Search

The use of artificial intelligence systems in clinical routine is still hampered by the necessity of a medical device certification and/or by the difficulty of implementing these systems in a clinic's quality management system. In this context, the key questions for a user are how to ensure robust model predictions and how to appraise the quality of a model's results on a regular basis. In this paper we discuss some conceptual foundation for a clinical implementation of a machine learning system and argue that both vendors and users should take certain responsibilities, as is already common practice for high-risk medical equipment. We propose the methodology from AAPM Task Group 100 report No. 283 as a conceptual framework for developing risk-driven a quality management program for a clinical process that encompasses a machine learning system. This is illustrated with an example of a clinical workflow. Our analysis shows how the risk evaluation in this framework can accommodate artificial intelligence based systems independently of their robustness evaluation or the user's in–house expertise. In particular, we highlight how the degree of interpretability of a machine learning system can be systematically accounted for within the risk evaluation and in the development of a quality management system. [ABSTRACT FROM AUTHOR]

By integrating data-driven analysis methods into existing procedures, quality and failure management performance can be increased systematically. Linking product and process data with existing failure and quality knowledge offers significant potential for enhancing the continuous improvement of processes and products. Nevertheless, the potential of data-driven analysis still needs to be fully exploited. Despite the apparent advantages of analysis-oriented approaches, many companies are hesitant to implement such transformation projects because quantifying possible benefits is challenging. Thus, there is an economic risk due to the limited availability of resources, which must be utilized purposefully. An approach that allows the systematic identification and prioritization of promising use cases and reduces the risk of introducing data-based approaches is missing. This paper conceptualizes a model to evaluate the potential for introducing data-based analysis in production processes. A maturity assessment, consisting of four dimensions and seventeen sub-dimensions, is presented, which enables the identification of promising use cases for implementing data-based approaches. The conceptualized model is validated using an expert survey. [ABSTRACT FROM AUTHOR]

A skilled workforce is essential for producing high quality construction work, efficiently and effectively. This paper is formulated to improve the understanding and knowledge surrounding the skill shortage currently being faced within the UK, and the significant impact it is having on quality management. It surrounds around each main area, and the impacts of recent years: Brexit, Covid-19 and ageing workforce. A mixed method approach was applied to collect data from the quantitative and qualitative sources. The quantitative survey data was collected through snowball sampling from the 130 construction professionals working the UK construction industry. Moreover, a case study has been conducted on a large-scale construction project located in the Northeast of England where the outcome of these issues can be seen in all aspects of the work. Training and development are the fundamental issues highlighted during the literature review and then subsequently expressed by participants of the surveys. In addition, the moderation analysis also provides the important role of training and development in reducing the negative impacts of COVID-19 and Brexit towards quality management. However, it was also revealed that the training and development are not useful for the aging workforce in combating the skilled shortage challenges towards quality management system in the construction industry. This research will allow the industry to understand the need for a skilled workforce and how it benefits the quality management elements of a construction project. [ABSTRACT FROM AUTHOR]

The study aims to identify the antecedents responsible for sustaining quality control in the context of under-studied agriculture value chains. There is a pressing need to understand the dynamics of technology implementation in an emerging economy context. The conceptual model is designed from complexity, and collective action theory perspectives. An empirical study validates the model and considers the role of traceability, collective action, big data predictive capability, and behavioral uncertainties in sustaining quality in agriculture value chains (AVCs). The paper addresses the call for in-depth deliberations on exploring the factors of AVC quality. The empirical validation of the theoretical model shows a significant positive relationship among the antecedents. The path coefficients and effect size have been derived from understanding the regression equations of cause and effect groups. It also identifies the avenues for improving quality in value chains. This is a pioneering study to design a new operation model for sustaining the quality of AVCs. It also adds a new theoretical debate to AVC technology deployment in the context of an emerging economy. The study is limited to recognizing a few antecedents from the literature in the Indian context. The deliberations contribute significantly to minimizing agricultural waste in developing countries through quality control. [ABSTRACT FROM AUTHOR]