Prototyping the Automated Food Imaging and Nutrient Intake Tracking System: Modified Participatory Iterative Design Sprint

Design of a Dyadic Digital Health Module for Chronic Disease Shared Care: Development Study

BACKGROUND

The COVID-19 pandemic forced the spread of digital health tools to address limited clinical resources for chronic health management. It also illuminated a population of older patients requiring an informal caregiver (IC) to access this care due to accessibility, technological literacy, or English proficiency concerns. For patients with heart failure (HF), this rapid transition exacerbated the demand on ICs and pushed Canadians toward a dyadic care model where patients and ICs comanage care. Our previous work identified an opportunity to improve this dyadic HF experience through a shared model of dyadic digital health. We call this alternative model of care "Caretown for Medly," which empowers ICs to concurrently expand patients' self-care abilities while acknowledging ICs' eagerness to provide greater support.

OBJECTIVE

We present the systematic design and development of the Caretown for Medly dyadic management module. While HF is the outlined use case, we outline our design methodology and report on 6 core disease-invariant features applied to dyadic shared care for HF management. This work lays the foundation for future usability assessments of Caretown for Medly.

METHODS

We conducted a qualitative, human-centered design study based on 25 semistructured interviews with self-identified ICs of loved ones living with HF. Interviews underwent thematic content analysis by 2 coders independently for themes derived deductively (eg, based on the interview guide) and inductively refined. To build the Caretown for Medly model, we (1) leveraged the Knowledge to Action (KTA) framework to translate knowledge into action and (2) borrowed Google Sprint's ability to quickly "solve big problems and test new ideas," which has been effective in the medical and digital health spaces. Specifically, we blended these 2 concepts into a new framework called the "KTA Sprint."

RESULTS

We identified 6 core disease-invariant features to support ICs in care dyads to provide more effective care while capitalizing on dyadic care's synergistic benefits. Features were designed for customizability to suit the patient's condition, informed by stakeholder analysis, corroborated with literature, and vetted through user needs assessments. These features include (1) live reports to enhance data sharing and facilitate appropriate IC support, (2) care cards to enhance guidance on the caregiving role, (3) direct messaging to dissolve the disconnect across the circle of care, (4) medication wallet to improve guidance on managing complex medication regimens, (5) medical events timeline to improve and consolidate management and organization, and (6) caregiver resources to provide disease-specific education and support their self-care.

CONCLUSIONS

These disease-invariant features were designed to address ICs' needs in supporting their care partner. We anticipate that the implementation of these features will empower a shared model of care for chronic disease management through digital health and will improve outcomes for care dyads.

Dietary assessment methods for measurement of oral intake in acute care and critically ill hospitalised patients: a scoping review

Quantification of oral intake within the hospital setting is required to guide nutrition care. Multiple dietary assessment methods are available, yet details regarding their application in the acute care setting are scarce. This scoping review, conducted in accordance with JBI methodology, describes dietary assessment methods used to measure oral intake in acute and critical care hospital patients. The search was run across four databases to identify primary research conducted in adult acute or critical care settings from 1st of January 2000-15th March 2023 which quantified oral diet with any dietary assessment method. In total, 155 articles were included, predominantly from the acute care setting (n = 153, 99%). Studies were mainly single-centre (n = 138, 88%) and of observational design (n = 135, 87%). Estimated plate waste (n = 59, 38%) and food records (n = 43, 28%) were the most frequent assessment methods with energy and protein the main nutrients quantified (n = 81, 52%). Validation was completed in 23 (15%) studies, with the majority of these using a reference method reliant on estimation (n = 17, 74%). A quarter of studies (n = 39) quantified completion (either as complete versus incomplete or degree of completeness) and four studies (2.5%) explored factors influencing completion. Findings indicate a lack of high-quality evidence to guide selection and application of existing dietary assessment methods to quantify oral intake with a particular absence of evidence in the critical care setting. Further validation of existing tools and identification of factors influencing completion is needed to guide the optimal approach to quantification of oral intake in both research and clinical contexts.

Boundary Objects as Dialogical Learning Accelerators for Social Change in Design for Health: Systematic Review

Background

Boundary objects can add value for innovative design and implementation research in health care through their organizational focus and the dynamic structure between ill-structured and tailored use. However, when innovation is approached as a boundary object, more attention will need to be paid to the preimplementation phase. Research and design thinking pay attention to the preimplementation stage but do not have a social or organizational focus per se. The integration of boundary objects in design methodologies can provide a more social and organizational focus in innovative design projects by mapping out the mechanisms that occur at boundaries during design. Four dialogical learning mechanisms that can be triggered at boundaries have been described in the literature: identification, coordination, reflection, and transformation. These mechanisms seem suitable for integration in innovative design research on health.

Objective

Focusing on innovation in health, this study aims to find out whether the different learning mechanisms can be linked to studies on health innovation that mention boundary objects as a concept and assess whether the related mechanisms provide insight into the stage of the design and implementation or change process.

Methods

The following 6 databases were searched for relevant abstracts: PubMed, Scopus, Education Resources Information Center, PsycINFO, Information Science and Technology Abstracts, and Embase. These databases cover a wide range of published studies in the field of health.

Results

Our initial search yielded 3102 records; after removing the duplicates, 2186 (70.47%) records were screened on the title and abstract, and 25 (0.81%) papers were included; of the 13 papers where we identified 1 mechanism, 5 (38%) described an innovation or innovative project, and of the 12 papers where we identified more mechanisms, 9 (75%) described the development or implementation of an innovation. The reflective mechanism was not identified solely but was present in papers describing a more successful development or implementation project of innovation. In these papers, the predetermined goals were achieved, and the process of integration was relatively smoother.

Conclusions

The concept of boundary objects has found its way into health care. Although the idea of a boundary object was introduced to describe how specific artifacts can fulfill a bridging function between different sociocultural sites and thus have a social focus, the focus in the included papers was often on the boundary object itself rather than the social effect. The reflection and transformation mechanisms were underrepresented in the included studies but based on the findings in this review, pursuing to trigger the reflective mechanism in design, development, and implementation projects can lead to a more fluid and smooth integration of innovation into practice.

Automated food intake tracking requires depth-refined semantic segmentation to rectify visual-volume discordance in long-term care homes

Malnutrition is a multidomain problem affecting 54% of older adults in long-term care (LTC). Monitoring nutritional intake in LTC is laborious and subjective, limiting clinical inference capabilities. Recent advances in automatic image-based food estimation have not yet been evaluated in LTC settings. Here, we describe a fully automatic imaging system for quantifying food intake. We propose a novel deep convolutional encoder-decoder food network with depth-refinement (EDFN-D) using an RGB-D camera for quantifying a plate's remaining food volume relative to reference portions in whole and modified texture foods. We trained and validated the network on the pre-labelled UNIMIB2016 food dataset and tested on our two novel LTC-inspired plate datasets (689 plate images, 36 unique foods). EDFN-D performed comparably to depth-refined graph cut on IOU (0.879 vs. 0.887), with intake errors well below typical 50% (mean percent intake error: [Formula: see text]%). We identify how standard segmentation metrics are insufficient due to visual-volume discordance, and include volume disparity analysis to facilitate system trust. This system provides improved transparency, approximates human assessors with enhanced objectivity, accuracy, and precision while avoiding hefty semi-automatic method time requirements. This may help address short-comings currently limiting utility of automated early malnutrition detection in resource-constrained LTC and hospital settings.

Developing an Asthma Self-management Intervention Through a Web-Based Design Workshop for People With Limited Health Literacy: User-Centered Design Approach

Background

Technology, including mobile apps, has the potential to support self-management of long-term conditions and can be tailored to enhance adoption. We developed an app to support asthma self-management among people with limited health literacy in a web-based workshop (to ensure physical distancing during the COVID-19 pandemic).

Objective

The aim of this study is to develop and test a prototype asthma self-management mobile app tailored to the needs of people with limited health literacy through a web-based workshop.

Methods

We recruited participants from a primary care center in Malaysia. We adapted a design sprint methodology to a web-based workshop in five stages over 1 week. Patients with asthma and limited health literacy provided insights into real-life self-management issues in stage 1, which informed mobile app development in stages 2-4. We recruited additional patients to test the prototype in stage 5 using a qualitative research design. Participants gave feedback through a concurrent thinking-aloud process moderated by a researcher. Each interview lasted approximately 1 hour. Screen recordings of app browsing activities were performed. Interviews were audio-recorded and analyzed using a thematic approach to identify utility and usability issues.

Results

The stakeholder discussion identified four themes: individual, family, friends, and society and system levels. Five patients tested the prototype. Participants described 4 ways in which the app influenced or supported self-management (utility): offering information, providing access to an asthma action plan, motivating control of asthma through support for medication adherence, and supporting behavior change through a reward system. Specific usability issues addressed navigation, comprehension, and layout.

Conclusions

This study proved that it was possible to adapt the design sprint workshop to a web-based format with the added advantage that it allowed the development and the testing process to be done efficiently through various programs. The resultant app incorporated advice from stakeholders, including sources for information about asthma, medication and appointment reminders, accessible asthma action plans, and sources for social support. The app is now ready to move to feasibility testing.

Using the Design Sprint process to enhance and accelerate behavioral medicine progress: a case study and guidance

While challenges in the translation of behavioral medicine knowledge from academic settings to real-world use are well documented, they could potentially be reduced through the use of the Design Sprint process, a roadmap that facilitates progression from an idea to a product in 5 days via agile design and user-centered design principles. The Design Sprint is well aligned with several priorities of and methods common in behavioral medicine, including obtaining end-user feedback and thinking about implementation during intervention development. The Design Sprint could be used by behavioral medicine researchers for the development of research tools, implementation strategies, and behavior change interventions. The process may encourage creative and focused thinking, speed product development, and facilitate early user input. However, translating the Design Sprint to behavioral medicine research may present challenges, such as difficulty getting buy-in from team members, inconsistencies between the Design Sprint timeline, the need to obtain institutional review board approval for user testing, and the lack of traditional research processes (e.g., incorporating scientific research into intervention design). Several solutions and adaptations are possible to overcome these challenges while still maintaining the core features of the Design Sprint process. To demonstrate the use of the Design Sprint and potential adaptations, we present a case study of the development of a patient-facing digital tool for weight management and an accompanying implementation strategy. In conclusion, the Design Sprint offers behavioral medicine researchers an approach to developing new products with numerous potential benefits to researchers and to the individuals and communities we seek to impact.