responsibility and technical coordination. At the level of specific improvement measures, it is possible to integrate the three stages of model development, usage, and content dissemination of generative AI. During the model development stage, generative AI providers have specific transparency obligations. In the usage stage, a self-regulatory system centered around platform autonomy should be constructed. In the content dissemination stage, the proactive notification obligations of the dissemination platforms should be clearly defined. Additionally, the enforcement of technical interoperability requirements is necessary, thereby promoting the orderly development of generative AI applications.

From Pixels to Principles: A Decade of Progress and Landscape in Trustworthy Computer Vision

The rapid development of computer vision technologies and applications has brought forth a range of social and ethical challenges. Due to the unique characteristics of visual technology in terms of data modalities and application scenarios, computer vision poses specific ethical issues. However, the majority of existing literature either addresses artificial intelligence as a whole or pays particular attention to natural language processing, leaving a gap in specialized research on ethical issues and systematic solutions in the field of computer vision. This paper utilizes bibliometrics and text-mining techniques to quantitatively analyze papers from prominent academic conferences in computer vision over the past decade. It first reveals the developing trends and specific distribution of attention regarding trustworthy aspects in the computer vision field, as well as the inherent connections between ethical dimensions and different stages of visual model development. A life-cycle framework regarding trustworthy computer vision is then presented by making the relevant trustworthy issues, the operation pipeline of AI models, and viable technical solutions interconnected, providing researchers and policymakers with references and guidance for achieving trustworthy CV. Finally, it discusses particular motivations for conducting trustworthy practices and underscores the consistency and ambivalence among various trustworthy principles and technical attributes.

Clinical Validation of a Deep Learning-Based Software for Lumbar Bone Mineral Density and T-Score Prediction from Chest X-ray Images.

Screening for osteoporosis is crucial for early detection and prevention, yet it faces challenges due to the low accuracy of calcaneal quantitative ultrasound (QUS) and limited access to dual-energy X-ray absorptiometry (DXA) scans. Recent advances in AI offer a promising solution through opportunistic screening using existing medical images. This study aims to utilize deep learning techniques to develop a model that analyzes chest X-ray (CXR) images for osteoporosis screening. This study included the AI model development stage and the clinical validation stage. In the AI model development stage, the combined dataset of 5122 paired CXR images and DXA reports from the patients aged 20 to 98 years at a medical center was collected. The images were enhanced and filtered for hardware retention such as pedicle screws, bone cement, artificial intervertebral discs or severe deformity in target level of T12 and L1. The dataset was then separated into training, validating, and testing datasets for model training and performance validation. In the clinical validation stage, we collected 440 paired CXR images and DXA reports from both the TCVGH and Joy Clinic, including 304 pared data from TCVGH and 136 paired data from Joy Clinic. The pre-clinical test yielded an area under the curve (AUC) of 0.940, while the clinical validation showed an AUC of 0.946. Pearson's correlation coefficient was 0.88. The model demonstrated an overall accuracy, sensitivity, and specificity of 89.0%, 88.7%, and 89.4%, respectively. This study proposes an AI model for opportunistic osteoporosis screening through CXR, demonstrating good performance and suggesting its potential for broad adoption in preliminary screening among high-risk populations.

Predictive models in Alzheimer's disease: an evaluation based on data mining techniques

The increasing prevalence of Alzheimer's disease in older adults has raised significant concern in recent years. Aware of this challenge, this research set out to develop predictive models that allow early identification of people at risk for Alzheimer's disease, considering several variables associated with the disease. To achieve this objective, data mining techniques were employed, specifically the decision tree algorithm, using the RapidMiner Studio tool. The sample explore modify model and assess (SEMMA) methodology was implemented systematically at each stage of model development, ensuring an orderly and structured approach. The results obtained revealed that 45.00% of people with dementia present characteristics that identify them as candidates for confirmation of a diagnosis of Alzheimer's disease. In contrast, 52.78% of those who do not have dementia show no danger of contracting the disease. In the conclusion of the research, it was noted that most patients diagnosed with Alzheimer's are older than 65 years, indicating that this stage of life tends to trigger brain changes associated with the disease. This finding underscores the importance of considering age as a key factor in the early identification of the disease.

Multi-centre benchmarking of deep learning models for COVID-19 detection in chest x-rays.

This study is a retrospective evaluation of the performance of deep learning models that were developed for the detection of COVID-19 from chest x-rays, undertaken with the goal of assessing the suitability of such systems as clinical decision support tools. Models were trained on the National COVID-19 Chest Imaging Database (NCCID), a UK-wide multi-centre dataset from 26 different NHS hospitals and evaluated on independent multi-national clinical datasets. The evaluation considers clinical and technical contributors to model error and potential model bias. Model predictions are examined for spurious feature correlations using techniques for explainable prediction. Models performed adequately on NHS populations, with performance comparable to radiologists, but generalised poorly to international populations. Models performed better in males than females, and performance varied across age groups. Alarmingly, models routinely failed when applied to complex clinical cases with confounding pathologies and when applied to radiologist defined "mild" cases. This comprehensive benchmarking study examines the pitfalls in current practices that have led to impractical model development. Key findings highlight the need for clinician involvement at all stages of model development, from data curation and label definition, to model evaluation, to ensure that all clinical factors and disease features are appropriately considered during model design. This is imperative to ensure automated approaches developed for disease detection are fit-for-purpose in a clinical setting.

The Google Form and Microsoft Excel applications: Non-Cognitive Initial Diagnostic Test Instrument for Guidance and Counseling Teachers

This research is motivated by the lack of effectiveness and efficiency of the implementation of the distribution of non-cognitive initial diagnostic tests conducted by Guidance and Counseling teachers. The very long time allocation makes many Guidance and Counseling teachers unwilling to carry out the initial non-cognitive diagnostic test because it requires up time for other student assistance services. The Non-Cognitive Initial Diagnostic Test is very important to do as student learning profiling, which can be used as initial data in conducting differentiated learning. This study aims to determine the effectiveness and efficiency of the use of Google Forms and Ms Excel applications as non-cognitive initial diagnostic test instruments for Guidance and Counseling teachers. The type of research is descriptive qualitative. Data collection uses observation, interviews and documentation studies. Data validity techniques using triangulation techniques. The results of research use the Five Stages method, namely the Preliminary Research Stage, Model Development Stage, Model Validation Stage, Effectiveness Test Stage, and Dissemination Stage. Google Forms and Ms. Excel have ease of operation, distribution, data processing and accessibility. Google Forms and Ms. Excel a very appropriate combinations of applications for conducting non-cognitive diagnostic tests, because of their effectiveness efficiency and operation.

A Scoping Review of Artificial Intelligence Detection of Voice Pathology: Challenges and Opportunities.

Survey the current literature on artificial intelligence (AI) applications for detecting and classifying vocal pathology using voice recordings, and identify challenges and opportunities for advancing the field forward. PubMed, EMBASE, CINAHL, and Scopus databases. A comprehensive literature search was performed following the Preferred Reporting Items for Systematic Reviews and Meta-analysesExtension for Scoping Reviews guidelines. Peer-reviewed journal articles in the English language were included if they used an AI approach to detect or classify pathological voices using voice recordings from patients diagnosed with vocal pathologies. Eighty-two studies were included in the review between the years 2000 and 2023, with an increase in publication rate from one study per year in 2012 to 10 per year in 2022. Seventy-two studies (88%) were aimed at detecting the presence of voice pathology, 24 (29%) at classifying the type of voice pathology present, and 4 (5%) at assessing pathological voice using the Grade, Roughness, Breathiness, Asthenia, and Strainscale. Thirty-six databases were used to collect and analyze speech samples. Fourteen articles (17%) did not provide information about their AI model validation methodology. Zero studies moved beyond the preclinical and offline AI model development stages. Zero studies specified following a reporting guideline for AI research. There is rising interest in the potential of AI technology to aid the detection and classification of voice pathology. Three challenges-and areas of opportunities-for advancing this research are heterogeneity of databases, lack of clinical validation studies, and inconsistent reporting.

Pengembangan Media Poop Up Book Berbasis Problem Based Learning Kelas 1 Tema 7 Benda, Hewan dan Tanaman di Sekitarku

This development research aims to (1) Develop poop up book media based on problem based learning on the theme of 7 objects, animals and plants around me (2) Find out the feasibility of poop up book learning media with a problem based learning model (3) To find out the teacher's response to poop up book learning media. The type of research model used in this research is the Research and Development (R&D) model. ADDIE development is a model that involves model development stages with five steps or five phases including: Analysis, Design, Develop, Implement and Evaluate. The subjects in this research were grade 1 students at SD IT Al-Furqon Lubuk Rotan, validators (media experts and material experts). The instrument used to collect data was a questionnaire. The data analysis technique used in this research is the Likert scale. Based on analysis of data obtained through validity tests of media experts, material experts, teacher responses and student responses. The validation results by media experts were 88.3%, including the Very Eligible category. The validation results by material experts were 83% in the Very Eligible category. The validation results from teacher responses were 93.1% in the Very Appropriate category, while student responses were 90.8% in the Very Appropriate category. Based on the percentage results from media experts, material experts, teacher responses and student responses, it can be concluded that the development of poop up book media with a problem based learning model in thematic learning on the theme of 7 objects, animals and plants around me which was developed by researchers at SD IT Al -Furqin for class I elementary school is included in the Very Suitable category to be applied or used as learning media in class I elementary school.

Understanding and Mitigating Bias in Imaging Artificial Intelligence.

Artificial intelligence (AI) algorithms are prone to bias at multiple stages of model development, with potential for exacerbating health disparities. However, bias in imaging AI is a complex topic that encompasses multiple coexisting definitions. Bias may refer to unequal preference to a person or group owing to preexisting attitudes or beliefs, either intentional or unintentional. However, cognitive bias refers to systematic deviation from objective judgment due to reliance on heuristics, and statistical bias refers to differences between true and expected values, commonly manifesting as systematic error in model prediction (ie, a model with output unrepresentative of real-world conditions). Clinical decisions informed by biased models may lead to patient harm due to action on inaccurate AI results or exacerbate health inequities due to differing performance among patient populations. However, while inequitable bias can harm patients in this context, a mindful approach leveraging equitable bias can address underrepresentation of minority groups or rare diseases. Radiologists should also be aware of bias after AI deployment such as automation bias, or a tendency to agree with automated decisions despite contrary evidence. Understanding common sources of imaging AI bias and the consequences of using biased models can guide preventive measures to mitigate its impact. Accordingly, the authors focus on sources of bias at stages along the imaging machine learning life cycle, attempting to simplify potentially intimidating technical terminology for general radiologists using AI tools in practice or collaborating with data scientists and engineers for AI tool development. The authors review definitions of bias in AI, describe common sources of bias, and present recommendations to guide quality control measures to mitigate the impact of bias in imaging AI. Understanding the terms featured in this article will enable a proactive approach to identifying and mitigating bias in imaging AI. Published under a CC BY 4.0 license. Test Your Knowledge questions for this article are available in the supplemental material. See the invited commentary by Rouzrokh and Erickson in this issue.

대학의 비교과교육과정 개발⋅운영 모형 연구

Objectives The purpose of this study is to help universities systemically develop and operate extracurricular curriculum that can reflect their own characteristics, through research on a development and management model for extracurricular curriculum activities. Methods The steps of research were progressed with three stages: research planning, literature review and the model development. Based on the Taba’s(1962) curriculum development model, the research planning stage planned the extracurricular curriculum development and operation model of the university. The literature research stage collected and analyzed the extracurricular, extracurricular activities, extracurricular curriculum which were related to the pilot study, curriculum development model, model research, curriculum development the research paper and also were related to the books and research papers. The model development stage based on the curriculum model and the curriculum development model which are the foundation of curriculum brought out the implication and the model was confirmed after a feasibility study by a expert of curriculum. Results The management and development model for extracurricular curriculums consists of four stages: 1. Drafting a proposal and planning of university extracurricular curriculums; 2. crafting detailed plans for each extracurricular curriculum activity; 3. executing and operating the extracurricular curriculum activities; and 4. evaluating and assessing university extracurricular curriculums. Each stage is comprised of five different sub-categories, such as ① subject, ② period, ③ foundation, ④ method, and ⑤ model. Conclusions The reason for the establishment and operation of the extracurricular curriculum is to instill students with the university’s core values and help them become competent members of society and the university. Therefore, the university extracurricular curriculum must be developed and operated according to the stages and procedures as in the required and elective curriculum.