1
|
Lu J, Hutchens R, Hung J, Bennamoun M, McQuillan B, Briffa T, Sohel F, Murray K, Stewart J, Chow B, Sanfilippo F, Dwivedi G. Performance of multilabel machine learning models and risk stratification schemas for predicting stroke and bleeding risk in patients with non-valvular atrial fibrillation. Comput Biol Med 2022; 150:106126. [PMID: 36206696 DOI: 10.1016/j.compbiomed.2022.106126] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/21/2022] [Revised: 09/10/2022] [Accepted: 09/18/2022] [Indexed: 11/26/2022]
Abstract
BACKGROUND Appropriate anticoagulant therapy for patients with atrial fibrillation (AF) requires assessment of stroke and bleeding risks. However, risk stratification schemas such as CHA2DS2-VASc and HAS-BLED have modest predictive capacity for patients with AF. Multilabel machine learning (ML) techniques may improve predictive performance and support decision-making for anticoagulant therapy. We compared the performance of multilabel ML models with the currently used risk scores for predicting outcomes in AF patients. METHODS This was a retrospective cohort study of 9670 patients, mean age 76.9 years, 46% women, who were hospitalized with non-valvular AF, and had 1-year follow-up. The outcomes were ischemic stroke (167), major bleeding (430) admissions, all-cause death (1912) and event-free survival (7387). Discrimination and calibration of ML models were compared with clinical risk scores by area under the curve (AUC). Risk stratification was assessed using net reclassification index (NRI). RESULTS Multilabel gradient boosting classifier chain provided the best AUCs for stroke (0.685 95% CI 0.676, 0.694), major bleeding (0.709 95% CI 0.703, 0.716) and death (0.765 95% CI 0.763, 0.768) compared to multi-layer neural networks and classifier chain using support vector machine. It provided modest performance improvement for stroke compared to AUC of CHA2DS2-VASc (0.652, NRI = 3.2%, p-value = 0.1), but significantly improved major bleeding prediction compared to AUC of HAS-BLED (0.522, NRI = 22.8%, p-value < 0.05). It also achieved greater discriminant power for death compared with AUC of CHA2DS2-VASc (0.606, p-value < 0.05). ML models identified additional risk features such as hemoglobin level, renal function. CONCLUSIONS Multilabel ML models can outperform clinical risk stratification scores for predicting the risk of major bleeding and death in non-valvular AF patients.
Collapse
Affiliation(s)
- Juan Lu
- Department of Computer Science and Software Engineering, The University of Western Australia, Perth, Australia; Medical School, The University of Western Australia, Perth, Australia; Harry Perkins Institute of Medical Research, Perth, Australia
| | - Rebecca Hutchens
- Medical School, The University of Western Australia, Perth, Australia; Sir Charles Gairdner Hospital, Perth, WA, Australia
| | - Joseph Hung
- Medical School, The University of Western Australia, Perth, Australia
| | - Mohammed Bennamoun
- Department of Computer Science and Software Engineering, The University of Western Australia, Perth, Australia
| | - Brendan McQuillan
- Medical School, The University of Western Australia, Perth, Australia; Sir Charles Gairdner Hospital, Perth, WA, Australia
| | - Tom Briffa
- School of Population and Global Health, The University of Western Australia, Perth, Australia
| | - Ferdous Sohel
- Discipline of Information Technology, Murdoch University, Perth, Australia
| | - Kevin Murray
- School of Population and Global Health, The University of Western Australia, Perth, Australia
| | - Jonathon Stewart
- Medical School, The University of Western Australia, Perth, Australia; Harry Perkins Institute of Medical Research, Perth, Australia
| | - Benjamin Chow
- Department of Medicine, Division of Cardiology, University of Ottawa Heart Institute, Ottawa, Canada
| | - Frank Sanfilippo
- School of Population and Global Health, The University of Western Australia, Perth, Australia
| | - Girish Dwivedi
- Medical School, The University of Western Australia, Perth, Australia; Harry Perkins Institute of Medical Research, Perth, Australia; Cardiology Department, Fiona Stanley Hospital, Perth, Australia.
| |
Collapse
|
2
|
Hutchens R, Hung J, Briffa T, McQuillan B. Antithrombotic Therapy in Atrial Fibrillation Management in Western Australia: Temporal Trends and Evidence-Treatment Gaps. Heart Lung Circ 2021; 30:955-962. [DOI: 10.1016/j.hlc.2020.10.026] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/12/2019] [Revised: 10/13/2020] [Accepted: 10/31/2020] [Indexed: 12/31/2022]
|
3
|
Lu J, Dwivedi G, Sanfilippo F, Bennamoun M, Hung J, Briffa T, Sohel F, Hutchens R, Stewart J, Chow B, McQuillan B. 230 Machine Learning Models for Predicting Ischemic Stroke and Major Bleeding Risk in Patients with Atrial Fibrillation. Heart Lung Circ 2020. [DOI: 10.1016/j.hlc.2020.09.237] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
|
4
|
Hutchens R, McQuillan B, Briffa T, Hung J. Underutilisation of Oral Anticoagulation (OAC) Therapy for Stroke Prevention in Non-Valvular Atrial Fibrillation (AF) Management Among Women. Heart Lung Circ 2017. [DOI: 10.1016/j.hlc.2017.06.603] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/26/2022]
|
5
|
Hutchens R, McQuillan B, Briffa T, Hung J. Translating the Evidence in Atrial Fibrillation Management. Can We Improve Appropriate Use of Anticoagulation Through the Use of an Electronic Clinical Decision Support Tool? Heart Lung Circ 2017. [DOI: 10.1016/j.hlc.2017.06.602] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/19/2022]
|