Growdon ME, Harrison KL, Steinman MA
… +5 more, Hunt LJ, Stone RI, Tran T, Johnson JK, Portacolone E
JAMA Intern Med
· 2026 May · PMID 42189533
·
Publisher ↗
IMPORTANCE: More than one-fourth of older individuals in the US with cognitive impairment live alone. These individuals often lack support for medication management and face a high risk of medication-related harm. OBJECT...IMPORTANCE: More than one-fourth of older individuals in the US with cognitive impairment live alone. These individuals often lack support for medication management and face a high risk of medication-related harm. OBJECTIVE: To elucidate barriers and facilitators to medication management experienced by older adults living alone with cognitive impairment and their social contacts. DESIGN, SETTING, AND PARTICIPANTS: This qualitative study was conducted between May 2016 and February 2024 among adults of diverse racial and ethnic backgrounds aged 55 years or older living alone with cognitive impairment in California, Louisiana, and Michigan (ie, participants), along with their social contacts, defined as family members or other familiar persons. Data were analyzed between February 2024 and March 2025. MAIN OUTCOMES AND MEASURES: As part of the Living Alone With Cognitive Impairment Project, participants' and social contacts' perspectives regarding barriers and facilitators were elicited via semistructured interviews conducted in English, Spanish, Cantonese, or Mandarin. Participants were interviewed a mean of 4 times (486 interviews total), mostly in their homes. Combined inductive and deductive thematic analysis was used to examine discussions specific to medication management. RESULTS: A total of 116 older adults living alone with cognitive impairment (median [range] age, 74 [57-103] years; 86 females [74.1%]) and 54 social contacts (median [range] age, 59 [29-89] years; 44 females [81.5%]) were interviewed. At an individual level, barriers to medication management included a lack of reminders to take medications due to a lack of cohabitants, fear of experiencing adverse effects while alone, and stress related to managing complex medication regimens with inadequate support. At an interpersonal level, barriers included difficulty in verifying medication behaviors without cohabitants, distrust of health care professionals related to a desire to maintain independence, and communication barriers. At a system level, barriers included difficulty navigating health system logistics without advocates. Participants received crucial but intermittent support with medication management from noncohabiting social contacts. Both groups suggested potential solutions to barriers, but they nevertheless conveyed a sense of precarity related to medication management. CONCLUSIONS AND RELEVANCE: This qualitative study involving racially and ethnically diverse participants from 3 states highlights the substantial barriers older adults living alone with cognitive impairment experience in managing their medications. Identification of cognitive impairment in older adults who live alone should spur targeted efforts to overcome medication-related challenges. In addition, more home- and community-based services are needed to provide medication management support to individuals living alone with cognitive impairment.
Desai N, Majhail N, Dredze M
… +8 more, Hogarth M, Smith D, Callaway C, Dezfulian C, Padman R, Kochanek PM, Ayers JW, Horvat CM
JAMA Intern Med
· 2026 May · PMID 42149572
·
Full text
IMPORTANCE: High-quality, timely cardiopulmonary resuscitation (CPR) after out-of-hospital cardiac arrest (OHCA) is vital, but bystanders need help to act. Telecommunicator-CPR by 911 dispatchers promotes bystander CPR b...IMPORTANCE: High-quality, timely cardiopulmonary resuscitation (CPR) after out-of-hospital cardiac arrest (OHCA) is vital, but bystanders need help to act. Telecommunicator-CPR by 911 dispatchers promotes bystander CPR but may be limited by inherent variability and delays in human-led systems. OBJECTIVE: To evaluate the performance of widely available artificial intelligence (AI) models in delivering guideline-concordant CPR instruction and to develop and assess ChatCPR, a purpose-built AI CPR instructor agent in an early proof-of-concept study design. DESIGN, SETTING, AND PARTICIPANTS: In this cross-sectional study, simulated emergency scenarios were used to evaluate baseline CPR instructing capabilities of widely available AI models (ChatGPT, Claude, Gemini, Grok, Llama, and Mistral). Models were evaluated for their adherence to minimally viable criteria, which included instructions like performing appropriate-depth chest compressions, and maximally effective criteria, which included more nuanced instructions like ensuring that compressions achieved full recoil, all derived from major association CPR guidelines. These insights informed development of the purpose-built AI CPR instructor agent that was subsequently evaluated using standard test-retest methods across the same simulated scenarios and 911 dispatcher-assisted calls where CPR was indicated. Data were analyzed from April through December 2025. RESULTS: In simulated OHCA scenarios among 6 widely available AI models, the models achieved 89.7% (95% CI, 84.8%-93.2%) of minimally viable criteria, ranging from 79.4% (95% CI, 63.2%-89.7%) for Gemini to 97.1% (95% CI, 85.1%-99.5%) for Grok and Claude. Models achieved a mean of 69.8% (95% CI, 65.5%-73.7%) of maximally effective criteria, ranging from 61.3% (95% CI, 50.3%-71.2%) for Llama to 75.0% (95% CI, 64.5%-83.2%) for GPT-4o. The instructor agent achieved 100% (95% CI, 89.8%-100%) and 100% (95% CI, 95.4%-100%) adherence to minimally viable and maximally effective criteria, respectively, for the same scenarios. In a retest using 911 calls, the agent achieved 100% (95% CI, 88.6%-100%) adherence to minimally viable and 98.9% (95% CI, 94.0%-99.8%) adherence to maximally effective criteria, representing absolute improvements of 15.5 percentage points (95% CI, 2.1-27.4 percentage points; P = .02) and 36.1 percentage points (95% CI, 27.2-44.3 percentage points; P < .001) over dispatchers (84.5%; 95% CI, 73.1%-91.6% and 62.8%; 95% CI, 55.0%-70.0%, respectively). CONCLUSIONS AND RELEVANCE: These findings suggest that AI-enabled CPR instruction shows promise for supporting bystanders. Further validation in diverse, general population settings is warranted to define the role of AI-based CPR instruction as a scalable public health intervention for OHCAs.