Identification of important risk factors for all-cause mortality of acquired long QT syndrome patients using random survival forests and non-negative matrix factorization

Published:October 27, 2020DOI:


      Acquired long QT syndrome (aLQTS) is often associated with poor clinical outcomes.


      The purpose of this study was to examine the important predictors of all-cause mortality of aLQTS patients by applying both random survival forest (RSF) and non-negative matrix factorization (NMF) analyses.


      Clinical characteristics and manually measured electrocardiographic (ECG) parameters were initially entered into the RSF model. Subsequently, latent variables identified using NMF were entered into the RSF as additional variables. The primary outcome was all-cause mortality.


      A total of 327 aLQTS patients were included. The RSF model identified 16 predictive factors with positive variable importance values: cancer, potassium, RR interval, calcium, age, JT interval, diabetes mellitus, QRS duration, QTp interval, chronic kidney disease, QTc interval, hypertension, QT interval, female, JTc interval, and cerebral hemorrhage. Increasing the number of latent features between ECG indices, which incorporated from n = 0 to n = 4 by NMF, maximally improved the prediction ability of the RSF-NMF model (C-statistic 0.77 vs 0.89).


      Cancer and serum potassium and calcium levels can predict all-cause mortality of aLQTS patients, as can ECG indicators including JTc and QRS. The present RSF-NMF model significantly improved mortality prediction.


      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic and Personal
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'


      Subscribe to Heart Rhythm
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect


        • Kallergis E.M.
        • Goudis C.A.
        • Simantirakis E.N.
        • Kochiadakis G.E.
        • Vardas P.E.
        Mechanisms, risk factors, and management of acquired long QT syndrome: a comprehensive review.
        ScientificWorldJournal. 2012; 2012: 212178
        • Yu H.
        • Zhang L.
        • Liu J.
        • et al.
        Acquired long QT syndrome in hospitalized patients.
        Heart Rhythm. 2017; 14: 974-978
        • Goldberg R.J.
        • Bengtson J.
        • Chen Z.Y.
        • Anderson K.M.
        • Locati E.
        • Levy D.
        Duration of the QT interval and total and cardiovascular mortality in healthy persons (The Framingham Heart Study experience).
        Am J Cardiol. 1991; 67: 55-58
        • Day C.P.
        • McComb J.M.
        • Campbell R.W.
        QT dispersion: an indication of arrhythmia risk in patients with long QT intervals.
        Br Heart J. 1990; 63: 342-344
        • Tse G.
        • Gong M.
        • Meng L.
        • et al.
        Predictive value of T peak-T end indices for adverse outcomes in acquired QT prolongation: a meta-analysis.
        Front Physiol. 2018; 9: 1226
        • Zulqarnain M.A.
        • Qureshi W.T.
        • O'Neal W.T.
        • Shah A.J.
        • Soliman E.Z.
        Risk of mortality associated with QT and JT intervals at different levels of QRS duration (from the Third National Health and Nutrition Examination Survey).
        Am J Cardiol. 2015; 116: 74-78
        • Tse G.
        • Yan B.P.
        Traditional and novel electrocardiographic conduction and repolarization markers of sudden cardiac death.
        Europace. 2017; 19: 712-721
        • Ishwaran H.
        • Kogalur U.B.
        • Blackstone E.H.
        • Lauer M.S.
        Random survival forests.
        Ann Appl Stat. 2008; 2: 841-860
        • Hsich E.
        • Gorodeski E.Z.
        • Blackstone E.H.
        • Ishwaran H.
        • Lauer M.S.
        Identifying important risk factors for survival in patient with systolic heart failure using random survival forests.
        Circ Cardiovasc Qual Outcomes. 2011; 4: 39-45
        • Mamyrova G.
        • O'Hanlon T.P.
        • Monroe J.B.
        • et al.
        Immunogenetic risk and protective factors for juvenile dermatomyositis in Caucasians.
        Arthritis Rheum. 2006; 54: 3979-3987
        • Lee D.D.
        • Seung H.S.
        Learning the parts of objects by non-negative matrix factorization.
        Nature. 1999; 401: 788-791
        • Frigyesi A.
        • Höglund M.
        Non-negative matrix factorization for the analysis of complex gene expression data: identification of clinically relevant tumor subtypes.
        Cancer Inform. 2008; 6: 275-292
        • Niegowski M.
        • Zivanovic M.
        ECG-EMG separation by using enhanced non-negative matrix factorization.
        2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Chicago, IL2014: 4212-4215 (doi: 10.1109/EMBC.2014.6944553)
        • Rautaharju P.M.
        • Surawicz B.
        • Gettes L.S.
        • et al.
        AHA/ACCF/HRS recommendations for the standardization and interpretation of the electrocardiogram: part IV: the ST segment, T and U waves, and the QT interval: a scientific statement from the American Heart Association Electrocardiography and Arrhythmias Committee, Council on Clinical Cardiology; the American College of Cardiology Foundation; and the Heart Rhythm Society. Endorsed by the International Society for Computerized Electrocardiology.
        J Am Coll Cardiol. 2009; 53: 982-991
        • Kors J.A.
        • Ritsema van Eck H.J.
        • van Herpen G.
        The meaning of the Tp-Te interval and its diagnostic value.
        J Electrocardiol. 2008; 41: 575-580
        • Bazett H.
        An analysis of the time-relations of electrocardiograms.
        Ann Noninvas Electrocardiol. 1997; 2: 177-194
        • Ishwaran H.
        • Kogalur U.B.
        • Gorodeski E.Z.
        • Minn A.J.
        • Lauer M.S.
        High-dimensional variable selection for survival data.
        J Am Stat Assoc. 2010; 105: 205-217
        • Hoyer P.O.
        Non-negative matrix factorization with sparseness constraints.
        J Mach Learn Res. 2004; 5: 1457-1469
        • Breiman L.
        Random forests.
        Mach Learn. 2001; 45: 5-32
        • Guyot P.
        • Djermoune E.-H.
        • Bastogne T.
        Assessment of non-negative matrix factorization for the preprocessing of long-term ECG.
        J Pharmacol Toxicol Methods. 2019; 99 (doi: 10.1016/j.vascn.2019.05.095): 106595
        • Tse G.
        • Zhou J.
        • Lee S.
        • et al.
        Incorporating latent variables using nonnegative matrix factorization improves risk stratification in Brugada syndrome.
        J Am Heart Assoc. 2020; 9e012714
        • Wang J.
        • An J.
        • Tse G.
        • et al.
        Prognostic potential of electrocardiographic parameters in patients with multiple myeloma: a retrospective analysis of the multiple myeloma population.
        Adv Ther. 2020; 37: 2946-2955
        • Chen Z.
        • Lu K.
        • Zhou L.
        • et al.
        Electrocardiographic characteristics of diffuse large B-cell lymphoma patients treated with anthracycline-based chemotherapy.
        J Electrocardiol. 2020; 60: 195-199
        • Akintunde A.A.
        • Ayodele O.E.
        • Opadijo O.G.
        • Oyedeji A.T.
        • Familoni O.B.
        QT Interval prolongation and dispersion: epidemiology and clinical correlates in subjects with newly diagnosed systemic hypertension in Nigeria.
        J Cardiovasc Dis Res. 2012; 3: 290-295
        • Lin Y.
        • Yu H.
        • Liu F.
        • et al.
        Hospitalized cancer patients with acquired long QT syndrome—a matched case-control study.
        Cardio-oncology. 2020; 6: 1-7
        • Choy A.M.
        • Lang C.C.
        • Chomsky D.M.
        • Rayos G.H.
        • Wilson J.R.
        • Roden D.M.
        Normalization of acquired QT prolongation in humans by intravenous potassium.
        Circulation. 1997; 96: 2149-2154
        • Al-Khatib S.M.
        • LaPointe N.M.A.
        • Kramer J.M.
        • Califf R.M.
        What clinicians should know about the QT interval.
        JAMA. 2003; 289: 2120-2127
        • Tse G.
        Mechanisms of cardiac arrhythmias.
        J Arrhythm. 2016; 32: 75-81
        • Zareba W.
        • McNitt S.
        • Polonsky S.
        • Couderc J.P.
        JT interval: what does this interval mean?.
        J Electrocardiol. 2017; 50: 748-751
        • Kurl S.
        • Mäkikallio T.H.
        • Rautaharju P.
        • Kiviniemi V.
        • Laukkanen J.A.
        Duration of QRS complex in resting electrocardiogram is a predictor of sudden cardiac death in men.
        Circulation. 2012; 125: 2588-2594
        • Vink A.S.
        • Clur S.-A.B.
        • Wilde A.A.
        • Blom N.A.
        Effect of age and gender on the QTc-interval in healthy individuals and patients with long-QT syndrome.
        Trends Cardiovasc Med. 2018; 28: 64-75
        • Pasquier M.
        • Pantet O.
        • Hugli O.
        • et al.
        Prevalence and determinants of QT interval prolongation in medical inpatients.
        Intern Med J. 2012; 42: 933-940
        • Malik R.
        • Waheed S.
        • Parashara D.
        • Perez J.
        • Waheed S.
        Association of QT interval with mortality by kidney function: results from the National Health and Nutrition Examination Survey (NHANES).
        Open Heart. 2017; 4e000683
        • Liu P.
        • Wang L.
        • Han D.
        • Sun C.
        • Xue X.
        • Li G.
        Acquired long QT syndrome in chronic kidney disease patients.
        Ren Fail. 2020; 42: 54-65