A Machine Learning Model for the Accurate Prediction of 1-Year Survival in TAVI Patients: A Retrospective Observational Cohort Study
Background: predicting the 1-year survival of patients undergoing transcatheter aortic valve implantation (TAVI) is indispensable for managing safe early discharge strategies and resource optimization. Methods: Routinely acquired data (134 variables) were used from 629 patients, who underwent transf...
Main Authors: | , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-08-01
|
Series: | Journal of Clinical Medicine |
Subjects: | |
Online Access: | https://www.mdpi.com/2077-0383/12/17/5481 |
_version_ | 1797582343510163456 |
---|---|
author | Francesco Pollari Wolfgang Hitzl Magnus Rottmann Ferdinand Vogt Miroslaw Ledwon Christian Langhammer Dennis Eckner Jürgen Jessl Thomas Bertsch Matthias Pauschinger Theodor Fischlein |
author_facet | Francesco Pollari Wolfgang Hitzl Magnus Rottmann Ferdinand Vogt Miroslaw Ledwon Christian Langhammer Dennis Eckner Jürgen Jessl Thomas Bertsch Matthias Pauschinger Theodor Fischlein |
author_sort | Francesco Pollari |
collection | DOAJ |
description | Background: predicting the 1-year survival of patients undergoing transcatheter aortic valve implantation (TAVI) is indispensable for managing safe early discharge strategies and resource optimization. Methods: Routinely acquired data (134 variables) were used from 629 patients, who underwent transfemoral TAVI from 2012 up to 2018. Support vector machines, neuronal networks, random forests, nearest neighbour and Bayes models were used with new, previously unseen patients to predict 1-year mortality in TAVI patients. A genetic variable selection algorithm identified a set of predictor variables with high predictive power. Results: Univariate analyses revealed 19 variables (clinical, laboratory, echocardiographic, computed tomographic and ECG) that significantly influence 1-year survival. Before applying the reject option, the model performances in terms of negative predictive value (NPV) and positive predictive value (PPV) were similar between all models. After applying the reject option, the random forest model identified a subcohort showing a negative predictive value of 96% (positive predictive value = 92%, accuracy = 96%). Conclusions: Our model can predict the 1-year survival with very high negative and sufficiently high positive predictive value, with very high accuracy. The “reject option” allows a high performance and harmonic integration of machine learning in the clinical decision process. |
first_indexed | 2024-03-10T23:20:46Z |
format | Article |
id | doaj.art-a6ce2fcff1d0459eb1e41553d4fa3ac7 |
institution | Directory Open Access Journal |
issn | 2077-0383 |
language | English |
last_indexed | 2024-03-10T23:20:46Z |
publishDate | 2023-08-01 |
publisher | MDPI AG |
record_format | Article |
series | Journal of Clinical Medicine |
spelling | doaj.art-a6ce2fcff1d0459eb1e41553d4fa3ac72023-11-19T08:21:14ZengMDPI AGJournal of Clinical Medicine2077-03832023-08-011217548110.3390/jcm12175481A Machine Learning Model for the Accurate Prediction of 1-Year Survival in TAVI Patients: A Retrospective Observational Cohort StudyFrancesco Pollari0Wolfgang Hitzl1Magnus Rottmann2Ferdinand Vogt3Miroslaw Ledwon4Christian Langhammer5Dennis Eckner6Jürgen Jessl7Thomas Bertsch8Matthias Pauschinger9Theodor Fischlein10Cardiac Surgery, Cardiovascular Center, Paracelsus Medical University-Klinikum Nuremberg, 90471 Nuremberg, GermanyResearch and Innovation Management (RIM), Team Biostatistics and Publication of Clinical Trial Studies, Paracelsus Medical University, 5020 Salzburg, AustriaCardiac Surgery, Cardiovascular Center, Paracelsus Medical University-Klinikum Nuremberg, 90471 Nuremberg, GermanyCardiac Surgery, Cardiovascular Center, Paracelsus Medical University-Klinikum Nuremberg, 90471 Nuremberg, GermanyCardiac Surgery, Cardiovascular Center, Paracelsus Medical University-Klinikum Nuremberg, 90471 Nuremberg, GermanyInstitute of Clinical Chemistry, Laboratory Medicine and Transfusion Medicine, Paracelsus Medical University, 90471 Nuremberg, GermanyCardiology, Cardiovascular Center, Paracelsus Medical University-Klinikum Nuremberg, 90419 Nuremberg, GermanyCardiology, Cardiovascular Center, Paracelsus Medical University-Klinikum Nuremberg, 90419 Nuremberg, GermanyInstitute of Clinical Chemistry, Laboratory Medicine and Transfusion Medicine, Paracelsus Medical University, 90471 Nuremberg, GermanyCardiology, Cardiovascular Center, Paracelsus Medical University-Klinikum Nuremberg, 90419 Nuremberg, GermanyCardiac Surgery, Cardiovascular Center, Paracelsus Medical University-Klinikum Nuremberg, 90471 Nuremberg, GermanyBackground: predicting the 1-year survival of patients undergoing transcatheter aortic valve implantation (TAVI) is indispensable for managing safe early discharge strategies and resource optimization. Methods: Routinely acquired data (134 variables) were used from 629 patients, who underwent transfemoral TAVI from 2012 up to 2018. Support vector machines, neuronal networks, random forests, nearest neighbour and Bayes models were used with new, previously unseen patients to predict 1-year mortality in TAVI patients. A genetic variable selection algorithm identified a set of predictor variables with high predictive power. Results: Univariate analyses revealed 19 variables (clinical, laboratory, echocardiographic, computed tomographic and ECG) that significantly influence 1-year survival. Before applying the reject option, the model performances in terms of negative predictive value (NPV) and positive predictive value (PPV) were similar between all models. After applying the reject option, the random forest model identified a subcohort showing a negative predictive value of 96% (positive predictive value = 92%, accuracy = 96%). Conclusions: Our model can predict the 1-year survival with very high negative and sufficiently high positive predictive value, with very high accuracy. The “reject option” allows a high performance and harmonic integration of machine learning in the clinical decision process.https://www.mdpi.com/2077-0383/12/17/5481personalizedTAVImachine learningpredictionoutcomesurvival |
spellingShingle | Francesco Pollari Wolfgang Hitzl Magnus Rottmann Ferdinand Vogt Miroslaw Ledwon Christian Langhammer Dennis Eckner Jürgen Jessl Thomas Bertsch Matthias Pauschinger Theodor Fischlein A Machine Learning Model for the Accurate Prediction of 1-Year Survival in TAVI Patients: A Retrospective Observational Cohort Study Journal of Clinical Medicine personalized TAVI machine learning prediction outcome survival |
title | A Machine Learning Model for the Accurate Prediction of 1-Year Survival in TAVI Patients: A Retrospective Observational Cohort Study |
title_full | A Machine Learning Model for the Accurate Prediction of 1-Year Survival in TAVI Patients: A Retrospective Observational Cohort Study |
title_fullStr | A Machine Learning Model for the Accurate Prediction of 1-Year Survival in TAVI Patients: A Retrospective Observational Cohort Study |
title_full_unstemmed | A Machine Learning Model for the Accurate Prediction of 1-Year Survival in TAVI Patients: A Retrospective Observational Cohort Study |
title_short | A Machine Learning Model for the Accurate Prediction of 1-Year Survival in TAVI Patients: A Retrospective Observational Cohort Study |
title_sort | machine learning model for the accurate prediction of 1 year survival in tavi patients a retrospective observational cohort study |
topic | personalized TAVI machine learning prediction outcome survival |
url | https://www.mdpi.com/2077-0383/12/17/5481 |
work_keys_str_mv | AT francescopollari amachinelearningmodelfortheaccuratepredictionof1yearsurvivalintavipatientsaretrospectiveobservationalcohortstudy AT wolfganghitzl amachinelearningmodelfortheaccuratepredictionof1yearsurvivalintavipatientsaretrospectiveobservationalcohortstudy AT magnusrottmann amachinelearningmodelfortheaccuratepredictionof1yearsurvivalintavipatientsaretrospectiveobservationalcohortstudy AT ferdinandvogt amachinelearningmodelfortheaccuratepredictionof1yearsurvivalintavipatientsaretrospectiveobservationalcohortstudy AT miroslawledwon amachinelearningmodelfortheaccuratepredictionof1yearsurvivalintavipatientsaretrospectiveobservationalcohortstudy AT christianlanghammer amachinelearningmodelfortheaccuratepredictionof1yearsurvivalintavipatientsaretrospectiveobservationalcohortstudy AT denniseckner amachinelearningmodelfortheaccuratepredictionof1yearsurvivalintavipatientsaretrospectiveobservationalcohortstudy AT jurgenjessl amachinelearningmodelfortheaccuratepredictionof1yearsurvivalintavipatientsaretrospectiveobservationalcohortstudy AT thomasbertsch amachinelearningmodelfortheaccuratepredictionof1yearsurvivalintavipatientsaretrospectiveobservationalcohortstudy AT matthiaspauschinger amachinelearningmodelfortheaccuratepredictionof1yearsurvivalintavipatientsaretrospectiveobservationalcohortstudy AT theodorfischlein amachinelearningmodelfortheaccuratepredictionof1yearsurvivalintavipatientsaretrospectiveobservationalcohortstudy AT francescopollari machinelearningmodelfortheaccuratepredictionof1yearsurvivalintavipatientsaretrospectiveobservationalcohortstudy AT wolfganghitzl machinelearningmodelfortheaccuratepredictionof1yearsurvivalintavipatientsaretrospectiveobservationalcohortstudy AT magnusrottmann machinelearningmodelfortheaccuratepredictionof1yearsurvivalintavipatientsaretrospectiveobservationalcohortstudy AT ferdinandvogt machinelearningmodelfortheaccuratepredictionof1yearsurvivalintavipatientsaretrospectiveobservationalcohortstudy AT miroslawledwon machinelearningmodelfortheaccuratepredictionof1yearsurvivalintavipatientsaretrospectiveobservationalcohortstudy AT christianlanghammer machinelearningmodelfortheaccuratepredictionof1yearsurvivalintavipatientsaretrospectiveobservationalcohortstudy AT denniseckner machinelearningmodelfortheaccuratepredictionof1yearsurvivalintavipatientsaretrospectiveobservationalcohortstudy AT jurgenjessl machinelearningmodelfortheaccuratepredictionof1yearsurvivalintavipatientsaretrospectiveobservationalcohortstudy AT thomasbertsch machinelearningmodelfortheaccuratepredictionof1yearsurvivalintavipatientsaretrospectiveobservationalcohortstudy AT matthiaspauschinger machinelearningmodelfortheaccuratepredictionof1yearsurvivalintavipatientsaretrospectiveobservationalcohortstudy AT theodorfischlein machinelearningmodelfortheaccuratepredictionof1yearsurvivalintavipatientsaretrospectiveobservationalcohortstudy |