RATIONALE: Susceptibility to VT/VF (ventricular tachycardia/fibrillation) is difficult to predict in patients with ischemic cardiomyopathy either by clinical tools or by attempting to translate cellular mechanisms to the bedside. OBJECTIVE: To develop computational phenotypes of patients with ischemic cardiomyopathy, by training then interpreting machine learning of ventricular monophasic action potentials (MAPs) to reveal phenotypes that predict long-term outcomes. METHODS AND RESULTS: We recorded 5706 ventricular MAPs in 42 patients with coronary artery disease and left ventricular ejection fraction ≤40% during steady-state pacing. Patients were randomly allocated to independent training and testing cohorts in a 70:30 ratio, repeated K=10-fold. Support vector machines and convolutional neural networks were trained to 2 end points: (1) sustained VT/VF or (2) mortality at 3 years. Support vector machines provided superior classification. For patient-level predictions, we computed personalized MAP scores as the proportion of MAP beats predicting each end point. Patient-level predictions in independent test cohorts yielded c-statistics of 0.90 for sustained VT/VF (95% CI, 0.76-1.00) and 0.91 for mortality (95% CI, 0.83-1.00) and were the most significant multivariate predictors. Interpreting trained support vector machine revealed MAP morphologies that, using in silico modeling, revealed higher L-type calcium current or sodium-calcium exchanger as predominant phenotypes for VT/VF. CONCLUSIONS: Machine learning of action potential recordings in patients revealed novel phenotypes for long-term outcomes in ischemic cardiomyopathy. Such computational phenotypes provide an approach which may reveal cellular mechanisms for clinical outcomes and could be applied to other conditions.
RATIONALE: Susceptibility to VT/VF (ventricular tachycardia/fibrillation) is difficult to predict in patients with ischemic cardiomyopathy either by clinical tools or by attempting to translate cellular mechanisms to the bedside. OBJECTIVE: To develop computational phenotypes of patients with ischemic cardiomyopathy, by training then interpreting machine learning of ventricular monophasic action potentials (MAPs) to reveal phenotypes that predict long-term outcomes. METHODS AND RESULTS: We recorded 5706 ventricular MAPs in 42 patients with coronary artery disease and left ventricular ejection fraction ≤40% during steady-state pacing. Patients were randomly allocated to independent training and testing cohorts in a 70:30 ratio, repeated K=10-fold. Support vector machines and convolutional neural networks were trained to 2 end points: (1) sustained VT/VF or (2) mortality at 3 years. Support vector machines provided superior classification. For patient-level predictions, we computed personalized MAP scores as the proportion of MAP beats predicting each end point. Patient-level predictions in independent test cohorts yielded c-statistics of 0.90 for sustained VT/VF (95% CI, 0.76-1.00) and 0.91 for mortality (95% CI, 0.83-1.00) and were the most significant multivariate predictors. Interpreting trained support vector machine revealed MAP morphologies that, using in silico modeling, revealed higher L-type calcium current or sodium-calcium exchanger as predominant phenotypes for VT/VF. CONCLUSIONS: Machine learning of action potential recordings in patients revealed novel phenotypes for long-term outcomes in ischemic cardiomyopathy. Such computational phenotypes provide an approach which may reveal cellular mechanisms for clinical outcomes and could be applied to other conditions.
Entities:
Keywords:
artificial intelligence; coronary disease; death, sudden, cardiac; heart failure; ion channels; systems biology
Authors: Jeffrey J Goldberger; Anirban Basu; Robin Boineau; Alfred E Buxton; Michael E Cain; John M Canty; Peng-Sheng Chen; Sumeet S Chugh; Otto Costantini; Derek V Exner; Alan H Kadish; Byron Lee; Donald Lloyd-Jones; Arthur J Moss; Robert J Myerburg; Jeffrey E Olgin; Rod Passman; William G Stevenson; Gordon F Tomaselli; Wojciech Zareba; Douglas P Zipes; Laurie Zoloth Journal: Circulation Date: 2014-01-28 Impact factor: 29.690
Authors: Yiyi Zhang; Eliseo Guallar; Elena Blasco-Colmenares; Darshan Dalal; Barbara Butcher; Sanaz Norgard; Fleur V Y Tjong; Zayd Eldadah; Timm Dickfeld; Kenneth A Ellenbogen; Joseph E Marine; Gordon F Tomaselli; Alan Cheng Journal: Heart Rhythm Date: 2014-10-30 Impact factor: 6.343
Authors: Ian D Greener; Tetsuo Sasano; Xiaoping Wan; Tomonori Igarashi; Maria Strom; David S Rosenbaum; J Kevin Donahue Journal: J Am Coll Cardiol Date: 2012-08-08 Impact factor: 24.094
Authors: Andrew J Sweatt; Haley K Hedlin; Vidhya Balasubramanian; Andrew Hsi; Lisa K Blum; William H Robinson; Francois Haddad; Peter M Hickey; Robin Condliffe; Allan Lawrie; Mark R Nicolls; Marlene Rabinovitch; Purvesh Khatri; Roham T Zamanian Journal: Circ Res Date: 2019-03-15 Impact factor: 17.367
Authors: Awni Y Hannun; Pranav Rajpurkar; Masoumeh Haghpanahi; Geoffrey H Tison; Codie Bourn; Mintu P Turakhia; Andrew Y Ng Journal: Nat Med Date: 2019-01-07 Impact factor: 53.440
Authors: Gary R Mirams; Mark R Davies; Stephen J Brough; Matthew H Bridgland-Taylor; Yi Cui; David J Gavaghan; Najah Abi-Gerges Journal: J Pharmacol Toxicol Methods Date: 2014-07-31 Impact factor: 1.950
Authors: Pei-Chi Yang; Kevin R DeMarco; Parya Aghasafari; Mao-Tsuen Jeng; John R D Dawson; Slava Bekker; Sergei Y Noskov; Vladimir Yarov-Yarovoy; Igor Vorobyov; Colleen E Clancy Journal: Circ Res Date: 2020-02-24 Impact factor: 17.367
Authors: Cheuk To Chung; George Bazoukis; Sharen Lee; Ying Liu; Tong Liu; Konstantinos P Letsas; Antonis A Armoundas; Gary Tse Journal: Int J Arrhythmia Date: 2022-04-01