PMID- 33221198
OWN - NLM
STAT- MEDLINE
DCOM- 20210930
LR  - 20210930
IS  - 1552-6259 (Electronic)
IS  - 0003-4975 (Linking)
VI  - 112
IP  - 3
DP  - 2021 Sep
TI  - Machine Learning Approaches to Analyzing Adverse Events Following Durable LVAD 
      Implantation.
PG  - 770-777
LID - S0003-4975(20)31938-X [pii]
LID - 10.1016/j.athoracsur.2020.09.040 [doi]
AB  - BACKGROUND: This study employed machine learning approaches to analyze sequences 
      of adverse events (AEs) after left ventricular assist device (LVAD) implantation. 
      METHODS: Data on patients implanted with the HeartWare HVAD durable LVAD were 
      extracted from the ENDURANCE and ENDURANCE Supplemental clinical trials, with 
      follow-up through 5 years. Major AEs included device malfunction, major bleeding, 
      major infection, neurological dysfunction, renal dysfunction, respiratory 
      dysfunction, and right heart failure (RHF). Time interval and transition 
      probability analyses were performed. We created a Sankey diagram to visualize 
      transitions between AEs. Hierarchical clustering was applied to dissimilarity 
      matrices based on the longest common subsequence to identify clusters of patients 
      with similar AE profiles. RESULTS: A total of 568 patients underwent HVAD 
      implantation with 3590 AEs. Bleeding and RHF comprised the highest proportion of 
      early AEs after surgery whereas infection and bleeding accounted for most AEs 
      occurring after 3 months. The highest transition probabilities were observed with 
      infection to infection (0.34), bleeding to bleeding (0.31), RHF to bleeding 
      (0.31), RHF to infection (0.28), and bleeding to infection (0.26). Five distinct 
      clusters of patients were generated, each with different patterns of time 
      intervals between AEs, transition rates between AEs, and clinical outcomes. 
      CONCLUSIONS: Machine learning approaches allow for improved visualization and 
      understanding of AE burden after LVAD implantation. Distinct patterns and 
      relationships provide insights that may be important for quality improvement 
      efforts.
CI  - Copyright (c) 2021 The Society of Thoracic Surgeons. Published by Elsevier Inc. All 
      rights reserved.
FAU - Kilic, Arman
AU  - Kilic A
AD  - Division of Cardiac Surgery, University of Pittsburgh Medical Center, Pittsburgh, 
      Pennsylvania. Electronic address: kilica2@upmc.edu.
FAU - Macickova, Jana
AU  - Macickova J
AD  - Heinz College of Information Systems and Public Policy, Carnegie Mellon 
      University, Pittsburgh, Pennsylvania.
FAU - Duan, Lingli
AU  - Duan L
AD  - Heinz College of Information Systems and Public Policy, Carnegie Mellon 
      University, Pittsburgh, Pennsylvania.
FAU - Movahedi, Faezeh
AU  - Movahedi F
AD  - School of Electrical and Computer Engineering, University of Pittsburgh, 
      Pittsburgh, Pennsylvania.
FAU - Seese, Laura
AU  - Seese L
AD  - Division of Cardiac Surgery, University of Pittsburgh Medical Center, Pittsburgh, 
      Pennsylvania.
FAU - Zhang, Yiye
AU  - Zhang Y
AD  - Division of Health Informatics, Department of Population Health Sciences, Weill 
      Cornell Medicine, New York, New York.
FAU - Jacoski, Mary V
AU  - Jacoski MV
AD  - Department of Clinical and Medical Affairs, Medtronic, Framingham, Massachusetts.
FAU - Padman, Rema
AU  - Padman R
AD  - Heinz College of Information Systems and Public Policy, Carnegie Mellon 
      University, Pittsburgh, Pennsylvania.
LA  - eng
PT  - Journal Article
DEP - 20201120
PL  - Netherlands
TA  - Ann Thorac Surg
JT  - The Annals of thoracic surgery
JID - 15030100R
SB  - IM
MH  - Heart-Assist Devices/*adverse effects
MH  - Humans
MH  - *Machine Learning
MH  - Postoperative Complications/*etiology
EDAT- 2020/11/23 06:00
MHDA- 2021/10/01 06:00
CRDT- 2020/11/22 20:32
PHST- 2020/07/13 00:00 [received]
PHST- 2020/09/05 00:00 [revised]
PHST- 2020/09/21 00:00 [accepted]
PHST- 2020/11/23 06:00 [pubmed]
PHST- 2021/10/01 06:00 [medline]
PHST- 2020/11/22 20:32 [entrez]
AID - S0003-4975(20)31938-X [pii]
AID - 10.1016/j.athoracsur.2020.09.040 [doi]
PST - ppublish
SO  - Ann Thorac Surg. 2021 Sep;112(3):770-777. doi: 10.1016/j.athoracsur.2020.09.040. 
      Epub 2020 Nov 20.