AI Science Tracker
EN

Division of Engineering in Medicine, Department of Medicine, Brigham and Women's Hospital, Harvard Medical School, Boston, Massachusetts 02139, United States

1 discovery from 2020

Discoveries

Mobile Health (mHealth) Viral Diagnostics Enabled with Adaptive Adversarial Learning

Source check: Source checked. Not independent scientific confirmation.

Finding: Adaptive adversarial image classifiers plus StyleGAN augmentation supported phone-based detection across five virus targets in 179 patient samples; the SARS-CoV-2 test panel had 62 nasal swabs and reported 100% sensitivity and specificity, with confidence intervals and a single study setting limiting interpretation.

Technology: Conditional adversarial neural networks adapt image classifiers across virus domains; StyleGAN produces synthetic images for the unlabeled target library.

Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.

AI contribution
Conditional adversarial neural networks adapt image classifiers across virus domains; StyleGAN produces synthetic images for the unlabeled target library.
Test and result
Results report 179 patient samples across five targets; SARS-CoV-2 panel n=62 reports 100% sensitivity/specificity and corresponding confidence intervals.
Limitation / still unknown
Independent test set uses patient samples and compares SARS-CoV-2 panel with qRT-PCR; evidence remains one study panel, not external deployment.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://pmc.ncbi.nlm.nih.gov/articles/PMC8299938/ · https://doi.org/10.1021/acsnano.0c06807 · https://pubmed.ncbi.nlm.nih.gov/33226787/

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: linked separately.

Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 2/5 · Validation 2/5 · Novelty 2/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Open the interactive profile for the timeline, or browse all organizations and model families.