Back
Harnessing Mechanistic Simulators for Rapid Diagnostic Test Capture and Deep Learning Classification
Rogers, E.; Turbe, V.; Gareta, D.; Herbst, C.; Herbst, K.; Shahmanesh, M.; McKendry, R. A.
2025-02-25
public and global health
10.1101/2025.02.25.25322677
medRxiv
Show abstract
Rapid diagnostic tests (RDTs) support affordable disease diagnosis. Machine learning (ML) can improve RDT interpretation but often relies on large, proprietary, and costly real-world image libraries. We present SynSight - a ML-enabled RDT segmentation and classification pipeline trained on synthetic data. Validated on HIV (98% sensitivity, 99% specificity) and COVID-19 RDTs (up to 99% accuracy), SynSight enables rapid ML training without real-world images, keeping pace with new RDT development.
Matching journals
●Non-profit
◐University press
○Commercial
The top 3 journals account for 50% of the predicted probability mass.
1
Nature Medicine
○
117 papers in training set
Top 0.1%
26.4%
2
npj Digital Medicine
○
97 papers in training set
Top 0.2%
19.0%
3
Nature Communications
○
4913 papers in training set
Top 17%
10.3%
50% of probability mass above
4
Nature Methods
○
336 papers in training set
Top 1%
8.6%
5
Genome Medicine
○
154 papers in training set
Top 2%
4.0%
6
Cell Reports Medicine
○
140 papers in training set
Top 1%
3.7%
7
Nature Biomedical Engineering
○
42 papers in training set
Top 0.3%
3.3%
8
Nature Machine Intelligence
○
61 papers in training set
Top 2%
1.7%
9
eLife
●
5422 papers in training set
Top 41%
1.7%
10
Med
○
38 papers in training set
Top 0.3%
1.5%
11
Communications Biology
○
886 papers in training set
Top 11%
1.5%
12
Patterns
○
70 papers in training set
Top 1%
1.4%
13
eBioMedicine
○
130 papers in training set
Top 2%
1.2%
14
PLOS ONE
●
4510 papers in training set
Top 60%
1.2%
15
Molecular Systems Biology
○
142 papers in training set
Top 0.9%
1.2%
16
Scientific Reports
○
3102 papers in training set
Top 66%
1.2%
17
Cell
○
370 papers in training set
Top 15%
0.9%
18
Nature Genetics
○
240 papers in training set
Top 7%
0.8%
19
The Lancet Digital Health
○
25 papers in training set
Top 1%
0.8%
20
Proceedings of the National Academy of Sciences
●
2130 papers in training set
Top 48%
0.5%
21
Nature Biotechnology
○
147 papers in training set
Top 9%
0.5%
22
PLOS Computational Biology
●
1633 papers in training set
Top 28%
0.5%
23
Science Advances
●
1098 papers in training set
Top 34%
0.5%
24
Communications Medicine
○
85 papers in training set
Top 2%
0.5%