Journal of the American Pharmacists Association : JAPhA · 2025
Application of health data analytics in pharmacy: An innovative approach to developing a heart failure dashboard.
СтатьяВалидационное исследованиеНазвание и аннотация: Перевод в очереди
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.
Khalil Viviane, Doody Hannah, Nelson Adam J, Nicholls Stephen J, Rao Sriram D, Kirsa Sue
Аннотация
BACKGROUND: There has been increasing interest in the utilisation of health data analytics for decision support systems and prioritising pharmacy clinical work. Despite this potential, there remains limited evidence in the Australian context regarding the design and implementation of data-driven dashboards tailored specifically for pharmacists.
OBJECTIVES: We aimed to develop a disease state dashboard in an Australian hospital to assist clinicians in identifying and prioritising the review of heart failure (HF) patients when admitted for other reasons, enabling timely optimisation of their care.
PRACTICE DESCRIPTION: This project was undertaken to enhance clinical pharmacy services through the integration of health data analytics.
PRACTICE INNOVATION: Using agile methodology to develop the dashboard to accurately identify HF patients regardless of their admission reason or specialty.
EVALUATION METHODS: A prospective validation was conducted to evaluate the sensitivity, specificity, and accuracy of the HF dashboard parameters. A random sample of 100 patients with confirmed HF diagnoses was reviewed by a clinical pharmacist to establish a reference standard. The same patient list was used to test the dashboard's ability to accurately identify HF cases using five key clinical indicators, including any form and dose of loop diuretics, intravenous loop diuretics, ICD-10 coding taxonomy, guidelines-directed medical therapy (GDMT), and BNP levels.
RESULTS: A stakeholder group designed and built the dashboard from a set of 18 carefully chosen HF clinical and non-clinical parameters. Testing and validation of the dashboard demonstrated overall calculated accuracy to be > 70% for the 5 HF main clinical parameters built in the dashboard. Positive predictive values for all parameters were also > 80%, indicating a low likelihood identifying incorrect patients.
CONCLUSION: The dashboard is scalable and transferable due to its flexible, parameter-driven design and use of standardized clinical data. Its agile development and real-time integration support expansion to other conditions and settings.
OBJECTIVES: We aimed to develop a disease state dashboard in an Australian hospital to assist clinicians in identifying and prioritising the review of heart failure (HF) patients when admitted for other reasons, enabling timely optimisation of their care.
PRACTICE DESCRIPTION: This project was undertaken to enhance clinical pharmacy services through the integration of health data analytics.
PRACTICE INNOVATION: Using agile methodology to develop the dashboard to accurately identify HF patients regardless of their admission reason or specialty.
EVALUATION METHODS: A prospective validation was conducted to evaluate the sensitivity, specificity, and accuracy of the HF dashboard parameters. A random sample of 100 patients with confirmed HF diagnoses was reviewed by a clinical pharmacist to establish a reference standard. The same patient list was used to test the dashboard's ability to accurately identify HF cases using five key clinical indicators, including any form and dose of loop diuretics, intravenous loop diuretics, ICD-10 coding taxonomy, guidelines-directed medical therapy (GDMT), and BNP levels.
RESULTS: A stakeholder group designed and built the dashboard from a set of 18 carefully chosen HF clinical and non-clinical parameters. Testing and validation of the dashboard demonstrated overall calculated accuracy to be > 70% for the 5 HF main clinical parameters built in the dashboard. Positive predictive values for all parameters were also > 80%, indicating a low likelihood identifying incorrect patients.
CONCLUSION: The dashboard is scalable and transferable due to its flexible, parameter-driven design and use of standardized clinical data. Its agile development and real-time integration support expansion to other conditions and settings.