TY - JOUR
T1 - Clinical validation of an artificial intelligence-based decision support system for diagnosis and risk stratification of heart failure (STRATIFYHF)
T2 - a protocol for a prospective, multicentre longitudinal study
AU - Charman, Sarah Jane
AU - Okwose, Nduka C
AU - Groenewegen, Amy
AU - Del Franco, Annamaria
AU - Tafelmeier, Maria
AU - Preveden, Andrej
AU - Garcia Sebastian, Cristina
AU - Fuller, Amy S
AU - Sinclair, David
AU - Edwards, Duncan
AU - Nelissen, Anne Pauline
AU - Malitas, Petros
AU - Zisaki, Aikaterini
AU - Darba, Josep
AU - Bosnic, Zoran
AU - Vracar, Petar
AU - Barlocco, Fausto
AU - Fotiadis, Dimitris
AU - Banerjee, Prithwish
AU - MacGowan, Guy A
AU - Fernandez, Oscar
AU - Zamorano, José
AU - Jiménez-Blanco Bravo, Marta
AU - Maier, Lars S
AU - Olivotto, Iacopo
AU - Rutten, Frans H
AU - Mant, Jonathan
AU - Velicki, Lazar
AU - Seferović, Petar M
AU - Filipovic, Nenad
AU - Jakovljevic, Djordje G
N1 - Publisher Copyright:
© Author(s) (or their employer(s)) 2025.
PY - 2025/1/7
Y1 - 2025/1/7
N2 - Introduction Heart failure (HF) is a complex clinical syndrome. Accurate risk stratification and early diagnosis of HF are challenging as its signs and symptoms are non-specific. We propose to address this global challenge by developing the STRATIFYHF artificial intelligence-driven decision support system (DSS), which uses novel analytical methods in determining the risk, diagnosis and prognosis of HF. The primary aim of the present study is to collect prospective clinical data to validate the STRATIFYHF DSS (in terms of diagnostic accuracy, sensitivity and specificity) as a tool to predict the risk, diagnosis and progression of HF. The secondary outcomes are the demographic and clinical predictors of risk, diagnosis and progression of HF. Methods and analysis STRATIFYHF is a prospective, multicentre, longitudinal study that will recruit up to 1600 individuals (n=800 suspected/at risk of HF and n=800 diagnosed with HF) aged ≥45 years old, with up to 24 months of follow-up observations. Individuals suspected of HF will be divided into two categories based on current definitions and predefined inclusion criteria. All participants will have their medical history recorded, along with data on physical examination (signs and symptoms), blood tests including serum natriuretic peptides levels, ECG and echocardiogram results, as well as demographic, socioeconomic and lifestyle data, and use of complete novel technologies (cardiac output response to stress test and voice recognition biomarkers). All measurements will be recorded at baseline and at 12-month follow-up, with medical history and hospitalisation also recorded at 24-month follow-up. Cardiovascular MRI assessment will be completed in a subset of participants (n=20-40) from eligible clinical centres only at baseline. Each clinical centre will recruit a subset of participants (n=30) who will complete a 6-month home-based monitoring of clinical characteristics and accelerometry (wrist-worn monitor) to determine the feasibility and acceptability of the STRATIFYHF mobile application. Focus groups and semistructured interviews will be conducted with up to 15 healthcare professionals and up to 20 study participants (10 at risk of HF and 10 diagnosed with HF) to explore the needs of patients and healthcare professionals prior to the development of the STRATIFYHF DSS and to evaluate the acceptability of this mobile application. Ethics and dissemination Ethical approval has been granted by the East Midlands - Leicester Central Research Ethics Committee (24/EM/0101). Dissemination activities will include journal publications and presentations at conferences, as well as development of training materials and delivery of focused training on the STRATIFYHF DSS and mobile application. We will develop and propose policy guidelines for integration of the STRATIFYHF DSS and mobile application into the standard of care in the HF care pathway.
AB - Introduction Heart failure (HF) is a complex clinical syndrome. Accurate risk stratification and early diagnosis of HF are challenging as its signs and symptoms are non-specific. We propose to address this global challenge by developing the STRATIFYHF artificial intelligence-driven decision support system (DSS), which uses novel analytical methods in determining the risk, diagnosis and prognosis of HF. The primary aim of the present study is to collect prospective clinical data to validate the STRATIFYHF DSS (in terms of diagnostic accuracy, sensitivity and specificity) as a tool to predict the risk, diagnosis and progression of HF. The secondary outcomes are the demographic and clinical predictors of risk, diagnosis and progression of HF. Methods and analysis STRATIFYHF is a prospective, multicentre, longitudinal study that will recruit up to 1600 individuals (n=800 suspected/at risk of HF and n=800 diagnosed with HF) aged ≥45 years old, with up to 24 months of follow-up observations. Individuals suspected of HF will be divided into two categories based on current definitions and predefined inclusion criteria. All participants will have their medical history recorded, along with data on physical examination (signs and symptoms), blood tests including serum natriuretic peptides levels, ECG and echocardiogram results, as well as demographic, socioeconomic and lifestyle data, and use of complete novel technologies (cardiac output response to stress test and voice recognition biomarkers). All measurements will be recorded at baseline and at 12-month follow-up, with medical history and hospitalisation also recorded at 24-month follow-up. Cardiovascular MRI assessment will be completed in a subset of participants (n=20-40) from eligible clinical centres only at baseline. Each clinical centre will recruit a subset of participants (n=30) who will complete a 6-month home-based monitoring of clinical characteristics and accelerometry (wrist-worn monitor) to determine the feasibility and acceptability of the STRATIFYHF mobile application. Focus groups and semistructured interviews will be conducted with up to 15 healthcare professionals and up to 20 study participants (10 at risk of HF and 10 diagnosed with HF) to explore the needs of patients and healthcare professionals prior to the development of the STRATIFYHF DSS and to evaluate the acceptability of this mobile application. Ethics and dissemination Ethical approval has been granted by the East Midlands - Leicester Central Research Ethics Committee (24/EM/0101). Dissemination activities will include journal publications and presentations at conferences, as well as development of training materials and delivery of focused training on the STRATIFYHF DSS and mobile application. We will develop and propose policy guidelines for integration of the STRATIFYHF DSS and mobile application into the standard of care in the HF care pathway.
KW - Artificial Intelligence
KW - Clinical Decision-Making
KW - Heart failure
KW - Risk management
UR - http://www.scopus.com/inward/record.url?scp=85214697741&partnerID=8YFLogxK
U2 - 10.1136/bmjopen-2024-091793
DO - 10.1136/bmjopen-2024-091793
M3 - Article
C2 - 39773784
SN - 2044-6055
VL - 15
JO - BMJ Open
JF - BMJ Open
IS - 1
M1 - e091793
ER -