TransAMR: An Interpretable Transformer Model for Accurate Prediction of Antimicrobial Resistance Using Antibiotic Administration Data
Antimicrobial Resistance (AMR) is a growing public and veterinary health concern, and the ability to accurately predict AMR from antibiotics administration data is crucial for effectively treating and managing infections. While genomics-based approaches can provide better results, sequencing, assemb...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10185002/ |
| _version_ | 1797771736029069312 |
|---|---|
| author | Mukunthan Tharmakulasingam Wenwu Wang Michael Kerby Roberto La Ragione Anil Fernando |
| author_facet | Mukunthan Tharmakulasingam Wenwu Wang Michael Kerby Roberto La Ragione Anil Fernando |
| author_sort | Mukunthan Tharmakulasingam |
| collection | DOAJ |
| description | Antimicrobial Resistance (AMR) is a growing public and veterinary health concern, and the ability to accurately predict AMR from antibiotics administration data is crucial for effectively treating and managing infections. While genomics-based approaches can provide better results, sequencing, assembling, and applying Machine Learning (ML) methods can take several hours. Therefore, alternative approaches are required. This study focused on using ML for antimicrobial stewardship by utilising data extracted from hospital electronic health records, which can be done in real-time, and developing an interpretable 1D-Transformer model for predicting AMR. A multi-baseline Integrated Gradient pipeline was also incorporated to interpret the model, and quantitative validation metrics were introduced to validate the model. The performance of the proposed 1D-Transformer model was evaluated using a dataset of urinary tract infection (UTI) patients with four antibiotics. The proposed 1D-Transformer model achieved 10% higher area under curve (AUC) in predicting AMR and outperformed traditional ML models. The Explainable Artificial Intelligence (XAI) pipeline also provided interpretable results, identifying the signatures contributing to the predictions. This could be used as a decision support tool for personalised treatment, introducing AMR-aware food and management of AMR, and it could also be used to identify signatures for targeted interventions. |
| first_indexed | 2024-03-12T21:40:56Z |
| format | Article |
| id | doaj.art-f2c441560efa44d095c52c64cdd655c2 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-12T21:40:56Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-f2c441560efa44d095c52c64cdd655c22023-07-26T23:00:35ZengIEEEIEEE Access2169-35362023-01-0111753377535010.1109/ACCESS.2023.329622110185002TransAMR: An Interpretable Transformer Model for Accurate Prediction of Antimicrobial Resistance Using Antibiotic Administration DataMukunthan Tharmakulasingam0https://orcid.org/0000-0002-2081-7865Wenwu Wang1https://orcid.org/0000-0002-8393-5703Michael Kerby2Roberto La Ragione3https://orcid.org/0000-0001-5861-613XAnil Fernando4Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, U.K.Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, U.K.Synergy Farm Health Ltd., Maiden Newton, Dorset, U.K.School of Veterinary Medicine, University of Surrey, Guildford, U.K.Department of Computer and Information Sciences, University of Strathclyde, Glasgow, U.K.Antimicrobial Resistance (AMR) is a growing public and veterinary health concern, and the ability to accurately predict AMR from antibiotics administration data is crucial for effectively treating and managing infections. While genomics-based approaches can provide better results, sequencing, assembling, and applying Machine Learning (ML) methods can take several hours. Therefore, alternative approaches are required. This study focused on using ML for antimicrobial stewardship by utilising data extracted from hospital electronic health records, which can be done in real-time, and developing an interpretable 1D-Transformer model for predicting AMR. A multi-baseline Integrated Gradient pipeline was also incorporated to interpret the model, and quantitative validation metrics were introduced to validate the model. The performance of the proposed 1D-Transformer model was evaluated using a dataset of urinary tract infection (UTI) patients with four antibiotics. The proposed 1D-Transformer model achieved 10% higher area under curve (AUC) in predicting AMR and outperformed traditional ML models. The Explainable Artificial Intelligence (XAI) pipeline also provided interpretable results, identifying the signatures contributing to the predictions. This could be used as a decision support tool for personalised treatment, introducing AMR-aware food and management of AMR, and it could also be used to identify signatures for targeted interventions.https://ieeexplore.ieee.org/document/10185002/Transformermulti-drug AMRantimicrobial stewardshipmissing labelsXAImulti-label prediction |
| spellingShingle | Mukunthan Tharmakulasingam Wenwu Wang Michael Kerby Roberto La Ragione Anil Fernando TransAMR: An Interpretable Transformer Model for Accurate Prediction of Antimicrobial Resistance Using Antibiotic Administration Data IEEE Access Transformer multi-drug AMR antimicrobial stewardship missing labels XAI multi-label prediction |
| title | TransAMR: An Interpretable Transformer Model for Accurate Prediction of Antimicrobial Resistance Using Antibiotic Administration Data |
| title_full | TransAMR: An Interpretable Transformer Model for Accurate Prediction of Antimicrobial Resistance Using Antibiotic Administration Data |
| title_fullStr | TransAMR: An Interpretable Transformer Model for Accurate Prediction of Antimicrobial Resistance Using Antibiotic Administration Data |
| title_full_unstemmed | TransAMR: An Interpretable Transformer Model for Accurate Prediction of Antimicrobial Resistance Using Antibiotic Administration Data |
| title_short | TransAMR: An Interpretable Transformer Model for Accurate Prediction of Antimicrobial Resistance Using Antibiotic Administration Data |
| title_sort | transamr an interpretable transformer model for accurate prediction of antimicrobial resistance using antibiotic administration data |
| topic | Transformer multi-drug AMR antimicrobial stewardship missing labels XAI multi-label prediction |
| url | https://ieeexplore.ieee.org/document/10185002/ |
| work_keys_str_mv | AT mukunthantharmakulasingam transamraninterpretabletransformermodelforaccuratepredictionofantimicrobialresistanceusingantibioticadministrationdata AT wenwuwang transamraninterpretabletransformermodelforaccuratepredictionofantimicrobialresistanceusingantibioticadministrationdata AT michaelkerby transamraninterpretabletransformermodelforaccuratepredictionofantimicrobialresistanceusingantibioticadministrationdata AT robertolaragione transamraninterpretabletransformermodelforaccuratepredictionofantimicrobialresistanceusingantibioticadministrationdata AT anilfernando transamraninterpretabletransformermodelforaccuratepredictionofantimicrobialresistanceusingantibioticadministrationdata |