Passive sensing data predicts stress in university students: a supervised machine learning method for digital phenotyping.

Introduction: University students are particularly susceptible to developing high levels of stress, which occur when environmental demands outweigh an individual's ability to cope. The growing advent of mental health smartphone apps has led to a surge in use by university students seeking ways to help them cope with stress. Use of these apps has afforded researchers the unique ability to collect extensive amounts of passive sensing data including GPS and step detection. Despite this, little is known about the relationship between passive sensing data and stress. Further, there are no established methodologies or tools to predict stress from passive sensing data in this group. Methods: In this study, we establish a clear machine learning-based methodological pipeline for processing passive sensing data and extracting features that may be relevant in the context of mental health. Results: We then use this methodology to determine the relationship between passive sensing data and stress in university students. Discussion: In doing so, we offer the first proof-of-principle data for the utility of our methodological pipeline and highlight that passive sensing data can indeed digitally phenotype stress in university students. Clinical trial registration: Australia New Zealand Clinical Trials Registry (ANZCTR), identifier ACTRN12621001223820.

Optimizing Technology-Based Prompts for Supporting People Living With Dementia in Completing Activities of Daily Living at Home: Experimental Approach to Prompt Modality, Task Breakdown, and Attentional Support.

BACKGROUND: Assistive technology is becoming increasingly accessible and affordable for supporting people with dementia and their care partners living at home, with strong potential for technology-based prompting to assist with initiation and tracking of complex, multistep activities of daily living. However, there is limited direct comparison of different prompt features to guide optimal technology design. OBJECTIVE: Across 3 experiments, we investigated the features of tablet-based prompts that best support people with dementia to complete activities of daily living at home, measuring prompt effectiveness and gaining feedback from people with dementia and their care partners about their experiences. METHODS: Across experiments, we developed a specialized iPad app to enable data collection with people with dementia at home over an extended experimental period. In experiment 1, we varied the prompts in a 3 (visual type: text instruction, iconic image, and photographic image) × 3 (audio type: no sound, symbolic sound, and verbal instruction) experimental design using repeated measures across multiple testing sessions involving single-step activities. In experiment 2, we tested the most effective prompt breakdown for complex multistep tasks comparing 3 conditions (1-prompt, 3-prompt, and 7-prompt conditions). In experiment 3, we compared initiation and maintenance alerts that involved either an auditory tone or an auditory tone combined with a verbal instruction. Throughout, we asked people with dementia and their care partners to reflect on the usefulness of prompting technology in their everyday lives and what could be developed to better meet their needs. RESULTS: First, our results showed that audible verbal instructions were more useful for task completion than either tone-based or visual prompts. Second, a more granular breakdown of tasks was generally more useful and increased independent use, but this varied across individuals. Third, while a voice or text maintenance alert enabled people with dementia to persist with a multistep task for longer when it was more frequent, task initiation still frequently required support from a care partner. CONCLUSIONS: These findings can help inform developers of assistive technology about the design features that promote the usefulness of home prompting systems for people with dementia as well as the preferences and insights of people with dementia and their care partners regarding assistive technology design.

Use of smartphone sensor data in detecting and predicting depression and anxiety in young people (12-25 years): A scoping review.

Digital phenotyping is a promising method for advancing scalable detection and prediction methods in mental health research and practice. However, little is known about how digital phenotyping data are used to make inferences about youth mental health. We conducted a scoping review of 35 studies to better understand how passive sensing (e.g., Global Positioning System, microphone etc) and electronic usage data (e.g., social media use, device activity etc) collected via smartphones are used in detecting and predicting depression and/or anxiety in young people between 12 and 25 years-of-age. GPS and/or Wifi association logs and accelerometers were the most used sensors, although a wide variety of low-level features were extracted and computed (e.g., transition frequency, time spent in specific locations, uniformity of movement). Mobility and sociability patterns were explored in more studies compared to other behaviours such as sleep, phone use, and circadian movement. Studies used machine learning, statistical regression, and correlation analyses to examine relationships between variables. Results were mixed, but machine learning indicated that models using feature combinations (e.g., mobility, sociability, and sleep features) were better able to predict and detect symptoms of youth anxiety and/or depression when compared to models using single features (e.g., transition frequency). There was inconsistent reporting of age, gender, attrition, and phone characteristics (e.g., operating system, models), and all studies were assessed to have moderate to high risk of bias. To increase translation potential for clinical practice, we recommend the development of a standardised reporting framework to improve transparency and replicability of methodology.

A web-based video messaging intervention for suicide prevention in men: study protocol for a five-armed randomised controlled trial.

BACKGROUND: More than 50% of people who die by suicide have not been in contact with formal mental health services. The rate of people who fly 'under the radar' of mental health services is higher among men than women, indicating a need to improve engagement strategies targeted towards men who experience suicidal thoughts and/or behaviours. In Australia, a range of mental health support services exist, designed specifically for men, yet, a substantial proportion of men do not use these services. The aim of this study is to evaluate whether a brief online video-based messaging intervention is an effective approach for encouraging men with suicidal thoughts and/or behaviours to engage with existing support services. METHODS: Informed by a literature review, surveys, and consultation with men with a lived experience of suicidal thoughts and/or behaviours, we designed five video-based messages that will be used in this five-arm randomised controlled trial. A total of 380 (76 per arm) men aged 18 years or older with suicidal thoughts who are not currently accessing formal mental health services will be recruited online and randomly assigned to watch one of the five web-based video messages. After viewing the video, men will be presented with information about four existing Australian support services, along with links to these services. The primary outcome will be help-seeking, operationalised as a click on any one of the four support service links, immediately after viewing the video. Secondary outcomes include immediate self-reported help-seeking intentions in addition to self-reported use of the support services during a 1-week follow-up period. We will also use the Discrete Choice Experiment methodology to determine what aspects of support services (e.g. low cost, short appointment wait times) are most valued by this group of men. DISCUSSION: This study is the first to evaluate the effectiveness of a brief web-based video messaging intervention for promoting engagement with existing support services among men with suicidal thoughts who are not currently receiving formal help. If found to be effective, this would represent a scalable, cost-effective approach to promote help-seeking for this at-risk population. Limitations and strengths of this study design are discussed.

Technology for dementia care: what would good technology look like and do, from carers' perspectives?

BACKGROUND: The development of technology in dementia care has largely been without consultation with carers, and has primarily focused on safety, monitoring devices, and supporting activities of daily living. Further, while involving end-users in the design of technology has been recommended, this is yet to become common practice. METHOD: We conducted a mixed methods study with the aim of investigating carers' values and priorities for technology development, including prior experiences, barriers to use, and what they would like technology to do. Importantly, we asked carers for their design ideas and bespoke technology solutions for future development. RESULTS: Carers of people living with dementia (N = 127), including both unpaid (n = 102) and paid carers (n = 25) residing in Australia, completed an online survey. In addition, a subsample of carers (n = 23) participated in semi-structured interviews. Findings demonstrate that carers want technology to be person-centred, customisable, and to increase opportunities for meaningful social connection. Findings also demonstrate the ability of carers to generate creative design solutions for dementia care. CONCLUSIONS: These findings and implications will be discussed in relation to the importance of co-design with carers and engineers during the design phase of assistive technology. Also, the importance of technology to enhance, not replace, human-to-human social interactions is highlighted.

Machine learning identifies a COVID-19-specific phenotype in university students using a mental health app.

Background: Advances in smartphone technology have allowed people to access mental healthcare via digital apps from wherever and whenever they choose. University students experience a high burden of mental health concerns. Although these apps improve mental health symptoms, user engagement has remained low. Studies have shown that users can be subgrouped based on unique characteristics that just-in-time adaptive interventions (JITAIs) can use to improve engagement. To date, however, no studies have examined the effect of the COVID-19 pandemic on these subgroups. Objective: Here, we sought to examine user subgroup characteristics across three COVID-19-specific timepoints: during lockdown, immediately following lockdown, and three months after lockdown ended. Methods: To do this, we used a two-step machine learning approach combining unsupervised and supervised machine learning. Results: We demonstrate that there are three unique subgroups of university students who access mental health apps. Two of these, with either higher or lower mental well-being, were defined by characteristics that were stable across COVID-19 timepoints. The third, situational well-being, had characteristics that were timepoint-dependent, suggesting that they are highly influenced by traumatic stressors and stressful situations. This subgroup also showed feelings and behaviours consistent with burnout. Conclusions: Overall, our findings clearly suggest that user subgroups are unique: they have different characteristics and therefore likely have different mental healthcare goals. Our findings also highlight the importance of including questions and additional interventions targeting traumatic stress(ors), reason(s) for use, and burnout in JITAI-style mental health apps to improve engagement.

Protocol for a bandit-based response adaptive trial to evaluate the effectiveness of brief self-guided digital interventions for reducing psychological distress in university students: the Vibe Up study.

INTRODUCTION: Meta-analytical evidence confirms a range of interventions, including mindfulness, physical activity and sleep hygiene, can reduce psychological distress in university students. However, it is unclear which intervention is most effective. Artificial intelligence (AI)-driven adaptive trials may be an efficient method to determine what works best and for whom. The primary purpose of the study is to rank the effectiveness of mindfulness, physical activity, sleep hygiene and an active control on reducing distress, using a multiarm contextual bandit-based AI-adaptive trial method. Furthermore, the study will explore which interventions have the largest effect for students with different levels of baseline distress severity. METHODS AND ANALYSIS: The Vibe Up study is a pragmatically oriented, decentralised AI-adaptive group sequential randomised controlled trial comparing the effectiveness of one of three brief, 2-week digital self-guided interventions (mindfulness, physical activity or sleep hygiene) or active control (ecological momentary assessment) in reducing self-reported psychological distress in Australian university students. The adaptive trial methodology involves up to 12 sequential mini-trials that allow for the optimisation of allocation ratios. The primary outcome is change in psychological distress (Depression, Anxiety and Stress Scale, 21-item version, DASS-21 total score) from preintervention to postintervention. Secondary outcomes include change in physical activity, sleep quality and mindfulness from preintervention to postintervention. Planned contrasts will compare the four groups (ie, the three intervention and control) using self-reported psychological distress at prespecified time points for interim analyses. The study aims to determine the best performing intervention, as well as ranking of other interventions. ETHICS AND DISSEMINATION: Ethical approval was sought and obtained from the UNSW Sydney Human Research Ethics Committee (HREC A, HC200466). A trial protocol adhering to the requirements of the Guideline for Good Clinical Practice was prepared for and approved by the Sponsor, UNSW Sydney (Protocol number: HC200466_CTP). TRIAL REGISTRATION NUMBER: ACTRN12621001223820.

Nurses' harm prevention practices during admission of an older person to the hospital: A multi-method qualitative study.

BACKGROUND: Nurses' harm prevention practices during the admission of older persons to hospital have important consequences for patient safety, preventable patient harm and length of hospital stay. Novel solutions are needed to assist nurses to balance complexity, high workload burden and patient safety during admission processes. AIM: Explore the nurses' experiences of harm prevention practices during the admission of an older person to the hospital. DESIGN: A multi-method qualitative study informed by frameworks of behaviour change and human-centred co-design. METHODS: The purposive sample included 44 nurses, 5 clinicians from other disciplines and 3 consumers recruited from five general medicine wards across three hospitals of a large public health service in metropolitan Melbourne, Australia. Data were collected over 12 h of naturalistic observations of nurses during eight patient admissions, and during four participatory human-centred co-design workshops between August 2019 and January 2020. Observation, field notes and workshop artefact data were integrated for qualitative content and thematic analysis. RESULTS: Analysis revealed a 5-step journey map, with a temporal logic, that captured nurses' experiences, as well as the enablers and barriers to harm prevention practices when admitting an older person to the hospital. The consensus was reached on three priority features to assist nurses to implement harm prevention practices when they admit an older person to the hospital: (1) prioritize important care; (2) tailor care to the individual and (3) see the big picture for the patient. CONCLUSION: The novel research approach identified five steps in nurses' activities and harm prevention practices during admission of an older person to the hospital, and key features for a solution to assist nurses to keep patients safe. The findings provide the foundation for further research to develop interventions to assist nurses to manage high workloads during this complex activity.

Nursing guidelines for comprehensive harm prevention strategies for adult patients in acute hospitals: An integrative review and synthesis.

BACKGROUND: Harm prevention research has seldom considered the complex demands on nurses negotiating multiple interrelated factors that contribute to preventable harms common in hospitalized patients. Best practice guidelines are available for individual risk factors, but few consider multiple factors that contribute to risk. As a consequence, duplication, contradiction, gaps, and volume of information limit harm prevention guideline use by nurses in daily practice. OBJECTIVES: To systematically synthesise best-evidence recommendations from clinical practice guidelines to support nurses to deliver comprehensive harm prevention during acute hospitalization. DESIGN: An integrative review process was used to systematically identify, examine, evaluate and synthesise clinical nursing guidelines to prevent harm to hospitalized patients. METHODS: The search strategy developed with an expert librarian used a combination of targeted searching for guidelines published on websites, and forward and backward citation searching. Guidelines included were those most recently published, relevant to the international nursing context, and addressing one or more of eight factors contributing to preventable harms. The AGREE-REX (Appraisal of Guidelines Research and Evaluation-Recommendations Excellence) tool was used for critical appraisal of guidelines regarding appropriateness to target users (i.e., nurses), trustworthiness, and implementable in acute hospitals. EndNote and NVIVO 12 were used to manage the high volume of extracted data and facilitate analysis. Analyses involved using the framework method to code data for relevance to an eight-factor harm prevention framework; steps for inductive thematic analyses were used for synthesis. Iterations of the thematic model were refined by sharing with hospital patient safety experts, who endorsed the final model. RESULTS: 154 guidelines met inclusion criteria, providing 7,429 recommendations. Synthesis involved mapping of recommendations across the eight-factor framework that informed a hierarchy of risk for harm prevention activity. Six themes represented nursing care strategies across the eight-factors that could be integrated into local practice contexts. The themes are framed into a model for nurse comprehensive harm prevention. CONCLUSIONS: The complexity and volume of guidance for comprehensive harm prevention necessitates contemporaneous, integrated, and accessible guidance to support nurses' decision-making in their daily care provision. This research provides an integrated model to assist nurses to identify patients most vulnerable to multiple preventable harms during hospitalization and guide a comprehensive harm prevention strategy to keep them safe in hospital. TWEETABLE ABSTRACT: Review of nursing guidelines generates integrated model to help identify patients most vulnerable to multiple preventable harms during hospitalization.