Can an AI-based virtual voice assistant help in the effective follow-up of TAVI patients?
30 Aug 2024
In the face of an increasing elderly population and the number of those living with chronic pathologies, artificial intelligence (AI) may provide an effective alternative to the classic face-to-face consultation model, being acceptable to patients and optimising limited healthcare resources.
An example of this is provided by Doctor Marta Herrero Brocal (Dr. Balmis General University Hospital of Alicante - Alicante, Spain) who today presents results from the prospective, observational TeleTAVI study looking at the application of a virtual voice assistant – LOLA – to monitor patients after TAVI implantation. Based on AI and natural language processing, LOLA carried out telephone follow-ups during weeks 1 and 2, and months 1, 3 and 12, using a series of questions related mainly to vascular access and the patient’s cardiovascular situation. Information collected during the calls was uploaded to a web platform, where it was analysed by the care team and used to determine the need for intervention.
Telephone follow-up using LOLA was offered to all patients receiving TAVI in the unit during 2023 and who had no language barrier to its use. Altogether, 274 patients were included in the study, with only 6 patients expressing a preference not to use the system. A total of 1,039 calls were made, with an average call duration of 4 minutes and 3 seconds, resulting in around 385 hours of autonomous conversation. The vast majority of calls (94%) were completed (percentage of answered calls in which all questions were answered) and the degree of adherence remained above 85% throughout the follow-up period (percentage of answered calls). In most cases, 89%, the call was answered by the patient.
No alerts were detected in 44% of calls. Among the remainder, there were 926 alerts resulting in at least one intervention in 57% of the calls (593 interventions in total). The number of alerts decreased as follow-up increased, highlighting the early stages of post-TAVI implantation follow-up as the key time for implementing LOLA.
The virtual voice assistant also facilitated rapid patient discharge. Knowing that automated close follow-up was available, 40.1% of patients were able to be discharged within 24 hours of the procedure and 32.9% between 24 and 48 hours.
The patients generally had a favourable response to the system. The customer satisfaction score was 4.68/5 and 89% of patients reported good or very good satisfaction, with 86% of patients saying that they would recommend the use of LOLA.
Doctor Herrero Brocal concludes, “The TeleTAVI study found that follow-up with the virtual voice assistant enables safe and early discharge after TAVI, with a low complication rate and without increasing the burden on healthcare resources. Patients know that behind ‘LOLA’ is a doctor or a nurse, so they are very happy to speak to it, as reflected in our high patient satisfaction rates.”
Do you think it would be feasible to incorporate voice technology into your clinical work? For follow-up or for other purposes? Join the discussion today!
