Development and validation of a digital biomarker predicting acute kidney injury following cardiac surgery on an hourly basisCentral MessagePerspective
Objectives: To develop and validate a digital biomarker for predicting the onset of acute kidney injury (AKI) on an hourly basis up to 24 hours in advance in the intensive care unit after cardiac surgery. Methods: The study analyzed data from 6056 adult patients undergoing coronary artery bypass gra...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-12-01
|
| Series: | JTCVS Open |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666273623002954 |
| _version_ | 1797385041519575040 |
|---|---|
| author | Linda Lapp, PhD Marc Roper, PhD Kimberley Kavanagh, PhD Stefan Schraag, MD |
| author_facet | Linda Lapp, PhD Marc Roper, PhD Kimberley Kavanagh, PhD Stefan Schraag, MD |
| author_sort | Linda Lapp, PhD |
| collection | DOAJ |
| description | Objectives: To develop and validate a digital biomarker for predicting the onset of acute kidney injury (AKI) on an hourly basis up to 24 hours in advance in the intensive care unit after cardiac surgery. Methods: The study analyzed data from 6056 adult patients undergoing coronary artery bypass graft and/or valve surgery between April 1, 2012, and December 31, 2018 (development phase, training, and testing) and 3572 patients between January 1, 2019, and June 30, 2022 (validation phase). The study used 2 dynamic predictive modeling approaches, namely logistic regression and bootstrap aggregated regression trees machine (BARTm), to predict AKI. The mean area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and positive and negative predictive values across all lead times before the occurrence of AKI were reported. The clinical practicality was assessed using calibration. Results: Of all included patients, 8.45% and 16.66% had AKI in the development and validation phases, respectively. When applied to testing data, AKI was predicted with the mean AUC of 0.850 and 0.802 by BARTm and logistic regression, respectively. When applied to validation data, BARTm and LR resulted in a mean AUC of 0.844 and 0.786, respectively. Conclusions: This study demonstrated the successful prediction of AKI on an hourly basis up to 24 hours in advance. The digital biomarkers developed and validated in this study have the potential to assist clinicians in optimizing treatment and implementing preventive strategies for patients at risk of developing AKI after cardiac surgery in the intensive care unit. |
| first_indexed | 2024-03-08T21:48:24Z |
| format | Article |
| id | doaj.art-bb1bd27ff21347ce8002b7051ac9fbf8 |
| institution | Directory Open Access Journal |
| issn | 2666-2736 |
| language | English |
| last_indexed | 2024-03-08T21:48:24Z |
| publishDate | 2023-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | JTCVS Open |
| spelling | doaj.art-bb1bd27ff21347ce8002b7051ac9fbf82023-12-20T07:38:17ZengElsevierJTCVS Open2666-27362023-12-0116540581Development and validation of a digital biomarker predicting acute kidney injury following cardiac surgery on an hourly basisCentral MessagePerspectiveLinda Lapp, PhD0Marc Roper, PhD1Kimberley Kavanagh, PhD2Stefan Schraag, MD3Department of Computer and Information Sciences, Faculty of Science, University of Strathclyde, Glasgow, Scotland; Address for reprints: Linda Lapp, PhD, Department of Computer and Information Sciences, Faculty of Science, University of Strathclyde, 26 Richmond St, Glasgow G1 1XH, United Kingdom.Department of Computer and Information Sciences, Faculty of Science, University of Strathclyde, Glasgow, ScotlandDepartment of Mathematics and Statistics, Faculty of Science, University of Strathclyde, Glasgow, ScotlandDepartment of Anaesthesia and Perioperative Medicine, Golden Jubilee National Hospital, Clydebank, United KingdomObjectives: To develop and validate a digital biomarker for predicting the onset of acute kidney injury (AKI) on an hourly basis up to 24 hours in advance in the intensive care unit after cardiac surgery. Methods: The study analyzed data from 6056 adult patients undergoing coronary artery bypass graft and/or valve surgery between April 1, 2012, and December 31, 2018 (development phase, training, and testing) and 3572 patients between January 1, 2019, and June 30, 2022 (validation phase). The study used 2 dynamic predictive modeling approaches, namely logistic regression and bootstrap aggregated regression trees machine (BARTm), to predict AKI. The mean area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and positive and negative predictive values across all lead times before the occurrence of AKI were reported. The clinical practicality was assessed using calibration. Results: Of all included patients, 8.45% and 16.66% had AKI in the development and validation phases, respectively. When applied to testing data, AKI was predicted with the mean AUC of 0.850 and 0.802 by BARTm and logistic regression, respectively. When applied to validation data, BARTm and LR resulted in a mean AUC of 0.844 and 0.786, respectively. Conclusions: This study demonstrated the successful prediction of AKI on an hourly basis up to 24 hours in advance. The digital biomarkers developed and validated in this study have the potential to assist clinicians in optimizing treatment and implementing preventive strategies for patients at risk of developing AKI after cardiac surgery in the intensive care unit.http://www.sciencedirect.com/science/article/pii/S2666273623002954cardiac surgeryacute kidney injuryintensive care unitprediction modelbiomarkersrisk prediction |
| spellingShingle | Linda Lapp, PhD Marc Roper, PhD Kimberley Kavanagh, PhD Stefan Schraag, MD Development and validation of a digital biomarker predicting acute kidney injury following cardiac surgery on an hourly basisCentral MessagePerspective JTCVS Open cardiac surgery acute kidney injury intensive care unit prediction model biomarkers risk prediction |
| title | Development and validation of a digital biomarker predicting acute kidney injury following cardiac surgery on an hourly basisCentral MessagePerspective |
| title_full | Development and validation of a digital biomarker predicting acute kidney injury following cardiac surgery on an hourly basisCentral MessagePerspective |
| title_fullStr | Development and validation of a digital biomarker predicting acute kidney injury following cardiac surgery on an hourly basisCentral MessagePerspective |
| title_full_unstemmed | Development and validation of a digital biomarker predicting acute kidney injury following cardiac surgery on an hourly basisCentral MessagePerspective |
| title_short | Development and validation of a digital biomarker predicting acute kidney injury following cardiac surgery on an hourly basisCentral MessagePerspective |
| title_sort | development and validation of a digital biomarker predicting acute kidney injury following cardiac surgery on an hourly basiscentral messageperspective |
| topic | cardiac surgery acute kidney injury intensive care unit prediction model biomarkers risk prediction |
| url | http://www.sciencedirect.com/science/article/pii/S2666273623002954 |
| work_keys_str_mv | AT lindalappphd developmentandvalidationofadigitalbiomarkerpredictingacutekidneyinjuryfollowingcardiacsurgeryonanhourlybasiscentralmessageperspective AT marcroperphd developmentandvalidationofadigitalbiomarkerpredictingacutekidneyinjuryfollowingcardiacsurgeryonanhourlybasiscentralmessageperspective AT kimberleykavanaghphd developmentandvalidationofadigitalbiomarkerpredictingacutekidneyinjuryfollowingcardiacsurgeryonanhourlybasiscentralmessageperspective AT stefanschraagmd developmentandvalidationofadigitalbiomarkerpredictingacutekidneyinjuryfollowingcardiacsurgeryonanhourlybasiscentralmessageperspective |