Dana Bradford

Background: Sleep-dependent memory consolidation (SDMC), the process by which sleep supports the transfer of memories into long-term storage, declines with age but remains underexplored in older adults with subjective cognitive decline and mild cognitive impairment. Traditional SDMC assessments are typically conducted in lab settings, with limited evidence for feasibility to do these assessments at home for this clinical population. Objective: To address this, we co-designed the Sleep Memories app, which assesses overnight memory for a previously validated 32-item word-pairs task. This pilot study first explored the feasibility and acceptability of the app, including willingness to participate. Second, we explored various demographic, clinical, and subjective sleep factors associated with task completion and SDMC performance in a memory clinic sample. Methods: Within an 8-month period, we invited 141 older adults aged 50 years and above (mean 71.27, SD 7.51 y) from the Healthy Brain Ageing clinic, a specialist brain health and memory clinic in Sydney, to pilot the Sleep Memories app. Of these, 76 (mean 70.19, SD 7.75) agreed to participate. All participants underwent a full neuropsychological test battery, medical assessment, and mood assessment. Results: Sixty-eight participants completed at least 1 test of the word-pairs task. The word-pairs task completion rate for all trials was over 50%. There was 57% (39/68) completion of both evening and morning delayed recall tests. Lower willingness to participate was associated with lower global cognitive scores, poorer sleep behavior, and clinical factors. Higher task completion was associated with greater education and greater anxiety levels. User feedback indicated that the app was well-accepted and liked, although some participants reported minor technical difficulties. Conclusions: These findings support the feasibility of mobile app–based SDMC assessment in older adults at risk of cognitive decline and underscore the importance of considering individual characteristics (eg, subjective sleep factors, clinical characteristics, and education) when designing digital SDMC tools.

BACKGROUND Sleep-dependent memory consolidation (SDMC), the process by which sleep supports the transfer of memories into long-term storage, declines with age but remains underexplored in older adults with subjective cognitive decline (SCD) and mild cognitive impairment (MCI). Traditional SDMC assessments often lack ecological validity and are difficult to scale for this clinical population. OBJECTIVE To address this, we co-designed the Sleep Memories app, which assesses overnight memory for a previously validated 32-item word-pair task. This pilot study explored willingness to participate, feasibility, and acceptability of the app, and various demographic, clinical, and sleep factors associated with task completion and SDMC performance in a memory clinic sample. METHODS Within an 8-month period, we invited 141 older adults aged 50 and above (mean 71.27, SD 7.51) from the Healthy Brain Ageing clinic, a specialist brain health and memory clinic in Sydney, to pilot the Sleep Memories app. All participants underwent a full neuropsychological test battery, medical, and mood assessment. RESULTS The word-pair task completion rate for all trials was over 50%. There was 57.35% (39/68) completion of both evening and morning delayed recall tests. Lower willingness to participate was associated with lower global cognitive scores, poorer sleep behavior, and clinical factors. Higher task completion was associated with greater education and greater anxiety levels. User feedback indicated that the app was well accepted and liked, although some participants reported minor technical difficulties. CONCLUSIONS These findings support the feasibility of mobile app-based SDMC assessment in older adults at risk of cognitive decline and underscore the importance of considering individual characteristics (e.g., sleep factors, clinical characteristics, and education) when designing digital SDMC tools.

Cerebral palsy is the most common physical disability and the fifth most common cause of death in childhood. There is no known cure for this lifelong condition that has complex variations in symptoms and severity. Families are faced with challenges in how to find new, safe and effective interventions and how to choose treatments that align with their family priorities. People with the lived experience of cerebral palsy were connected with clinical experts, software developers and mHealth researchers through focus groups and workshops. Together, a mobile health (mHealth) aide was codesigned and developed to streamline and filter treatments based on family priorities. The aide contains a step-by-step guide, a search function, treatment factsheets, and support resources to empower evidence-based personalised decision making. The mHealth app has been endorsed by research partners and will be freely available in app stores worldwide.

Artificial intelligence (AI)-driven clinical decision support (CDS) tools offer promising solutions for health care delivery by optimizing resource allocation, detecting deterioration, and enabling early interventions. However, adoption remains limited due to insufficient validation and a lack of transparency and trust. Explainable AI (XAI) seeks to improve user understanding of AI outputs; however, how clinicians interpret and integrate these explanations into their decision-making remains underexplored. Furthermore, discrepancies in explanations, known as the "disagreement problem," can undermine trust and, at worst, lead to poor clinical decisions. This study examines clinicians' perspectives on the role and value of explainability in AI-driven CDS tools within Australian critical care settings and the impact of discrepancies in AI-generated explanations on clinical decision-making. Qualitative data were collected using semistructured interviews with 14 clinical experts, incorporating scenario-based exercises, and were analyzed using inductive thematic analysis. Clinicians valued explainability, particularly in complex or unfamiliar situations, when explanations were clear, plausible, and actionable. Trust and perceived usefulness extended beyond explanation quality, encompassing factors such as system accuracy, alignment with clinicians' reasoning, workflow integration, and perceived reliability. Discrepancies in explanations generated by different XAI methods were not a major concern, provided that the AI-generated predictive alerts were accurate. This study provides design recommendations for developing trustworthy, user-centric CDS tools that incorporate XAI. Findings highlight that explainability is critical for establishing initial trust in AI-driven tools by supporting perceived usefulness, but its importance diminishes over time and with user expertise and familiarity, as learned usefulness takes precedence. Recommendations highlight the importance of aligning the design and implementation of AI tools with clinicians' needs to enhance trust, mitigate risks, and promote successful adoption for improved patient outcomes.

BACKGROUND AI-driven clinical decision support (CDS) tools offer promising solutions for healthcare delivery by optimising resource allocation, detecting deterioration and enabling early interventions. However, adoption remains limited due to insufficient validation and a lack of transparency. eXplainable AI (XAI) provides users with insights into AI-driven recommendations, but discrepancies in explanations, known as the "Disagreement Problem", can undermine trust and at worst, lead to poor clinical decisions. OBJECTIVE This study explores the perspectives of clinicians from Australian critical care settings on XAI and the impact of discrepancies in AI-generated explanations on decision-making. METHODS Qualitative data were collected using semi-structured interviews with 14 clinical experts, incorporating scenario-based exercises, and analysed using inductive thematic analysis. RESULTS Key factors influencing trust in XAI are identified, and the role of explainability in AI-driven tools are highlighted. Explainability was considered valuable, especially in unfamiliar situations or complex decisions, if the explanations were clear, plausible, and actionable. Discrepancies in explanations generated by different XAI methods are not the primary concern for clinicians, provided the AI’s prediction was accurate and the explanations offered actionable insights aligning with their mental model. CONCLUSIONS This study has identified design recommendations and implementation strategies for developing trustworthy, user-centric XAI-supported CDS tools. It also highlights that discrepancy between different explanations is not inherently problematic, provided the explanations are consistent with clinicians’ reasoning. Recommendations made highlight the importance of aligning the design and implementation of AI tools with clinicians’ needs to enhance trust, mitigate risks, and promote successful adoption for improved patient outcomes.

Background: Sleep-dependent memory (SDM) is the phenomenon where newly obtained memory traces are consolidated from short-term memory stores to long-term memory, underpinning memory for daily life. Administering SDM tasks presents considerable challenges, particularly for older adults with memory concerns, due to the need for sleep laboratories and research staff being present to administer the task. In response, we have developed a prototype mobile app aimed at automating the data collection process. Objective: This study investigates the perspectives of older adults, with subjective or objective cognitive impairment, regarding barriers and facilitators to using a new mobile app for at-home assessment of SDM. Methods: In total, 11 participants aged 50 years and older were recruited from the Healthy Brain Ageing memory clinic, a specialized research memory clinic that focuses on the assessment and early intervention of cognitive decline. Two focus groups were conducted and thematically analyzed using NVivo (version 13; Lumivero). Results: On average, participants were aged 68.5 (SD 5.1) years, and 4/11 were male. Eight participants had subjective cognitive impairment, and 3 participants had mild cognitive (objective) impairment. Two main themes emerged from the focus groups, shedding light on participants’ use of mobile phones and the challenges and facilitators associated with transitioning from traditional laboratory-based assessments to home assessments. These challenges include maintaining accurate data, engaging with humans versus robots, and ensuring accessibility and task compliance. Additionally, potential solutions to these challenges were identified. Conclusions: Our findings underscore the importance of app flexibility in accommodating diverse user needs and preferences as well as in overcoming barriers. While some individuals required high-level assistance, others expressed the ability to navigate the app independently or with minimal support. In conclusion, older adults provided valuable insights into the app modifications, user needs, and accessibility requirements enabling home-based SDM assessment.

BACKGROUND Sleep-dependent memory is the phenomenon where newly obtained memory traces are consolidated from short-term memory stores to long-term memory, underpinning memory for daily life. Administering sleep-dependent memory tasks presents considerable challenges, particularly for older adults with memory concerns due to the need for sleep laboratories and research staff present to administer the task. In response, we have developed a prototype mobile application aimed at automating the data collection process. OBJECTIVE This study investigates the perspectives of older adults, both with and without cognitive impairment, regarding barriers and facilitators to using a new mobile application for at-home assessment of Sleep-Dependent Memory. METHODS Eleven participants aged over 50 were recruited from the Healthy Brain Ageing memory clinic, a specialised research memory clinic that focuses on the assessment and early intervention of cognitive decline. Two focus groups were conducted and thematically analysed using NVivo and the techniques described in Braun and Clarke (2006). RESULTS On average, participants were aged 68.5 (4/11 were male), eight participants had subjective cognitive impairment, and three participants had mild cognitive impairment. Two main themes emerged from the focus groups, shedding light on participants' use of mobile phones and the challenges and facilitators associated with transitioning from traditional laboratory-based assessments to home assessments. These challenges include maintaining accurate data, engaging with humans versus robots, and ensuring accessibility and task compliance. Additionally, potential solutions to these challenges were identified. CONCLUSIONS Our findings underscore the importance of app flexibility in accommodating diverse user needs and preferences, as well as in overcoming barriers. While some individuals require high-level assistance, others express the ability to navigate the app independently with minimal support. In conclusion, older adults, regardless of cognitive status, express a desire for flexibility in mobile applications used for cognitive assessments.

There are numerous behavioural, social and environmental factors that influence the symptomatology of a chronic health condition. These factors and how they manifest are often very specific to the individual, which creates challenges for applying macro population health approaches and insights to guide treatment. An artificial intelligence system, referred to as a non-axiomatic reasoning system (NARS), is presented. Learning in NARS is incremental and ongoing. A practical application of NARS in chronic pain management is demonstrated, as NARS can establish associations with behavioural activities that might exacerbate pain levels and revise the strengths of these associations over time. The system has potential application in any condition requiring patient-centric adaption.

An innovative chatbot incorporates a drawing tool allowing users to draw pictures that symbolise the nature of their chronic pain. Rather than simply ask ‘What did you draw?” what if the chatbot could engage the user to provide insight into symbols and images related to pain and suffering? The system was tested on images that included features of clinical interest in a first step toward a chatbot able to ‘see’ and discuss visual input. Such a chatbot has the potential for retrospective and prospective applications. *Contains childhood sexual abuse references*

Decompressive craniectomy (DC) is a surgical procedure where a portion of the skull is removed to relieve potentially fatal brain swelling. As the swelling can take months to subside, the patient is discharged from an acute care facility to recover prior to cranioplasty (reconstruction surgery). Cranioplasty is associated with complications due to infection, seizure, haematoma and death. The interval between these surgeries is potentially a modifiable risk factor to reduce the rate of complication. We aim to allow clinicians to remotely monitor patients to facilitate an optimal pre-operative review. We have developed a platform technology encompassing a 'smart' device fitted into a skullcap to measure physiological parameters, such as changes in brain swelling, and a clinician portal that allows remote viewing of the patients' physiological data. The use of patient generated data during the transition between craniectomy and cranioplasty has the potential to significantly improve neurorehabilitation outcomes for patients.