An Explainable AI Approach for the Rapid Diagnosis of Covid-19 Using Ensemble Learning Algorithms
Bibliographic Data
| ID | 22073131 |
|---|---|
| Authors | Houwu Gong (0000-0001-5011-1225, Hunan University), Miye Wang (0000-0002-4137-0310, Sichuan University), Hanxue Zhang (Hunan University), Md Fazla Elahe (0000-0002-0839-5946, Hunan University), Min Jin (0009-0009-5438-1236, Hunan University, corresponding author) |
| Year | 2022 |
| Volume | 10 |
| Pages | 874455-874455 |
| Publication date | 2022-06-21 |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | Frontiers in Public Health (JOURNAL) |
| Journal identifiers | ISSN: 2296-2565 • E-ISSN: 2296-2565 |
| Publisher | Frontiers Media SA (PUBLISHER • CH) |
| DOI | 10.3389/fpubh.2022.874455 |
| PMID | 35801239 |
| OpenAlex | W4283203964 |
| Language | EN |
| Citations received | 2 |
| References cited | 44 |
Background: Artificial intelligence-based disease prediction models have a greater potential to screen COVID-19 patients than conventional methods. However, their application has been restricted because of their underlying black-box nature. Objective: To addressed this issue, an explainable artificial intelligence (XAI) approach was developed to screen patients for COVID-19. Methods: A retrospective study consisting of 1,737 participants (759 COVID-19 patients and 978 controls) admitted to San Raphael Hospital (OSR) from February to May 2020 was used to construct a diagnosis model. Finally, 32 key blood test indices from 1,374 participants were used for screening patients for COVID-19. Four ensemble learning algorithms were used: random forest (RF), adaptive boosting (AdaBoost), gradient boosting decision tree (GBDT), and extreme gradient boosting (XGBoost). Feature importance from the perspective of the clinical domain and visualized interpretations were illustrated by using local interpretable model-agnostic explanations (LIME) plots. Results: The GBDT model [area under the curve (AUC): 86.4%; 95% confidence interval (CI) 0.821-0.907] outperformed the RF model (AUC: 85.7%; 95% CI 0.813-0.902), AdaBoost model (AUC: 85.4%; 95% CI 0.810-0.899), and XGBoost model (AUC: 84.9%; 95% CI 0.803-0.894) in distinguishing patients with COVID-19 from those without. The cumulative feature importance of lactate dehydrogenase, white blood cells, and eosinophil counts was 0.145, 0.130, and 0.128, respectively. Conclusions: Ensemble machining learning (ML) approaches, mainly GBDT and LIME plots, are efficient for screening patients with COVID-19 and might serve as a potential tool in the auxiliary diagnosis of COVID-19. Patients with higher WBC count, higher LDH level, or higher EOT count, were more likely to have COVID-19
AdaBoost · Algorithm · Confidence interval · Decision tree · Disease · Ensemble forecasting · Ensemble learning · Gradient boosting · Machine learning · Random forest · Receiver operating characteristic · Support vector machine · Computer Science · COVID-19 Clinical Research Studies · COVID-19 diagnosis using AI · Explainable Artificial Intelligence (XAI · Medicine · Artificial Intelligence · Internal Medicine
Reinforcement Learning
Association of Public Health Interventions With the Epidemiology of the Covid-19 Outbreak in Wuhan, China
Nowcasting and forecasting the potential domestic and international spread of the 2019-nCoV outbreak originating in Wuhan, China
Prediction models for diagnosis and prognosis of covid-19
XAI—Explainable artificial intelligence
Bagging predictors
| Citations per year | 1 |
|---|---|
| Citation span | 2024 - 2025 (2) |
| Highly cited | No |