Background In the last decade, there has been a rapid increase in research on the use of artificial intelligence (AI) to improve child and youth participation in daily life activities, which is a key rehabilitation outcome. However, existing reviews place variable focus on participation, are narrow in scope, and are restricted to select diagnoses, hindering interpretability regarding the existing scope of AI applications that target the participation of children and youth in a pediatric rehabilitation setting. Objective The aim of this scoping review is to examine how AI is integrated into pediatric rehabilitation interventions targeting the participation of children and youth with disabilities or other diagnosed health conditions in valued activities. Methods We conducted a comprehensive literature search using established Applied Health Sciences and Computer Science databases. Two independent researchers screened and selected the studies based on a systematic procedure. Inclusion criteria were as follows: participation was an explicit study aim or outcome or the targeted focus of the AI application; AI was applied as part of the provided and tested intervention; children or youth with a disability or other diagnosed health conditions were the focus of either the study or AI application or both; and the study was published in English. Data were mapped according to the types of AI, the mode of delivery, the type of personalization, and whether the intervention addressed individual goal-setting. Results The literature search identified 3029 documents, of which 94 met the inclusion criteria. Most of the included studies used multiple applications of AI with the highest prevalence of robotics (72/94, 77%) and human-machine interaction (51/94, 54%). Regarding mode of delivery, most of the included studies described an intervention delivered in-person (84/94, 89%), and only 11% (10/94) were delivered remotely. Most interventions were tailored to groups of individuals (93/94, 99%). Only 1% (1/94) of interventions was tailored to patients’ individually reported participation needs, and only one intervention (1/94, 1%) described individual goal-setting as part of their therapy process or intervention planning. Conclusions There is an increasing amount of research on interventions using AI to target the participation of children and youth with disabilities or other diagnosed health conditions, supporting the potential of using AI in pediatric rehabilitation. On the basis of our results, 3 major gaps for further research and development were identified: a lack of remotely delivered participation-focused interventions using AI; a lack of individual goal-setting integrated in interventions; and a lack of interventions tailored to individually reported participation needs of children, youth, or families.
more »
« less
Capturing and Operationalizing Participation in Pediatric Re/Habilitation Research Using Artificial Intelligence: A Scoping Review
Background There is increased interest in using artificial intelligence (AI) to provide participation-focused pediatric re/habilitation. Existing reviews on the use of AI in participation-focused pediatric re/habilitation focus on interventions and do not screen articles based on their definition of participation. AI-based assessments may help reduce provider burden and can support operationalization of the construct under investigation. To extend knowledge of the landscape on AI use in participation-focused pediatric re/habilitation, a scoping review on AI-based participation-focused assessments is needed. Objective To understand how the construct of participation is captured and operationalized in pediatric re/habilitation using AI. Methods We conducted a scoping review of literature published in Pubmed, PsycInfo, ERIC, CINAHL, IEEE Xplore, ACM Digital Library, ProQuest Dissertation and Theses, ACL Anthology, AAAI Digital Library, and Google Scholar. Documents were screened by 2–3 independent researchers following a systematic procedure and using the following inclusion criteria: (1) focuses on capturing participation using AI; (2) includes data on children and/or youth with a congenital or acquired disability; and (3) published in English. Data from included studies were extracted [e.g., demographics, type(s) of AI used], summarized, and sorted into categories of participation-related constructs. Results Twenty one out of 3,406 documents were included. Included assessment approaches mainly captured participation through annotated observations ( n = 20; 95%), were administered in person ( n = 17; 81%), and applied machine learning ( n = 20; 95%) and computer vision ( n = 13; 62%). None integrated the child or youth perspective and only one included the caregiver perspective. All assessment approaches captured behavioral involvement, and none captured emotional or cognitive involvement or attendance. Additionally, 24% ( n = 5) of the assessment approaches captured participation-related constructs like activity competencies and 57% ( n = 12) captured aspects not included in contemporary frameworks of participation. Conclusions Main gaps for future research include lack of: (1) research reporting on common demographic factors and including samples representing the population of children and youth with a congenital or acquired disability; (2) AI-based participation assessment approaches integrating the child or youth perspective; (3) remotely administered AI-based assessment approaches capturing both child or youth attendance and involvement; and (4) AI-based assessment approaches aligning with contemporary definitions of participation.
more »
« less
- Award ID(s):
- 2125411
- NSF-PAR ID:
- 10339784
- Date Published:
- Journal Name:
- Frontiers in Rehabilitation Sciences
- Volume:
- 3
- ISSN:
- 2673-6861
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
The 4T Study 1 is a clinical pragmatic research trial that starts continuous glucose monitoring (CGM) within 30 days of T1D diagnosis and monitors PROs. We report the longitudinal relationship of PROs between newly diagnosed youth and parents/guardians (PG). PROs surveys were administered to youth and PG at baseline, 3, and 6 months. PG PROs included the 20-item parent Diabetes Distress Scale (DDS-P) and youth PROs were the 2-item Diabetes Distress Scale (DDS-2) and the 7-item PROMIS Pediatric Global Health Scale (PGH-7). Pearson correlations evaluated the relationship between scores on the PG and youth PROs. Youth (n=60 who were aged ≥11 years) with new onset T1D and their PG (n=125) were eligible to complete PROs, yet response rates varied (at baseline, 3-, 6-months: Youth 59%, 53%, and 50% vs PG 74%, 70%, and 66%). Correlations showed that PG diabetes distress was positively correlated with child diabetes distress at baseline (r=0.48, p=0.003) and at 3 months (r= 0.35, p=0.058). However, by 6 months, this association decreased in strength and significance (r=0.16, p=0.42). Youth global health was inversely correlated with PG diabetes distress at baseline (r=-0.36, p=0.029) and 3 months (r=-0.53, p=0.002) and this correlation was not significant at 6 months (r =-0.049, p=0.81). These data suggest that the relationship between PG diabetes distress and youth psychosocial states are dynamic. PG and youth psychosocial states are strongly associated after diagnosis and decrease over time. Utilization of CGM, age, T1D duration, response rate, and changes in the PG-youth relationship (such as decreased adult involvement or increased independence of youth) may contribute to our findings. Further investigation of longitudinal relationships between PG and youth PROs may provide additional insight into PG and youth psychosocial states and diabetes outcomes and indicate optimal timing for assessment and treatment referral. Disclosure S.A.Alamarie: None. F.K.Bishop: None. D.P.Zaharieva: Advisory Panel; Dexcom, Inc., Research Support; Hemsley Charitable Trust, International Society for Pediatric and Adolescent Diabetes, Insulet Corporation, Speaker's Bureau; American Diabetes Association, Ascensia Diabetes Care, Medtronic. P.Prahalad: None. M.Desai: None. D.M.Maahs: Advisory Panel; Medtronic, LifeScan Diabetes Institute, MannKind Corporation, Consultant; Abbott, Research Support; Dexcom, Inc. K.K.Hood: Consultant; Cecelia Health. A.Addala: None. E.Pang: None. A.L.Cortes-navarro: None. N.Arrizon-ruiz: None. I.Balistreri: None. A.Loyola: None. A.Schneider-utaka: None. V.Ritter: None. B.Shaw: None. Funding National Institutes of Health (R18DK122422)more » « less
-
Continuous glucose monitoring (CGM) use soon after T1D diagnosis in the 4T Study was associated with improved glycemic outcomes. We evaluated participant factors associated with elevated versus in target A1c for youth in the 4T Study. All youth from the 4T Study 1 (n=133) were evaluated. In this analysis, the 110 youth who had a final A1c between 6-13 months were included in a complete case analysis. These 110 youth were comparable to the 133 4T Study 1 youth by race/ethnicity, insurance, preferred language, and age. Group differences by non-ordered A1c categories were evaluated for categorical (race/ethnicity, insurance, gender, and language) and continuous (age and time from CGM start) variables via chi-square and ANOVA, respectively. A majority of youth in the 4T Study 1 met glycemic targets (65% with A1c ≤7% between 6-13 months post-diagnosis). Age, race/ethnicity, and insurance status were significantly associated with A1c categories (p=0.02 for all; Table). Higher A1c categories were more likely to include Hispanic youth and youth with public insurance. In the 4T Study 1, Hispanic youth and youth with public insurance had higher A1c categories despite similar CGM access and training. These findings suggest the need to address additional drivers of disparities in addition to CGM access. Approaches focused on health equity are required to improve glycemic outcomes in all youth newly diagnosed with T1D. Disclosure J. Kim: None. D. P. Zaharieva: Advisory Panel; Dexcom, Inc., Research Support; Hemsley Charitable Trust, International Society for Pediatric and Adolescent Diabetes, Insulet Corporation, Speaker's Bureau; American Diabetes Association, Ascensia Diabetes Care, Medtronic. F. K. Bishop: None. D. Scheinker: None. R. Johari: None. M. Desai: None. K. K. Hood: Consultant; Cecelia Health. D. M. Maahs: Advisory Panel; Medtronic, LifeScan Diabetes Institute, MannKind Corporation, Consultant; Abbott, Research Support; Dexcom, Inc. A. Addala: None. Funding National Institute of Diabetes and Digestive and Kidney Diseases (K23DK13134201, R18DK122422)more » « less
-
Methods to optimize care after T1D diagnosis are needed. We hypothesized lowering A1c targets to <7% would further lower A1c in the 4T Study in which CGM with asynchronous remote patient monitoring (RPM) is initiated after T1D diagnosis. All youth with newly diagnosed T1D (June 2020-March 2022) were offered CGM and RPM after diagnosis (Study 1, n=133). We compared A1c at 1-year in Study 1 with the 4T Pilot (2018-20) and Historical cohorts (2014-16). We visualized population-based A1c trajectories using locally estimated scatter plot smoothing (Fig) and % meeting A1c targets. Mean A1c at diagnosis was similar in Pilot (12.2%±2.1%) and Study 1 (12.2±2.4%) and higher than the Historical cohort (10.7±2.5%). In Study 1, the median age of diagnosis was 10.8 years, 55% male, 40% non-Hispanic White, and 38% with public insurance. CGM initiation occurred within 30 days of diagnosis in 98.5%. At 3, 6, 9, and 12 months post-diagnosis, the Study 1 cohort had LOESS-based mean A1c differences of 0.16%, 0.24%, 0.31%, and 0.58% lower than the Pilot and 0.04%, 0.60%, 0.83%, and 1.06% lower than the Historical cohort. A1c target <7% was met by 61% of youth in Study 1, 51% in the Pilot and 28% in the Historical cohort. Time <70mg/dl was ≤2.3%. The 4T program which emphasizes early CGM initiation, RPM, tighter glucose targets, and consistent team messaging was associated with lower A1c. These data support implementation of the 4T program in youth with T1D. Disclosure P.Prahalad: None. D.M.Maahs: Advisory Panel; Medtronic, LifeScan Diabetes Institute, MannKind Corporation, Consultant; Abbott, Research Support; Dexcom, Inc. 4t study group: n/a. V.Ding: None. D.P.Zaharieva: Advisory Panel; Dexcom, Inc., Research Support; Hemsley Charitable Trust, International Society for Pediatric and Adolescent Diabetes, Insulet Corporation, Speaker's Bureau; American Diabetes Association, Ascensia Diabetes Care, Medtronic. A.Addala: None. F.K.Bishop: None. D.Scheinker: None. R.Johari: None. M.Desai: None. K.K.Hood: Consultant; Cecelia Health. Funding National Institutes of Health (P30DK116074), (R18DK122422 to D.M.M.); Dexcom, Inc.; Lucile Packard Children’s Hospital Auxiliaries Endowment; Stanford Maternal and Child Health Research Institutemore » « less
-
Background Autism spectrum disorder (ASD) is a developmental disorder characterized by deficits in social communication and interaction, and restricted and repetitive behaviors and interests. The incidence of ASD has increased in recent years; it is now estimated that approximately 1 in 40 children in the United States are affected. Due in part to increasing prevalence, access to treatment has become constrained. Hope lies in mobile solutions that provide therapy through artificial intelligence (AI) approaches, including facial and emotion detection AI models developed by mainstream cloud providers, available directly to consumers. However, these solutions may not be sufficiently trained for use in pediatric populations. Objective Emotion classifiers available off-the-shelf to the general public through Microsoft, Amazon, Google, and Sighthound are well-suited to the pediatric population, and could be used for developing mobile therapies targeting aspects of social communication and interaction, perhaps accelerating innovation in this space. This study aimed to test these classifiers directly with image data from children with parent-reported ASD recruited through crowdsourcing. Methods We used a mobile game called Guess What? that challenges a child to act out a series of prompts displayed on the screen of the smartphone held on the forehead of his or her care provider. The game is intended to be a fun and engaging way for the child and parent to interact socially, for example, the parent attempting to guess what emotion the child is acting out (eg, surprised, scared, or disgusted). During a 90-second game session, as many as 50 prompts are shown while the child acts, and the video records the actions and expressions of the child. Due in part to the fun nature of the game, it is a viable way to remotely engage pediatric populations, including the autism population through crowdsourcing. We recruited 21 children with ASD to play the game and gathered 2602 emotive frames following their game sessions. These data were used to evaluate the accuracy and performance of four state-of-the-art facial emotion classifiers to develop an understanding of the feasibility of these platforms for pediatric research. Results All classifiers performed poorly for every evaluated emotion except happy. None of the classifiers correctly labeled over 60.18% (1566/2602) of the evaluated frames. Moreover, none of the classifiers correctly identified more than 11% (6/51) of the angry frames and 14% (10/69) of the disgust frames. Conclusions The findings suggest that commercial emotion classifiers may be insufficiently trained for use in digital approaches to autism treatment and treatment tracking. Secure, privacy-preserving methods to increase labeled training data are needed to boost the models’ performance before they can be used in AI-enabled approaches to social therapy of the kind that is common in autism treatments.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.3389/fresc.2022.855240
