A scalable federated learning solution for secondary care using low-cost microcomputing: privacy-preserving development and evaluation of a COVID-19 screening test in UK hospitals
<p><b>Background</b></p> Multicentre training could reduce biases in medical artificial intelligence (AI); however, ethical, legal, and technical considerations can constrain the ability of hospitals to share data. Federated learning enables institutions to participate in alg...
| Auteurs principaux: | , , , , , , , , , , |
|---|---|
| Format: | Journal article |
| Langue: | English |
| Publié: |
Elsevier
2024
|
| _version_ | 1826312002906095616 |
|---|---|
| author | Soltan, AS Thakur, A Yang, J Chauhan, A D'Cruz, LG Dickson, P Soltan, MA Thickett, DR Eyre, DW Zhu, T Clifton, DA |
| author_facet | Soltan, AS Thakur, A Yang, J Chauhan, A D'Cruz, LG Dickson, P Soltan, MA Thickett, DR Eyre, DW Zhu, T Clifton, DA |
| author_sort | Soltan, AS |
| collection | OXFORD |
| description | <p><b>Background</b></p>
Multicentre training could reduce biases in medical artificial intelligence (AI); however, ethical, legal, and technical considerations can constrain the ability of hospitals to share data. Federated learning enables institutions to participate in algorithm development while retaining custody of their data but uptake in hospitals has been limited, possibly as deployment requires specialist software and technical expertise at each site. We previously developed an artificial intelligence-driven screening test for COVID-19 in emergency departments, known as CURIAL-Lab, which uses vital signs and blood tests that are routinely available within 1 h of a patient's arrival. Here we aimed to federate our COVID-19 screening test by developing an easy-to-use embedded system—which we introduce as full-stack federated learning—to train and evaluate machine learning models across four UK hospital groups without centralising patient data.
<p><b>Methods</b></p>
We supplied a Raspberry Pi 4 Model B preloaded with our federated learning software pipeline to four National Health Service (NHS) hospital groups in the UK: Oxford University Hospitals NHS Foundation Trust (OUH; through the locally linked research University, University of Oxford), University Hospitals Birmingham NHS Foundation Trust (UHB), Bedfordshire Hospitals NHS Foundation Trust (BH), and Portsmouth Hospitals University NHS Trust (PUH). OUH, PUH, and UHB participated in federated training, training a deep neural network and logistic regressor over 150 rounds to form and calibrate a global model to predict COVID-19 status, using clinical data from patients admitted before the pandemic (COVID-19-negative) and testing positive for COVID-19 during the first wave of the pandemic. We conducted a federated evaluation of the global model for admissions during the second wave of the pandemic at OUH, PUH, and externally at BH. For OUH and PUH, we additionally performed local fine-tuning of the global model using the sites’ individual training data, forming a site-tuned model, and evaluated the resultant model for admissions during the second wave of the pandemic. This study included data collected between Dec 1, 2018, and March 1, 2021; the exact date ranges used varied by site. The primary outcome was overall model performance, measured as the area under the receiver operating characteristic curve (AUROC). Removable micro secure digital (microSD) storage was destroyed on study completion.
<p><b>Findings</b></p>
Clinical data from 130 941 patients (1772 COVID-19-positive), routinely collected across three hospital groups (OUH, PUH, and UHB), were included in federated training. The evaluation step included data from 32 986 patients (3549 COVID-19-positive) attending OUH, PUH, or BH during the second wave of the pandemic. Federated training of a global deep neural network classifier improved upon performance of models trained locally in terms of AUROC by a mean of 27·6% (SD 2·2): AUROC increased from 0·574 (95% CI 0·560–0·589) at OUH and 0·622 (0·608–0·637) at PUH using the locally trained models to 0·872 (0·862–0·882) at OUH and 0·876 (0·865–0·886) at PUH using the federated global model. Performance improvement was smaller for a logistic regression model, with a mean increase in AUROC of 13·9% (0·5%). During federated external evaluation at BH, AUROC for the global deep neural network model was 0·917 (0·893–0·942), with 89·7% sensitivity (83·6–93·6) and 76·6% specificity (73·9–79·1). Site-specific tuning of the global model did not significantly improve performance (change in AUROC <0·01).
<p><b>Interpretation</b></p>
We developed an embedded system for federated learning, using microcomputing to optimise for ease of deployment. We deployed full-stack federated learning across four UK hospital groups to develop a COVID-19 screening test without centralising patient data. Federation improved model performance, and the resultant global models were generalisable. Full-stack federated learning could enable hospitals to contribute to AI development at low cost and without specialist technical expertise at each site.
<p><b>Funding</b></p>
The Wellcome Trust, University of Oxford Medical and Life Sciences Translational Fund.
|
| first_indexed | 2024-03-07T08:19:38Z |
| format | Journal article |
| id | oxford-uuid:12e2da0c-e509-4d20-bc0d-07e5b5563eae |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-07T08:19:38Z |
| publishDate | 2024 |
| publisher | Elsevier |
| record_format | dspace |
| spelling | oxford-uuid:12e2da0c-e509-4d20-bc0d-07e5b5563eae2024-01-26T08:46:56ZA scalable federated learning solution for secondary care using low-cost microcomputing: privacy-preserving development and evaluation of a COVID-19 screening test in UK hospitalsJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:12e2da0c-e509-4d20-bc0d-07e5b5563eaeEnglishSymplectic ElementsElsevier2024Soltan, ASThakur, AYang, JChauhan, AD'Cruz, LGDickson, PSoltan, MAThickett, DREyre, DWZhu, TClifton, DA<p><b>Background</b></p> Multicentre training could reduce biases in medical artificial intelligence (AI); however, ethical, legal, and technical considerations can constrain the ability of hospitals to share data. Federated learning enables institutions to participate in algorithm development while retaining custody of their data but uptake in hospitals has been limited, possibly as deployment requires specialist software and technical expertise at each site. We previously developed an artificial intelligence-driven screening test for COVID-19 in emergency departments, known as CURIAL-Lab, which uses vital signs and blood tests that are routinely available within 1 h of a patient's arrival. Here we aimed to federate our COVID-19 screening test by developing an easy-to-use embedded system—which we introduce as full-stack federated learning—to train and evaluate machine learning models across four UK hospital groups without centralising patient data. <p><b>Methods</b></p> We supplied a Raspberry Pi 4 Model B preloaded with our federated learning software pipeline to four National Health Service (NHS) hospital groups in the UK: Oxford University Hospitals NHS Foundation Trust (OUH; through the locally linked research University, University of Oxford), University Hospitals Birmingham NHS Foundation Trust (UHB), Bedfordshire Hospitals NHS Foundation Trust (BH), and Portsmouth Hospitals University NHS Trust (PUH). OUH, PUH, and UHB participated in federated training, training a deep neural network and logistic regressor over 150 rounds to form and calibrate a global model to predict COVID-19 status, using clinical data from patients admitted before the pandemic (COVID-19-negative) and testing positive for COVID-19 during the first wave of the pandemic. We conducted a federated evaluation of the global model for admissions during the second wave of the pandemic at OUH, PUH, and externally at BH. For OUH and PUH, we additionally performed local fine-tuning of the global model using the sites’ individual training data, forming a site-tuned model, and evaluated the resultant model for admissions during the second wave of the pandemic. This study included data collected between Dec 1, 2018, and March 1, 2021; the exact date ranges used varied by site. The primary outcome was overall model performance, measured as the area under the receiver operating characteristic curve (AUROC). Removable micro secure digital (microSD) storage was destroyed on study completion. <p><b>Findings</b></p> Clinical data from 130 941 patients (1772 COVID-19-positive), routinely collected across three hospital groups (OUH, PUH, and UHB), were included in federated training. The evaluation step included data from 32 986 patients (3549 COVID-19-positive) attending OUH, PUH, or BH during the second wave of the pandemic. Federated training of a global deep neural network classifier improved upon performance of models trained locally in terms of AUROC by a mean of 27·6% (SD 2·2): AUROC increased from 0·574 (95% CI 0·560–0·589) at OUH and 0·622 (0·608–0·637) at PUH using the locally trained models to 0·872 (0·862–0·882) at OUH and 0·876 (0·865–0·886) at PUH using the federated global model. Performance improvement was smaller for a logistic regression model, with a mean increase in AUROC of 13·9% (0·5%). During federated external evaluation at BH, AUROC for the global deep neural network model was 0·917 (0·893–0·942), with 89·7% sensitivity (83·6–93·6) and 76·6% specificity (73·9–79·1). Site-specific tuning of the global model did not significantly improve performance (change in AUROC <0·01). <p><b>Interpretation</b></p> We developed an embedded system for federated learning, using microcomputing to optimise for ease of deployment. We deployed full-stack federated learning across four UK hospital groups to develop a COVID-19 screening test without centralising patient data. Federation improved model performance, and the resultant global models were generalisable. Full-stack federated learning could enable hospitals to contribute to AI development at low cost and without specialist technical expertise at each site. <p><b>Funding</b></p> The Wellcome Trust, University of Oxford Medical and Life Sciences Translational Fund. |
| spellingShingle | Soltan, AS Thakur, A Yang, J Chauhan, A D'Cruz, LG Dickson, P Soltan, MA Thickett, DR Eyre, DW Zhu, T Clifton, DA A scalable federated learning solution for secondary care using low-cost microcomputing: privacy-preserving development and evaluation of a COVID-19 screening test in UK hospitals |
| title | A scalable federated learning solution for secondary care using low-cost microcomputing: privacy-preserving development and evaluation of a COVID-19 screening test in UK hospitals |
| title_full | A scalable federated learning solution for secondary care using low-cost microcomputing: privacy-preserving development and evaluation of a COVID-19 screening test in UK hospitals |
| title_fullStr | A scalable federated learning solution for secondary care using low-cost microcomputing: privacy-preserving development and evaluation of a COVID-19 screening test in UK hospitals |
| title_full_unstemmed | A scalable federated learning solution for secondary care using low-cost microcomputing: privacy-preserving development and evaluation of a COVID-19 screening test in UK hospitals |
| title_short | A scalable federated learning solution for secondary care using low-cost microcomputing: privacy-preserving development and evaluation of a COVID-19 screening test in UK hospitals |
| title_sort | scalable federated learning solution for secondary care using low cost microcomputing privacy preserving development and evaluation of a covid 19 screening test in uk hospitals |
| work_keys_str_mv | AT soltanas ascalablefederatedlearningsolutionforsecondarycareusinglowcostmicrocomputingprivacypreservingdevelopmentandevaluationofacovid19screeningtestinukhospitals AT thakura ascalablefederatedlearningsolutionforsecondarycareusinglowcostmicrocomputingprivacypreservingdevelopmentandevaluationofacovid19screeningtestinukhospitals AT yangj ascalablefederatedlearningsolutionforsecondarycareusinglowcostmicrocomputingprivacypreservingdevelopmentandevaluationofacovid19screeningtestinukhospitals AT chauhana ascalablefederatedlearningsolutionforsecondarycareusinglowcostmicrocomputingprivacypreservingdevelopmentandevaluationofacovid19screeningtestinukhospitals AT dcruzlg ascalablefederatedlearningsolutionforsecondarycareusinglowcostmicrocomputingprivacypreservingdevelopmentandevaluationofacovid19screeningtestinukhospitals AT dicksonp ascalablefederatedlearningsolutionforsecondarycareusinglowcostmicrocomputingprivacypreservingdevelopmentandevaluationofacovid19screeningtestinukhospitals AT soltanma ascalablefederatedlearningsolutionforsecondarycareusinglowcostmicrocomputingprivacypreservingdevelopmentandevaluationofacovid19screeningtestinukhospitals AT thickettdr ascalablefederatedlearningsolutionforsecondarycareusinglowcostmicrocomputingprivacypreservingdevelopmentandevaluationofacovid19screeningtestinukhospitals AT eyredw ascalablefederatedlearningsolutionforsecondarycareusinglowcostmicrocomputingprivacypreservingdevelopmentandevaluationofacovid19screeningtestinukhospitals AT zhut ascalablefederatedlearningsolutionforsecondarycareusinglowcostmicrocomputingprivacypreservingdevelopmentandevaluationofacovid19screeningtestinukhospitals AT cliftonda ascalablefederatedlearningsolutionforsecondarycareusinglowcostmicrocomputingprivacypreservingdevelopmentandevaluationofacovid19screeningtestinukhospitals AT soltanas scalablefederatedlearningsolutionforsecondarycareusinglowcostmicrocomputingprivacypreservingdevelopmentandevaluationofacovid19screeningtestinukhospitals AT thakura scalablefederatedlearningsolutionforsecondarycareusinglowcostmicrocomputingprivacypreservingdevelopmentandevaluationofacovid19screeningtestinukhospitals AT yangj scalablefederatedlearningsolutionforsecondarycareusinglowcostmicrocomputingprivacypreservingdevelopmentandevaluationofacovid19screeningtestinukhospitals AT chauhana scalablefederatedlearningsolutionforsecondarycareusinglowcostmicrocomputingprivacypreservingdevelopmentandevaluationofacovid19screeningtestinukhospitals AT dcruzlg scalablefederatedlearningsolutionforsecondarycareusinglowcostmicrocomputingprivacypreservingdevelopmentandevaluationofacovid19screeningtestinukhospitals AT dicksonp scalablefederatedlearningsolutionforsecondarycareusinglowcostmicrocomputingprivacypreservingdevelopmentandevaluationofacovid19screeningtestinukhospitals AT soltanma scalablefederatedlearningsolutionforsecondarycareusinglowcostmicrocomputingprivacypreservingdevelopmentandevaluationofacovid19screeningtestinukhospitals AT thickettdr scalablefederatedlearningsolutionforsecondarycareusinglowcostmicrocomputingprivacypreservingdevelopmentandevaluationofacovid19screeningtestinukhospitals AT eyredw scalablefederatedlearningsolutionforsecondarycareusinglowcostmicrocomputingprivacypreservingdevelopmentandevaluationofacovid19screeningtestinukhospitals AT zhut scalablefederatedlearningsolutionforsecondarycareusinglowcostmicrocomputingprivacypreservingdevelopmentandevaluationofacovid19screeningtestinukhospitals AT cliftonda scalablefederatedlearningsolutionforsecondarycareusinglowcostmicrocomputingprivacypreservingdevelopmentandevaluationofacovid19screeningtestinukhospitals |