Lilian Dindo

Aligning treatment with patients’ self-determined goals and health priorities is challenging in dementia care. Wearable-based remote health monitoring may facilitate determining the active participation of individuals with dementia towards achieving the determined goals. The present study aimed to demonstrate the feasibility of using wearables to assess healthcare goals set by older adults with cognitive impairment. We present four specific cases that assess (1) the feasibility of using wearables to monitor healthcare goals, (2) differences in function after goal-setting visits, and (3) goal achievement. Older veterans (n = 17) with cognitive impairment completed self-report assessments of mobility, then had an audio-recorded encounter with a geriatrician and wore a pendant sensor for 48 h. Follow-up was conducted at 4–6 months. Data obtained by wearables augments self-reported data and assessed function over time. Four patient cases illustrate the utility of combining sensors, self-report, notes from electronic health records, and visit transcripts at baseline and follow-up to assess goal achievement. Using data from multiple sources, we showed that the use of wearable devices could support clinical communication, mainly when patients, clinicians, and caregivers work to align care with the patient’s priorities.

Roughly 40% of persons with HIV (PWH) are not consistently involved in HIV care in the US. Finding out-of-care PWH is difficult, but hospitalization is common and presents an opportunity to re-engage PWH in outpatient care. The aims of this study were to (1) develop an Acceptance and Commitment Therapy (ACT)-based intervention for hospitalized, out-of-care PWH who endorse avoidance-coping to improve HIV treatment engagement; (2) examine the intervention’s initial feasibility and acceptability; and (3) to revise the study protocol (including the intervention), based on stakeholder feedback, in preparation for a randomized controlled trial (RCT) comparing ACT to treatment as usual. Therapists and HIV care experts developed a four-session ACT-based intervention to be delivered during hospitalization. Fifteen hospitalized patients with poorly controlled HIV enrolled in the open trial, eight completed four sessions, two completed three sessions, and seven provided qualitative feedback. Patients universally liked the intervention and the holistic approach to mental health and HIV care. Refinements included repeating key concepts, including representative graphics, and translating to Spanish. Among the patients who attended ≥3 ACT sessions, 5/10 attended a HIV-care follow-up visit and 5/7 who had labs had a viral load <20 2-months post-intervention. Next steps include conducting a randomized clinical trial exploring the impact of the refined intervention to treatment as usual on retention in care and viral load. ClinicalTrials.gov Identifier: NCT04481373.

Background: Patient Priorities Care (PPC) is a model of care that aligns health care recommendations with priorities of older adults who have multiple chronic conditions. Following identification of patient priorities, this information is documented in the patient’s electronic health record (EHR). Objective: Our goal is to develop and validate a natural language processing (NLP) model that reliably documents when clinicians identify patient priorities (ie, values, outcome goals, and care preferences) within the EHR as a measure of PPC adoption. Methods: This is a retrospective analysis of unstructured National Veteran Health Administration EHR free-text notes using an NLP model. The data were sourced from 778 patient notes of 658 patients from encounters with 144 social workers in the primary care setting. Each patient’s free-text clinical note was reviewed by 2 independent reviewers for the presence of PPC language such as priorities, values, and goals. We developed an NLP model that utilized statistical machine learning approaches. The performance of the NLP model in training and validation with 10-fold cross-validation is reported via accuracy, recall, and precision in comparison to the chart review. Results: Of 778 notes, 589 (75.7%) were identified as containing PPC language (kappa=0.82, P<.001). The NLP model in the training stage had an accuracy of 0.98 (95% CI 0.98-0.99), a recall of 0.98 (95% CI 0.98-0.99), and precision of 0.98 (95% CI 0.97-1.00). The NLP model in the validation stage had an accuracy of 0.92 (95% CI 0.90-0.94), recall of 0.84 (95% CI 0.79-0.89), and precision of 0.84 (95% CI 0.77-0.91). In contrast, an approach using simple search terms for PPC only had a precision of 0.757. Conclusions: An automated NLP model can reliably measure with high precision, recall, and accuracy when clinicians document patient priorities as a key step in the adoption of PPC.

We partnered with veteran-serving nonprofits in order to identify distressed rural veterans and provide them with a mental health workshop in community-based settings. Community organizations helped recruit veterans and provided space for 1-day (5-h) Acceptance and Commitment Therapy (ACT) group workshops conducted in rural locations. Qualitative interviews were conducted at 1- and 3-months post-intervention to assess acceptability. Quantitative measures were conducted at baseline, 1- and 3-months post-intervention to measure effectiveness. We successfully engaged community partners throughout every stage of the research and delivered workshops to thirty-one veterans in rural community-based locations. Veterans appreciated the structure, content, and environment of the workshops; most implemented ACT skills into their daily lives and some initiated new treatment following workshop participation. Quantitative measures showed improvements in functioning (Cohen’s d ranging from .27 to .40), reintegration (Cohen’s d = .45), meaning and purpose (Cohen’s d = .40), and reductions in distress (Cohen’s d ranging from .28 to .40) 3-months following workshop participation. Collaborating with rural veteran-serving nonprofit organizations holds promise for engaging hard-to-reach distressed veterans in mental health care.