development evaluation
Recently Published Documents


TOTAL DOCUMENTS

886
(FIVE YEARS 254)

H-INDEX

35
(FIVE YEARS 5)

2022 ◽  
Vol 5 (1) ◽  
Author(s):  
Anne A. H. de Hond ◽  
Artuur M. Leeuwenberg ◽  
Lotty Hooft ◽  
Ilse M. J. Kant ◽  
Steven W. J. Nijman ◽  
...  

AbstractWhile the opportunities of ML and AI in healthcare are promising, the growth of complex data-driven prediction models requires careful quality and applicability assessment before they are applied and disseminated in daily practice. This scoping review aimed to identify actionable guidance for those closely involved in AI-based prediction model (AIPM) development, evaluation and implementation including software engineers, data scientists, and healthcare professionals and to identify potential gaps in this guidance. We performed a scoping review of the relevant literature providing guidance or quality criteria regarding the development, evaluation, and implementation of AIPMs using a comprehensive multi-stage screening strategy. PubMed, Web of Science, and the ACM Digital Library were searched, and AI experts were consulted. Topics were extracted from the identified literature and summarized across the six phases at the core of this review: (1) data preparation, (2) AIPM development, (3) AIPM validation, (4) software development, (5) AIPM impact assessment, and (6) AIPM implementation into daily healthcare practice. From 2683 unique hits, 72 relevant guidance documents were identified. Substantial guidance was found for data preparation, AIPM development and AIPM validation (phases 1–3), while later phases clearly have received less attention (software development, impact assessment and implementation) in the scientific literature. The six phases of the AIPM development, evaluation and implementation cycle provide a framework for responsible introduction of AI-based prediction models in healthcare. Additional domain and technology specific research may be necessary and more practical experience with implementing AIPMs is needed to support further guidance.


Author(s):  
Takaaki Miyaguchi

AbstractNumerous challenges confront the task of evaluating sustainable development—its complex nature, complementary evaluation criteria, and the difficulty of evaluation at the nexus of human and natural systems. Theory-based evaluation, drawn from critical realism, is well suited to this task. When constructing a program theory/theory of change for evaluating sustainable development, concepts of socioecological systems and coupled human and natural systems are useful. The chapter discusses four modes of inference and the application of different theory-based evaluation approaches. It introduces the CHANS (coupled human and natural systems) framework, a holistic, analytical framework that is useful in evaluating such complex, social-ecological systems and resonates with the challenging elements of sustainable development evaluation.


Author(s):  
Juha I. Uitto

AbstractThe world is facing multiple crises as manifested in runaway climate change, a global pandemic, loss of ecosystems and biological species, and rapidly growing inequality. These are all closely interlinked as recognized in the 2030 Agenda for Sustainable Development. Addressing them will require broad transformational change that encompasses the economy, institutions, and how we interact with the natural environment. This chapter introduces the book that is intended to highlight how evaluation can contribute to such transformations. The chapter first reviews the state of development evaluation. It then briefly introduces the state of the global environment before discussing the implications of this context for evaluation, and how evaluation as a profession and practice must change in order to respond to the challenges of sustainability. The chapter ends by explaining the flow of the book in its four parts that focus on: transformational change, drivers of sustainability, climate change mitigation and adaptation, and evaluation approaches.


2022 ◽  
Vol 158 ◽  
pp. 106977
Author(s):  
Ning Wei ◽  
Qijun Zhang ◽  
Yanjie Zhang ◽  
Jiaxin Jin ◽  
Junyu Chang ◽  
...  

2021 ◽  
Vol 3 ◽  
Author(s):  
Catherine Olivier ◽  
Isabelle Ganache ◽  
Olivier Demers-Payette ◽  
Louis Lochhead ◽  
Sandra Pelaez ◽  
...  

Since the beginning of the COVID-19 pandemic, numerous studies have been conducted to identify interventions that could contribute to alleviating the burden it has caused. The Institut national d'excellence en santé et en services sociaux (INESSS) has played a key role in informing the government of Québec regarding the evaluation of specific pandemic-related interventions. This process took place in a context characterized by a sense of urgency to assess and recommend potential interventions that could save lives and reduce the effects of the disease on populations and healthcare systems, which increased the pressure on the regulatory agencies leading these evaluations. While some of the interventions examined were considered promising, results from COVID-19 studies often led to uncertainty regarding their efficacy or safety. Regulatory agencies evaluating the value of promising interventions thus face challenges in deciding whether these should be made available to the population, particularly when assessing their benefit-risk balance. To shed light on these challenges, we identified underlying ethical considerations that can influence such an assessment. A rapid literature review was conducted in February 2021, to identify the main challenges associated with the benefit-risk balance assessment of promising interventions. To reinforce our understanding of the underlying ethical considerations, we initiated a discussion among various social actors involved in critical thinking surrounding the evaluation of promising interventions, including ethicists, clinicians and researchers involved in clinical or public health practice, as well as patients and citizens. This discussion allowed us to create a space for exchange and mutual understanding among these various actors who contributed equally to the identification of ethical considerations. The knowledge and perspectives stemming from the scientific literature and those consulted were integrated in a common reflection on these ethical considerations. This allowed patients and citizens, directly affected by the evaluation of pandemic-related interventions and the resulting social choices, to contribute to the identification of the relevant ethical considerations. It also allowed for reflection on the responsibilities of the various actors involved in the development, evaluation, and distribution of promising interventions in a setting of urgency and uncertainty, such as that brought about by the COVID-19 pandemic.


2021 ◽  
Vol 3 ◽  
Author(s):  
Wenzhi Jiang ◽  
Jenifer Bush ◽  
Jen Sheen

The ultimate goal of technology development in genome editing is to enable precisely targeted genomic changes in any cells or organisms. Here we describe protoplast systems for precise and efficient DNA sequence changes with preassembled Cas9 ribonucleoprotein (RNP) complexes in Arabidopsis thaliana, Nicotiana benthamiana, Brassica rapa, and Camelina sativa. Cas9 RNP-mediated gene disruption with dual gRNAs could reach ∼90% indels in Arabidopsis protoplasts. To facilitate facile testing of any Cas9 RNP designs, we developed two GFP reporter genes, which led to sensitive detection of nonhomologous end joining (NHEJ) and homology-directed repair (HDR), with editing efficiency up to 85 and 50%, respectively. When co-transfected with an optimal single-stranded oligodeoxynucleotide (ssODN) donor, precise editing of the AtALS gene via HDR reached 7% by RNPs. Significantly, precise mutagenesis mediated by preassembled primer editor (PE) RNPs led to 50% GFP reporter gene recovery in protoplasts and up to 4.6% editing frequency for the specific AtPDS mutation in the genome. The rapid, versatile and efficient gene editing by CRISPR RNP variants in protoplasts provides a valuable platform for development, evaluation and optimization of new designs and tools in gene and genomic manipulation and is applicable in diverse plant species.


Oryx ◽  
2021 ◽  
pp. 1-12
Author(s):  
Eleanor J. Sterling ◽  
Amanda Sigouin ◽  
Erin Betley ◽  
Jennifer Zavaleta Cheek ◽  
Jennifer N. Solomon ◽  
...  

Abstract Capacity development is critical to long-term conservation success, yet we lack a robust and rigorous understanding of how well its effects are being evaluated. A comprehensive summary of who is monitoring and evaluating capacity development interventions, what is being evaluated and how, would help in the development of evidence-based guidance to inform design and implementation decisions for future capacity development interventions and evaluations of their effectiveness. We built an evidence map by reviewing peer-reviewed and grey literature published since 2000, to identify case studies evaluating capacity development interventions in biodiversity conservation and natural resource management. We used inductive and deductive approaches to develop a coding strategy for studies that met our criteria, extracting data on the type of capacity development intervention, evaluation methods, data and analysis types, categories of outputs and outcomes assessed, and whether the study had a clear causal model and/or used a systems approach. We found that almost all studies assessed multiple outcome types: most frequent was change in knowledge, followed by behaviour, then attitude. Few studies evaluated conservation outcomes. Less than half included an explicit causal model linking interventions to expected outcomes. Half of the studies considered external factors that could influence the efficacy of the capacity development intervention, and few used an explicit systems approach. We used framework synthesis to situate our evidence map within the broader literature on capacity development evaluation. Our evidence map (including a visual heat map) highlights areas of low and high representation in investment in research on the evaluation of capacity development.


2021 ◽  
Vol 10 (11) ◽  
pp. 788
Author(s):  
Marcela Jarošová ◽  
František Staněk

The present study is focused on spatial modelling of a kaolin deposit in Karlovy Vary, Czech Republic, and the methodical procedure of development, evaluation and visualization of a 3D model are described step by step. The implementation of this methodology is performed in Visual Studio 2019 with use of the Surfer and Voxler objects from Golden Software. This methodology combined with the newly developed software (Kaolin_A and Kaolin_Viz programs) allow a user to create a variant dynamic model for the same or similar types of deposits. It enables a quick update of the model when changing the input data, based on the new mining exploration or when changing the modelling parameters. The presented approach leads to a more advanced evaluation of deposits, including various estimates of reserves according to pre-specified usability conditions. The efficiency of the developed methodology and the software for the evaluation of the deposit are demonstrated on the kaolin deposit Jimlíkov-East, located near the village Jimlíkov about 5 km west of Karlovy Vary in the Czech Republic.


PLoS ONE ◽  
2021 ◽  
Vol 16 (11) ◽  
pp. e0259624
Author(s):  
Laurie Needham ◽  
Murray Evans ◽  
Darren P. Cosker ◽  
Steffi L. Colyer

This study describes the development, evaluation and application of a computer vision and deep learning system capable of capturing sprinting and skeleton push start step characteristics and mass centre velocities (sled and athlete). Movement data were captured concurrently by a marker-based motion capture system and a custom markerless system. High levels of agreement were found between systems, particularly for spatial based variables (step length error 0.001 ± 0.012 m) while errors for temporal variables (ground contact time and flight time) were on average within ± 1.5 frames of the criterion measures. Comparisons of sprinting and pushing revealed decreased mass centre velocities as a result of pushing the sled but step characteristics were comparable to sprinting when aligned as a function of step velocity. There were large asymmetries between the inside and outside leg during pushing (e.g. 0.22 m mean step length asymmetry) which were not present during sprinting (0.01 m step length asymmetry). The observed asymmetries suggested that force production capabilities during ground contact were compromised for the outside leg. The computer vision based methods tested in this research provide a viable alternative to marker-based motion capture systems. Furthermore, they can be deployed into challenging, real world environments to non-invasively capture data where traditional approaches are infeasible.


Sign in / Sign up

Export Citation Format

Share Document