beamandrew / medical-data Goto Github PK

Under UCI datasets, I notice that Breast Cancer and Lymphography datasets are included, but the third one in the group is omitted for some reason. Please add the Primary Tumor data set: https://archive.ics.uci.edu/ml/datasets/primary+tumor

Add Clinical NLP Challenges Datasets from Filannino and Uzuner's Advancing the State of the Art in Clinical Natural Language Processing through Shared Tasks. While some are already included (e.g. TREC), others could be added (e.g. CLEF/eHealth). May requires a followup checklist to track since there are a number indicated in Table 1.

May be it will be useful:

• https://archive.ics.uci.edu/ml/datasets.html?format=&task=&att=&area=life&numAtt=&numIns=&type=&sort=nameUp&view=table

• http://www.ebusinessgems.com/blog/socio-economic-database/database-diseases-disorders-illnesses/

• http://disease-ontology.org/downloads/

• https://www.kaggle.com/plarmuseau/sdsort

Have to fix the following mistakes in README.md

• Spelling
• Grammatical
• Repeated words

Have to update the following dataset link:

• DRIVE
• LIDC-IDRI
• Belarus TB dataset
• DDSM
• SCR Database
• VISCERAL
• Coding4Cancer
• Parkinson Speech Dataset with Multiple Types of Sound Recordings Data Set
• Parkinson's Disease Classification Data Set

Have to update the following paper link:

• Learning Low-Dimensional Representations of Medical Concept

Including the following dataset link:

• SCMR Consensus, Sunnybrook Cardiac Data

http://spineweb.digitalimaginggroup.ca/spineweb/index.php?n=Main.Datasets

If possible, please include the link to the followings:

1. Emergency Tele-Orthopedics X-ray Digital Library.
2. IMT Segmentation
3. Needle EMG MUAP Time Domain Features
4. Interactive Tool of Clinical Concept Embeddings Learned from Massive Sources of Medical Data
5. DocGraph
6. PICO elements (data + website)
7. EMOTASS
8. Autism Sub-Challenge (Paper + Link)

Are there any cell counting dataset available?

Do you know those Continuous Registration Challenge and Histology dataset ?

The link is dead for this data-set.

It could be worth mentionning the dream Challenges on this page, either as a single entry for all of them, or an entry per challenge.

http://dreamchallenges.org/

In particular:

The Digital Mammography DREAM Challenge.
June 29, 2016- Feb. 20, 2017 (open)
With generous support from the Laura and John Arnold Foundation this $1.2 million Challenge, one of two large prize Coding4Cancer Challenges, seeks to improve the accuracy of breast cancer detection and reduce the current rate of patient callbacks.

Hi :)
Theres a database of classified skin lesions - "Isic Archive"
It can be accessed through here:
https://www.isic-archive.com/#!/topWithHeader/onlyHeaderTop/gallery
And i've also made a script to download it:
https://github.com/GalAvineri/ISIC-Archive-Downloader

Can you please add these to your collection? :)

There may be some wheat in the chaff https://datasetsearch.research.google.com/search?query=ECG&docid=sU%2FLa8M%2FP9nUeWMAAAAAAA%3D%3D

Dataset: https://bmirds.github.io/LungCancer/

This dataset comprises 143 hematoxylin and eosin (H&E)-stained formalin-fixed paraffin-embedded (FFPE) whole-slide images of lung adenocarcinoma. The dataset is de-identified and released with permission from Dartmouth-Hitchcock Health (D-HH) Institutional Review Board (IRB). All whole-slide images are labeled according to the consensus opinion of three pathologists at Dartmouth-Hitchcock Medical Center (DHMC) for the predominant pattern of lung adenocarcinoma. For more information about this dataset, please refer to “Pathologist-level classification of histologic patterns on resected lung adenocarcinoma slides with deep neural networks”.

Hi, I downloaded the pre-trained embedding file. The file type says its a csv but actually its a binary, I used python dictionary to open it but I get an error.
I have also used gensim, KeyedVectors to load embedding but I get error
word_vectors = KeyedVectors.load_word2vec_format('__MACOSX/emb.csv', binary=True)
#changed name of the file to emb.csv
UnicodeDecodeError: 'utf-8' codec can't decode byte 0xf9 in position 37: invalid start byte

So could tell me as to what tool is needed to open this file..?

Would love to see EEG data included in the mega-list.

Hi,

I shared a set of Word2Vec embeddings of LOINC codes via GitHub. I trained them from lab orders at my organization (City of Hope National Medical Center). I wonder if you could include it in your list. The markdown with description and related links is below.

Thank you!
Lorenzo

Evaluation of Embeddings of Laboratory Test Codes for Patients at a Cancer Center
200 dimensional Word2Vec embeddings of 1098 laboratory test codes (LOINCs) trained from 8,280,238 lab orders for 79,081 patients at City of Hope National Medical Center
Paper: https://arxiv.org/abs/1907.09600
Data: https://github.com/elleros/DSHealth2019_loinc_embeddings

Dear Drew,
in 2011 there was TREC-MED https://trec.nist.gov/pubs/trec21/papers/MED12OVERVIEW.pdf perhaps you might want to add that to your list too :-)

https://echonet.github.io/dynamic/

CMS has released additional info since the FIOA request by Fred. You can find the other years in a FAQ on the CMS site.

https://questions.cms.gov/faq.php?faqId=7977

If you accept pull requests, I may have some additional suggested edits/additions.