Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

OCR finds words that are not in the figure #18

Open
khanspers opened this issue Nov 26, 2024 · 0 comments
Open

OCR finds words that are not in the figure #18

khanspers opened this issue Nov 26, 2024 · 0 comments
Labels
bug Something isn't working

Comments

@khanspers
Copy link
Member

khanspers commented Nov 26, 2024

I found several results where PFOCR reported diseases that are not in the figure. Here's a list of PFOCR urls, with the false positive diseases listed for each, meaning these are reported in the Disease mentions table, and in the rds.

On the PFOCR website, the diseases are listed ("Word" column), but are not mapped. In the rds, "doid" is non-blank for these diseases. This may be related to #16.

https://pfocr.wikipathways.org/figures/PMC3093193__nihms289177f2.html: Melanoma. Potentially misread of melanocyte, melanogenesis or melanogenic.
https://pfocr.wikipathways.org/figures/PMC2744676__1478-811X-7-20-2.html: Cancer, Cardiomyopathy, Lung cancer, Melanoma, Noonan syndrome
https://pfocr.wikipathways.org/figures/PMC4851838__ajcr0006-0577-f1.html: Cancer, Cardiomyopathy, Lung cancer, Melanoma, Noonan syndrome, Cholangiocarcinoma
https://pfocr.wikipathways.org/figures/PMC4505740__nihms655432f1.html: Cancer, Lung cancer, Melanoma
https://pfocr.wikipathways.org/figures/PMC3251651__nihms339102f4.html: Cancer, Melanoma
https://pfocr.wikipathways.org/figures/PMC5385394__WJG-23-2276-g001.html: Cancer, Melanoma

These were found from reviewing PFOCR-augmented BTE results, from two queries related to Melanoma and Lung cancer. If I find other cases, I will add them here.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working
Projects
None yet
Development

No branches or pull requests

1 participant