Tabula Rasa: A Case Study in Chronic Pain Management Using Individual-Centric AI.

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.

Conversations in Content and Context: Can We Teach AI to Chat About Drawings?

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.

Understanding the Barriers to Genomic Healthcare in Queensland Through an Information Management Lens.

Genomic science has the potential to rapidly advance understanding of human biology in the medical context and the subsequent provision of tailored healthcare. Implementing such a disruptive and transformative technology into an existing and stretched health system will require a whole of system approach and a keen understanding of the limitations to be navigated in broadening the system to include genomic healthcare. This paper reports on the barriers to implementation faced by clinical demonstration projects in integrating into the existing infrastructure in Queensland.

Developing Digital Facilitation of Assessments in the Absence of an Interpreter: Participatory Design and Feasibility Evaluation With Allied Health Groups.

BACKGROUND: To ensure appropriate and timely care, interpreters are often required to aid communication between clinicians and patients from non-English speaking backgrounds. In a hospital environment, where care is delivered 24 hours a day, interpreters are not always available. Subsequently, culturally and linguistically diverse (CALD) patients are sometimes unable to access timely assessment because of clinicians' inability to communicate directly with them. OBJECTIVE: The aim of this study was to design and evaluate CALD Assist, a tablet app to assist communication between patients and allied health clinicians in the absence of an interpreter. CALD Assist uses key phrases translated into common languages and uses pictorial, written, and voice-over prompts to facilitate communication during basic patient assessment. METHODS: CALD Assist's design, functionality, and content were determined through focus groups with clinicians and informed by interpreting and cultural services. An evaluation was conducted in a live trial phase on eight wards across 2 campuses of a hospital in Victoria, Australia. RESULTS: A commercial grade CALD Assist mobile app for five disciplines within allied health was developed and evaluated. The app includes a total of 95 phrases in ten different languages to assist clinicians during their initial assessment. Evaluation results show that clinicians' confidence in their assessment increased with use of the CALD Assist app: clinicians' reports of "complete confidence" increased from 10% (3/30) to 42% (5/12), and assessment reports of "no confidence" decreased from 57% (17/30) to 17% (2/12). Average time required to complete an assessment with patients from non-English speaking backgrounds reduced from 42.0 to 15.6 min. CONCLUSIONS: Through the use of CALD Assist, clinician confidence in communicating with patients from non-English speaking backgrounds in the absence of an interpreter increased, providing patients from non-English speaking backgrounds with timely initial assessments and subsequent care in line with their English speaking peers. Additionally, the inclusion of images and video demonstrations in CALD Assist increased the ability to communicate with patients and overcome literacy-related barriers. Although a number of hurdles were faced, user uptake and satisfaction were positive, and the app is now available in the Apple App Store.

Understanding Smart Home Sensor Data for Ageing in Place Through Everyday Household Routines: A Mixed Method Case Study.

BACKGROUND: An ongoing challenge for smart homes research for aging-in-place is how to make sense of the large amounts of data from in-home sensors to facilitate real-time monitoring and develop reliable alerts. OBJECTIVE: The objective of our study was to explore the usefulness of a routine-based approach for making sense of smart home data for the elderly. METHODS: Maximum variation sampling was used to select three cases for an in-depth mixed methods exploration of the daily routines of three elderly participants in a smart home trial using 180 days of power use and motion sensor data and longitudinal interview data. RESULTS: Sensor data accurately matched self-reported routines. By comparing daily movement data with personal routines, it was possible to identify changes in routine that signaled illness, recovery from bereavement, and gradual deterioration of sleep quality and daily movement. Interview and sensor data also identified changes in routine with variations in temperature and daylight hours. CONCLUSIONS: The findings demonstrated that a routine-based approach makes interpreting sensor data easy, intuitive, and transparent. They highlighted the importance of understanding and accounting for individual differences in preferences for routinization and the influence of the cyclical nature of daily routines, social or cultural rhythms, and seasonal changes in temperature and daylight hours when interpreting information based on sensor data. This research has demonstrated the usefulness of a routine-based approach for making sense of smart home data, which has furthered the understanding of the challenges that need to be addressed in order to make real-time monitoring and effective alerts a reality.

Interacting with Genomic Data: Clinician Requirements and Prototype Structure.

Healthcare is currently being transformed by the introduction of genomic sequencing - a major advancement in personalised medicine. This advent provides new opportunities for clinicians to use genomic data in decision making about patient diagnosis and treatment, but this can only be achieved through access to data and support in its use. Engaging with clinicians in the development of decision support tools will optimise relevance and adoption of genomic sequencing in healthcare. In this study, existing data from clinician workshops and interviews together with horizon scanning of relevant technologies were used to define clinician portal specifications. We describe a preliminary structure of a decision support tool for use by clinicians and the manner in which the technology may be evaluated.

Hello Harlie: Enabling Speech Monitoring Through Chat-Bot Conversations.

People with neurological conditions such as Parkinson's disease and dementia are known to have difficulties in language and communication. This paper presents initial testing of an artificial conversational agent, called Harlie. Harlie runs on a smartphone and is able to converse with the user on a variety of topics. A description of the application and a sample dialog are provided to illustrate the various roles chat-bots can play in the management of neurological conditions. Harlie can be used for measuring voice and communication outcomes during the daily life of the user, and for gaining information about challenges encountered. Moreover, it is anticipated that she may also have an educational and support role.

Designing Technology for Assessments of CALD Patients.

Interpreters are required to aid communication between clinicians and culturally and linguistically diverse (CALD) patients to ensure appropriate and timely care. Demand for interpreting services however, often exceeds supply. A mobile app to translate clinical assessment questions in 10 common languages using pictorial, written and voice-over prompts to assist patient assessments when interpreters are unavailable has been developed. This paper reports on the User Needs Analysis that informed the app. The analysis consisted of focus groups with allied health clinicians to understand pertinent aspects of initial allied health assessments and the communication needs to be addressed in the design of an app-based patient assessment tool. Outcomes show that of primary importance to clinicians was the ability to not only ask the patients questions, but to communicate information to increase understanding of, and ensure compliance with, treatments and interventions to promote patient function and comfort.

Activity of Daily Living assessment through wireless sensor data.

Activity of Daily Living has become a clinical de facto instrument to assess daily functional status of older people living independently at home. Almost all ADLs scales are based on subjective assessment of clinical staff and self-reported responses of the elderly person. A great deal of variability in ADL assessment is likely due to the different cultural beliefs, language and education, and over-assessment of personal capability to potentially avoid negative consequences. This paper proposes automatic and objective ADLs assessment as key component of a technology platform that supports older people to live independently in their home, called Smarter Safer Homes. The objective ADL assessment is achieved through communicating data from simple non-intrusive, wireless sensors placed in a home environment. Pilot sensor data sets were collected over six months from nine independent living homes of participants aged 70+ year. The application of a clustering based, unsupervised learning method on these data sets demonstrates the potential to automatically detect five domains of activity contributing to functional independence. Furthermore, the method provides features that support elderlys self-monitoring of daily activities more regularly, that could provide the potential for timely and early intervention from family and carers.