Artificial Intelligence (AI), Dementia, Palliative Care
Conditions
Brief summary
This study aims to evaluate the effectiveness of an artificial intelligence (AI)-based software in personalizing high-quality end-of-life care for elderly patients. As the elderly population grows, providing tailored and quality care during the final stages of life becomes increasingly important. This AI software continuously monitors vital signs and behaviors through wearable sensors, offers smart medication reminders, alerts the care team to potential risks, and provides personalized care plans along with psychological and social support. The study is designed as a randomized controlled trial comparing two groups: one receiving standard end-of-life care and the other using the AI software. Key outcomes include improving quality of life, reducing adverse events like falls and emergency hospitalizations, increasing patient and family satisfaction, improving medication management, and reducing caregiver burden. Data will be collected over six months to assess these effects. The results will help determine whether AI technology can enhance end-of-life care for seniors and support families and healthcare providers.
Detailed description
This section provides a comprehensive overview of the study design, objectives, population, interventions, and methods without repeating information already included in other sections of the record. It elaborates on the rationale for using AI-based software to personalize end-of-life care for elderly patients, details the randomized controlled trial setup, explains inclusion and exclusion criteria, intervention specifics, outcome measures, data collection methods, and planned statistical analyses. This description ensures a clear understanding of the study's scope and methodology.
Interventions
BEHAVIORALAI-based Software for Personalized End-of-Life Care
This intervention involves the use of an AI-powered software system designed to personalize end-of-life care for elderly patients. The software continuously monitors vital signs and behavior through wearable sensors, sends smart medication reminders, issues preventive alerts to care providers, delivers customized care plans, and provides psychological and social support through communication features.
Sponsors
Baqiyatallah Medical Sciences University
Study design
Allocation
RANDOMIZED
Intervention model
PARALLEL
Primary purpose
PREVENTION
Masking
SINGLE (Outcomes Assessor)
Intervention model description
Participants will be randomly assigned to one of two parallel groups: an intervention group receiving AI-based palliative care through a personalized software system, and a control group receiving standard end-of-life care without the AI intervention. Randomization will be conducted using block randomization to ensure balance in baseline characteristics. Although the study is open-label, outcome assessors will be blinded to group assignments to minimize assessment bias.
Eligibility
Sex/Gender
ALL
Age
60 Years to No maximum
Healthy volunteers
No
Inclusion criteria
Age ≥ 60 years Clinical diagnosis of being in the end-of-life stage, based on criteria such as the Karnofsky Performance Scale or Palliative Performance Scale Informed consent obtained from the participant or legal representative Ability to use technology independently or with support provided by the research team Access to necessary equipment for the intervention (e.g., wearable sensors, smartphone/tablet)
Exclusion criteria
Presence of severe cognitive impairment preventing software use Voluntary withdrawal from the study at any stage Critical medical deterioration or death during the study Poor adherence or insufficient engagement with the intervention software in the intervention group
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Change in Quality of Life Score | Up to 3 months after intervention start | Assessed using a validated instrument such as the Quality of Life at the End of Life (QUAL-E) scale to measure overall well-being, comfort, and satisfaction with care during end-of-life. |
Outcome results
None listed