International journal of laboratory hematology · 2026
Design and Implementation of an Automated Interpretation Algorithm for Lupus Anticoagulant Functional Testing.
СтатьяНазвание и аннотация: Перевод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
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.
Novelli Chiara, Gatti Arianna, Ierna Flora, Riccardi Elena, Cuppari Irene
Аннотация
INTRODUCTION: Lupus anticoagulant (LA) testing is essential, albeit complex, in the laboratory diagnosis of antiphospholipid syndrome (APS). Given the multi-step workflow and the variability introduced by anticoagulant therapy, reagent differences, and interpretive approaches, result interpretation requires expert evaluation. To address these challenges, we implemented a middleware-based automated algorithm in our four-hospital institution using the HemoHub system, guided by the latest ISTH recommendations. The objectives were to automate reflex testing, standardize interpretation, and support clinical decision-making.
METHODS: The algorithm incorporated rules aligned with good laboratory practice for LA diagnostics, including reflex testing, result interpretation, internal comments, integration of historical data, and auto-validation of negative cases. Retrospective validation was performed on 190 historical cases in which the diagnosis was made conventionally and corroborated by follow-up data. A subsequent prospective blind comparison with manual operator-based workflow was conducted on 481 routine samples.
RESULTS: Concordance between automated and manual interpretations reached 100% for LA negative and positive cases, with slightly lower agreement for first-time positives (88.6% and 82.4%). When automated interpretation was not assignable, the system still provided useful internal comments. Additionally, 58.4% of samples were auto-validated, significantly reducing manual workload. Time comparison demonstrated substantial savings for both experienced and less-experienced pathologists.
CONCLUSION: The implementation of the automated algorithm improved consistency, reduced interpretation time, and minimized intra- and inter-laboratory variability. By integrating clinical context and historical data, it enhanced diagnostic accuracy. These findings support the use of middleware-based, rule-driven interpretation as a reliable and efficient approach to standardizing LA testing and optimizing laboratory workflow.
METHODS: The algorithm incorporated rules aligned with good laboratory practice for LA diagnostics, including reflex testing, result interpretation, internal comments, integration of historical data, and auto-validation of negative cases. Retrospective validation was performed on 190 historical cases in which the diagnosis was made conventionally and corroborated by follow-up data. A subsequent prospective blind comparison with manual operator-based workflow was conducted on 481 routine samples.
RESULTS: Concordance between automated and manual interpretations reached 100% for LA negative and positive cases, with slightly lower agreement for first-time positives (88.6% and 82.4%). When automated interpretation was not assignable, the system still provided useful internal comments. Additionally, 58.4% of samples were auto-validated, significantly reducing manual workload. Time comparison demonstrated substantial savings for both experienced and less-experienced pathologists.
CONCLUSION: The implementation of the automated algorithm improved consistency, reduced interpretation time, and minimized intra- and inter-laboratory variability. By integrating clinical context and historical data, it enhanced diagnostic accuracy. These findings support the use of middleware-based, rule-driven interpretation as a reliable and efficient approach to standardizing LA testing and optimizing laboratory workflow.