Sold by: OpenMed
Deployed on AWS
Open-source NER model for disease entities in biomedical and clinical text. Trained on NCBI-Disease and optimized for state-of-the-art precision, it enables reliable extraction with fast, easy deployment via Hugging Face Transformers.
Overview
Open-Source Disease NER Model: State-of-the-Art Biomedical Entity Recognition Discover a powerful, open-source Named Entity Recognition (NER) model specially fine-tuned for accurate identification and extraction of disease entities from biomedical and clinical documents. Engineered on the curated NCBI-Disease dataset, this model surpasses licensed alternatives with industry-leading precision. Why Choose OpenMed NCBI Disease NER Model? Open-Source & Free Forever: No licensing fees fully accessible to empower your biomedical research. State-of-the-Art Accuracy: Achieve unmatched precision in extracting disease names, outperforming commercial solutions. Clinical & Biomedical Excellence: Expertly validated on clinical benchmarks for reliability in disease detection, healthcare analytics, and clinical studies. Easy & Fast Integration: Seamlessly integrates into the Hugging Face Transformers ecosystem for effortless deployment. Ideal for Biomedical Applications Including: Disease detection and monitoring Disease extraction from patient records Adverse event monitoring Literature mining for disease research Biomedical knowledge graph construction Clinical informatics and pathology research Built on the NCBI-Disease Dataset: This specialized dataset contains comprehensive annotations for disease names and conditions, making it ideal for clinical informatics, pathology research, and advanced biomedical text mining. Entity Types Supported: B-Disease OpenMed-Disease Experience industry-leading biomedical NER performance open-source and completely free.
Highlights
- Open-Source and Free Forever: Eliminate licensing costs while accessing state-of-the-art biomedical entity recognition.
- Clinical-Grade Accuracy: Superior precision validated on the NCBI-Disease dataset, ideal for clinical analytics and decision support.
- Easy Integration: Fully compatible with Hugging Face Transformers for fast and effortless deployment.
Details
Sold by
Delivery method
Latest version
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
This product is available free of charge. Free subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimensions summary
This model is free to use, so you pay only for the AWS compute you run. You pick an instance size based on how much processing power you need. Inference comes in two modes. Batch mode handles groups of records at once, with four instance sizes available. Real-time mode returns results as requests arrive, with five instance sizes available. Billing is per host-hour in both modes. Larger instance types offer more compute capacity. You choose the mode and size that fit your workload and run them on your own AWS account.
Top-of-mind questions for buyers
A host-hour is one hour that your chosen instance runs. Charges accrue while the instance is provisioned and running, not per record processed. Real-time endpoints keep running until you stop them, so they bill continuously. Batch jobs run only during processing, so you pay for that active window.
Batch mode processes groups of records in one job, so you run an instance only for that job's duration. Real-time mode keeps an endpoint running to answer requests as they arrive, so it meters time the endpoint stays up. Batch suits large one-off datasets; real-time suits ongoing on-demand requests.
The model software is free. You pay only the AWS compute host-hours for the instance type you select. There is no separate per-record or software license charge added to the host-hour rate shown in the table.
huggingface.co
Helpful?
Vendor refund policy
free
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
Amazon SageMaker model
An Amazon SageMaker model package is a pre-trained machine learning model ready to use without additional training. Use the model package to create a model on Amazon SageMaker for real-time inference or batch processing. Amazon SageMaker is a fully managed platform for building, training, and deploying machine learning models at scale.
Deploy the model on Amazon SageMaker AI using the following options:
Version release notes
Initial release of OpenMed NER models for comprehensive biomedical entity recognition. These models deliver high‑precision token classification across clinical and research text, covering organisms and species, chemicals, diseases and phenotypes, genes and proteins, genetic variants/genomics, anatomy, oncology (including CLL), and related biomedical concepts. Designed for enterprise‑grade accuracy, optimized performance on medical text, and production‑ready reliability for healthcare and life sciences applications.
Additional details
Inputs
- Summary
This model accepts clinical text, research papers, and biomedical documents as input. The input should be provided as JSON with an "inputs" field containing the text to analyze. The model processes natural language text and identifies medical entities including organisms, species, diseases, and other biomedical terms. Input text can range from short clinical notes to longer research documents, with optimal performance on medical and scientific content.
- Input MIME type
- application/json
{"inputs": "Tumor profiling identified KRAS G12D and BRAF V600E variants. Additional findings include PIK3CA mutations."}
{"inputs": ["Tumor profiling identified KRAS G12D and BRAF V600E variants. Additional findings include PIK3CA mutations.", "Sequencing detected EGFR L858R and ALK fusion. BRCA1 frameshift variant reported in family history."]}
Support
Vendor support
For any questions or support, please join the discussions on OpenMed:
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
Open-source NER model for disease entities in biomedical and clinical text. Trained on NCBI-Disease and optimized for state-of-the-art precision, it enables reliable extraction with fast, easy deployment via Hugging Face Transformers.
Open-source NER model for disease entities in biomedical and clinical text. Trained on NCBI-Disease and optimized for state-of-the-art precision, it enables reliable extraction with fast, easy deployment via Hugging Face Transformers.
Open-source NER model for disease entities in biomedical and clinical text. Trained on NCBI-Disease and optimized for state-of-the-art precision, it enables reliable extraction with fast, easy deployment via Hugging Face Transformers.
Open-source NER model for cancer genetics entities in biomedical and clinical text. Trained on BioNLP2013-CG and optimized for state-of-the-art precision, it enables reliable extraction with fast, easy deployment via Hugging Face Transformers.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.