An official website of the United States government
Abstract Customizing participation-focused pediatric rehabilitation interventions is an important but also complex and potentially resource intensive process, which may benefit from automated and simplified steps. This research aimed at applying natural language processing to develop and identify a best performing predictive model that classifies caregiver strategies into participation-related constructs, while filtering out non-strategies. We created a dataset including 1,576 caregiver strategies obtained from 236 families of children and youth (11–17 years) with craniofacial microsomia or other childhood-onset disabilities. These strategies were annotated to four participation-related constructs and a non-strategy class. We experimented with manually created features (i.e., speech and dependency tags, predefined likely sets of words, dense lexicon features (i.e., Unified Medical Language System (UMLS) concepts)) and three classical methods (i.e., logistic regression, naïve Bayes, support vector machines (SVM)). We tested a series of binary and multinomial classification tasks applying 10-fold cross-validation on the training set (80%) to test the best performing model on the held-out test set (20%). SVM using term frequency-inverse document frequency (TF-IDF) was the best performing model for all four classification tasks, with accuracy ranging from 78.10 to 94.92% and a macro-averaged F1-score ranging from 0.58 to 0.83. Manually created features only increased model performance when filtering out non-strategies. Results suggest pipelined classification tasks (i.e., filtering out non-strategies; classification into intrinsic and extrinsic strategies; classification into participation-related constructs) for implementation into participation-focused pediatric rehabilitation interventions like Participation and Environment Measure Plus (PEM+) among caregivers who complete the Participation and Environment Measure for Children and Youth (PEM-CY).
more »
« less
Diversified caregiver input to upgrade the Young Children’s Participation and Environment Measure for equitable pediatric re/habilitation practice
Abstract BackgroundPractitioner and family experiences of pediatric re/habilitation can be inequitable. The Young Children’s Participation and Environment Measure (YC-PEM) is an evidence-based and promising electronic patient-reported outcome measure that was designed with and for caregivers for research and practice. This study examined historically minoritized caregivers’ responses to revised YC-PEM content modifications and their perspectives on core intelligent virtual agent functionality needed to improve its reach for equitable service design. MethodsCaregivers were recruited during a routine early intervention (EI) service visit and met five inclusion criteria: (1) were 18 + years old; (2) identified as the parent or legal guardian of a child 0–3 years old enrolled in EI services for 3 + months; (3) read, wrote, and spoke English; (4) had Internet and telephone access; and (5) identified as a parent or legal guardian of a Black, non-Hispanic child or as publicly insured. Three rounds of semi-structured cognitive interviews (55–90 min each) used videoconferencing to gather caregiver feedback on their responses to select content modifications while completing YC-PEM, and their ideas for core intelligent virtual agent functionality. Interviews were transcribed verbatim, cross-checked for accuracy, and deductively and inductively content analyzed by multiple staff in three rounds. ResultsEight Black, non-Hispanic caregivers from a single urban EI catchment and with diverse income levels (Mdn = $15,001–20,000) were enrolled, with children (M = 21.2 months,SD = 7.73) enrolled in EI. Caregivers proposed three ways to improve comprehension (clarify item wording, remove or simplify terms, add item examples). Environmental item edits prompted caregivers to share how they relate and respond to experiences with interpersonal and institutional discrimination impacting participation. Caregivers characterized three core functions of a virtual agent to strengthen YC-PEM navigation (read question aloud, visual and verbal prompts, more examples and/or definitions). ConclusionsResults indicate four ways that YC-PEM content will be modified to strengthen how providers screen for unmet participation needs and determinants to design pediatric re/habilitation services that are responsive to family priorities. Results also motivate the need for user-centered design of an intelligent virtual agent to strengthen user navigation, prior to undertaking a community-based pragmatic trial of its implementation for equitable practice.
more »
« less
- Award ID(s):
- 2125411
- PAR ID:
- 10448346
- Publisher / Repository:
- Springer Science + Business Media
- Date Published:
- Journal Name:
- Journal of Patient-Reported Outcomes
- Volume:
- 7
- Issue:
- 1
- ISSN:
- 2509-8020
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Preparing preservice teachers (PSTs) to be able to notice, interpret, respond to and orchestrate student ideas—the core practices of responsive teaching—is a key goal for contemporary science and mathematics teacher education. This mixed‐methods study, employing a virtual reality (VR)‐supported simulation integrated with artificial intelligence (AI)‐powered virtual students, explored the frequent patterns of PSTs' talk moves as they attempted to orchestrate a responsive discussion, as well as the affordances and challenges of leveraging AI‐supported virtual simulation to enhance PSTs' responsive teaching skills. Sequential analysis of the talk moves of both PSTs (n = 24) and virtual students indicated that although PSTs did employ responsive talk moves, they encountered difficulties in transitioning from the authoritative, teacher‐centred teaching approach to a responsive way of teaching. The qualitative analysis with triangulated dialogue transcripts, observational field notes and semi‐structured interviews revealed participants' engagement in (1) orchestrating discussion by leveraging the design features of AI‐supported simulation, (2) iterative rehearsals through naturalistic and contextualized interactions and (3) exploring realism and boundaries in AI‐powered virtual students. The study findings provide insights into the potential of leveraging AI‐supported virtual simulation to improve PSTs' responsive teaching skills. The study also underscores the need for PSTs to engage in well‐designed pedagogical practices with adaptive and in situ support. Practitioner notesWhat is already known about this topicDeveloping the teaching capacity of responsive teaching is an important goal for preservice teacher (PST) education. PSTs need systematic opportunities to build fluency in this approach.Virtual simulations can provide PSTs with the opportunities to practice interactive teaching and have been shown to improve their teaching skills.Artificial intelligence (AI)‐powered virtual students can be integrated into virtual simulations to enable interactive and authentic practice of teaching.What this paper addsAI‐supported simulation has the potential to support PSTs' responsive teaching skills.While PSTs enact responsive teaching talk moves, they struggle to enact those talk moves in challenging teaching scenarios due to limited epistemic and pedagogical resources.AI‐supported simulation affords iterative and contextualized opportunities for PSTs to practice responsive teaching talk moves; it challenges teachers to analyse student discourse and respond in real time.Implications for practice and/or policyPSTs should build a teaching repertoire with both basic and advanced responsive talk moves.The learning module should adapt to PSTs' prior experience and provide PSTs with in situ learning support to navigate challenging teaching scenarios.Integrating interaction features and AI‐based virtual students into the simulation can facilitate PSTs' active participation.more » « less
-
Abstract This paper outlines the potential gains for Constructionist research and praxis in modelling that might be obtained by recognising the power of the Patch—a humble computational being in the NetLogo modelling environment that has been overshadowed by its more popular fellow agent, the Turtle. To contextualise this opportunity, I describe how Constructionist modelling has thrived by promoting forms of learning that rely on learners’ identifying with agents. I argue that patches are a neglected agent type in this multi‐agent modelling tradition, and that the possibilities for learners to adopt the patch perspective in support of exploratory forms of modelling and aesthetic expression have been under‐researched. Nevertheless, I show there are a variety of powerful ways for learners––both individually and in groups––to identify with patches. I describe ongoing research showing how taking an aesthetic approach to patches has the potential to support individuals and groups in powerful forms of learning with and about multi‐agent modelling. Practitioner notesWhat is already known about this topicTurtles (movable agents in Logo and Constructionist environments descended from Logo) can be ‘transitional objects’ that provide learners a way to make powerful ideas their own.These agents can be powerful ‘objects‐to‐think‐with’ in large part because they encourage learners to identify with them in a form of learning known as ‘syntonic learning’.Expressive activities that draw on learners’aestheticinterests can support their learning with and about computational representations.Multi‐agent modelling is a powerful extension of Logo‐based learning environments that provides access to powerful ideas about complex systems and their emergent properties.In the multi‐agent setting, individual learners and/or groups of learners can identify syntonically with agents to provide entry points for reasoning about complexity.What this paper addsPatches (non‐movable agents in the NetLogo modelling environment) are under‐represented in the research on multi‐agent modelling, and the potential for learners to adopt the patches’ perspective has been neglected.An aesthetically driven approach to patches can ground students’ understanding of their expressive value.Participatory activities in which learners play the role of patches (called ‘Stadium Card’ activities) can ground the patch perspective, so that learners can achieve a form of syntonicity and/or collectively adopt the perspective of patches in the aggregate.Participatory activities that blend intrinsic and extrinsic perspectives on the patch grid can further enhance learners’ facility with programming for patches and their understanding of patches’ collective expressive power.Implications for practice and/or policyBalancing the focus between turtles and patches can enrich the modelling toolbox of learners new to agent‐based modelling.Patchesdocapture important aspects of individual and collective experience, and so can be good objects‐to‐think‐with, especially when conceptualising phenomena at a larger scale.The expressive potential of the patch grid is an important topic for computer science as well (eg, through 2D cellular automata). This is a rich context for learning in itself, which can be made accessible to groups of learners through physical or virtual participatory role‐play.Moreover, physical or virtual grids of people‐patches may exhibit novel aggregate computational properties that could in turn become interesting areas for research in computer science.more » « less
-
Teaching supports the high‐fidelity transmission of knowledge and skills. This study examined similarities and differences in caregiver teaching practices in the United States and Vanuatu (N = 125 caregiver and 3‐ to 8‐year‐old child pairs) during a collaborative problem‐solving task. Caregivers used diverse verbal and nonverbal teaching practices and adjusted their behaviors in response to task difficulty and child age in both populations. U.S. caregivers used practices consistent with a direct active teaching style typical of formal education, including guiding children’s participation, frequent praise, and facilitation. In contrast, Ni‐Vanuatu caregivers used practices associated with informal education and divided tasks with children based on difficulty. The implications of these findings for claims about the universality and diversity of caregiver teaching are discussed.more » « less
-
Abstract ObjectiveA mother–child dyad trajectory model of weight and body composition spanning from conception to adolescence was developed to understand how early life exposures shape childhood body composition. MethodsAfrican American (49.3%) and Dominican (50.7%) pregnant mothers (n= 337) were enrolled during pregnancy, and their children (47.5% female) were followed from ages 5 to 14. Gestational weight gain (GWG) was abstracted from medical records. Child weight, height, percentage body fat, and waist circumference were measured. GWG and child body composition trajectories were jointly modeled with a flexible latent class model with a class membership component that included prepregnancy BMI. ResultsFour prenatal and child body composition trajectory patterns were identified, and sex‐specific patterns were observed for the joint GWG–postnatal body composition trajectories with more distinct patterns among girls but not boys. Girls of mothers with high GWG across gestation had the highest BMIzscore, waist circumference, and percentage body fat trajectories from ages 5 to 14; however, boys in this high GWG group did not show similar growth patterns. ConclusionsJointly modeled prenatal weight and child body composition trajectories showed sex‐specific patterns. Growth patterns from childhood though early adolescence appeared to be more profoundly affected by higher GWG patterns in females, suggesting sex differences in developmental programming.more » « less
