PMID- 30689812
OWN - NLM
STAT- MEDLINE
DCOM- 20200605
LR  - 20220129
IS  - 1522-9645 (Electronic)
IS  - 0195-668X (Print)
IS  - 0195-668X (Linking)
VI  - 40
IP  - 13
DP  - 2019 Apr 1
TI  - Machine learning algorithms estimating prognosis and guiding therapy in adult 
      congenital heart disease: data from a single tertiary centre including 10 019 
      patients.
PG  - 1069-1077
LID - 10.1093/eurheartj/ehy915 [doi]
AB  - AIMS: To assess the utility of machine learning algorithms on estimating 
      prognosis and guiding therapy in a large cohort of patients with adult congenital 
      heart disease (ACHD) or pulmonary hypertension at a single, tertiary centre. 
      METHODS AND RESULTS: We included 10 019 adult patients (age 36.3 +/- 17.3 years) 
      under follow-up at our institution between 2000 and 2018. Clinical and 
      demographic data, ECG parameters, cardiopulmonary exercise testing, and selected 
      laboratory markers where collected and included in deep learning (DL) algorithms. 
      Specific DL-models were built based on raw data to categorize diagnostic group, 
      disease complexity, and New York Heart Association (NYHA) class. In addition, 
      models were developed to estimate need for discussion at multidisciplinary team 
      (MDT) meetings and to gauge prognosis of individual patients. Overall, the 
      DL-algorithms-based on over 44 000 medical records-categorized diagnosis, disease 
      complexity, and NYHA class with an accuracy of 91.1%, 97.0%, and 90.6%, 
      respectively in the test sample. Similarly, patient presentation at MDT-meetings 
      was predicted with a test sample accuracy of 90.2%. During a median follow-up 
      time of 8 years, 785 patients died. The automatically derived disease 
      severity-score derived from clinical information was related to survival on Cox 
      analysis independently of demographic, exercise, laboratory, and ECG parameters. 
      CONCLUSION: We present herewith the utility of machine learning algorithms 
      trained on large datasets to estimate prognosis and potentially to guide therapy 
      in ACHD. Due to the largely automated process involved, these DL-algorithms can 
      easily be scaled to multi-institutional datasets to further improve accuracy and 
      ultimately serve as online based decision-making tools.
CI  - Published on behalf of the European Society of Cardiology. All rights reserved. (c) 
      The Author(s) 2019. For permissions, please email: journals.permissions@oup.com.
FAU - Diller, Gerhard-Paul
AU  - Diller GP
AD  - Adult Congenital Heart Centre, National Centre for Pulmonary Hypertension, Royal 
      Brompton Hospital, Sydney Street, London, UK.
AD  - National Heart and Lung Institute, Imperial College School of Medicine, Dovehouse 
      Street, London, UK.
AD  - Department of Cardiology III - Adult Congenital and Valvular Heart Disease, 
      University Hospital Muenster, Albert-Schweitzer-Campus 1, Muenster, Germany.
AD  - Competence Network for Congenital Heart Defects, DZHK (German Centre for 
      Cardiovascular Research), Augustenburger Platz 1, Berlin, Germany.
FAU - Kempny, Aleksander
AU  - Kempny A
AD  - Adult Congenital Heart Centre, National Centre for Pulmonary Hypertension, Royal 
      Brompton Hospital, Sydney Street, London, UK.
AD  - National Heart and Lung Institute, Imperial College School of Medicine, Dovehouse 
      Street, London, UK.
FAU - Babu-Narayan, Sonya V
AU  - Babu-Narayan SV
AD  - Adult Congenital Heart Centre, National Centre for Pulmonary Hypertension, Royal 
      Brompton Hospital, Sydney Street, London, UK.
AD  - National Heart and Lung Institute, Imperial College School of Medicine, Dovehouse 
      Street, London, UK.
FAU - Henrichs, Marthe
AU  - Henrichs M
AD  - Department of Cardiology III - Adult Congenital and Valvular Heart Disease, 
      University Hospital Muenster, Albert-Schweitzer-Campus 1, Muenster, Germany.
FAU - Brida, Margarita
AU  - Brida M
AD  - Adult Congenital Heart Centre, National Centre for Pulmonary Hypertension, Royal 
      Brompton Hospital, Sydney Street, London, UK.
AD  - Division of Valvular Heart Disease and Adult Congenital Heart Disease, Department 
      of Cardiovascular Medicine, University Hospital Centre Zagreb, Kispaticeva 12, 
      Zagreb, Croatia.
FAU - Uebing, Anselm
AU  - Uebing A
AD  - Adult Congenital Heart Centre, National Centre for Pulmonary Hypertension, Royal 
      Brompton Hospital, Sydney Street, London, UK.
AD  - Division of Paediatric Cardiology, University Hospital Muenster, 
      Albert-Schweitzer-Campus 1, Muenster, Germany.
FAU - Lammers, Astrid E
AU  - Lammers AE
AD  - Division of Paediatric Cardiology, University Hospital Muenster, 
      Albert-Schweitzer-Campus 1, Muenster, Germany.
FAU - Baumgartner, Helmut
AU  - Baumgartner H
AD  - Department of Cardiology III - Adult Congenital and Valvular Heart Disease, 
      University Hospital Muenster, Albert-Schweitzer-Campus 1, Muenster, Germany.
AD  - Competence Network for Congenital Heart Defects, DZHK (German Centre for 
      Cardiovascular Research), Augustenburger Platz 1, Berlin, Germany.
FAU - Li, Wei
AU  - Li W
AD  - Adult Congenital Heart Centre, National Centre for Pulmonary Hypertension, Royal 
      Brompton Hospital, Sydney Street, London, UK.
AD  - National Heart and Lung Institute, Imperial College School of Medicine, Dovehouse 
      Street, London, UK.
FAU - Wort, Stephen J
AU  - Wort SJ
AD  - Adult Congenital Heart Centre, National Centre for Pulmonary Hypertension, Royal 
      Brompton Hospital, Sydney Street, London, UK.
AD  - National Heart and Lung Institute, Imperial College School of Medicine, Dovehouse 
      Street, London, UK.
FAU - Dimopoulos, Konstantinos
AU  - Dimopoulos K
AD  - Adult Congenital Heart Centre, National Centre for Pulmonary Hypertension, Royal 
      Brompton Hospital, Sydney Street, London, UK.
AD  - National Heart and Lung Institute, Imperial College School of Medicine, Dovehouse 
      Street, London, UK.
FAU - Gatzoulis, Michael A
AU  - Gatzoulis MA
AD  - Adult Congenital Heart Centre, National Centre for Pulmonary Hypertension, Royal 
      Brompton Hospital, Sydney Street, London, UK.
AD  - National Heart and Lung Institute, Imperial College School of Medicine, Dovehouse 
      Street, London, UK.
LA  - eng
GR  - FS/11/38/28864/BHF_/British Heart Foundation/United Kingdom
PT  - Journal Article
PT  - Research Support, Non-U.S. Gov't
PL  - England
TA  - Eur Heart J
JT  - European heart journal
JID - 8006263
SB  - IM
CIN - Eur Heart J. 2019 Apr 1;40(13):1078-1080. PMID: 30863860
MH  - Adult
MH  - *Algorithms
MH  - Clinical Decision-Making/methods
MH  - Deep Learning
MH  - Electrocardiography/methods
MH  - Exercise Test/methods
MH  - Follow-Up Studies
MH  - Heart Defects, Congenital/blood/*mortality/physiopathology/therapy
MH  - Humans
MH  - Hypertension, Pulmonary/blood/*mortality/physiopathology/therapy
MH  - Machine Learning
MH  - Middle Aged
MH  - Patient Care Team/*standards
MH  - Prognosis
MH  - Retrospective Studies
MH  - Severity of Illness Index
MH  - Tertiary Care Centers
PMC - PMC6441851
OTO - NOTNLM
OT  - Adult congenital heart disease
OT  - Deep learning
OT  - Machine learning
OT  - Mortality
OT  - Prognostication
EDAT- 2019/01/29 06:00
MHDA- 2020/06/06 06:00
PMCR- 2020/04/01
CRDT- 2019/01/29 06:00
PHST- 2018/09/10 00:00 [received]
PHST- 2018/11/23 00:00 [revised]
PHST- 2018/12/31 00:00 [accepted]
PHST- 2019/01/29 06:00 [pubmed]
PHST- 2020/06/06 06:00 [medline]
PHST- 2019/01/29 06:00 [entrez]
PHST- 2020/04/01 00:00 [pmc-release]
AID - 5301309 [pii]
AID - ehy915 [pii]
AID - 10.1093/eurheartj/ehy915 [doi]
PST - ppublish
SO  - Eur Heart J. 2019 Apr 1;40(13):1069-1077. doi: 10.1093/eurheartj/ehy915.