Preventing Medication Mismanagement in People Living with Dementia through Automated Medication Dispensing with Facial Recognition and Video Observation: an usability study (Preprint)
Notice bibliographique
Résumé
BACKGROUND Medication mismanagement is one of the most prevalent and concerning risk factors for persons living with dementia (PlwD) living at home, contributing to preventable hospitalizations, adverse drug events, and an increased caregiver burden. Each year, over 3 million older U.S. adults are admitted to nursing homes due to medication-related adherence problems. PlwD often manage complex regimens involving multiple medications where errors and challenges in medication consumption are significantly prone. Medication adherence is a critical yet often unmet need in dementia care, with traditional systems like pill bottles and manual tracking proving insufficient. HiDO is an automated, artificial intelligence (AI)-driven, medication dispensing and direct observation platform designed to optimize adherence. The innovative device integrates medication delivery, dose timing, medication synchronization, and a pair of front-facing video cameras to validate the right medications, right route, right time, right dosage to the right patient (5R’s). OBJECTIVE The study objective was to obtain pilot end-user validation through usability testing with the goal of creating an automated, secure, AI-driven medication delivery and observation platform to maximize therapy compliance and health outcomes for PlwDs. METHODS PlwDs with mild cognitive impairment or early-stage dementia (Montreal Cognitive Assessment (MoCA) score of 18 to 24, inclusive) and their caregivers were recruited for in-person usability testing in the Midwest region of the US. After written informed consent was obtained, dyads learned about the HiDO device and watched a demonstration of its set-up and typical usage. Dyads were then asked to complete a series of tasks using the device and to evaluate its ease of use. Subjective feedback was elicited using a semi-structured interview process. It was expected that device setup would take less than 5 minutes, at least 75% of all tasks would be successfully completed, and no more than one non-critical error would occur per dyad. Following usability testing, dyads also completed the System Usability Scale (SUS). RESULTS Fifteen dyads were recruited in the Midwest region of the US. The mean SUS score was 80, suggesting high usability and typically placing the system in the top 10-15% of products evaluated with the scale. Two critical and 13 non-critical errors were experienced. Minor device adjustments could enhance usability further. Themes in qualitative comments regarding usability included: a) Positive Perceptions of Innovation; b) Perceived Usefulness for Polypharmacy; c) Size and Placement Constraints; d) Accessibility and Display Preferences; and e) Need for Setup Guidance and Support Features for Care givers. CONCLUSIONS This usability study provides an understanding of how PlwDs perceived the HiDO device, its utility, and its usability. Most participants found the device usable; those who had minor usability issues suggested corrective design actions. The results are limited by the set of 15 dyads. Further utility, technology effectiveness, and usability testing in a larger cohort and an in-field trial are necessary. CLINICALTRIAL NCT06691256
Récupéré en direct depuis OpenAlex et désinversé. Les résumés ne sont pas conservés dans cette base de données : les index inversés représentent 8,6 Go des 9,3 Go de texte de la base, et le serveur dispose de 13 Go libres.
Comment cette classification a été obtenuedéplier
Prédiction machine sur la base complète
Imitation des enseignantsNi prévalence calibrée, ni vérité terrain. Validation humaine à venir. Le volet Gemma est une étiquette directe du modèle pour chaque travail de la base, lue sur la notice réduite au titre. Le volet Codex est un classifieur appris des 10 348 étiquettes directes de Codex et calibré sur les taux pondérés de l'échantillon; les champs sans appui suffisant ne portent aucun appel Codex. Le mode candidate est l'union des deux volets; le consensus est leur intersection. Ces sorties portent le statut machine_predicted_unvalidated et ne sont pas des étiquettes humaines.
Scores du classifieur distillé par catégorie (deux têtes)
| Catégorie | Codex | Gemma |
|---|---|---|
| Métarecherche | 0,005 | 0,012 |
| Méta-épidémiologie (sens strict) | 0,001 | 0,000 |
| Méta-épidémiologie (sens large) | 0,001 | 0,001 |
| Bibliométrie | 0,000 | 0,000 |
| Études des sciences et des technologies | 0,001 | 0,000 |
| Communication savante | 0,001 | 0,001 |
| Science ouverte | 0,000 | 0,001 |
| Intégrité de la recherche | 0,001 | 0,000 |
| Charge utile insuffisante (le modèle a refusé de juger) | 0,003 | 0,000 |
Scores machine (provisoires)
Les deux têtes enseignantes du modèle étudiant, lues sur ce travail. Un score ordonne la base pour la relecture; il n'affirme jamais une catégorie, et le statut de validation accompagne chaque rangée tel quel.
Scores de référence d'un modèle non mature (critères de maturité non atteints, 7 itérations). Un score ordonne; il n'affirme jamais une catégorie.
score_only:v0-immature-baseline · tel quel depuis la passe de notation : score_only signifie que le nombre peut ordonner les travaux, et qu'aucune étiquette de catégorie n'en découleClassification
machine, non validéePrédiction automatique; un appel candidat d’une seule source (Gemma direct ou Codex distillé), pas un consensus.
Le détail, modèle par modèle et score par score, se trouve en fin de page sous « Comment cette classification a été obtenue ».