Analyzing Topics and Sentiments from Twitter to Gain Insights to Refine Interventions for Family Caregivers of Persons with Alzheimer's Disease and Related Dementias (ADRD) During COVID-19 Pandemic

Using Natural Language Processing on Expert Panel Discussions to Gain Insights for Recruitment, Retention and Intervention Adherence for Online Social Support Interventions on a Stage II-III Clinical Trial Among Hispanic and African American Dementia Caregivers

We applied natural language processing (NLP) to a corpus extracted from 4 hours of expert panel discussion transcripts to determine the sustainability of a Stage II-III clinical trial of online social support interventions for Hispanic and African American dementia caregivers. Prominent topics included Technology/hard to reach populations, Training younger populations, Building trust, Privacy and security issues, Simplification of screening questions and recruitment procedures, Understanding participants' needs, Planning strategies and logistics, Potential recruitment places, Adjusting intervention size downwards to engage elderly participants, Targeting different generations, Internet-based interventions by age range, and Providing step-by-step instructions and an overview of the entire research process during recruitment. The application of NLP to qualitative data on a dementia caregiving clinical trial provides useful insights for recruitment, retention, and adherence to guidelines for such interventions serving Hispanic and African American dementia caregivers.

Understanding stigma of dementia during COVID-19: a scoping review

Introduction

Stigma of dementia is one of the greatest challenges for people living with dementia. However, there is little research on the different types of stigma of dementia in the COVID-19 pandemic. The purpose of this scoping review is to synthesize the existing literature on dementia-related stigma (self, public, and structural stigma), during the pandemic.

Methods

Guided by Arksey and O'Malley's scoping review framework and PRISMA guidelines, CINAHL, EMBASE, Google Scholar, Medline, PsycINFO, and Web of Science were searched for English language literature from January 2020 to June 2023. Inclusion criteria consisted of peer-reviewed, original research articles addressing stigma of dementia during the COVID-19 pandemic. Thematic analysis was used to analyze the data and steps were taken to ensure rigor.

Results

Fifteen articles met our inclusion criteria. Four primary themes were identified including: 1) COVID-19 stereotypes and assumptions of dementia; 2) human rights issues and deprived dignity; 3) disparate access to health services and supports; and 4) cultural inequities and distrust.

Discussion

The COVID-19 pandemic has contributed to the stigmatization of people living with dementia. Further research is needed to develop, implement, and evaluate interventions targeted towards the different types of dementia-related stigma (including self, public, and structural stigma). Moreover, our findings highlight the need for more collaborative research that prioritizes the lived experience and input of diverse people living with dementia. Research partnerships with diverse people living with dementia are vital to improving future pandemic planning. Only through evidence-informed research and lived experience can we begin to fully address the different types of dementia-related stigma and enhance the quality of life of people living with dementia.

Building community engagement with caregivers through online interaction and a salutogenic approach in a period of isolation

Background

Informal caregivers are essential figures that deal with the effects of dependence in the elderly. However, they suffer from poorer health-related quality of life, particularly regarding mental health. Social support is crucial, but this was suspended or dramatically reduced during the Covid-19 pandemic. Salutogenesis theory explores the contributing factors for the promotion and maintenance of health. Considering all these, we offered caregivers the opportunity to join a participatory project aimed at creating communication spaces where they could share experiences, think together about potential solutions, and explore which salutogenic actions they used in their daily basis and how they had changed during Covid-19 restrictions.

Methods

We used a qualitative methodology with a socio-constructivist and phenomenological approach and purposive sampling. We organized two focus groups consisting of online semi-structured discussions with seven participants in total. Conversations were videotaped and transcribed and we conducted content thematic analyses using the NVivo software.

Results

Caregiving in our setting are primarily women with high levels of education that do not always feel comfortable with this load because it interferes with their personal and professional lives. The pandemic increased caregivers feelings of loneliness, resignation, and burden, directly affecting their mental health. Furthermore, the disappearance of prevention programs and the difficulties to access healthcare services produced negative consequences on the already fragile elderly and their family caregivers.

Conclusion

The pandemic and its restrictions exacerbated the problematics affecting informal caregivers. Although these people are aware of their situation and have valued knowledge of how to improve their health, they cannot always put it into practice. We call policymakers to reframe interventions aimed at caregivers by introducing the voice of the community in the planning and to rethink the management of vulnerable people and their carers in other potential health crises.

Automatically Identifying Twitter Users for Interventions to Support Dementia Family Caregivers: Annotated Data Set and Benchmark Classification Models

BACKGROUND

More than 6 million people in the United States have Alzheimer disease and related dementias, receiving help from more than 11 million family or other informal caregivers. A range of traditional interventions has been developed to support family caregivers; however, most of them have not been implemented in practice and remain largely inaccessible. While recent studies have shown that family caregivers of people with dementia use Twitter to discuss their experiences, methods have not been developed to enable the use of Twitter for interventions.

OBJECTIVE

The objective of this study is to develop an annotated data set and benchmark classification models for automatically identifying a cohort of Twitter users who have a family member with dementia.

METHODS

Between May 4 and May 20, 2021, we collected 10,733 tweets, posted by 8846 users, that mention a dementia-related keyword, a linguistic marker that potentially indicates a diagnosis, and a select familial relationship. Three annotators annotated 1 random tweet per user to distinguish those that indicate having a family member with dementia from those that do not. Interannotator agreement was 0.82 (Fleiss kappa). We used the annotated tweets to train and evaluate support vector machine and deep neural network classifiers. To assess the scalability of our approach, we then deployed automatic classification on unlabeled tweets that were continuously collected between May 4, 2021, and March 9, 2022.

RESULTS

A deep neural network classifier based on a BERT (bidirectional encoder representations from transformers) model pretrained on tweets achieved the highest F1-score of 0.962 (precision=0.946 and recall=0.979) for the class of tweets indicating that the user has a family member with dementia. The classifier detected 128,838 tweets that indicate having a family member with dementia, posted by 74,290 users between May 4, 2021, and March 9, 2022-that is, approximately 7500 users per month.

CONCLUSIONS

Our annotated data set can be used to automatically identify Twitter users who have a family member with dementia, enabling the use of Twitter on a large scale to not only explore family caregivers' experiences but also directly target interventions at these users.

The Impact of the SARS-CoV-2 Pandemic on the Needs of Non-Infected Patients and Their Families in Palliative Care—Interviews with Those Concerned

During humanitarian crises, such as a pandemic, healthcare systems worldwide face unknown challenges. This study aimed to explore and describe the effect of the SARS-CoV-2 pandemic on the needs of non-infected patients and family caregivers in specialist palliative care, using qualitative, semi-structured interviews. Data were analyzed using inductive content analysis, following the framework approach. Thirty-one interviews were conducted with patients/family caregivers (15/16) in palliative care units/specialist palliative home care (21/10) from June 2020 to January 2021. Well-known needs of patients and family caregivers at the end of life remained during the pandemic. Pandemic- dependent themes were (1) implications of the risk of contagion, (2) impact of the restriction of social interactions, (3) effects on the delivery of healthcare, and (4) changes in the relative’s role as family caregiver. Restriction on visits limited family caregivers’ ability to be present in palliative care units. In specialist palliative home care, family caregivers were concerned about the balance between preserving social contacts at the end of life and preventing infection. Specialist palliative care during a pandemic needs to meet both the well-known needs at the end of life and additional needs in the pandemic context. In particular, attention should be given to the needs and burden of family caregivers, which became more multifaceted with regards to the pandemic.

Applying Participatory Design Mixed-Methods Approaches to Refine Twitter-Based Social Support Interventions for African Americans and Hispanic Family Caregivers of Persons with Dementia

We applied mixed-methods to refine our first version of the Twitter message library (English 400, translated into Spanish 400) for African Americans and Hispanic family caregivers for a person with dementia. We conducted a series of expert panels to collect quantitative and qualitative data using surveys and in-depth interviews. Using mixed methods to ensure unbiased results, the panelists first independently scored them (1 message/5 panelist) on a scale of 1 to 4 (1: lowest, 4: highest), followed by in-depth interviews and group discussions. Survey results showed that the average score was 3.47, indicating good to excellent (SD 0.35, ranges from 1.8 to 4). Quantitative surveys and qualitative interviews showed different results in emotional support messages.