1
|
Lee SW, Lee HC, Suh J, Lee KH, Lee H, Seo S, Kim TK, Lee SW, Kim YJ. Multi-center validation of machine learning model for preoperative prediction of postoperative mortality. NPJ Digit Med 2022; 5:91. [PMID: 35821515 PMCID: PMC9276734 DOI: 10.1038/s41746-022-00625-6] [Citation(s) in RCA: 11] [Impact Index Per Article: 5.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/07/2022] [Accepted: 06/02/2022] [Indexed: 11/09/2022] Open
Abstract
Accurate prediction of postoperative mortality is important for not only successful postoperative patient care but also for information-based shared decision-making with patients and efficient allocation of medical resources. This study aimed to create a machine-learning prediction model for 30-day mortality after a non-cardiac surgery that adapts to the manageable amount of clinical information as input features and is validated against multi-centered rather than single-centered data. Data were collected from 454,404 patients over 18 years of age who underwent non-cardiac surgeries from four independent institutions. We performed a retrospective analysis of the retrieved data. Only 12–18 clinical variables were used for model training. Logistic regression, random forest classifier, extreme gradient boosting (XGBoost), and deep neural network methods were applied to compare the prediction performances. To reduce overfitting and create a robust model, bootstrapping and grid search with tenfold cross-validation were performed. The XGBoost method in Seoul National University Hospital (SNUH) data delivers the best performance in terms of the area under receiver operating characteristic curve (AUROC) (0.9376) and the area under the precision-recall curve (0.1593). The predictive performance was the best when the SNUH model was validated with Ewha Womans University Medical Center data (AUROC, 0.941). Preoperative albumin, prothrombin time, and age were the most important features in the model for each hospital. It is possible to create a robust artificial intelligence prediction model applicable to multiple institutions through a light predictive model using only minimal preoperative information that can be automatically extracted from each hospital.
Collapse
Affiliation(s)
- Seung Wook Lee
- School of Medicine, Kyungpook National University, Daegu, Republic of Korea
| | - Hyung-Chul Lee
- Department of Anesthesiology and Pain Medicine, Seoul National University Hospital, Seoul National University College of Medicine, Seoul, Republic of Korea
| | - Jungyo Suh
- Department of Urology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea
| | - Kyung Hyun Lee
- Department of Digital Health, SAIHST, Sungkyunkwan University, Seoul, Republic of Korea
| | - Heonyi Lee
- Bioinformatics Collaboration Unit, Department of Biomedical Systems informatics, Yonsei University College of medicine, Seoul, Republic of Korea
| | - Suryang Seo
- Department of Nursing, SMG-SNU Boramae Medical Center, Seoul National University College of Medicine, Seoul, South Korea
| | - Tae Kyong Kim
- Department of Anesthesiology and Pain Medicine, SMG-SNU Boramae Medical Center, Seoul National University College of Medicine, Seoul, South Korea
| | - Sang-Wook Lee
- Department of Anesthesiology and Pain Medicine, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea.
| | - Yi-Jun Kim
- Institute of Convergence Medicine, Ewha Womans University Mokdong Hospital, Seoul, Republic of Korea.
| |
Collapse
|
2
|
Aparna M. A medical elaboration on von Willebrand disease with its dental management. JOURNAL OF ORAL AND MAXILLOFACIAL SURGERY MEDICINE AND PATHOLOGY 2016. [DOI: 10.1016/j.ajoms.2016.06.005] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 10/21/2022]
|
3
|
[Perioperative management of type 2B Von Willebrand's disease in a patient undergoing urgent abdominal surgery]. ACTA ACUST UNITED AC 2013; 61:226-7. [PMID: 23871098 DOI: 10.1016/j.redar.2013.05.013] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/23/2013] [Revised: 05/14/2013] [Accepted: 05/29/2013] [Indexed: 11/22/2022]
|
4
|
Alraies MC, Kumar A. Assessing and Managing Hematologic Disorders. Perioper Med (Lond) 2012. [DOI: 10.1002/9781118375372.ch13] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/11/2022] Open
|
5
|
Liumbruno GM, Bennardello F, Lattanzio A, Piccoli P, Rossetti G. Recommendations for the transfusion management of patients in the peri-operative period. I. The pre-operative period. BLOOD TRANSFUSION = TRASFUSIONE DEL SANGUE 2011; 9:19-40. [PMID: 21235852 PMCID: PMC3021395 DOI: 10.2450/2010.0074-10] [Citation(s) in RCA: 32] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [MESH Headings] [Subscribe] [Scholar Register] [Indexed: 01/15/2023]
Affiliation(s)
- Giancarlo Maria Liumbruno
- Units of Immunohaematology, Transfusion Medicine and Clinical Pathology, San Giovanni Calibita Fatebenefratelli Hospital, Rome, Italy
| | | | | | | | | |
Collapse
|
6
|
Thornton P, Douglas J. Coagulation in pregnancy. Best Pract Res Clin Obstet Gynaecol 2010; 24:339-52. [DOI: 10.1016/j.bpobgyn.2009.11.010] [Citation(s) in RCA: 61] [Impact Index Per Article: 4.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/30/2009] [Accepted: 11/25/2009] [Indexed: 10/19/2022]
|
7
|
Bullinger M, Gringeri A, von Mackensen S. Lebensqualität von jungen Patienten mit Hämophilie in Europa. Bundesgesundheitsblatt Gesundheitsforschung Gesundheitsschutz 2008; 51:637-45. [DOI: 10.1007/s00103-008-0539-0] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
|
8
|
Abstract
The present understanding of the coagulation process emphasizes the final common pathway and the proteolytic systems that result in the degradation of formed clots and the prevention of unwanted clot formations, as well as a variety of defense systems that include tissue repair, autoimmune processes, arteriosclerosis, tumor growth, the spread of metastases, and defense systems against micro-organisms. This article discusses diagnosis and management of some of the most common bleeding disorders. The goals are to provide a simple guide on how best to manage patients afflicted with congenital or acquired clotting abnormalities during the perioperative period, present a brief overview of the methods of testing and monitoring the coagulation defects, and discuss the appropriate pharmacologic or blood component therapies for each disease.
Collapse
Affiliation(s)
- Doreen E Soliman
- Division of Pediatric Anesthesiology, University of Pittsburgh Medical Center and Children's Hospital of Pittsburgh, 3705 Fifth Avenue, Pittsburgh, PA 15213, USA.
| | | |
Collapse
|