ORCID Profile
0000-0002-7297-0984
Current Organisations
Dublin City University
,
University of Oxford
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
Publisher: Elsevier BV
Date: 04-2022
Publisher: Oxford University Press (OUP)
Date: 11-2019
Abstract: The usefulness of genomic prediction in crop and livestock breeding programs has prompted efforts to develop new and improved genomic prediction algorithms, such as artificial neural networks and gradient tree boosting. However, the performance of these algorithms has not been compared in a systematic manner using a wide range of datasets and models. Using data of 18 traits across six plant species with different marker densities and training population sizes, we compared the performance of six linear and six non-linear algorithms. First, we found that hyperparameter selection was necessary for all non-linear algorithms and that feature selection prior to model training was critical for artificial neural networks when the markers greatly outnumbered the number of training lines. Across all species and trait combinations, no one algorithm performed best, however predictions based on a combination of results from multiple algorithms (i.e., ensemble predictions) performed consistently well. While linear and non-linear algorithms performed best for a similar number of traits, the performance of non-linear algorithms vary more between traits. Although artificial neural networks did not perform best for any trait, we identified strategies (i.e., feature selection, seeded starting weights) that boosted their performance to near the level of other algorithms. Our results highlight the importance of algorithm selection for the prediction of trait values.
Publisher: Wiley
Date: 07-10-2021
DOI: 10.1111/DME.14706
Abstract: To conduct a systematic review of published studies reporting on the longitudinal impacts of hypoglycaemia on quality of life (QoL) in adults with type 2 diabetes. Database searches with no restrictions by language or date were conducted in MEDLINE, Cochrane Library, CINAHL and PsycINFO. Studies were included for review if they used a longitudinal design (e.g. cohort studies, randomised controlled trials) and reported on the association between hypoglycaemia and changes over time in patient‐reported outcomes related to QoL. In all, 20 longitudinal studies published between 1998 and 2020, representing 50,429 adults with type 2 diabetes, were selected for review. A descriptive synthesis following Synthesis Without Meta‐analysis guidelines indicated that self‐treated symptomatic hypoglycaemia was followed by impairments in daily functioning along with elevated symptoms of generalised anxiety, diabetes distress and fear of hypoglycaemia. Severe hypoglycaemic events were associated with reduced confidence in diabetes self‐management and lower ratings of perceived health over time. Frequent hypoglycaemia was followed by reduced energy levels and diminished emotional well‐being. There was insufficient evidence, however, to conclude that hypoglycaemia impacted sleep quality, depressive symptoms, general mood, social support or overall diabetes‐specific QoL. Longitudinal evidence in this review suggests hypoglycaemia is a common occurrence among adults with type 2 diabetes that impacts key facets in the physical and psychological domains of QoL. Nonetheless, additional longitudinal research is needed—in particular, studies targeting erse forms of hypoglycaemia, more varied facets of QoL and outcomes assessed using hypoglycaemia‐specific measures.
Publisher: Elsevier BV
Date: 09-2020
Location: United Kingdom of Great Britain and Northern Ireland
No related grants have been discovered for Andrew McCarren.