Every time a patient sees a doctor, the symptoms, procedures and diagnoses need to be translated into standardized labels chosen from tens of thousands of possibilities. In the United States, that list has 72,000 options. These labels are called medical codes. They determine whether the hospital gets paid, whether the insurance claim goes through, and whether the visit gets counted in national health statistics. Choose the wrong one and the consequences range from a rejected bill to a patient's medical record with an incorrect diagnosis.
The codes are, at first glance, absurd in their specificity:
The specificity exists because the system must account for everything. When you look at which codes appear most frequently in which countries, something unexpected happens. The billing system becomes an accidental anthropology – a map of how people in each nation actually live: what animals they share space with, what they do on weekends, how they celebrate, and what their domestic life looks like from the emergency room.
In this interview, Corti’s, Joakim Edin will talk more about medical coding – from the mundane to the bizarre - and how important it is for the consumer that their healthcare professionals get it right. Errors can be quite expensive and potentially harmful, and Edin discusses Corti’s new AI model that will support this system that costs the U.S. $36 billion each year.
For more information, please visit: corti.ai
MORE ABOUT JOAKIM EDIN:
Joakim Edin is an AI researcher at Corti, and one of the architects of Symphony for Medical Coding, the breakthrough agentic model described in this report.
Produced for: Corti