Truace
Subscribe

Assessing AI Feasibility for Pain Evaluation in Hospitalized Cognitively Impaired Older Adults

Purpose The objectives for this study were to examine the acceptability and feasibility of using the artificial intelligence-driven application PainChek Ⓡ to identify pain within older adults with cognitive impairment in the inpatient setting within Ontario. Design A prospective cohort design was used. Methods Six nurses were recruited and completed standardized training. Following the recruitment and onboarding of nurse participants, 25 patient participants were enrolled and assessed using the application. Once…

By the Truvace desk2 min read1 sourcePeer-reviewedTRV-2026-1342· cite & verify
Assessing AI Feasibility for Pain Evaluation in Hospitalized Cognitively Impaired Older Adults
Construction site tour of the Skilled Nursing Residence, in Edgartown, on the island of Martha's Vineyard, in Dukes County, Maryland on August 5, 2024 - 42 by USDAgov. Public domain

In brief

Researchers in Ontario tested PainChek, an artificial intelligence-driven application, as a way to detect pain in hospitalized older adults who have cognitive impairment. Six nurses completed standardized training and then used the app to assess 25 patients, after which they were interviewed about their experiences.

This matters because pain is hard to evaluate when patients cannot reliably describe it, and the study offers early evidence that a digital tool can fit into nursing practice. However, the sample was small and the authors say feasibility and scalability still need testing in real-world environments, and the study does not report how accurate the app's pain scores were.

Main points

  1. The study used a prospective cohort design in an inpatient setting in Ontario.
  2. Six nurses were trained and 25 patients were enrolled and assessed with the app.
  3. Among participants, 64% had dementia, 20% had cognitive impairment, and 16% had delirium.
  4. Average length of stay in the study was 7.8 days, and average pain scores were in the mild range.
  5. Nurse interviews were analyzed with descriptive content analysis and validated through member checking.

The gain

In a small Ontario inpatient study, nurses found an AI-driven pain assessment app acceptable and feasible for identifying pain in older adults with delirium, cognitive impairment, or dementia.

The rundown

The research team recruited six nurses, gave them standardized training, and then enrolled 25 patients who were assessed using the PainChek application. Qualitative interviews with the nurses followed once patient data collection was finished.

Descriptive statistics were used for patient and nurse data. The cohort comprised mostly patients with dementia, with smaller groups with cognitive impairment and delirium, and pain scores averaged in the mild range during assessment.

Nurses' accounts were coded thematically using the nursing metaparadigm as the conceptual framework, and results were checked through member checking. The authors conclude the tool is acceptable and feasible in this hospital setting.

Sources

  1. Peer-reviewedPain Management Nursing2026-10-03

The debate