Abstract Introduction The number of procedures and patients candidates for transcatheter aortic valve implantation (TAVI) has increased considerably due to population ageing and the rise in scientific evidence supporting this technique in patients with increasingly lower surgical risk. Early discharge would allow for a more efficient use of available resources, in addition to improving patients’ functionality and quality of life. Objective The use of a virtual voice assistant based on artificial intelligence, could be an effective and safe alternative to closely monitor patients after TAVI implantation in order to facilitate early identification of complications and a more efficient use of the resources available in Cardiology services. Material and methods Observational, prospective, single-center and consecutive study of the implementation of a technology based on artificial intelligence and natural language processing to monitor all patients undergoing transfemoral TAVI implantation, according to usual clinical practice, in the hemodynamics unit of our hospital in the year 2023. The virtual voice assistant, "Lola", carries out a telephonic follow-up during week 1, week 2, month 1, month 3 and 12. In these calls, it asks a series of questions mainly related to vascular access and with the patient's cardiovascular situation. After finishing the call, all the information collected is uploaded to a web platform where we monitor the collected data and thus take the appropriate measures. Results After 12 months, 274 patients have been included to whom 1,039 calls have been made with a total of 385 hours of autonomous conversation. In 44% of the calls, no alerts were detected and, therefore, did not required further review. From the remaining calls, a total of 926 alerts were collected, the predominant ones being: dizziness (24.9%), contact with the emergency services (11.3%) and alteration of general status (10.4%). The number of alerts decreases as the follow-up progresses, reflecting the need for closer monitoring in the initial stages after implantation. These alerts generated at least one intervention in 57% of the calls, the predominant ones being: medical contact (43.0%), nursing contact (26.3%) and medication adjustment (4.0%). These calls resulted in a total of 15 in-person examinations (5.4% of patients), detecting in 2 of them a 3rd degree atrioventricular block, in 3 a femoral pseudoaneurysm and in 1 a critical stenosis of the common femoral artery. According to a patient survey, 88.9% of patients were satisfied or very satisfied (Customer Satisfaction score 4.68/5). Conclusions The application of artificial intelligence permits strict control of the patient after TAVI implantation, thus facilitating early detection of complications. Patient satisfaction regarding this follow-up system was very high.
Read full abstract