> ## Documentation Index
> Fetch the complete documentation index at: https://developer.eka.care/llms.txt
> Use this file to discover all available pages before exploring further.

# Medical Document Parsing

> Structured data from Indian medical documents — lab reports, prescriptions, discharge summaries, insurance policies — with PII redaction and document classification.

Eka's document parsing stack turns scanned, photographed or digital medical documents into structured, coded, FHIR-ready data. It is built on our own vision models ([Parrotlet-v](/eka-medai/models)), trained on Indian documents, handwriting and formats, and runs without a human in the loop.

## What it does

* **Classifies** an incoming document (lab report, prescription, discharge summary, insurance policy, invoice and more) and flags handwritten and non-medical inputs
* **Extracts** structured fields per document type: tests, results, units and reference ranges from lab reports; diagnoses, medications, dosages and advice from prescriptions; policy and claim details from insurance documents
* **Codes** the output to standard ontologies: [LOINC](https://loinc.org/) and [UCUM](https://ucum.org/) for lab tests, [SNOMED CT](https://www.snomed.org/) for clinical concepts, our drug database for medications
* **Redacts** personally identifiable information in text and in the document image itself
* **Returns** results as JSON and as an [HL7 FHIR](https://www.hl7.org/fhir/overview.html) document bundle

Capabilities, supported document classes and accuracy numbers change with each model release; the current state is always on the model cards and launch blogs below.

## Read more

* [Releasing Parrotlet Open Models: Open Weights for Medical Document Intelligence](https://info.eka.care/services/releasing-parrotlet-open-models-open-weights-for-medical-document-intelligence) – Parrotlet-v 2.5 Pro, Med Doc Classifier and Document PII Redactor
* [Parrotlet-V Lite (4B)](https://info.eka.care/services/parrotlet-v-lite-4b-releasing-our-purpose-built-vision-llm-for-parsing-medical-records) – our first open vision LLM for medical records
* [Lab-Ready and Prescription-Perfect: Eka Care's Small LLMs vs. Industry Giants](https://info.eka.care/services/lab-ready-and-prescription-perfect-ekas-small-llms-vs-industry-giants)
* [Extracting Structured Information from Lab Reports: Challenges and Learnings](https://info.eka.care/services/eka-smart-report)

## Models and tools

* [Parrotlet-v 2.5 Pro](https://huggingface.co/ekacare/parrotlet-v-2.5-pro) · [Parrotlet-V-Lite-4B](https://huggingface.co/ekacare/parrotlet-v-lite-4b) · [Med Doc Classifier](https://huggingface.co/ekacare/med-doc-classifier) · [Document PII Redactor](https://huggingface.co/ekacare/document-pii-redactor)
* Evaluation set: [Medical Records Parsing Validation Set](https://huggingface.co/datasets/ekacare/medical_records_parsing_validation_set)
* Reference: [LOINC-linkable lab tests](/eka-medai/resources#reference-lists)

## Try it out

* Live demos: [Medical records](https://medai.eka.care/medical-records) · [Classifier](https://medai.eka.care/classifier) · [PII redactor](https://medai.eka.care/pii-redactor)
* API: [Medical Document Parsing](/api-reference/health-ai/medical-document-parsing/introduction)
* Entity linking: [Medical Entity Codification](/eka-medai/technologies/codification/overview)