AI Hesitancy and Acceptability-Perceptions of AI Chatbots for Chronic Health Management and Long COVID Support: Survey Study.

Background: Artificial intelligence (AI) chatbots have the potential to assist individuals with chronic health conditions by providing tailored information, monitoring symptoms, and offering mental health support. Despite their potential benefits, research on public attitudes toward health care chatbots is still limited. To effectively support individuals with long-term health conditions like long COVID (or post-COVID-19 condition), it is crucial to understand their perspectives and preferences regarding the use of AI chatbots. Objective: This study has two main objectives: (1) provide insights into AI chatbot acceptance among people with chronic health conditions, particularly adults older than 55 years and (2) explore the perceptions of using AI chatbots for health self-management and long COVID support. Methods: A web-based survey study was conducted between January and March 2023, specifically targeting individuals with diabetes and other chronic conditions. This particular population was chosen due to their potential awareness and ability to self-manage their condition. The survey aimed to capture data at multiple intervals, taking into consideration the public launch of ChatGPT, which could have potentially impacted public opinions during the project timeline. The survey received 1310 clicks and garnered 900 responses, resulting in a total of 888 usable data points. Results: Although past experience with chatbots (P<.001, 95% CI .110-.302) and online information seeking (P<.001, 95% CI .039-.084) are strong indicators of respondents' future adoption of health chatbots, they are in general skeptical or unsure about the use of AI chatbots for health care purposes. Less than one-third of the respondents (n=203, 30.1%) indicated that they were likely to use a health chatbot in the next 12 months if available. Most were uncertain about a chatbot's capability to provide accurate medical advice. However, people seemed more receptive to using voice-based chatbots for mental well-being, health data collection, and analysis. Half of the respondents with long COVID showed interest in using emotionally intelligent chatbots. Conclusions: AI hesitancy is not uniform across all health domains and user groups. Despite persistent AI hesitancy, there are promising opportunities for chatbots to offer support for chronic conditions in areas of lifestyle enhancement and mental well-being, potentially through voice-based user interfaces.

Health Outcomes Following Engagement With a Digital Health Tool Among People With Prediabetes and Type 2 Diabetes: Prospective Evaluation Study.

BACKGROUND: Diabetes is a worldwide chronic condition causing morbidity and mortality, with a growing economic burden on health care systems. Complications from poorly controlled diabetes are associated with increased socioeconomic costs and reduced quality of life. Smartphones have become an influential platform, providing feasible tools such as health apps to deliver tailored support to enhance the ability of patients with diabetes for self-management. Gro Health is a National Health Service division X-certified digital health tool used to deliver educational and monitoring support to facilitate the development of skills and practices for maintaining good health. OBJECTIVE: This study aims to assess self-reported outcomes of the Gro Health app among users with diabetes and prediabetes and identify the factors that determine engagement with the digital health tool. METHODS: This was a service evaluation of self-reported data collected prospectively by the developers of the Gro Health app. The EQ-5D questionnaire is a standardized tool used to measure health status for clinical and economic appraisal. Gro Health users completed the EQ-5D at baseline and 6 months after using the app. Users provided informed consent for the use of their anonymized data for research purposes. EQ-5D index scores and visual analogue scale (VAS) scores were calculated at baseline and 6 months for individuals with prediabetes and type 2 diabetes. Descriptive statistics and multiple-regression models were used to assess changes in the outcome measures and determine factors that affected engagement with the digital tool. RESULTS: A total of 84% (1767/2114) of Gro Health participants completed EQ-5D at baseline and 6 months. EQ-5D index scores are average values that reflect people's preferences about their health state (1=full health and 0=moribund). There was a significant and clinically meaningful increase in mean EQ-5D index scores among app users between baseline (0.746, SD 0.23) and follow-up (0.792, SD 0.22; P<.001). The greatest change was observed in the mean VAS score, with a percentage change of 18.3% improvement (61.7, SD 18.1 at baseline; 73.0, SD 18.8 at follow-up; P<.001). Baseline EQ-5D index scores, age, and completion of educational modules were associated with significant changes in the follow-up EQ-5D index scores, with baseline EQ-5D index scores, race and ethnicity, and completion of educational modules being significantly associated with app engagement (P<.001). CONCLUSIONS: This study provides evidence of a significant positive effect on self-reported quality of life among people living with type 2 diabetes engaging with a digital health intervention. The improvements, as demonstrated by the EQ-5D questionnaire, are facilitated through access to education and monitoring support tools within the app. This provides an opportunity for health care professionals to incorporate National Health Service-certified digital tools, such as Gro Health, as part of the holistic management of people living with diabetes.

Implementation of a Digital Health Tool for Patients Awaiting Input From a Specialist Weight Management Team: Observational Study.

BACKGROUND: Digital tools are increasingly used on a population level as a weight loss strategy for people living with overweight and obesity. Evidence supports the feasibility of digital tools for the management of obesity in a community setting, but there is only emerging evidence for the feasibility of such tools in specialist weight management services. No study has assessed the uptake of digital tools among patients awaiting their first appointment with a specialist weight management service. OBJECTIVE: The objective of this study was to understand interest, acceptance, and engagement with a digital behavioral change platform to support specialist weight management. METHODS: This was an observational study registered as a service innovation. All patients on the waiting list for a first appointment in the tier 3 weight management service at University Hospitals Coventry and Warwickshire National Health Service (NHS) Trust were eligible to access the NHS-approved digital tool. Data on interest and engagement with the digital tool were collected. Routine clinical data were used to describe patient demographics. Focus groups were held to explore patients' views on the use of digital tools as part of a specialist weight management service. RESULTS: A total of 199 patients on the waiting list were informed about the available digital tool. Just over a half (n=102, 51.3%) of patients were interested in using the app, with over one-third (n=68, 34%) of all patients engaging with the app. Overall, a third of patients on the waiting list (n=63, 32%) did not respond to the invite and 34 (17%) of patients expressed no interest in the app. Emotional eating and higher BMI was associated with interest in the Gro Health app. Male gender was associated with reduced engagement with the app. There were no differences in interest in the Gro Health app according to age, ethnicity, metabolic measures of glycemia, and lipid profile. CONCLUSIONS: It is feasible to offer digital tools such as Gro Health to patients awaiting their first appointment with specialist weight management services. Future research should explore barriers and facilitators of engagement with digital tools. Additionally, there is a need to further evaluate the effectiveness of such tools in specialist weight management services.

Understanding the Security and Privacy Concerns About the Use of Identifiable Health Data in the Context of the COVID-19 Pandemic: Survey Study of Public Attitudes Toward COVID-19 and Data-Sharing.

BACKGROUND: The COVID-19 pandemic increased the availability and use of population and individual health data to optimize tracking and analysis of the spread of the virus. Many health care services have had to rapidly digitalize in order to maintain the continuity of care provision. Data collection and dissemination have provided critical support for defending against the spread of the virus since the beginning of the pandemic; however, little is known about public perceptions of and attitudes toward the use, privacy, and security of data. OBJECTIVE: The goal of this study is to better understand people's willingness to share data in the context of the COVID-19 pandemic. METHODS: A web-based survey was conducted on individuals' use of and attitudes toward health data for individuals aged 18 years and older, and in particular, with a reported diagnosis of a chronic health condition placing them at the highest risk of severe COVID-19. RESULTS: In total, 4764 individuals responded to this web-based survey, of whom 4674 (98.1%) reported a medical diagnosis of at least 1 health condition (3 per person on average), with type 2 diabetes (n=2974, 62.7%), hypertension (n=2147, 45.2%), and type 1 diabetes (n=1299, 27.4%) being most prominent in our sample. In general, more people are comfortable with sharing anonymized data than personally identifiable data. People reported feeling comfortable sharing data that were able to benefit others; 66% (3121 respondents) would share personal identifiable data if its primary purpose was deemed beneficial for the health of others. Almost two-thirds (n=3026; 63.9%) would consent to sharing personal, sensitive health data with government or health authority organizations. Conversely, over a quarter of respondents (n=1297, 27.8%) stated that they did not trust any organization to protect their data, and 54% (n=2528) of them reported concerns about the implications of sharing personal information. Almost two-thirds (n=3054, 65%) of respondents were concerned about the provisions of appropriate legislation that seeks to prevent data misuse and hold organizations accountable in the case of data misuse. CONCLUSIONS: Although our survey focused mainly on the views of those living with chronic health conditions, the results indicate that data sensitivity is highly contextual. More people are more comfortable with sharing anonymized data rather than personally identifiable data. Willingness to share data also depended on the receiving body, highlighting trust as a key theme, in particular who may have access to shared personal health data and how they may be used in the future. The nascency of legal guidance in this area suggests a need for humanitarian guidelines for data responsibility during disaster relief operations such as pandemics and for involving the public in their development.

The Low Carb Program for people with type 2 diabetes and pre-diabetes: a mixed methods feasibility study of signposting from general practice.

BACKGROUND: Evidence shows type 2 diabetes mellitus (T2DM) can be effectively treated with a reduced-carbohydrate diet to support weight loss. Digital apps are increasingly used to support weight loss, yet little is known about their use as part of general practice diabetes care. AIM: Determine the feasibility of signposting from routine NHS general practice to a digital weight management tool (Low Carb Program) for patients with T2DM and pre-diabetes. DESIGN & SETTING: Mixed-methods feasibility study implemented within routine general practice consultations at four practices in the Midlands, England. METHOD: General practices offered signposting to eligible patients attending consultations of any type during a 4-week recruitment period. Rates of offering and accepting signposting were recorded, with program registration, program completion, and self-reported health outcomes (weight, haemoglobin A1C [HbA1c]). RESULTS: Signposting was offered to 351 patients; 160 (45.6%) accepted, 103 (29.3%) registered with the intervention and 43 (26.9% of patients accepting signposting) completed the programme. GPs reported that signposting added between 1-4 minutes to the consultation length. Patients completing the programme reported greater weight loss (7.2kg versus 1.6kg, P<0.001) and HbA1c improvements (-9.1mmol/mol versus 1.7mmol/mol, P<0.001) compared to those who did not, and were more likely to reduce the number of prescribed diabetes medications in general practice. CONCLUSIONS: Signposting from real-world general practice to the Low Carb Program is feasible and can potentially improve diabetes outcomes. Further research should explore whether the process of signposting can be enhanced to increase registration, identify whether additional practice-led support leads to increased programme completion, and confirm the intervention's clinical and cost-effectiveness.

Low Carb Program Health App Within a Hospital-Based Obesity Setting: Observational Service Evaluation.

BACKGROUND: Obesity underlies much chronic disease. Digitalization of obesity management provides an opportunity to innovate our traditional model of health care delivery within this setting, and to transform its scalability potentially to the population level. OBJECTIVE: The objective was to assess the feasibility and effectiveness of the Low Carb Program app for weight loss, applied within our hospital-based (tier 3) obesity service. Due to the disrupting effects of the COVID-19 pandemic on our obesity service, we compared the clinical outcomes from the Low Carb Program app applied in the context of remote patient appointments over the telephone with the prepandemic traditional standard of care. METHODS: We invited patients who attended our hospital-based obesity service to engage with the Low Carb Program smartphone app. We combined this approach with remote delivery (over the telephone) of obesity management from medical and psychology members of our obesity team during the COVID-19 pandemic. Outcome variables included changes in body weight and changes in HbA1c as a marker of glycemic control. We compared data from the Low Carb Program group with a retrospective control group (n=126) that had received traditional face-to-face obesity management from our team without concomitant use of the Low Carb Program app in the pre-COVID-19 era. T test comparisons were employed, with P<.05 considered significant. RESULTS: The mean weight of participants (n=105) was 130.2 kg, with 59% (n=62) females and a mean age of 48.8 years. Most participants (90/105, 86%) completed the Low Carb Program app registration process and engaged with the Low Carb Program app program; at follow-up, most participants (88/105, 84%) had actively engaged with the Low Carb Program app within the prior 30 days. The majority of participants (58/105, 55%) self-reported outcomes within the app. Mean duration of clinical follow-up for recruited participants who received the app was 7.4 months. Paired data were available for 48 participants for body weight and 41 participants for HbA1c. Paired sample t test analysis revealed a statistically significant mean loss of body weight of 2.7 kg (P=.001) and improvement in HbA1c of 3.3 mmol/mol (P=.01). The mean weight of control group patients (n=126) was 137.1 kg, with 74% (93/126) females and a mean age of 44.4 years. The mean follow-up for this group was 6 months. Data comparisons between the app user group and the pre-COVID-19 retrospective control group revealed equivalence for loss of body weight and change in HbA1c between the two groups. CONCLUSIONS: We provide evidence to support the feasibility of implementing the Low Carb Program app combined with remote management; this is the first proof of concept for digitalized management within a hospital-based (tier 3) obesity service. We demonstrate the potential clinical efficacy of the approach in terms of improvements in body weight and glycemic control.