> ## Documentation Index
> Fetch the complete documentation index at: https://ekacare-quickstart-cleanup.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Prescription

## Overview

EkaCare's prescription parsing solution leverages its customised [vision-LLM](https://info.eka.care/services/lab-ready-and-prescription-perfect-ekas-small-llms-vs-industry-giants)
to accurately extract structured data such as symptoms, diagnosis, medical history, vitals and medications. Designed specifically for the Indian healthcare ecosystem our solution offers high level of accuracy and doesn't involve human in a loop.

#### This service offers:

* Extraction of symptoms, diagnosis, medical history, vitals, lab investigations, medications, advices etc.
* Linking of concepts with [SNOMED-CT](https://www.snomed.org/) identifiers
* Linking of medications with unified EkaCare identifiers
* Output as [HL7 FHIR](https://www.hl7.org/fhir/overview.html) document
* Ability to work with PDFs as well as scanned / clicked images of prescriptions

Example\*\*

## Use Cases

### 1. **HealthCare providers**

* Better clinical decision making leveraging comprehensive 360 degree view of patient's health based on the past prescriptions.

### 2. **Health Insurance Companies**

* Streamlining the processing of prescriptions submitted during insurance claims.
* Automate fraud detection by validating extracted prescription data.
* Health profiling based on historical medical encounters.

### 3. **Personal Health Record (PHR)**

* Comprehensive health view based on past prescription data.
* Improved awareness and management of health data.

## Technology Deep-Dive

Our prescription parsing technology is powered by or custom Large Language Models (LLMs), specifically trained on millions of anonymized medical documents.
These documents span diverse formats and contexts, with a particular focus on the Indian healthcare ecosystem. Our models understand drug names which
are specific to India, something that SOTA models such as GPT-4o and Sonnet 3.5 fails often.

Our rigorous training and fine-tuning process ensures exceptional accuracy while minimizing common pitfalls like hallucinations that often impact other SOTA LLMs.
The result is a highly reliable system, as demonstrated in the benchmarks provided in the subsequent section.

Our process consists of two core steps:

#### 1. **Medical Information Extraction:**

Extracting structured medical entities such as condition and medications from unstructured or pseudo-structured PDFs or images.

#### 2. **Medical Entity Linking:**

Assigning SNOMED-CT identifiers to the extracted medical concepts. This is what enables interoperability and interpretability of this rich medical data.

## Evaluation and Benchmarks

Our benchmark experiments with evaluation dataset comprising thousands of documents showcase Eka’s superior performance in terms of accuracy compared to other SOTA models. NOTE this evaluation dataset contains both PDF and clicked images.

| Task                 | Parrotlet-V (Eka Care's LLM) | OpenAI GPT-4o | Claude Sonnet 3.5 | Qwen2-VL (7B) | Llama-3.2-Vision (11B) | Phi-3.5-vision (4.2B) |
| -------------------- | ---------------------------- | ------------- | ----------------- | ------------- | ---------------------- | --------------------- |
| Prescription parsing | 0.921                        | 0.853         | 0.867             | 0.630         | 0.593                  | 0.433                 |

A deeper view on results of these experiments are summarised below.

| Field Name          | Parrotlet-V | GPT-4o    | Claude Sonnet 3.5 |
| ------------------- | ----------- | --------- | ----------------- |
| drug\_name          | 0.92        | 0.848     | 0.892             |
| drug\_generic       | 0.886       | 0.879     | 0.898             |
| drug\_dosage        | 0.828       | 0.658     | 0.629             |
| drug\_duration      | 0.903       | 0.904     | 0.913             |
| drug\_frequency     | 0.904       | 0.792     | 0.761             |
| medication\_time    | 0.838       | 0.648     | 0.605             |
| diagnosis           | 0.955       | 0.907     | 0.934             |
| labtests            | 0.93        | 0.868     | 0.908             |
| symptoms            | 0.953       | 0.909     | 0.954             |
| medical\_history    | 0.972       | 0.921     | 0.936             |
| findings            | 0.937       | 0.946     | 0.944             |
| current\_medication | 0.99        | 0.946     | 0.967             |
| advice              | 0.884       | 0.737     | 0.815             |
| family\_history     | 0.995       | 0.981     | 0.987             |
| **Average**         | **0.921**   | **0.853** | **0.867**         |

## Spotlight

* [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)

## Try Out

Experience the power of EkaCare's prescription parsing with our developer-friendly API.

1. Visit our [API Documentation](https://developer.eka.care/api-reference/general-tools/medical/lab-report/create-records-v2) to get started.
2. Upload a sample prescription and see our technology in action.
3. Contact us for a custom demo tailored to your use case.

Ready to unlock the full potential of prescription data? [Get in Touch](ekaconnect@eka.care) today.