This multicenter cluster-randomized study evaluates the impact of an artificial intelligence (AI) tool on the satisfaction of healthcare professionals and patients in outpatient consultations, measuring its effect on perceived satisfaction (through a visual analog scale), the duration of consultations, and the quality and quantity of clinical data recorded. Adult patients (18-80 years) seen in outpatient centers will participate, comparing those using the AI tool with centers following the usual procedure. The tool is expected to reduce the administrative burden, improve user satisfaction and increase the efficiency and quality of the clinical registry. Recruitment will take place between December 2024 and May 2025, with final analysis planned for the end of 2025.
This multicenter cluster-randomized study aims to evaluate the impact of an artificial intelligence (AI) tool designed to optimize real-time clinical registration during outpatient consultations. Its effect on patient and healthcare professional satisfaction will be analyzed, measured using a visual analog scale (VAS) and validated tools such as the Patient Experience Questionnaire (PEQ) and the Net Promoter Score (NPS). In addition, the duration of consultations and the quantity and quality of clinical data recorded in the intervention and control groups will be compared. The intervention group will use the AI tool, while the control group will continue with the usual recording without AI. Participants will be adult patients (18-80 years) seen in health centers linked to the study, recruited by prior informed consent. AI is expected to reduce the administrative burden on professionals, allowing them to devote more time to direct care, improving both the quality of the clinical record and the patient experience. Recruitment will take place between December 2024 and May 2025, and will follow the ethical guidelines set out in the Declaration of Helsinki. This project seeks to provide evidence on the implementation of AI-based technologies in the outpatient setting and their impact on the quality of healthcare.
Study Type
INTERVENTIONAL
Allocation
RANDOMIZED
Purpose
HEALTH_SERVICES_RESEARCH
Masking
TRIPLE
Enrollment
148
The intervention in this study consists of the implementation of an artificial intelligence tool for clinical registration during outpatient consultations. This technology facilitates the documentation of interactions in real time, optimizing the workflow of professionals and enabling more patient-centered care.
ACES Centers
Barcelona, Catalonia, Spain
RECRUITINGCSEU La Salle - UAM
Madrid, Spain
NOT_YET_RECRUITINGSatisfaction with the consultation
measured using a 10 cm Visual Analog Scale (VAS) of satisfaction, which assesses the degree of satisfaction perceived by patients and health professionals. From no satisfaction in the left side to Completely satisfied in the right side.
Time frame: From enrrolment to the end of the consultation the same day.
Duration of the consultation
Total time of the consultation, measured manually from the time of entry to the time of departure of the patient.
Time frame: From enrrolment to the end of the consultation the same day.
Number of clinical data recorded
Total number of words documented in the clinical history generated during the consultation, excluding headings
Time frame: From enrrolment to the end of the consultation the same day.
Patient Experience (Patient Expectation Questionnaire - PEQ)
Assessment of selected domains of the Patient Expectation Questionnaire (Health Service Process and Professional-Patient Communication). Format: 5-point Likert scale.
Time frame: at the begining and at the end of the consultation
Likelihood of recommendation (Net Promoter Score - NPS)
Patient's assessment of the likelihood of recommending the service received. Range: 0 (very unlikely) to 10 (very likely).
Time frame: From enrrolment to the end of the consultation the same day.
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.