Military Servicemembers and Veterans are at elevated risk for suicide, but rarely self-identify to their leaders or clinicians regarding their experience of suicidal thoughts. We developed an algorithm to identify posts containing suicide-related content on a military-specific social media platform.

Publicly-shared social media posts (n = 8449) from a military-specific social media platform were reviewed and labeled by our team for the presence/absence of suicidal thoughts and behaviors and used to train several machine learning models to identify such posts.

The best performing model was a deep learning (RoBERTa) model that incorporated post text and metadata and detected the presence of suicidal posts with relatively high sensitivity (0.85), specificity (0.96), precision (0.64), F1 score (0.73), and an area under the precision-recall curve of 0.84. Compared to non-suicidal posts, suicidal posts were more likely to contain explicit mentions of suicide, descriptions of risk factors (e.g. depression, PTSD) and help-seeking, and first-person singular pronouns.

Our results demonstrate the feasibility and potential promise of using social media posts to identify at-risk Servicemembers and Veterans. Future work will use this approach to deliver targeted interventions to social media users at risk for suicide.

The Interdisciplinary Home-bAsed Reablement Program (I-HARP) integrates evidence-based rehabilitation strategies into a dementia-specific person-centred, time-limited, home-based, interdisciplinary rehabilitation package. I-HARP was a 4-month model of care, incorporated into community aged care services and hospital-based community geriatric services. I-HARP involved: 8-10 individually tailored home visits by occupational therapist and registered nurse; 2-4 optional other allied health sessions; up to A$1,000 minor home modifications and/or assistive devices; and three individual carer support sessions. The aim of the study was to determine the effectiveness of I-HARP on the health and wellbeing of people living with dementia and their family carers.

A multi-centre pragmatic parallel-arm randomised controlled trial compared I-HARP to usual care in community-dwelling people with mild to moderate dementia and family carers in Sydney, Australia (2018-22). Assessments of the client’s daily activities, mobility and health-related quality of life, caregiver burden and quality of life were conducted at baseline, 4- and 12-month follow-up. Changes from baseline were compared between groups.

Of 260 recruited, 232 (116 dyads of clients and their carers, 58 dyads per group) completed the trial to 4-month follow-up (89% retention). Clients were: aged 60-97 years, 63% female, 57% with mild dementia and 43% with moderate dementia. The I-HARP group had somewhat better mean results for most outcome measures than usual care at both 4 and 12 months, but the only statistically significant difference was a reduction in home environment hazards at 4 months (reduction: 2.29 on Home Safety Self-Assessment Tool, 95% CI: 0.52, 4.08; p=.01, effect size [ES] 0.53). Post-hoc sub-group analysis of 66 clients with mild dementia found significantly better functional independence in the intervention group: 11.2 on Disability Assessment for Dementia (95% CI: 3.4, 19.1; p=.005; ES 0.69) at 4 months and 13.7 (95% CI: 3.7, 23.7; p=.007; ES 0.69) at 12 months.

The I-HARP model enhanced functional independence of people with mild dementia only but not significantly in people with moderate dementia, so did not result in better outcomes in the group overall. A different type of rehabilitation model or strategies may be required as dementia becomes more severe.

Research exploring the longitudinal course of posttraumatic stress disorder (PTSD) symptoms has documented four modal trajectories (low, remitting, high, and delayed), with proportions varying across studies. Heterogeneity could be due to differences in trauma types and patient demographic characteristics.

This analysis pooled data from six longitudinal studies of adult survivors of civilian-related injuries admitted to general hospital emergency departments (EDs) in six countries (pooled N = 3083). Each study included at least three assessments of the clinician-administered PTSD scale in the first post-trauma year. Latent class growth analysis determined the proportion of participants exhibiting various PTSD symptom trajectories within and across the datasets. Multinomial logistic regression analyses examined demographic characteristics, type of event leading to the injury, and trauma history as predictors of trajectories differentiated by their initial severity and course.

Five trajectories were found across the datasets: Low (64.5%), Remitting (16.9%), Moderate (6.7%), High (6.5%), and Delayed (5.5%). Female gender, non-white race, prior interpersonal trauma, and assaultive injuries were associated with increased risk for initial PTSD reactions. Female gender and assaultive injuries were associated with risk for membership in the Delayed (v. Low) trajectory, and lower education, prior interpersonal trauma, and assaultive injuries with risk for membership in the High (v. Remitting) trajectory.

The results suggest that over 30% of civilian-related injury survivors admitted to EDs experience moderate-to-high levels of PTSD symptoms within the first post-trauma year, with those reporting assaultive violence at increased risk of both immediate and longer-term symptoms.

The vision for dementia-friendly communities is challenged by limited public awareness and stigma about dementia. The study aim was to elicit stakeholder priorities for the message content of an education program to improve dementia awareness among youth; specifically, what do children need to know about dementia?

A qualitative inquiry using interviews and focus groups was used. Purposive sampling achieved maximum variation in dementia experience and participant characteristics. Focus groups with Scouts in the community aged 9–12 years old (n = 22) used innovative techniques to explore children's attitudes towards people with dementia. Participants with personal experience of dementia were five people with early-stage dementia; 12 adult primary carers; four non-primary carers; and six grandchildren of a person with dementia. They were asked what is important for children to understand about dementia and what attitudes they may like an education program to confer. Content analysis was performed using NVivo10.

Strong themes to emerge were that children need to know the whole truth about dementia; that individuals with dementia are “still people,” that it is “not the fault” of the person with dementia; and that dementia is different and typically unpredictable for everyone. Discussions also indicated a need to educate children about ways to relate to a person with dementia, and to appreciate “positives” within a relationship.

Children are our future citizens. Developing an education program for children with this message content may be fundamental to de-stigmatizing dementia and laying the foundation to dementia-friendly communities.