Each time healthcare providers administer care services or medications, they have to manually encode it into a dedicated software that will then bill patients. However, it happens that medical acts are occasionally forgotten: for instance, when a blood work is performed on a patient, the blood pouch equipment should also always be encoded as well. In practice, it is not always the case. These omissions, while individually arm less for hospital finances, can result in a big loss of revenue for the hospital at the end of the months. 

Saint-Luc, the largest hospital in Brussels, asked Sagacify for a solution to detect these revenue leakages. 

‍Key elements  

• Creation of custom AI models designed to detect invoicing errors from the INAMI codes
• Co-creation of an app allowing the financial team to drill down on the data and find the sources of invoicing errors. 

‍

To solve the problem of spotting invoicing anomalies, we split the anomalies detection into two different models: 

• The first model checks each invoice individually to validate the invoiced medical acts against a predicted “patient journey”
• The second model monitors the time series of all medical act types (INAMI codes) and validates that the observed variations are normal

Since the integration of the models is of crucial importance in this project, we also co-created a web application with the client, to facilitate the investigation of detected anomalies by the invoicing team.