Deep learning model for personalized prediction of positive MRSA culture using time-series electronic health records
Abstract Methicillin-resistant Staphylococcus aureus (MRSA) poses significant morbidity and mortality in hospitals. Rapid, accurate risk stratification of MRSA is crucial for optimizing antibiotic therapy. Our study introduced a deep learning model, PyTorch_EHR, which leverages electronic health rec...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-03-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-024-46211-0 |
| _version_ | 1827321399442669568 |
|---|---|
| author | Masayuki Nigo Laila Rasmy Bingyu Mao Bijun Sai Kannadath Ziqian Xie Degui Zhi |
| author_facet | Masayuki Nigo Laila Rasmy Bingyu Mao Bijun Sai Kannadath Ziqian Xie Degui Zhi |
| author_sort | Masayuki Nigo |
| collection | DOAJ |
| description | Abstract Methicillin-resistant Staphylococcus aureus (MRSA) poses significant morbidity and mortality in hospitals. Rapid, accurate risk stratification of MRSA is crucial for optimizing antibiotic therapy. Our study introduced a deep learning model, PyTorch_EHR, which leverages electronic health record (EHR) time-series data, including wide-variety patient specific data, to predict MRSA culture positivity within two weeks. 8,164 MRSA and 22,393 non-MRSA patient events from Memorial Hermann Hospital System, Houston, Texas are used for model development. PyTorch_EHR outperforms logistic regression (LR) and light gradient boost machine (LGBM) models in accuracy (AUROCPyTorch_EHR = 0.911, AUROCLR = 0.857, AUROCLGBM = 0.892). External validation with 393,713 patient events from the Medical Information Mart for Intensive Care (MIMIC)-IV dataset in Boston confirms its superior accuracy (AUROCPyTorch_EHR = 0.859, AUROCLR = 0.816, AUROCLGBM = 0.838). Our model effectively stratifies patients into high-, medium-, and low-risk categories, potentially optimizing antimicrobial therapy and reducing unnecessary MRSA-specific antimicrobials. This highlights the advantage of deep learning models in predicting MRSA positive cultures, surpassing traditional machine learning models and supporting clinicians’ judgments. |
| first_indexed | 2024-04-25T01:05:28Z |
| format | Article |
| id | doaj.art-f83fd91d4c1f4013ae7708c6baf3e5a2 |
| institution | Directory Open Access Journal |
| issn | 2041-1723 |
| language | English |
| last_indexed | 2024-04-25T01:05:28Z |
| publishDate | 2024-03-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj.art-f83fd91d4c1f4013ae7708c6baf3e5a22024-03-10T12:16:17ZengNature PortfolioNature Communications2041-17232024-03-0115111110.1038/s41467-024-46211-0Deep learning model for personalized prediction of positive MRSA culture using time-series electronic health recordsMasayuki Nigo0Laila Rasmy1Bingyu Mao2Bijun Sai Kannadath3Ziqian Xie4Degui Zhi5McGovern Medical School, University of Texas Health Science Center at HoustonMcWilliams School of Biomedical Informatics, University of Texas Health Science Center at HoustonMcWilliams School of Biomedical Informatics, University of Texas Health Science Center at HoustonDepartment of Internal Medicine, University of Arizona College of MedicineMcWilliams School of Biomedical Informatics, University of Texas Health Science Center at HoustonMcWilliams School of Biomedical Informatics, University of Texas Health Science Center at HoustonAbstract Methicillin-resistant Staphylococcus aureus (MRSA) poses significant morbidity and mortality in hospitals. Rapid, accurate risk stratification of MRSA is crucial for optimizing antibiotic therapy. Our study introduced a deep learning model, PyTorch_EHR, which leverages electronic health record (EHR) time-series data, including wide-variety patient specific data, to predict MRSA culture positivity within two weeks. 8,164 MRSA and 22,393 non-MRSA patient events from Memorial Hermann Hospital System, Houston, Texas are used for model development. PyTorch_EHR outperforms logistic regression (LR) and light gradient boost machine (LGBM) models in accuracy (AUROCPyTorch_EHR = 0.911, AUROCLR = 0.857, AUROCLGBM = 0.892). External validation with 393,713 patient events from the Medical Information Mart for Intensive Care (MIMIC)-IV dataset in Boston confirms its superior accuracy (AUROCPyTorch_EHR = 0.859, AUROCLR = 0.816, AUROCLGBM = 0.838). Our model effectively stratifies patients into high-, medium-, and low-risk categories, potentially optimizing antimicrobial therapy and reducing unnecessary MRSA-specific antimicrobials. This highlights the advantage of deep learning models in predicting MRSA positive cultures, surpassing traditional machine learning models and supporting clinicians’ judgments.https://doi.org/10.1038/s41467-024-46211-0 |
| spellingShingle | Masayuki Nigo Laila Rasmy Bingyu Mao Bijun Sai Kannadath Ziqian Xie Degui Zhi Deep learning model for personalized prediction of positive MRSA culture using time-series electronic health records Nature Communications |
| title | Deep learning model for personalized prediction of positive MRSA culture using time-series electronic health records |
| title_full | Deep learning model for personalized prediction of positive MRSA culture using time-series electronic health records |
| title_fullStr | Deep learning model for personalized prediction of positive MRSA culture using time-series electronic health records |
| title_full_unstemmed | Deep learning model for personalized prediction of positive MRSA culture using time-series electronic health records |
| title_short | Deep learning model for personalized prediction of positive MRSA culture using time-series electronic health records |
| title_sort | deep learning model for personalized prediction of positive mrsa culture using time series electronic health records |
| url | https://doi.org/10.1038/s41467-024-46211-0 |
| work_keys_str_mv | AT masayukinigo deeplearningmodelforpersonalizedpredictionofpositivemrsacultureusingtimeserieselectronichealthrecords AT lailarasmy deeplearningmodelforpersonalizedpredictionofpositivemrsacultureusingtimeserieselectronichealthrecords AT bingyumao deeplearningmodelforpersonalizedpredictionofpositivemrsacultureusingtimeserieselectronichealthrecords AT bijunsaikannadath deeplearningmodelforpersonalizedpredictionofpositivemrsacultureusingtimeserieselectronichealthrecords AT ziqianxie deeplearningmodelforpersonalizedpredictionofpositivemrsacultureusingtimeserieselectronichealthrecords AT deguizhi deeplearningmodelforpersonalizedpredictionofpositivemrsacultureusingtimeserieselectronichealthrecords |