Clinical and administrative applications

Corti automatically transcribes patient dialogues in real-time and across multiple languages, documenting the conversation as it occurs. This feature enables immediate access to the conversation's details and ensures no vital information is lost or misinterpreted due to manual transcription errors or delays.

The AI then extracts key information from the transcribed dialogues. It identifies important details such as specific symptoms, medications mentioned, and critical questions raised during the interaction, thus facilitating an efficient review of the encounter's highlights.

Leveraging the extracted information, Corti's AI recommends the best course of action for patient care. It compares the patient's data and insights against a database of millions of other data points to determine the most appropriate next steps.

After the encounter, Corti assists in documenting the interaction by automatically coding the procedure and diagnosis codes, such as ICD-10 and CPT. This automated coding process not only saves time but also reduces the potential for human error, ensuring accurate patient records and facilitating efficient billing.

To illustrate with a hematology example, consider a telemedicine consultation where a patient reports symptoms of fatigue, bruising, and frequent infections. Corti would transcribe this conversation in real time, extract the key symptoms, and based on comparison with other data points, could suggest the possibility of a blood disorder like leukemia. Once the encounter is complete, it would code the interaction appropriately with the corresponding ICD-10 and CPT codes. Through this process, Corti not only assists in the diagnostic process but also reduces the administrative burden associated with coding and documenting patient encounters.


Healthcare innovation ai

Clinical evidence

Corti AI was used by SOS Alarm in Sweden to improve their emergency call handling. Corti’s real-time decision support system was integrated into SOS Alarm’s existing infrastructure to assist emergency call-takers in detecting out-of-hospital cardiac arrests (OHCA) during calls. The system used machine learning to analyze the audio of the calls and provide real-time feedback to the call-taker, helping them to ask the right questions and make more accurate decisions.

The results of the pilot study showed that Corti was able to increase OHCA recognition by 14.4%, leading to faster dispatch times and better patient outcomes. use case (1).pdf