Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 29 of the 29 references it cites were found in a registry or an index.

Machine learning generalizability across healthcare settings: insights from multi-site COVID-19 screening

Open access
Yang, Jenny, Soltan, Andrew A. S., Clifton, David A. · 2022 · npj Digital Medicine

Published version of a preprint

Abstract

As patient health information is highly regulated due to privacy concerns, most machine learning (ML)-based healthcare studies are unable to test on external patient cohorts, resulting in a gap between locally reported model performance and cross-site generalizability. Different approaches have been introduced for developing models across multiple clinical sites, however less attention has been given to adopting ready-made models in new settings. We introduce three methods to do this—(1) applying a ready-made model “as-is” (2); readjusting the decision threshold on the model’s output using site-specific data and (3); finetuning the model using site-specific data via transfer learning. Using a case study of COVID-19 diagnosis across four NHS Hospital Trusts, we show that all methods achieve clinically-effective performances (NPV > 0.959), with transfer learning achieving the best results (mean AUROCs between 0.870 and 0.925). Our models demonstrate that site-specific customization improves predictive performance when compared to other ready-made approaches.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41746-022-00614-9

Cites

29 of 29 references verified0 citation errors · 0 not checkable

Statistics

Figures

Fig. 1 t-Stochastic Neighbor Embedding (t-SNE) visualization of data. Figure shows t-SNE representation of datasets used in the study, including all positive COVID-19 cases across four NHS trusts (OUH, PUH, UHB, BH).
Fig. 1 t-Stochastic Neighbor Embedding (t-SNE) visualization of data. Figure shows t-SNE representation of datasets used in the study, including all positive COVID-19 cases across four NHS trusts (OUH, PUH, UHB, BH).CC BY · PubMed Central
Fig. 2 Mean classification performance of different model-implementation methods. Panels compare each implementation method (ready-made, threshold adjustment, transfer learning) and baseline models (site-specific and multi-site), across four NHS Trusts: a OUH, b PUH, c UHB, and d BH (numerical results are shown in Supplementary Tables S4, S5). All models were optimized during training and validation to achieve sensitivities of 0.85 (optimal thresholds can be found in Supplementary Table S6). Error bars show 95% confidence intervals (CIs) based on standard error. CIs for AUROC are calculated using Hanley and McNeil’s method.
Fig. 2 Mean classification performance of different model-implementation methods. Panels compare each implementation method (ready-made, threshold adjustment, transfer learning) and baseline models (site-specific and multi-site), across four NHS Trusts: a OUH, b PUH, c UHB, and d BH (numerical results are shown in Supplementary Tables S4, S5). All models were optimized during training and validation to achieve sensitivities of 0.85 (optimal thresholds can be found in Supplementary Table S6). Error bars show 95% confidence intervals (CIs) based on standard error. CIs for AUROC are calculated using Hanley and McNeil’s method.CC BY · PubMed Central
Fig. 3 Model architecture used for classification. Figure shows neural network architecture used for classification, including a visual of the decision boundary used to determine COVID-19 positive or negative status.
Fig. 3 Model architecture used for classification. Figure shows neural network architecture used for classification, including a visual of the decision boundary used to determine COVID-19 positive or negative status.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 28 references

Cited by

See all 181

Metadata

Authors
Yang, J., Soltan, A. A. S., & Clifton, D. A.
Affiliations
  • University of Oxford (GB)
  • John Radcliffe Hospital (GB)
Corresponding author
Yang, Jenny
Venue
npj Digital Medicine
Published
2022-06-07
Volume
5
Issue
1
Pages
69-69
ISSN
2398-6352 (ISSN-L)
OpenAlex
W4281920142
Cited by
181
References
28
Citations by year
2026: 55 · 2025: 48 · 2024: 46 · 2023: 27 · 2022: 4
FWCI
10.28
Type
journal article
Language
en
Open access
Licence
Locations
  • npj Digital Medicine (publishedVersion, cc-by)
  • medRxiv (acceptedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
  • Wellcome Trust (0009350)
  • University Hospitals Birmingham NHS Foundation Trust
  • National Institute for Health and Care Research (ACF-2020-13-015)
  • University of Oxford
  • European Commission (HORIZON2020, 955681)
  • Oxford University Hospitals NHS Foundation Trust
  • Medical Research Council (MC_PC_19049)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
  • Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › COVID-19 diagnosis using AI
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
Keywords
model generalization, COVID-19 diagnosis, clinical decision support, model finetuning, external validation, NHS hospital trusts, predictive performance

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Machine learning generalizability across healthcare settings: insights from multi-site COVID-19 screening. https://app.cochat.ai/papers/10.1038/s41746-022-00614-9
The paper
Yang, J., Soltan, A. A. S., & Clifton, D. A. (2022). Machine learning generalizability across healthcare settings: insights from multi-site COVID-19 screening. npj Digital Medicine. https://doi.org/10.1038/s41746-022-00614-9

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.