Predicting the Need for Therapeutic Intervention and Mortality in Acute Pancreatitis: A Two-Center International Study Using Machine Learning



Shi, Na, Lan, Lan, Luo, Jiawei, Zhu, Ping, Ward, Thomas RW, Szatmary, Peter ORCID: 0000-0002-7454-9851, Sutton, Robert ORCID: 0000-0001-6600-562X, Huang, Wei, Windsor, John A, Zhou, Xiaobo
et al (show 1 more authors) (2022) Predicting the Need for Therapeutic Intervention and Mortality in Acute Pancreatitis: A Two-Center International Study Using Machine Learning. JOURNAL OF PERSONALIZED MEDICINE, 12 (4). 616-.

Access the full-text of this item by clicking on the Open Access link.
[img] PDF
Predicting the Need for Therapeutic Intervention and Mortality in Acute Pancreatitis A Two-Center International Study Using .pdf - Published version

Download (8MB) | Preview

Abstract

<h4>Background</h4>Current approaches to predicting intervention needs and mortality have reached 65-85% accuracy, which falls below clinical decision-making requirements in patients with acute pancreatitis (AP). We aimed to accurately predict therapeutic intervention needs and mortality on admission, in AP patients, using machine learning (ML).<h4>Methods</h4>Data were obtained from three databases of patients admitted with AP: one retrospective (Chengdu) and two prospective (Liverpool and Chengdu) databases. Intervention and mortality differences, as well as potential predictors, were investigated. Univariate analysis was conducted, followed by a random forest ML algorithm used in multivariate analysis, to identify predictors. The ML performance matrix was applied to evaluate the model's performance.<h4>Results</h4>Three datasets of 2846 patients included 25 potential clinical predictors in the univariate analysis. The top ten identified predictors were obtained by ML models, for predicting interventions and mortality, from the training dataset. The prediction of interventions includes death in non-intervention patients, validated with high accuracy (96%/98%), the area under the receiver-operating-characteristic curve (0.90/0.98), and positive likelihood ratios (22.3/69.8), respectively. The post-test probabilities in the test set were 55.4% and 71.6%, respectively, which were considerably superior to existing prognostic scores. The ML model, for predicting mortality in intervention patients, performed better or equally with prognostic scores.<h4>Conclusions</h4>ML, using admission clinical predictors, can accurately predict therapeutic interventions and mortality in patients with AP.

Item Type: Article
Uncontrolled Keywords: acute pancreatitis, machine learning, predictor, interventions, mortality
Divisions: Faculty of Health and Life Sciences
Faculty of Health and Life Sciences > Clinical Directorate
Faculty of Health and Life Sciences > Institute of Systems, Molecular and Integrative Biology
Depositing User: Symplectic Admin
Date Deposited: 18 Oct 2022 14:59
Last Modified: 18 Jan 2023 19:49
DOI: 10.3390/jpm12040616
Open Access URL: https://www.mdpi.com/2075-4426/12/4/616
Related URLs:
URI: https://livrepository.liverpool.ac.uk/id/eprint/3165617