Technology Overview

The presented technology is an Artificial Intelligence (AI) model developed to extract essential information from scanned medical certificates. This trained model can extract pertinent details from medical certificates issued locally in Singapore, aiding companies in streamlining their medical leave management process by automating the approval of medical leave requests.

The extracted details can seamlessly integrate with a company’s existing workflow. The technology enables prompt and precise handling of leave requests, thereby reducing administrative workload, processing time, and errors introduced due to manual entry.

Technology Features

The trained AI model recognises terms and entities from scanned medical certificates. This includes, but is not limited to:

• Clinic Name

• Clinic Address

• Clinic Telephone Number

• Patient Name

• Start & End Date of Medical Leave

• Duration of Medical Leave

The Name Entity Recognizer (NER) model is trained based on an open-source library and can be seamlessly integrated with the existing workflow or system to automate the extraction of information for approval or recording purposes.

Potential Applications

The model, in its current state, has been trained on a diverse dataset of medical certificates issued in Singapore and is suitable for application in systems providing Document Management and Human Resource solutions. The model’s application will be particularly useful for:

• Companies seeking to automate their medical leave processing or application workflow.

• Insurance providers and vendors specialising in Document Management, HR software solution, Payroll, and Attendance solutions.

The model can be integrated into existing solution to value-add in the processing of medical certificates.

Benefits

The model is implemented using Natural Language Processing and operates in the domain of Named Entity Recognition. It has been trained using a diverse dataset of medical certificates issued in Singapore and can automatically recognise entries of interest from a scanned copy of the document. The model accomodates variations of formats, prints, and naming of the entries and provide a recognisable input to the software systems that utilise it.

Commercialisation

• This technology is available for licensing and technology transfer.