Homogeneous ensemble models for predicting infection levels and mortality of COVID-19 patients : Evidence from China
© The Author(s) 2022..
Background: Persistence of long-term COVID-19 pandemic is putting high pressure on healthcare services worldwide for several years. This article aims to establish models to predict infection levels and mortality of COVID-19 patients in China.
Methods: Machine learning models and deep learning models have been built based on the clinical features of COVID-19 patients. The best models are selected by area under the receiver operating characteristic curve (AUC) scores to construct two homogeneous ensemble models for predicting infection levels and mortality, respectively. The first-hand clinical data of 760 patients are collected from Zhongnan Hospital of Wuhan University between 3 January and 8 March 2020. We preprocess data with cleaning, imputation, and normalization.
Results: Our models obtain AUC = 0.7059 and Recall (Weighted avg) = 0.7248 in predicting infection level, while AUC=0.8436 and Recall (Weighted avg) = 0.8486 in predicting mortality ratio. This study also identifies two sets of essential clinical features. One is C-reactive protein (CRP) or high sensitivity C-reactive protein (hs-CRP) and the other is chest tightness, age, and pleural effusion.
Conclusions: Two homogeneous ensemble models are proposed to predict infection levels and mortality of COVID-19 patients in China. New findings of clinical features for benefiting the machine learning models are reported. The evaluation of an actual dataset collected from January 3 to March 8, 2020 demonstrates the effectiveness of the models by comparing them with state-of-the-art models in prediction.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2022 |
|---|---|
| Erschienen: |
2022 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:8 |
|---|---|
| Enthalten in: |
Digital health - 8(2022) vom: 28. Jan., Seite 20552076221133692 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Wang, Jiafeng [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
COVID-19 |
|---|
| Anmerkungen: |
Date Revised 08.11.2022 published: Electronic-eCollection Citation Status PubMed-not-MEDLINE |
|---|
| doi: |
10.1177/20552076221133692 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM348537867 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM348537867 | ||
| 003 | DE-627 | ||
| 005 | 20231226040503.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231226s2022 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1177/20552076221133692 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1161.xml |
| 035 | |a (DE-627)NLM348537867 | ||
| 035 | |a (NLM)36339905 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Wang, Jiafeng |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Homogeneous ensemble models for predicting infection levels and mortality of COVID-19 patients |b Evidence from China |
| 264 | 1 | |c 2022 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Revised 08.11.2022 | ||
| 500 | |a published: Electronic-eCollection | ||
| 500 | |a Citation Status PubMed-not-MEDLINE | ||
| 520 | |a © The Author(s) 2022. | ||
| 520 | |a Background: Persistence of long-term COVID-19 pandemic is putting high pressure on healthcare services worldwide for several years. This article aims to establish models to predict infection levels and mortality of COVID-19 patients in China | ||
| 520 | |a Methods: Machine learning models and deep learning models have been built based on the clinical features of COVID-19 patients. The best models are selected by area under the receiver operating characteristic curve (AUC) scores to construct two homogeneous ensemble models for predicting infection levels and mortality, respectively. The first-hand clinical data of 760 patients are collected from Zhongnan Hospital of Wuhan University between 3 January and 8 March 2020. We preprocess data with cleaning, imputation, and normalization | ||
| 520 | |a Results: Our models obtain AUC = 0.7059 and Recall (Weighted avg) = 0.7248 in predicting infection level, while AUC=0.8436 and Recall (Weighted avg) = 0.8486 in predicting mortality ratio. This study also identifies two sets of essential clinical features. One is C-reactive protein (CRP) or high sensitivity C-reactive protein (hs-CRP) and the other is chest tightness, age, and pleural effusion | ||
| 520 | |a Conclusions: Two homogeneous ensemble models are proposed to predict infection levels and mortality of COVID-19 patients in China. New findings of clinical features for benefiting the machine learning models are reported. The evaluation of an actual dataset collected from January 3 to March 8, 2020 demonstrates the effectiveness of the models by comparing them with state-of-the-art models in prediction | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a COVID-19 | |
| 650 | 4 | |a Ensemble model | |
| 650 | 4 | |a electronic health records | |
| 650 | 4 | |a machine learning | |
| 650 | 4 | |a prediction models | |
| 700 | 1 | |a Zhou, Xianlong |e verfasserin |4 aut | |
| 700 | 1 | |a Hou, Zhitian |e verfasserin |4 aut | |
| 700 | 1 | |a Xu, Xiaoya |e verfasserin |4 aut | |
| 700 | 1 | |a Zhao, Yueyue |e verfasserin |4 aut | |
| 700 | 1 | |a Chen, Shanshan |e verfasserin |4 aut | |
| 700 | 1 | |a Zhang, Jun |e verfasserin |4 aut | |
| 700 | 1 | |a Shao, Lina |e verfasserin |4 aut | |
| 700 | 1 | |a Yan, Rong |e verfasserin |4 aut | |
| 700 | 1 | |a Wang, Mingshan |e verfasserin |4 aut | |
| 700 | 1 | |a Ge, Minghua |e verfasserin |4 aut | |
| 700 | 1 | |a Hao, Tianyong |e verfasserin |4 aut | |
| 700 | 1 | |a Tu, Yuexing |e verfasserin |4 aut | |
| 700 | 1 | |a Huang, Haijun |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Digital health |d 2015 |g 8(2022) vom: 28. Jan., Seite 20552076221133692 |w (DE-627)NLM266914608 |x 2055-2076 |7 nnns |
| 773 | 1 | 8 | |g volume:8 |g year:2022 |g day:28 |g month:01 |g pages:20552076221133692 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1177/20552076221133692 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 8 |j 2022 |b 28 |c 01 |h 20552076221133692 | ||