Márton Tokodi1, Sirish Shrestha2, Christopher Bianco2, Nobuyuki Kagiyama2, Grace Casaclang-Verzosa2, Jagat Narula3, Partho P Sengupta4. 1. Division of Cardiology, West Virginia University Heart & Vascular Institute, Morgantown, West Virginia; Heart and Vascular Center, Semmelweis University, Budapest, Hungary. 2. Division of Cardiology, West Virginia University Heart & Vascular Institute, Morgantown, West Virginia. 3. Division of Cardiology, Icahn School of Medicine at Mount Sinai, New York, New York. 4. Division of Cardiology, West Virginia University Heart & Vascular Institute, Morgantown, West Virginia. Electronic address: partho.sengupta@wvumedicine.org.
Abstract
OBJECTIVES: The authors applied unsupervised machine-learning techniques for integrating echocardiographic features of left ventricular (LV) structure and function into a patient similarity network that predicted major adverse cardiac event(s) (MACE) in an individual patient. BACKGROUND: Patient similarity analysis is an evolving paradigm for precision medicine in which patients are clustered or classified based on their similarities in several clinical features. METHODS: A retrospective cohort of 866 patients was used to develop a network architecture using 9 echocardiographic features of LV structure and function. The data for 468 patients from 2 prospective cohort registries were then added to test the model's generalizability. RESULTS: The map of cross-sectional data in the retrospective cohort resulted in a looped patient network that persisted even after the addition of data from the prospective cohort registries. After subdividing the loop into 4 regions, patients in each region showed unique differences in LV function, with Kaplan-Meier curves demonstrating significant differences in MACE-related rehospitalization and death (both p < 0.001). Addition of network information to clinical risk predictors resulted in significant improvements in net reclassification, integrated discrimination, and median risk scores for predicting MACE (p < 0.05 for all). Furthermore, the network predicted the cardiac disease cycle in each of the 96 patients who had second echocardiographic evaluations. An improvement or remaining in low-risk regions was associated with lower MACE-related rehospitalization rates than worsening or remaining in high-risk regions (3% vs. 37%; p < 0.001). CONCLUSIONS: Patient similarity analysis integrates multiple features of cardiac function to develop a phenotypic network in which patients can be mapped to specific locations associated with specific disease stage and clinical outcomes. The use of patient similarity analysis may have relevance for automated staging of cardiac disease severity, personalized prediction of prognosis, and monitoring progression or response to therapies.
OBJECTIVES: The authors applied unsupervised machine-learning techniques for integrating echocardiographic features of left ventricular (LV) structure and function into a patient similarity network that predicted major adverse cardiac event(s) (MACE) in an individual patient. BACKGROUND:Patient similarity analysis is an evolving paradigm for precision medicine in which patients are clustered or classified based on their similarities in several clinical features. METHODS: A retrospective cohort of 866 patients was used to develop a network architecture using 9 echocardiographic features of LV structure and function. The data for 468 patients from 2 prospective cohort registries were then added to test the model's generalizability. RESULTS: The map of cross-sectional data in the retrospective cohort resulted in a looped patient network that persisted even after the addition of data from the prospective cohort registries. After subdividing the loop into 4 regions, patients in each region showed unique differences in LV function, with Kaplan-Meier curves demonstrating significant differences in MACE-related rehospitalization and death (both p < 0.001). Addition of network information to clinical risk predictors resulted in significant improvements in net reclassification, integrated discrimination, and median risk scores for predicting MACE (p < 0.05 for all). Furthermore, the network predicted the cardiac disease cycle in each of the 96 patients who had second echocardiographic evaluations. An improvement or remaining in low-risk regions was associated with lower MACE-related rehospitalization rates than worsening or remaining in high-risk regions (3% vs. 37%; p < 0.001). CONCLUSIONS:Patient similarity analysis integrates multiple features of cardiac function to develop a phenotypic network in which patients can be mapped to specific locations associated with specific disease stage and clinical outcomes. The use of patient similarity analysis may have relevance for automated staging of cardiac disease severity, personalized prediction of prognosis, and monitoring progression or response to therapies.
Authors: Joanne Simpson; Pardeep S Jhund; Jose Silva Cardoso; Felipe Martinez; Arend Mosterd; Felix Ramires; Adel R Rizkala; Michele Senni; Iain Squire; Jianjian Gong; Martin P Lefkowitz; Victor C Shi; Akshay S Desai; Jean L Rouleau; Karl Swedberg; Michael R Zile; John J V McMurray; Milton Packer; Scott D Solomon Journal: J Am Coll Cardiol Date: 2015-11-10 Impact factor: 24.094
Authors: Timothy S C Hinks; Xiaoying Zhou; Karl J Staples; Borislav D Dimitrov; Alexander Manta; Tanya Petrossian; Pek Y Lum; Caroline G Smith; Jon A Ward; Peter H Howarth; Andrew F Walls; Stephan D Gadola; Ratko Djukanović Journal: J Allergy Clin Immunol Date: 2015-03-05 Impact factor: 10.793
Authors: P Y Lum; G Singh; A Lehman; T Ishkanov; M Vejdemo-Johansson; M Alagappan; J Carlsson; G Carlsson Journal: Sci Rep Date: 2013-02-07 Impact factor: 4.379
Authors: Partho P Sengupta; Sirish Shrestha; Nobuyuki Kagiyama; Yasmin Hamirani; Hemant Kulkarni; Naveena Yanamala; Rong Bing; Calvin W L Chin; Tania A Pawade; David Messika-Zeitoun; Lionel Tastet; Mylène Shen; David E Newby; Marie-Annick Clavel; Phillippe Pibarot; Marc R Dweck Journal: JACC Cardiovasc Imaging Date: 2021-05-19
Authors: Márton Tokodi; Anett Behon; Eperke Dóra Merkel; Attila Kovács; Zoltán Tősér; András Sárkány; Máté Csákvári; Bálint Károly Lakatos; Walter Richard Schwertner; Annamária Kosztin; Béla Merkely Journal: Front Cardiovasc Med Date: 2021-02-25