Digital self-guided mobile health [mHealth] applications are cost-effective, accessible, and well-suited to improve mental health at scale. This randomized controlled trial [RCT] evaluated the efficacy of a recently developed mHealth programme based on cognitive-behavioral therapy [CBT] principles in improving worry and anxiety. We also examined psychological mindedness [PM] as a mediator by which app engagement is thought to improve outcomes. The Intervention group completed a 2-week “Anxiety and Worry” programme with daily CBT-informed activities, while the active waitlist-control completed a matched 2-week mHealth programme on procrastination. Participants filled out the Generalized Anxiety Disorder [GAD-7], Patient Health Questionnaire [PHQ-9], and Psychological Mindedness Scale [PMS] at baseline, post-intervention, and 2-week follow-up. App engagement was measured at post-intervention only. Contrary to prediction, the Intervention group did not perform better than the Active Control group; both groups showed significant improvements on anxiety and depressive symptoms from baseline to follow-up. From post-intervention to follow-up, only the Intervention group showed further improvements for anxiety symptoms. Higher engagement with the mHealth app predicted lower anxiety and depressive symptoms at follow-up, and this relationship was fully mediated by psychological mindedness. This study provides evidence that [a] engaging in a CBT mHealth programme can reduce anxiety and worry, and [b] Psychological mindedness is a potential pathway by which engaging with a mHealth app improves anxiety and depressive symptoms. While overall effect sizes were small, at the population level, these can make significant contributions to public mental health.

The use of digital technology amongst people living with a range of long-term health conditions to support self-management has increased dramatically. More recently, digital health technologies to share and exchange personal health data with others have been investigated. Sharing personal health data with others is not without its risks: sharing data creates threats to the privacy and security of personal data and plays a role in trust, adoption and continued use of digital health technology. Our work aims to inform the design of these digital health technologies by investigating the reported intentions of sharing health data with others, the associated user experiences when using these digital health technologies and the trust, identity, privacy and security (TIPS) considerations for designing digital health technologies that support the trusted sharing of personal health data to support the self-management of long-term health conditions. To address these aims, we conducted a scoping review, analysing over 12,000 papers in the area of digital health technologies. We conducted a reflexive thematic analysis of 17 papers that described digital health technologies that support sharing of personal health data, and extracted design implications that could enhance the future development of trusted, private and secure digital health technologies.

Artificial intelligence (AI) has the potential to improve diagnostic accuracy. Yet people are often reluctant to trust automated systems, and some patient populations may be particularly distrusting. We sought to determine how diverse patient populations feel about the use of AI diagnostic tools, and whether framing and informing the choice affects uptake. To construct and pretest our materials, we conducted structured interviews with a diverse set of actual patients. We then conducted a pre-registered (osf.io/9y26x), randomized, blinded survey experiment in factorial design. A survey firm provided n = 2675 responses, oversampling minoritized populations. Clinical vignettes were randomly manipulated in eight variables with two levels each: disease severity (leukemia versus sleep apnea), whether AI is proven more accurate than human specialists, whether the AI clinic is personalized to the patient through listening and/or tailoring, whether the AI clinic avoids racial and/or financial biases, whether the Primary Care Physician (PCP) promises to explain and incorporate the advice, and whether the PCP nudges the patient towards AI as the established, recommended, and easy choice. Our main outcome measure was selection of AI clinic or human physician specialist clinic (binary, “AI uptake”). We found that with weighting representative to the U.S. population, respondents were almost evenly split (52.9% chose human doctor and 47.1% chose AI clinic). In unweighted experimental contrasts of respondents who met pre-registered criteria for engagement, a PCP’s explanation that AI has proven superior accuracy increased uptake (OR = 1.48, CI 1.24–1.77, p < .001), as did a PCP’s nudge towards AI as the established choice (OR = 1.25, CI: 1.05–1.50, p = .013), as did reassurance that the AI clinic had trained counselors to listen to the patient’s unique perspectives (OR = 1.27, CI: 1.07–1.52, p = .008). Disease severity (leukemia versus sleep apnea) and other manipulations did not affect AI uptake significantly. Compared to White respondents, Black respondents selected AI less often (OR = .73, CI: .55-.96, p = .023) and Native Americans selected it more often (OR: 1.37, CI: 1.01–1.87, p = .041). Older respondents were less likely to choose AI (OR: .99, CI: .987-.999, p = .03), as were those who identified as politically conservative (OR: .65, CI: .52-.81, p < .001) or viewed religion as important (OR: .64, CI: .52-.77, p < .001). For each unit increase in education, the odds are 1.10 greater for selecting an AI provider (OR: 1.10, CI: 1.03–1.18, p = .004). While many patients appear resistant to the use of AI, accuracy information, nudges and a listening patient experience may help increase acceptance. To ensure that the benefits of AI are secured in clinical practice, future research on best methods of physician incorporation and patient decision making is required.

Introduction: Maasai living in the Arusha region, Tanzania, face challenges in feeding their children because of decreasing grazing grounds for their cattle. Therefore, they requested birth control methods. Previous studies have shown that lack of knowledge about, and poor access to, family planning (FP) may worsen the situation. We developed an interactive voice response calling (IVRC) platform for Maasai and health care workers (HCW) to create a venue for communication about FP to increase knowledge and access to FP. The objective of this study was to explore the effect of the platform on knowledge, access and use of family planning methods. We applied a participatory action research approach using mixed methods for data collection to develop and pilot-test an mHealth-platform with IVRC using Maa language. We enrolled Maasai-couples and HCW in Monduli District (Esilalei ward), Arusha Region, and followed them for 20 months. A baseline assessment was done to explore knowledge about FP. Furthermore, we abstracted information on FP clinic visits. Based on that, we developed a system called Embiotishu. A toll-free number was provided to interact with the system by calling with their phone. The system offers pre-recorded voice messages with information about FP and reproductive health to educate Maasai. The system recorded the number of calls and the type of information accessed. We measured the outcome by (1) a survey investigating the knowledge of contraceptive methods before and after Embiotishu and (2) counting the number of clinic visits (2018–2020) from medical records and feedback from qualitative data for FP used among Maasai. The acceptability and feasibility were explored through focus group discussions (FGDs) with Maasai and in-depth interviews (IDIs) with HCW. We recruited 76 Maasai couples whom we interviewed during the baseline assessment. The overall knowledge of contraceptives increased significantly (p<0.005) in both men and women. The number of clinic visits rose from 137 in 2018 to 344 in 2019 and 228 in the first six months of 2020. Implants were the most prescribed family planning method, followed by injections and pills, as found in medical records. The number of incoming calls, missed calls, and questions were 24,033 over 20 months. Out of these calls, 14,547 topics were selected. The most selected topics were modern contraceptives (mainly implants, condoms, tubal ligation, and vasectomy). Natural methods of contraception (vaginal fluid observations, calendar, and temperature). Our study has shown that the IVRC system led to an improvement in knowledge about and access to contraceptives. Furthermore, it has potential to increase access to health information as well as improve dialogue between Health workers and Maasai.

Diagnosis of tuberculosis (TB) among young children (<5 years) is challenging due to the paucibacillary nature of clinical disease and clinical similarities to other childhood diseases. We used machine learning to develop accurate prediction models of microbial confirmation with simply defined and easily obtainable clinical, demographic, and radiologic factors. We evaluated eleven supervised machine learning models (using stepwise regression, regularized regression, decision tree, and support vector machine approaches) to predict microbial confirmation in young children (<5 years) using samples from invasive (reference-standard) or noninvasive procedure. Models were trained and tested using data from a large prospective cohort of young children with symptoms suggestive of TB in Kenya. Model performance was evaluated using areas under the receiver operating curve (AUROC) and precision-recall curve (AUPRC), accuracy metrics. (i.e., sensitivity, specificity), F-beta scores, Cohen’s Kappa, and Matthew’s Correlation Coefficient. Among 262 included children, 29 (11%) were microbially confirmed using any sampling technique. Models were accurate at predicting microbial confirmation in samples obtained from invasive procedures (AUROC range: 0.84–0.90) and from noninvasive procedures (AUROC range: 0.83–0.89). History of household contact with a confirmed case of TB, immunological evidence of TB infection, and a chest x-ray consistent with TB disease were consistently influential across models. Our results suggest machine learning can accurately predict microbial confirmation of M. tuberculosis in young children using simply defined features and increase the bacteriologic yield in diagnostic cohorts. These findings may facilitate clinical decision making and guide clinical research into novel biomarkers of TB disease in young children.

Background: Acute lateral ankle sprains (LAS) account for 4–5% of all Emergency Department (ED) visits. Few patients receive the recommended care of exercise rehabilitation. A simple solution is an exercise app for mobile devices, which can deliver tailored and real-time adaptive exercise programs. Purpose: The purpose of this pilot study was to investigate the use and preliminary effect of an app-based exercise program in patients with LAS seen in the Emergency Department at a public hospital. Materials and methods: We used an app that delivers evidence-based exercise rehabilitation for LAS using algorithm-controlled progression. Participants were recruited from the ED and followed for four months. Data on app-use and preliminary effect were collected continuously through the exercise app and weekly text-messages. Baseline and follow-up data were collected though an online questionnaire. Semi-structured interviews were performed after participants stopped using the app. Results: Health care professionals provided 485 patients with study information and exercise equipment. Of those, 60 participants chose to enroll in the study and 43 became active users. The active users completed a median of 7 exercise sessions. Most of the active users were very satisfied or satisfied (79%-93%) with the app and 95.7% would recommend it to others. The interviews showed that ankle sprains were considered an innocuous injury that would recover by itself. Several app users expressed they felt insufficiently informed from the ED health care professionals. Only 39% felt recovered when they stopped exercising, and 33% experienced a recurrent sprain in the study period. Conclusion: In this study, only few patients with LAS became active app users after receiving information in the ED about a free app-based rehabilitation program. We speculate the reason for this could be the perception that LAS is an innocuous injury. Most of the patients starting training were satisfied with the app, although few completed enough exercise sessions to realistically impact clinical recovery. Interestingly more than half of the participants did not feel fully recovered when they stopped exercising and one third experienced a recurrent sprain. Trial-identifiers: https://clinicaltrials.gov/ct2/show/NCT03550274, preprint (open access): https://www.medrxiv.org/content/10.1101/2022.01.31.22269313v1.

The transfer of new insights from basic or clinical research into clinical routine is usually a lengthy and time-consuming process. Conversely, there are still many barriers to directly provide and use routine data in the context of basic and clinical research. In particular, no coherent software solution is available that allows a convenient and immediate bidirectional transfer of data between concrete treatment contexts and research settings. Here, we present a generic framework that integrates health data (e.g., clinical, molecular) and computational analytics (e.g., model predictions, statistical evaluations, visualizations) into a clinical software solution which simultaneously supports both patient-specific healthcare decisions and research efforts, while also adhering to the requirements for data protection and data quality. Specifically, our work is based on a recently established generic data management concept, for which we designed and implemented a web-based software framework that integrates data analysis, visualization as well as computer simulation and model prediction with audit trail functionality and a regulation-compliant pseudonymization service. Within the front-end application, we established two tailored views: a clinical (i.e., treatment context) perspective focusing on patient-specific data visualization, analysis and outcome prediction and a research perspective focusing on the exploration of pseudonymized data. We illustrate the application of our generic framework by two use-cases from the field of haematology/oncology. Our implementation demonstrates the feasibility of an integrated generation and backward propagation of data analysis results and model predictions at an individual patient level into clinical decision-making processes while enabling seamless integration into a clinical information system or an electronic health record.

The use of wearable technology, which is often acquired to support well-being and a healthy lifestyle, has become popular in Western countries. At the same time, healthcare is gradually taking the first steps to introduce wearable technology into patient care, even though on a large scale the evidence of its’ effectiveness is still lacking. The objective of this study was to identify the factors associated with use of wearable technology to support activity, well-being, or a healthy lifestyle in the Finnish adult population (20–99) and among older adults (65–99). The study utilized a cross-sectional population survey of Finnish adults aged 20 and older (n = 6,034) to analyse non-causal relationships between wearable technology use and the users’ characteristics. Logistic regression models of wearable technology use were constructed using statistically significant sociodemographic, well-being, health, benefit, and lifestyle variables. Both in the general adult population and among older adults, wearable technology use was associated with getting aerobic physical activity weekly according to national guidelines and with marital status. In the general adult population, wearable technology use was also associated with not sleeping enough and agreeing with the statement that social welfare and healthcare e-services help in taking an active role in looking after one’s own health and well-being. Younger age was associated with wearable technology use in the general adult population but for older adults age was not a statistically significant factor. Among older adults, non-use of wearable technology went hand in hand with needing guidance in e-service use, using a proxy, or not using e-services at all. The results support exploration of the effects of wearable technology use on maintaining an active lifestyle among adults of all ages.

The Covid-19 pandemic required many clinical trials to adopt a decentralized framework to continue research activities during lock down restrictions. The STOPCoV study was designed to assess the safety and efficacy of Covid-19 vaccines in those aged 70 and above compared to those aged 30–50 years of age. In this sub-study we aimed to determine participant satisfaction for the decentralized processes, accessing the study website and collecting and submitting study specimens. The satisfaction survey was based on a Likert scale developed by a team of three investigators. Overall, there were 42 questions for respondents to answer. The invitation to participate with a link to the survey was emailed to 1253 active participants near the mid-way point of the main STOPCoV trial (April 2022). The results were collated and answers were compared between the two age cohorts. Overall, 70% (83% older, 54% younger cohort, no difference by sex) responded to the survey. The overall feedback was positive with over 90% of respondents answering that the website was easy to use. Despite the age gap, both the older cohort and younger cohort reported ease of performing study activities through a personal electronic device. Only 30% of the participants had previously participated in a clinical trial, however over 90% agreed that they would be willing to participate in future clinical research. Some difficulties were noted in refreshing the browser whenever updates to the website were made. The feedback attained will be used to improve current processes and procedures of the STOPCoV trial as well as share learning experiences to inform future fully decentralized research studies.

Electronic health records (EHRs) represent a major repository of real world clinical trajectories, interventions and outcomes. While modern enterprise EHR’s try to capture data in structured standardised formats, a significant bulk of the available information captured in the EHR is still recorded only in unstructured text format and can only be transformed into structured codes by manual processes. Recently, Natural Language Processing (NLP) algorithms have reached a level of performance suitable for large scale and accurate information extraction from clinical text. Here we describe the application of open-source named-entity-recognition and linkage (NER+L) methods (CogStack, MedCAT) to the entire text content of a large UK hospital trust (King’s College Hospital, London). The resulting dataset contains 157M SNOMED concepts generated from 9.5M documents for 1.07M patients over a period of 9 years. We present a summary of prevalence and disease onset as well as a patient embedding that captures major comorbidity patterns at scale. NLP has the potential to transform the health data lifecycle, through large-scale automation of a traditionally manual task.