[Reminiscence program supported by artificial intelligence and based on intangible cultural heritage aimed at the elderly: A pilot study]. / Programa de reminiscencia apoyado en inteligencia artificial y basado en el patrimonio cultural inmaterial dirigido a personas mayores: un estudio piloto.

INTRODUCTION: Technological applications are an innovative way of providing reminiscence therapy and must meet the users' needs. Intangible cultural heritage as a basis for such therapy has not been explored yet. We evaluated the applicability of a new technological application supported by artificial intelligence for reminiscence therapy based on intangible cultural heritage aimed at older people. MATERIAL AND METHODS: A prospective observational study was carried out with people aged 65 or over, without cognitive impairment and with mild and moderate cognitive impairment who attended six centers for older people in Spain and Portugal. Participants tested the first prototype of the individualized LONG-REMI program in four consecutive weekly sessions. The usability and satisfaction of the experience were evaluated using the VAS scale at the end of the intervention. Emotions were evaluated using the PANAS scale before and at the end of the intervention. RESULTS: Data from 56 participants were analysed. For all participants, usability and satisfaction were highly perceived, with scores of 7.75±1.88 and 8.38±1.57, respectively. The positive affect subscale PANAS showed significant changes (28.86±8.88 before the intervention versus 36.70±9.43 post intervention, Z = -4.18, P = 0.000). There were no significant changes in the PANAS negative affect subscale. CONCLUSIONS: The first prototype of the LONG-REMI technological application can be used by older people both with and without cognitive impairment. This has the potential to be an instrument for future cognitive therapies with stimulating activities and benefits for emotions.

Radiomics-Based Assessment of OCT Angiography Images for Diabetic Retinopathy Diagnosis.

Purpose: To evaluate the diagnostic accuracy of machine learning (ML) techniques applied to radiomic features extracted from OCT and OCT angiography (OCTA) images for diabetes mellitus (DM), diabetic retinopathy (DR), and referable DR (R-DR) diagnosis. Design: Cross-sectional analysis of a retinal image dataset from a previous prospective OCTA study (ClinicalTrials.govNCT03422965). Participants: Patients with type 1 DM and controls included in the progenitor study. Methods: Radiomic features were extracted from fundus retinographies, OCT, and OCTA images in each study eye. Logistic regression, linear discriminant analysis, support vector classifier (SVC)-linear, SVC-radial basis function, and random forest models were created to evaluate their diagnostic accuracy for DM, DR, and R-DR diagnosis in all image types. Main Outcome Measures: Area under the receiver operating characteristic curve (AUC) mean and standard deviation for each ML model and each individual and combined image types. Results: A dataset of 726 eyes (439 individuals) were included. For DM diagnosis, the greatest AUC was observed for OCT (0.82, 0.03). For DR detection, the greatest AUC was observed for OCTA (0.77, 0.03), especially in the 3 × 3 mm superficial capillary plexus OCTA scan (0.76, 0.04). For R-DR diagnosis, the greatest AUC was observed for OCTA (0.87, 0.12) and the deep capillary plexus OCTA scan (0.86, 0.08). The addition of clinical variables (age, sex, etc.) improved most models AUC for DM, DR and R-DR diagnosis. The performance of the models was similar in unilateral and bilateral eyes image datasets. Conclusions: Radiomics extracted from OCT and OCTA images allow identification of patients with DM, DR, and R-DR using standard ML classifiers. OCT was the best test for DM diagnosis, OCTA for DR and R-DR diagnosis and the addition of clinical variables improved most models. This pioneer study demonstrates that radiomics-based ML techniques applied to OCT and OCTA images may be an option for DR screening in patients with type 1 DM. Financial Disclosures: Proprietary or commercial disclosure may be found after the references.

LONG-REMI: An AI-Based Technological Application to Promote Healthy Mental Longevity Grounded in Reminiscence Therapy.

Reminiscence therapy (RT) consists of thinking about one's own experiences through the presentation of memory-facilitating stimuli, and it has as its fundamental axis the activation of emotions. An innovative way of offering RT involves the use of technology-assisted applications, which must also satisfy the needs of the user. This study aimed to develop an AI-based computer application that recreates RT in a personalized way, meeting the characteristics of RT guided by a therapist or a caregiver. The material guiding RT focuses on intangible cultural heritage. The application incorporates facial expression analysis and reinforcement learning techniques, with the aim of identifying the user's emotions and, with them, guiding the computer system that emulates RT dynamically and in real time. A pilot study was carried out at five senior centers in Barcelona and Portugal. The results obtained are very positive, showing high user satisfaction. Moreover, the results indicate that the high frequency of positive emotions increased in the participants at the end of the intervention, while the low frequencies of negative emotions were maintained at the end of the intervention.