Automated batch de-identification of unstructured healthcare documents

A data processing system adapted for batch de-identification of unstructured health care documents, the system comprising:

• a host computing platform comprising one or more computers, each with memory and one or processing units including one or more processing cores;
• and,
• a batch de-identification module comprising computer program instructions enabled while executing in the memory of at least one of the processing units of the host computing platform to perform:
• optical character recognizing a form-based document, the optical character recognition (OCR) producing an initial set of terms;
• identifying initial specific terms amongst the initial set of terms containing protected information and replacing in the form-based document each of the identified initial specific terms with synthetically generated corresponding terms;
• performing additional OCR on the form-based document to produce a new set of terms and identifying new specific terms amongst the new set of terms containing protected information;
• comparing the new specific terms to the initial specific terms;
• and,
• adding the form-based document to a repository of de-identified documents only if none of the new specific terms are equivalent to corresponding ones of the initial specific terms, but otherwise flagging the form-based document in error.

A computing device comprising a non-transitory computer readable storage medium having program instructions stored therein, the instructions being executable by at least one processing core of a processing unit to cause the processing unit to perform a method for batch de-identification of unstructured health care documents, the method including:

• optical character recognizing a form-based document, the optical character recognition (OCR) producing an initial set of terms;
• identifying initial specific terms amongst the initial set of terms containing protected information and replacing in the form-based document each of the identified initial specific terms with synthetically generated corresponding terms;
• performing additional OCR on the form-based document to produce a new set of terms and identifying new specific terms amongst the new set of terms containing protected information;
• comparing the new specific terms to the initial specific terms;
• and,
• adding the form-based document to a repository of de-identified documents only if none of the new specific terms are equivalent to corresponding ones of the initial specific terms, but otherwise flagging the form-based document in error.