Developing deep LSTMs with later temporal attention for predicting COVID-19 severity, clinical outcome, and antibody level by screening serological indicators over time
OBJECTIVE: The clinical course of COVID-19, as well as the immunological reaction, is notable for its extreme variability. Identifying the main associated factors might help understand the disease progression and physiological status of COVID-19 patients. The dynamic changes of the antibody against Spike protein are crucial for understanding the immune response. This work explores a temporal attention (TA) mechanism of deep learning to predict COVID-19 disease severity, clinical outcomes, and Spike antibody levels by screening serological indicators over time.
METHODS: We use feature selection techniques to filter feature subsets that are highly correlated with the target. The specific deep Long Short-Term Memory (LSTM) models are employed to capture the dynamic changes of disease severity, clinical outcome, and Spike antibody level. We also propose deep LSTMs with a TA mechanism to emphasize the later blood test records because later records often attract more attention from doctors.
RESULTS: Risk factors highly correlated with COVID-19 are revealed. LSTM achieves the highest classification accuracy for disease severity prediction. Temporal Attention Long Short-Term Memory (TA-LSTM) achieves the best performance for clinical outcome prediction. For Spike antibody level prediction, LSTM achieves the best permanence.
CONCLUSION: The experimental results demonstrate the effectiveness of the proposed models. The proposed models can provide a computer-aided medical diagnostics system by simply using time series of serological indicators.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2024 |
|---|---|
| Erschienen: |
2024 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:PP |
|---|---|
| Enthalten in: |
IEEE journal of biomedical and health informatics - PP(2024) vom: 02. Apr. |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Cai, Jiaxin [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
|---|
| Anmerkungen: |
Date Revised 02.04.2024 published: Print-Electronic Citation Status Publisher |
|---|
| doi: |
10.1109/JBHI.2024.3384333 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM37053851X |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM37053851X | ||
| 003 | DE-627 | ||
| 005 | 20240404000429.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 240404s2024 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1109/JBHI.2024.3384333 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1363.xml |
| 035 | |a (DE-627)NLM37053851X | ||
| 035 | |a (NLM)38564357 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Cai, Jiaxin |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Developing deep LSTMs with later temporal attention for predicting COVID-19 severity, clinical outcome, and antibody level by screening serological indicators over time |
| 264 | 1 | |c 2024 | |
| 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 02.04.2024 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status Publisher | ||
| 520 | |a OBJECTIVE: The clinical course of COVID-19, as well as the immunological reaction, is notable for its extreme variability. Identifying the main associated factors might help understand the disease progression and physiological status of COVID-19 patients. The dynamic changes of the antibody against Spike protein are crucial for understanding the immune response. This work explores a temporal attention (TA) mechanism of deep learning to predict COVID-19 disease severity, clinical outcomes, and Spike antibody levels by screening serological indicators over time | ||
| 520 | |a METHODS: We use feature selection techniques to filter feature subsets that are highly correlated with the target. The specific deep Long Short-Term Memory (LSTM) models are employed to capture the dynamic changes of disease severity, clinical outcome, and Spike antibody level. We also propose deep LSTMs with a TA mechanism to emphasize the later blood test records because later records often attract more attention from doctors | ||
| 520 | |a RESULTS: Risk factors highly correlated with COVID-19 are revealed. LSTM achieves the highest classification accuracy for disease severity prediction. Temporal Attention Long Short-Term Memory (TA-LSTM) achieves the best performance for clinical outcome prediction. For Spike antibody level prediction, LSTM achieves the best permanence | ||
| 520 | |a CONCLUSION: The experimental results demonstrate the effectiveness of the proposed models. The proposed models can provide a computer-aided medical diagnostics system by simply using time series of serological indicators | ||
| 650 | 4 | |a Journal Article | |
| 700 | 1 | |a Li, Yang |e verfasserin |4 aut | |
| 700 | 1 | |a Liu, Baichen |e verfasserin |4 aut | |
| 700 | 1 | |a Wu, Zhixi |e verfasserin |4 aut | |
| 700 | 1 | |a Zhu, Shengjun |e verfasserin |4 aut | |
| 700 | 1 | |a Chen, Qiliang |e verfasserin |4 aut | |
| 700 | 1 | |a Lei, Qing |e verfasserin |4 aut | |
| 700 | 1 | |a Hou, Hongyan |e verfasserin |4 aut | |
| 700 | 1 | |a Guo, Zhibin |e verfasserin |4 aut | |
| 700 | 1 | |a Jiang, Hewei |e verfasserin |4 aut | |
| 700 | 1 | |a Guo, Shujuan |e verfasserin |4 aut | |
| 700 | 1 | |a Wang, Feng |e verfasserin |4 aut | |
| 700 | 1 | |a Huang, Shengjing |e verfasserin |4 aut | |
| 700 | 1 | |a Zhu, Shunzhi |e verfasserin |4 aut | |
| 700 | 1 | |a Fan, Xionglin |e verfasserin |4 aut | |
| 700 | 1 | |a Tao, Shengce |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t IEEE journal of biomedical and health informatics |d 2013 |g PP(2024) vom: 02. Apr. |w (DE-627)NLM217081614 |x 2168-2208 |7 nnns |
| 773 | 1 | 8 | |g volume:PP |g year:2024 |g day:02 |g month:04 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1109/JBHI.2024.3384333 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d PP |j 2024 |b 02 |c 04 | ||