Gary Tse1,2, Jiandong Zhou3, Samuel Won Dong Woo4, Ching Ho Ko4, Rachel Wing Chuen Lai4, Tong Liu2, Yingzhi Liu5, Keith Sai Kit Leung6, Andrew Li7, Sharen Lee4, Ka Hou Christien Li8, Ishan Lakhani2, Qingpeng Zhang3. 1. Xiamen Cardiovascular Hospital, Xiamen University, Xiamen, China. 2. Tianjin Key Laboratory of Ionic-Molecular Function of Cardiovascular Disease, Department of Cardiology, Tianjin Institute of Cardiology, Second Hospital of Tianjin Medical University, Tianjin, 300211, China. 3. School of Data Science, City University of Hong Kong, Hong Kong, SAR, China. 4. Laboratory of Cardiovascular Physiology, Li Ka Shing Institute of Health Sciences, Hong Kong, China. 5. Department of Anaesthesia and Intensive Care, Faculty of Medicine, Chinese University of Hong Kong, Hong Kong, SAR, China. 6. Aston Medical School, Aston University, Birmingham, UK. 7. Faculty of Science, University of Calgary, Calgary, AB, Canada. 8. Faculty of Medicine, Newcastle University, Newcastle, UK.
Abstract
AIMS: Heart failure (HF) involves complex remodelling leading to electrical and mechanical dysfunction. We hypothesized that machine learning approaches incorporating data obtained from different investigative modalities including atrial and ventricular measurements from electrocardiography and echocardiography, blood inflammatory marker [neutrophil-to-lymphocyte ratio (NLR)], and prognostic nutritional index (PNI) will improve risk stratification for adverse outcomes in HF compared to logistic regression. METHODS AND RESULTS: Consecutive Chinese patients referred to our centre for transthoracic echocardiography and subsequently diagnosed with HF, between 1 January 2010 and 31 December 2016, were included in this study. Two machine learning techniques, multilayer perceptron and multi-task learning, were compared with logistic regression for their ability to predict incident atrial fibrillation (AF), transient ischaemic attack (TIA)/stroke, and all-cause mortality. This study included 312 HF patients [mean age: 64 (55-73) years, 75% male]. There were 76 cases of new-onset AF, 62 cases of incident TIA/stroke, and 117 deaths during follow-up. Univariate analysis revealed that age, left atrial reservoir strain (LARS) and contractile strain (LACS) were significant predictors of new-onset AF. Age and smoking predicted incident stroke. Age, hypertension, type 2 diabetes mellitus, chronic kidney disease, mitral or aortic regurgitation, P-wave terminal force in V1, the presence of partial inter-atrial block, left atrial diameter, ejection fraction, global longitudinal strain, serum creatinine and albumin, high NLR, low PNI, and LARS and LACS predicted all-cause mortality. Machine learning techniques achieved better prediction performance than logistic regression. CONCLUSIONS: Multi-modality assessment is important for risk stratification in HF. A machine learning approach provides additional value for improving outcome prediction.
AIMS: Heart failure (HF) involves complex remodelling leading to electrical and mechanical dysfunction. We hypothesized that machine learning approaches incorporating data obtained from different investigative modalities including atrial and ventricular measurements from electrocardiography and echocardiography, blood inflammatory marker [neutrophil-to-lymphocyte ratio (NLR)], and prognostic nutritional index (PNI) will improve risk stratification for adverse outcomes in HF compared to logistic regression. METHODS AND RESULTS: Consecutive Chinese patients referred to our centre for transthoracic echocardiography and subsequently diagnosed with HF, between 1 January 2010 and 31 December 2016, were included in this study. Two machine learning techniques, multilayer perceptron and multi-task learning, were compared with logistic regression for their ability to predict incident atrial fibrillation (AF), transient ischaemic attack (TIA)/stroke, and all-cause mortality. This study included 312 HF patients [mean age: 64 (55-73) years, 75% male]. There were 76 cases of new-onset AF, 62 cases of incident TIA/stroke, and 117 deaths during follow-up. Univariate analysis revealed that age, left atrial reservoir strain (LARS) and contractile strain (LACS) were significant predictors of new-onset AF. Age and smoking predicted incident stroke. Age, hypertension, type 2 diabetes mellitus, chronic kidney disease, mitral or aortic regurgitation, P-wave terminal force in V1, the presence of partial inter-atrial block, left atrial diameter, ejection fraction, global longitudinal strain, serum creatinine and albumin, high NLR, low PNI, and LARS and LACS predicted all-cause mortality. Machine learning techniques achieved better prediction performance than logistic regression. CONCLUSIONS: Multi-modality assessment is important for risk stratification in HF. A machine learning approach provides additional value for improving outcome prediction.
Authors: Marina Leitman; Peter Lysyansky; Stanislav Sidenko; Vladimir Shir; Eli Peleg; Michal Binenbaum; Edo Kaluski; Ricardo Krakover; Zvi Vered Journal: J Am Soc Echocardiogr Date: 2004-10 Impact factor: 5.251
Authors: Adam Rahman; Syed Jafry; Khursheed Jeejeebhoy; A Dave Nagpal; Barbara Pisani; Ravi Agarwala Journal: JPEN J Parenter Enteral Nutr Date: 2015-01-29 Impact factor: 4.016
Authors: Andreas Kalogeropoulos; Vasiliki Georgiopoulou; Bruce M Psaty; Nicolas Rodondi; Andrew L Smith; David G Harrison; Yongmei Liu; Udo Hoffmann; Douglas C Bauer; Anne B Newman; Stephen B Kritchevsky; Tamara B Harris; Javed Butler Journal: J Am Coll Cardiol Date: 2010-05-11 Impact factor: 24.094
Authors: Luis Alberto Escobar-Robledo; Antoni Bayés-de-Luna; Josep Lupón; Adrian Baranchuk; Pedro Moliner; Manuel Martínez-Sellés; Elisabet Zamora; Marta de Antonio; Mar Domingo; Germán Cediel; Julio Núñez; Evelyn Santiago-Vacas; Antoni Bayés-Genís Journal: Int J Cardiol Date: 2018-05-18 Impact factor: 4.164
Authors: Shanmugam Uthamalingam; Eshan A Patvardhan; Sharath Subramanian; Waleed Ahmed; William Martin; Marilyn Daley; Robert Capodilupo Journal: Am J Cardiol Date: 2011-02-01 Impact factor: 2.778
Authors: Ashwath Radhachandran; Anurag Garikipati; Nicole S Zelin; Emily Pellegrini; Sina Ghandian; Jacob Calvert; Jana Hoffman; Qingqing Mao; Ritankar Das Journal: BioData Min Date: 2021-03-31 Impact factor: 2.522
Authors: Chengsheng Ju; Jiandong Zhou; Sharen Lee; Martin Sebastian Tan; Tong Liu; George Bazoukis; Kamalan Jeevaratnam; Esther W Y Chan; Ian Chi Kei Wong; Li Wei; Qingpeng Zhang; Gary Tse Journal: ESC Heart Fail Date: 2021-06-03