MedElevator Войти в исследования
← Поиск публикаций

DOI 10.1016/j.prevetmed.2026.107012

Медицинская библиотека · Preventive veterinary medicine · 2026

Decoding persistent elevated mortality in farmed marine Scottish Atlantic salmon (Salmo salar L.) using artificial intelligence and logical modelling.

Moriarty Meadhbh, Duguid Sonia J, Parker Sarah-Jane, Murphy Joanne M, Smith Ronald J, Purvis Neil L, Murray Alexander G

СтатьяПеревод в очереди

Аннотация

Atlantic salmon (Salmo salar) farming, an important contributor to global seafood production, is the dominant sector of Scottish aquaculture. High mortality has been experienced in recent years, reflecting complex interactions between environment, pathogens, and operational factors. Understanding mortality trends enables proactive and empowered management and sustainable production. We developed a framework combining artificial intelligence (AI)-assisted data preparation, logic-based modelling and expert validation to identify and interpret mortality patterns from publicly available datasets. Definitions of recurrent mortality, persistent mortality and elevated mortality were developed to support reproducible and transparent interpretation. The framework was applied to Scottish marine salmon production data to identify sites exhibiting elevated mortality and to prioritise case for further investigation. Applying predefined criteria for recurrent, persistent and elevated mortality to 216 sites, 188 sites showed no evidence of persistent elevated mortality, 25 sites were prioritised for expert analysis with 20 sites taken forward for stakeholder engagement. Further evaluation involving additional data determined that 10 sites experienced persistent elevated mortality with the same cause, the remaining 10 represented recurrent elevated mortality arising from different factors. Expert review confirmed that prioritising ambiguous cases improved sensitivity at the expense of specificity, hence a relatively high false positive rate is needed to make assessment safely. This outcome demonstrated the value of combining automated screening with expert interpretation when assessing complex health and production datasets. Beyond aquaculture, the framework may provide a transferable approach for analysing mortality patterns in other production systems characterised by repeated production cycles and routinely collected mortality data.

Для цитирования: Moriarty Meadhbh, Duguid Sonia J, Parker Sarah-Jane, Murphy Joanne M, Smith Ronald J, Purvis Neil L, Murray Alexander G. Decoding persistent elevated mortality in farmed marine Scottish Atlantic salmon (Salmo salar L.) using artificial intelligence and logical modelling.. Preventive veterinary medicine. 2026. DOI: 10.1016/j.prevetmed.2026.107012.
Подготовка и перевод публикации
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…

История · было → стало

Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.

Тип публикации указан по данным источника. Уровень доказательности автоматически не присваивается.