Ensemble learning for poor prognosis predictions: A case study on SARS-CoV-2.

Wu, Honghan, Zhang, Huayu, Karwath, Andreas, Ibrahim, Zina, Shi, Ting, Zhang, Xin, Wang, Kun, Sun, Jiaxing, Dhaliwal, Kevin, Bean, Daniel, Cardoso, Victor Roth, Li, Kezhi, Teo, James T, Banerjee, Amitava, Gao-Smith, Fang, Whitehouse, Tony, Veenith, Tonny, Gkoutos, Georgios V, Wu, Xiaodong, Dobson, Richard and Guthrie, Bruce (2021) Ensemble learning for poor prognosis predictions: A case study on SARS-CoV-2. Journal of the American Medical Informatics Association : JAMIA, 28 (4). pp. 791-800. ISSN 1527-974X. This article is available to all UHB staff and students via ASK Discovery tool http://tinyurl.com/z795c8c by using their UHB Athens login IDs

[img]
Preview
Text (PDF file format)
ocaa295.pdf - Published Version
Available under License Creative Commons Attribution 4.0.

Download (1MB) | Preview
Official URL: http://jamia.oxfordjournals.org/

Abstract

OBJECTIVE

Risk prediction models are widely used to inform evidence-based clinical decision making. However, few models developed from single cohorts can perform consistently well at population level where diverse prognoses exist (such as the SARS-CoV-2 [severe acute respiratory syndrome coronavirus 2] pandemic). This study aims at tackling this challenge by synergizing prediction models from the literature using ensemble learning.

MATERIALS AND METHODS

In this study, we selected and reimplemented 7 prediction models for COVID-19 (coronavirus disease 2019) that were derived from diverse cohorts and used different implementation techniques. A novel ensemble learning framework was proposed to synergize them for realizing personalized predictions for individual patients. Four diverse international cohorts (2 from the United Kingdom and 2 from China; N = 5394) were used to validate all 8 models on discrimination, calibration, and clinical usefulness.

RESULTS

Results showed that individual prediction models could perform well on some cohorts while poorly on others. Conversely, the ensemble model achieved the best performances consistently on all metrics quantifying discrimination, calibration, and clinical usefulness. Performance disparities were observed in cohorts from the 2 countries: all models achieved better performances on the China cohorts.

DISCUSSION

When individual models were learned from complementary cohorts, the synergized model had the potential to achieve better performances than any individual model. Results indicate that blood parameters and physiological measurements might have better predictive powers when collected early, which remains to be confirmed by further studies.

CONCLUSIONS

Combining a diverse set of individual prediction models, the ensemble method can synergize a robust and well-performing model by choosing the most competent ones for individual patients.

Item Type: Article
Additional Information: This article is available to all UHB staff and students via ASK Discovery tool http://tinyurl.com/z795c8c by using their UHB Athens login IDs
Subjects: QA Mathematics. Computing
QZ Pathology. Oncology
W Public health. Health statistics. Occupational health. Health education
WG Cardiovascular system. Cardiology
WL Nervous system. Neurology
Divisions: Planned IP Care > Respiratory Medicine
Related URLs:
Depositing User: Jamie Edgar
Date Deposited: 21 Apr 2021 10:03
Last Modified: 21 Apr 2021 10:03
URI: http://www.repository.uhblibrary.co.uk/id/eprint/4223

Actions (login required)

View Item View Item