Sold by: John Snow Labs
Deployed on AWS
Free Trial
This pipeline can extract clinical conditions, and map the clinical conditions to their respective ICD-10-CM codes.
Overview
The ICD-10-CM Clinical Terminology Mapper is a comprehensive, pretrained Spark NLP pipeline designed to extract clinical conditions from unstructured medical text and map them to their corresponding ICD-10-CM codes. Utilizing advanced sentence embeddings, this pipeline facilitates accurate and standardized coding, enhancing clinical data analysis and interoperability.
Key Features
Entity Extraction: Identifies a wide range of clinical entities, including: Cerebrovascular Diseases, Communicable Diseases, Diabetes, Disease Syndromes and Disorders, EKG Findings, Heart Diseases, Hyperlipidemia, Hypertension, Imaging Findings, Injuries or Poisonings, Kidney Diseases, Obesity, Oncological Conditions, Overweight, Pregnancy-related Conditions, Psychological Conditions, Symptoms, Vital Sign Findings
IMPORTANT USAGE INFORMATION:
After subscribing to this product and creating a SageMaker endpoint, billing occurs on an HOURLY BASIS for as long as the endpoint is running.
-Charges apply even if the endpoint is idle and not actively processing requests.
-To stop charges, you MUST DELETE the endpoint in your SageMaker console.
-Simply stopping requests will NOT stop billing.
This ensures you are only billed for the time you actively use the service.
Highlights
- The pipeline accepts a single text document or an array of text documents or JSON Lines (JSONL) format as input.
- The pipeline returns information in JSON format, containing: - Detected named entity resolution (NER) chunk. - position of the detected NER chunk in the document - NER chunk label - NER chunk confidence score - Resolution code of the NER chunk - Resolution of the NER chunk - Score, representing Cosine distance score of the resolution - Billable, HCC status, and HCC score of the resolution code. See sample documentation for a complete information.
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
Free trial
Try this product free for 15 days according to the free trial terms set by the vendor.
Pricing is based on actual usage, with charges varying according to how much you consume. 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.
Dimension | Description | Cost/host/hour |
|---|---|---|
ml.m4.2xlarge Inference (Batch) Recommended | Model inference on the ml.m4.2xlarge instance type, batch mode | $47.52 |
ml.m4.xlarge Inference (Real-Time) Recommended | Model inference on the ml.m4.xlarge instance type, real-time mode | $23.76 |
ml.m5.2xlarge Inference (Batch) | Model inference on the ml.m5.2xlarge instance type, batch mode | $47.52 |
ml.m6i.2xlarge Inference (Batch) | Model inference on the ml.m6i.2xlarge instance type, batch mode | $47.52 |
ml.m7i.2xlarge Inference (Batch) | Model inference on the ml.m7i.2xlarge instance type, batch mode | $47.52 |
ml.c5.2xlarge Inference (Batch) | Model inference on the ml.c5.2xlarge instance type, batch mode | $47.52 |
ml.c6i.2xlarge Inference (Batch) | Model inference on the ml.c6i.2xlarge instance type, batch mode | $47.52 |
ml.c7i.2xlarge Inference (Batch) | Model inference on the ml.c7i.2xlarge instance type, batch mode | $47.52 |
ml.r6i.2xlarge Inference (Batch) | Model inference on the ml.r6i.2xlarge instance type, batch mode | $47.52 |
ml.r7i.2xlarge Inference (Batch) | Model inference on the ml.r7i.2xlarge instance type, batch mode | $47.52 |
Dimensions summary
You pay by the hour for the compute instance that runs the model, with no upfront commitment. Pricing splits into two processing modes. Batch mode runs on 2xlarge instances across several families, letting you process large volumes of clinical text in bulk jobs. Real-time mode runs on xlarge instances across the same families for on-demand, single-request coding. Within each mode, the instance families (general purpose, compute-optimized, and memory-optimized) let you match hardware to your workload. Your total cost scales with how many hours each chosen instance runs.
Top-of-mind questions for buyers
You pay for the running time of the compute instance that hosts the model, billed per hour. The model extracts clinical conditions from text and maps them to ICD-10-CM codes. Charges accrue only while the instance runs, so stopping the instance stops the software charge.
Batch mode runs on 2xlarge instances to process large sets of clinical documents in bulk jobs. Real-time mode runs on xlarge instances to code single requests on demand. Both meter host-hours the same way. Batch suits scheduled high-volume coding; real-time suits interactive, per-request lookups.
Each instance you run bills independently by the hour, and the charges add together on one invoice. Cost scales with the number of instances and hours, not with the volume of text processed. Running fewer instances or shutting them down between jobs lowers your total.
nlp.johnsnowlabs.com+1
Helpful?
Vendor refund policy
No refunds are possible.
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
Updated internal libs to 6.4.0
Additional details
Inputs
- Summary
Input Format
To use the model, you need to provide input in one of the following supported formats:
JSON Format Provide input as JSON. We support two variations within this format:
- Array of Text Documents: Use an array containing multiple text documents. Each element represents a separate text document.
{ "text": [ "Text document 1", "Text document 2", ... ] }
- Single Text Document: Provide a single text document as a string.
{ "text": "Single text document" }
JSON Lines (JSONL) Format
Provide input in JSON Lines format, where each line is a JSON object representing a text document.
{"text": "Text document 1"} {"text": "Text document 2"}
- Input MIME type
- application/json, application/jsonlines
https://github.com/JohnSnowLabs/spark-nlp-workshop/tree/master/products/sagemaker/models/icd10cm_vdb_resolver/inputs/real-time
https://github.com/JohnSnowLabs/spark-nlp-workshop/tree/master/products/sagemaker/models/icd10cm_vdb_resolver/inputs/batch
Resources
Vendor resources
Support
Vendor support
For any assistance, please reach out to support@johnsnowlabs.com .
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
OneData Software uses Amazon Comprehend Medical, a HIPAA-eligible NLP service, to extract valuable insights from unstructured clinical text. Their solutions automate the identification of medical conditions, medications, treatments, and protected health information (PHI), enhancing clinical workflows and decision-making. By integrating these capabilities, OneData enables healthcare organizations to streamline operations, improve patient outcomes, and ensure compliance with data privacy regulations.
Built with an industry-leading clinical NLP engine, the AGS AI Platform Computer-Assisted Coding (CAC) module enables flexible and scalable coding of facility and professional charts to increase accuracy, efficiency, productivity, and flexibility.
Co-innovated with Loka and the AWS Generative AI Innovation Center (GenAIIC) Partner Agent Factory (PAF), Loka MedEncAI - Encounter Assistant is an autonomous clinical documentation agent that transforms physician–patient encounter audio into structured, coded, evidence-linked clinical notes, built entirely on AWS services. Designed for ISVs and health-technology companies building clinical platforms, the solution ships as a white-label, single-tenant deployment in the customer's AWS account with full IP ownership. Powered by Amazon Bedrock AgentCore and the Strands SDK, the agent reasons over the complete encounter, grounds every medical code through authoritative AWS services, and self-corrects against a clinical rubric before emitting a note, delivering production-grade documentation in under two minutes with built-in hallucination verification.
Mental health symptoms often spread across several diagnostic categories and can collectively impair a person's ability to manage daily life. The historical focus on just one or two conditions is about to change. Recently updated USPSTF guidelines now endorse assessing for anxiety and depression together rather than individually, and the USPSTF has warned for years that anyone identified with depression must also be assessed for the risk of bipolar disorder. Too often, and sometimes with grave consequences, these recommendations have gone unheeded. M3 gives individuals and their clinicians a clear view of these problems, greatly helping with personalized care.
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.