JMIR Publications

ABSTRACT

Background:

To reduce the risk of stroke in patients with AF, strict control of the OAT is required. AI-based virtual assistants are proving their usefulness in the monitoring of chronic patients

Objective:

In this context, we have launched a pilot study with the aim of evaluating the use of a virtual assistant called LOLATAO, in the follow-up of patients with AF and OAT in our Digital Haemostasis and Thrombosis Unit.

Methods:

From January to December 2023, we have conducted a prospective observational study of patients with AF and TAO. LOLA, a virtual assistant (software as a medical device – SaMD, Tucuvi) based on AI was used. Patients were selected consecutively according to inclusion criteria. Demographic and clinical-biological data were collected through clinical interviews. All patients received a first contact call and then monthly calls, following a predefined protocol. The study was approved by the CEIM. The responses that should be generated by different types of interventions by the haematologists were established. At the end of the study, a satisfaction questionnaire was carried out on the participating patients

Results:

Fifty patients were included. The mean age was 75 years with 33% women. One-third of the patients (n=16) were with VKAs and two-thirds (33) with DOACs. A total of 579 calls were made with a median follow-up of 278 days. LOLA had high rates of acceptability (85%), adherence (90%) and satisfaction (>95%). The clinical problems detected during follow-up. It was detected that 42% (21) of the patients reported at least one forgetfulness in taking the OAT in the last month, with the most frequent being 1 or 2 doses (34%). 39% (n=19) of the patients reported having had at least one bleeding episode in the last month. All bleeding was mild and none was related to TAO. It should be noted that up to 31% (n=15) of patients reported having presented symptoms of stroke in the last month. However, after conducting a medical interview, it was found that they did not meet the criteria for stroke. 18% (9) of the patients reported having a scheduled intervention and requested an appointment to perform bridging therapy. In patients with VKAs (n=16), 94% (n=15) reported at least once being unaware of their TRT and, after performing an educational intervention, 75% (n=12) of patients reported having a TRT<65%. Those patients in whom TRT was confirmed<65% (9) were switched to DOACs. In patients with DOACs (n=33), in no case did the dose of OAT had to be adjusted. LOLA saved a total of 111h (10 hours per month) for the medical team in the follow-up of patients with AF and OAT.

Conclusions:

The results of the study suggest that LOLATAO seems to be a tool to help in the management of chronic follow-up of patients with AF and OAT that reduces the burden of care with high rates of acceptance and satisfaction by patients. In addition, it allows the identification of relevant clinical situations that require medical interventions and highlights the lack of knowledge of patients of their pathology and the need to improve their education for greater empowerment. Clinical Trial: Not applicable