Automated Medical Records OCR Data Extraction

This n8n workflow automates the extraction of structured data from medical documents through OCR processing and uploads the information into a Google Sheets database. It starts with a form webhook that users submit by uploading their medical documents. The document is then uploaded to Mistral’s API for file hosting, and a signed URL is retrieved for secure access. This URL is sent to Mistral’s OCR API to extract text information, which is subsequently processed and cleaned using a JavaScript code node. The script parses key medical fields such as patient name, date of birth, diagnosis, and lab results, and handles multi-record documents efficiently. Finally, the structured data is appended to a designated Google Sheets document for easy access and record-keeping. Practical use cases of this workflow include healthcare clinics automating patient data entry, medical research data collection, or any scenario where quick and accurate data extraction from scanned medical forms is needed.