entity_recognition.py

import json
from config import google_api
import os
import base64
from google import genai
from google.genai import types


def process_text(extracted_text):
    """Lab Test and metadata entity recognition using gemini flash"""
    ''' Return type: JSON '''
    print("Performing Named Entity Recognition...")

    client = genai.Client(
        api_key=google_api,
    )

    model = "gemini-2.0-flash"
    contents = [
        types.Content(
            role="user",
            parts=[
                types.Part.from_text(text="""The following text is extracted from a medical lab report using OCR.
There may be errors such as missing decimals, incorrect test names, and incorrect reference ranges.
Please correct the errors and extract both metadata and structured lab test data.
ALWAYS MAKE SURE THAT THE VALUE ALIGNS WITH THE REAL RANGE OF THE TEST
AND CLEARLY IDENTIFY REDS WITH LOW AND HIGH
Return the output in structured JSON format with all the information in lowercase to standardization.
And follow the JSON format provided and don't add any additional details in meta data or lab report other than that are specified


Extracted Text:
Dr. Onkar Test Sanjeevan Hospital\\n\\nMBBS, MD | Reg No: T123 12/4, Paud Road, Kothrud, Pune - 411023\\nPh: 0202526245, 8983390126, Timing: 09:15 AM -\\n02:30 PM, 05:30 PM - 09:30 PM, APPOINTMENTS\\nONLY | Closed: Monday,Friday\\n\\n \\n\\nPatient UID: 87 Report No: 00018\\n\\nName: AMAR SHAHA (Male} Rey, Date: 09-Jul-20\\n\\nAge 40 years Sample Collected At Hospital Lab\\n\\nAddress: MG Road, PUNE Sample Type/Quantity: Blood\\n\\nRef. By Doctor . Sample Collection D/T: 09-Jul-20, 9.50 AM\\nCr Test Result D/T: 09-Jul-20, 4:53 PM\\n\\n \\n \\n\\nDr. Amit Deshmukh\\n\\n     \\n\\nHEMOGRAM\\n\\nINVESTIGATION RESULT UNIT REF, RANGE\\nHAEMOGLOBIN : 14 gms/dl 12.0 - 17.0\\nRBC COUNT E 44 millfeumm 4.1-5.1\\nHAEMOTOCRIT (PCV) E 30 % 32.0 - 47.0\\nMCV $ 78 fl 760 - 100.0\\nMCH H 3246 Py 260-320\\nMCHC | : 328 n% 315-3465 ,\\nROW ; 13.9 % 11.6-150\\nMPV ; 11.2 fn 68- 12.6\\nWBC COUNT : 4567 /eamm 4000 - 11000\\nDIFFERENTIAL COUNT\\nNEUTROPHILS |» : 56 %y 40-70\\nLYMPHOCYTES ; 20 % 20.0- 45.0\\nEOSINOPHILS . 4 « % 0-6\\nMONOCYTES : 5 %

Expected JSON format:
{
    \"metadata\": {
        \"patient_name\": \"Prasahsst Pawar\",
        \"age\": \"20\",
        \"gender\": \"Male\",
        \"lab_name\": \"XYZ Diagnostics\",
        \"report_date\": \"05-03-2025\"
    },
    \"lab_tests\": [
        {
            \"test_name\": \"hemoglobin\",
            \"value\": \"14.2\",
            \"unit\": \"g/dL\",
            \"reference_range\": \"13.5 - 17.5 g/dL\"
        },
        {
      \"test_name\": \"rbc count\",
      \"value\": \"5.2\",
      \"unit\": \"million/cu mm\",
      \"reference_range\": \"4.1-5.1\"
    },
        {
            \"test_name\": \"glucose\",
            \"value\": \"65\",
            \"unit\": \"mg/dL\",
            \"reference_range\": \"70 - 110 mg/dL\"
        }
    ],
\"reds\":{
    \"low\":[\"glucose\"],
    \"high\":[\"rbc count\"]
}
}"""),
            ],
        ),
        types.Content(
            role="model",
            parts=[
                types.Part.from_text(text="""{
  \"lab_tests\": [
    {
      \"reference_range\": \"12.0 - 17.0\",
      \"test_name\": \"haemoglobin\",
      \"unit\": \"gms/dl\",
      \"value\": \"14\"
    },
    {
      \"reference_range\": \"4.1-5.1\",
      \"test_name\": \"rbc count\",
      \"unit\": \"mill/cu mm\",
      \"value\": \"4.4\"
    },
    {
      \"reference_range\": \"32.0 - 47.0\",
      \"test_name\": \"haematocrit (pcv)\",
      \"unit\": \"%\",
      \"value\": \"30\"
    },
    {
      \"reference_range\": \"76.0 - 100.0\",
      \"test_name\": \"mcv\",
      \"unit\": \"fl\",
      \"value\": \"78\"
    },
    {
      \"reference_range\": \"26.0-32.0\",
      \"test_name\": \"mch\",
      \"unit\": \"pg\",
      \"value\": \"32.46\"
    },
    {
      \"reference_range\": \"31.5-34.5\",
      \"test_name\": \"mchc\",
      \"unit\": \"%\",
      \"value\": \"32.8\"
    },
    {
      \"reference_range\": \"11.6-15.0\",
      \"test_name\": \"rdw\",
      \"unit\": \"%\",
      \"value\": \"13.9\"
    },
    {
      \"reference_range\": \"6.8- 12.6\",
      \"test_name\": \"mpv\",
      \"unit\": \"fn\",
      \"value\": \"11.2\"
    },
    {
      \"reference_range\": \"4000 - 11000\",
      \"test_name\": \"wbc count\",
      \"unit\": \"/cu mm\",
      \"value\": \"4567\"
    },
    {
      \"reference_range\": \"40-70\",
      \"test_name\": \"neutrophils\",
      \"unit\": \"%\",
      \"value\": \"56\"
    },
    {
      \"reference_range\": \"20.0- 45.0\",
      \"test_name\": \"lymphocytes\",
      \"unit\": \"%\",
      \"value\": \"20\"
    },
    {
      \"reference_range\": \"0-6\",
      \"test_name\": \"eosinophils\",
      \"unit\": \"%\",
      \"value\": \"4\"
    },
    {
      \"reference_range\": \"2-10\",
      \"test_name\": \"monocytes\",
      \"unit\": \"%\",
      \"value\": \"5\"
    }
  ],
  \"metadata\": {
    \"age\": \"40\",
    \"gender\": \"male\",
    \"lab_name\": \"sanjeevan hospital\",
    \"patient_name\": \"amar shaha\",
    \"report_date\": \"09-jul-20\"
  },
  \"reds\": {
    \"high\": [
      \"mch\"
    ],
    \"low\": [
      \"haematocrit (pcv)\"
    ]
  }
}"""),
            ],
        ),
        types.Content(
            role="user",
            parts=[
                types.Part.from_text(text=extracted_text),
            ],
        ),
    ]
    generate_content_config = types.GenerateContentConfig(
        temperature=1,
        top_p=0.95,
        top_k=40,
        max_output_tokens=8192,
        response_mime_type="application/json",
        response_schema=genai.types.Schema(
            type = genai.types.Type.OBJECT,
            enum = [],
            required = ["metadata", "lab_tests", "reds"],
            properties = {
                "metadata": genai.types.Schema(
                    type = genai.types.Type.OBJECT,
                    enum = [],
                    required = ["patient_name", "age", "gender", "lab_name", "report_date"],
                    properties = {
                        "patient_name": genai.types.Schema(
                            type = genai.types.Type.STRING,
                        ),
                        "age": genai.types.Schema(
                            type = genai.types.Type.STRING,
                        ),
                        "gender": genai.types.Schema(
                            type = genai.types.Type.STRING,
                        ),
                        "lab_name": genai.types.Schema(
                            type = genai.types.Type.STRING,
                        ),
                        "report_date": genai.types.Schema(
                            type = genai.types.Type.STRING,
                        ),
                    },
                ),
                "lab_tests": genai.types.Schema(
                    type = genai.types.Type.ARRAY,
                    items = genai.types.Schema(
                        type = genai.types.Type.OBJECT,
                        enum = [],
                        required = ["test_name", "value", "unit", "reference_range"],
                        properties = {
                            "test_name": genai.types.Schema(
                                type = genai.types.Type.STRING,
                            ),
                            "value": genai.types.Schema(
                                type = genai.types.Type.STRING,
                            ),
                            "unit": genai.types.Schema(
                                type = genai.types.Type.STRING,
                            ),
                            "reference_range": genai.types.Schema(
                                type = genai.types.Type.STRING,
                            ),
                        },
                    ),
                ),
                "reds": genai.types.Schema(
                    type = genai.types.Type.OBJECT,
                    enum = [],
                    required = ["low", "high"],
                    properties = {
                        "low": genai.types.Schema(
                            type = genai.types.Type.ARRAY,
                            items = genai.types.Schema(
                                type = genai.types.Type.STRING,
                            ),
                        ),
                        "high": genai.types.Schema(
                            type = genai.types.Type.ARRAY,
                            items = genai.types.Schema(
                                type = genai.types.Type.STRING,
                            ),
                        ),
                    },
                ),
            },
        ),
        system_instruction=[
            types.Part.from_text(text="""Always return the output as JSON only"""),
        ],
    )



    # for chunk in client.models.generate_content_stream(
    #     model=model,
    #     contents=contents,
    #     config=generate_content_config,
    # ):
    #     print(chunk.text, end="")

    try:
        response = client.models.generate_content(
            model=model, contents=contents, config=generate_content_config
        )

        json_response = response.text  # Ensure response is JSON formatted
        parsed_json = json.loads(json_response)  # Convert JSON string to Python dictionary
        return parsed_json

    except json.JSONDecodeError:
        print("Error: Invalid JSON response from the model.")
        return None