Explainable Artificial Intelligence (XAI) aims to provide insights into the inner workings and the outputs of AI systems. Recently, there’s been growing recognition that explainability is inherently human-centric, tied to how people perceive explanations. Despite this, there is no consensus in the research community on whether user evaluation is crucial in XAI, and if so, what exactly needs to be evaluated and how. This systematic literature review addresses this gap by providing a detailed overview of the current state of affairs in human-centered XAI evaluation. We reviewed 73 papers across various domains where XAI was evaluated with users. These studies assessed what makes an explanation “good” from a user’s perspective, i.e., what makes an explanation meaningful to a user of an AI system. We identified 30 components of meaningful explanations that were evaluated in the reviewed papers and categorized them into a taxonomy of human-centered XAI evaluation, based on: (a) the contextualized quality of the explanation, (b) the contribution of the explanation to human-AI interaction, and (c) the contribution of the explanation to human- AI performance. Our analysis also revealed a lack of standardization in the methodologies applied in XAI user studies, with only 19 of the 73 papers applying an evaluation framework used by at least one other study in the sample. These inconsistencies hinder cross-study comparisons and broader insights. Our findings contribute to understanding what makes explanations meaningful to users and how to measure this, guiding the XAI community toward a more unified approach in human-centered explainability.
MULTIFILE
BACKGROUND: Observation of movement quality (MQ) is an indelible element in the process of clinical reasoning for patients with non-specific low back pain (NS-LBP). However, the observation and evaluation of MQ in common daily activities are not standardized within allied health care. This study aims to describe how Dutch allied health care professionals (AHCPs) observe and assess MQ in patients with NS-LBP and whether AHCPs feel the need to have a specific outcome measure for assessing MQ in patients with NS-LBP.METHODS: In this cross-sectional digital survey study, Dutch primary care AHCPs (n = 114) answered one open and three closed questions about MQ in NS-LBP management. Qualitative and quantitative analyses were applied.RESULTS: Qualitative analyses of the answers to the open questions revealed four main themes: 1) movement pattern features, 2) motor control features, 3) environmental influences and 4) non-verbal expressions of pain and exertion. Quantitative analyses clearly indicated that AHCPs observe MQ in the diagnostic (92%), therapeutic (91%) and evaluation phases (86%), that they do not apply any objective measurement of MQ and that 63% of the AHCPs consider it important to have a specific outcome measure to assess MQ. The AHCPs expressed added benefits and critical notes regarding clinical reasoning and quality of care.CONCLUSION: AHCPs recognize the importance of observing MQ in the assessment and management of LBP in a standardized way. However, there is no consensus amongst AHCPs how MQ should be standardized. Prior to standardization, it will be important to develop a theoretical framework to determine which observable and measurable dimensions of MQ are most valid and relevant for patients with NS-LBP to include in the assessment.
Despite changing attitudes towards animal testing and current legislation to protect experimental animals, the rate of animal experiments seems to have changed little in recent years. On May 15–16, 2013, the In Vitro Testing Industrial Platform (IVTIP) held an open meeting to discuss the state of the art in alternative methods, how companies have, can, and will need to adapt and what drives and hinders regulatory acceptance and use. Several key messages arose from the meeting. First, industry and regulatory bodies should not wait for complete suites of alternative tests to become available, but should begin working with methods available right now (e.g., mining of existing animal data to direct future studies, implementation of alternative tests wherever scientifically valid rather than continuing to rely on animal tests) in non-animal and animal integrated strategies to reduce the numbers of animals tested. Sharing of information (communication), harmonization and standardization (coordination), commitment and collaboration are all required to improve the quality and speed of validation, acceptance, and implementation of tests. Finally, we consider how alternative methods can be used in research and development before formal implementation in regulations. Here we present the conclusions on what can be done already and suggest some solutions and strategies for the future.
Colours are an essential component of human lives since they can influence the final appearance of many products. A large variety of choices can be affected by the colours which are presented to us, for example in the food industry, product design, textiles etc. (Rao et al. 2017). Synthetic colours are dominating nowadays landscape, due to their ease of production, low manufacturing costs and resistance (UV, temperature) in use. However, many of these are also considered hazardous to both human and environmental wellbeing. In the effort of achieving a more sustainable society and limit environmental footprint, natural pigments are arising more and more interest (Velmurugan et al, 2009). As a consequence, the demand of natural pigments is expected to undergo a sharp rise in the future market (Venil et al. 2013). Further research is needed in order to render natural colours both more economically viable and better employable in industry (i.e. process standardization, pigments stability). Biobased pigments can derive from a variety of sources, such as plants, bacteria, algae and fungi (Venkatachalam et al. 2018). The present project is a feasibility study on producing novel biobased pigments with fungi. In order to understand the most optimal production requirements, the biological conditions and novel extraction techniques will be considered. The initial characterisation of the produced pigments will be carried out both regarding the chemical composition and the properties, such as UV- and thermal stability. The SME companies, BioscienZ and Phytonext and the Avans Centre of Expertise BioBased Economy (CoEBBE) will combine their expertise and collaborate with a goal to make a step change in production of biobased colourants.
