Dataset Information

A Prediction Model for Detecting Developmental Disabilities in Preschool-Age Children Through Digital Biomarker-Driven Deep Learning in Serious Games: Development Study.

ABSTRACT:

Background

Early detection of developmental disabilities in children is essential because early intervention can improve the prognosis of children. Meanwhile, a growing body of evidence has indicated a relationship between developmental disability and motor skill, and thus, motor skill is considered in the early diagnosis of developmental disability. However, there are challenges to assessing motor skill in the diagnosis of developmental disorder, such as a lack of specialists and time constraints, and thus it is commonly conducted through informal questions or surveys to parents.

Objective

This study sought to evaluate the possibility of using drag-and-drop data as a digital biomarker and to develop a classification model based on drag-and-drop data with which to classify children with developmental disabilities.

Methods

We collected drag-and-drop data from children with typical development and developmental disabilities from May 1, 2018, to May 1, 2020, via a mobile application (DoBrain). We used touch coordinates and extracted kinetic variables from these coordinates. A deep learning algorithm was developed to predict potential development disabilities in children. For interpretability of the model results, we identified which coordinates contributed to the classification results by applying gradient-weighted class activation mapping.

Results

Of the 370 children in the study, 223 had typical development, and 147 had developmental disabilities. In all games, the number of changes in the acceleration sign based on the direction of progress both in the x- and y-axes showed significant differences between the 2 groups (P<.001; effect size >0.5). The deep learning convolutional neural network model showed that drag-and-drop data can help diagnose developmental disabilities, with an area under the receiving operating characteristics curve of 0.817. A gradient class activation map, which can interpret the results of a deep learning model, was visualized with the game results for specific children.

Conclusions

Through the results of the deep learning model, we confirmed that drag-and-drop data can be a new digital biomarker for the diagnosis of developmental disabilities.

SUBMITTER: Kim HH

PROVIDER: S-EPMC8214184 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BACKGROUND:Developmental disabilities are a set of heterogeneous delays or difficulties in one or more areas of neuropsychological development. Considering that childhood is an essential stage of brain development and developmental delays lead to personal or social burdens, the early detection of childhood developmental disabilities is important. However, early screening for developmental disabilities has been a challenge because of the fear of positive results, expensive tests, differences in diagnosis depending on examiners' abilities, and difficulty in diagnosis arising from the need for long-term follow-up observation. OBJECTIVE:This study aimed to assess the feasibility of using a serious game-derived index to identify heterogeneous developmental disabilities. This study also examines the correlation between the game-derived index and existing neuropsychological test results. METHODS:The randomized controlled trial involved 48 children with either normal development or developmental disabilities. In this clinical trial, we used 19 features (6 from the Korean-Wechsler Preschool and Primary Scale of Intelligence, 8 from the Psychoeducational Profile Revised, 2 from the Bruininks-Oseretsky Test of Motor Proficiency, Second Edition, and 3 from the Pediatric Evaluation of Disability Inventory) from neuropsychological tests and 9 (7 game scores, path accuracy, and completion rate) from the serious game, DoBrain. The following analysis was conducted based on participants' baseline information and neuropsychological test and game-derived index data for one week: (1) we compared the baseline information between the normal development and developmental disabilities groups; (2) then we measured the correlation between the game-derived index and the neuropsychological test scores for each group; and (3) we built a classifier based on the game-derived index with a Gaussian process method and then compared the area under the curve (AUC) with a model based on neuropsychological test results. RESULTS:A total of 16 children (normal development=9; developmental disabilities=7) were analyzed after selection. Their developmental abilities were assessed before they started to play the serious games, and statistically significant differences were found in both groups. Specifically, the normal development group was more developed than the developmental disabilities group in terms of social function, gross motor function, full-scale IQ, and visual motor imitation, in that order. Similarly, the normal development group obtained a higher score on the game-derived index than the developmental disabilities group. In the correlation analysis between the game-derived index and the neuropsychological tests, the normal development group showed greater correlation with more variables than the developmental disabilities group. The game-derived index-based model had an AUC=0.9, a similar detection value as the neuropsychological test-based model's AUC=0.86. CONCLUSIONS:A game-derived index based on serious games can detect children with heterogenous developmental disabilities. This suggests that serious games can be used as a potential screening tool for developmental disabilities. TRIAL REGISTRATION:Clinical Research Information Service KCT0003247; https://cris.nih.go.kr/cris/en/search/search_result_st01 .jsp?seq=12365.

Project description:BackgroundArtificial intelligence (AI)-driven serious games have been used in health care to offer a customizable and immersive experience. Summarizing the features of the current AI-driven serious games is very important to explore how they have been developed and used and their current state to plan on how to leverage them in the current and future health care needs.ObjectiveThis study aimed to explore the features of AI-driven serious games in health care as reported by previous research.MethodsWe conducted a scoping review to achieve the abovementioned objective. The most popular databases in the information technology and health fields (ie, MEDLINE, PsycInfo, Embase, CINAHL, IEEE Xplore, ACM Digital Library, and Google Scholar) were searched using keywords related to serious games and AI. Two reviewers independently performed the study selection process. Three reviewers independently extracted data from the included studies. A narrative approach was used for data synthesis.ResultsThe search process returned 1470 records. Of these 1470 records, 46 (31.29%) met all eligibility criteria. A total of 64 different serious games were found in the included studies. Motor impairment was the most common health condition targeted by these serious games. Serious games were used for rehabilitation in most of the studies. The most common genres of serious games were role-playing games, puzzle games, and platform games. Unity was the most prominent game engine used to develop serious games. PCs were the most common platform used to play serious games. The most common algorithm used in the included studies was support vector machine. The most common purposes of AI were the detection of disease and the evaluation of user performance. The size of the data set ranged from 36 to 795,600. The most common validation techniques used in the included studies were k-fold cross-validation and training-test split validation. Accuracy was the most commonly used metric for evaluating the performance of AI models.ConclusionsThe last decade witnessed an increase in the development of AI-driven serious games for health care purposes, targeting various health conditions, and leveraging multiple AI algorithms; this rising trend is expected to continue for years to come. Although the evidence uncovered in this study shows promising applications of AI-driven serious games, larger and more rigorous, diverse, and robust studies may be needed to examine the efficacy and effectiveness of AI-driven serious games in different populations with different health conditions.

Project description:Today globally, more people die from chronic diseases than from war and terrorism. This is not due to aging alone but also because we lead unhealthy lifestyles with little or no exercise and typically consume food with poor nutritional content. This paper proffers the design science research method to create an artefact that can help people study the diffusion of serious games. The ultimate goal of the study is to create a serious game that can help people to improve their balance in physical exercise, nutrition and well-being. To do this, first we conducted 97 interviews to study if wearables can be used for gathering health data. Analysis indicates that designers, manufacturers, and developers of wearables and associated software and apps should make their devices reliable, relevant, and user friendly. To increase the diffusion, adoption, and habitual usage of wearables key issues such as privacy and security need to be addressed as well. Then, we created a paper prototype and conducted a further 32 interviews to validate the first prototype of the game, especially with respect to the diffusion possibilities of the game. Results are positive from a formal technology acceptance point of view showing relevance and usefulness. But informally in the open questions some limitations also became visible. In particular, ease of use is extremely important for acceptance and calling it a game can in fact be an obstruction. Moreover, the artefact should not be patronizing and age differences can also pose problems, hence the title not to make the serious game too serious. Future research plans to address these problems in the next iteration while the future implementation plan seeks for big platforms or companies to diffuse the serious game. A key theoretical contribution of this research is the identification of habit as a potential dependent variable for the intention to use wearables and the development of a diffusion model for serious games. The hedonic perspective is added to the model as well as trust and perceived risks. This model ends the cycle of critical design with an improvement of theory as result contributing to the societal goal of decreasing Obesities and Diabetes.

Project description:BackgroundSerious games for medical education have seen a resurgence in recent years, partly due to the growth of the video game industry and the ability of such games to support learning achievements. However, there is little consensus on what the serious and game components in a serious game are composed of. As a result, electronic learning (e-learning) and medical simulation modules are sometimes mislabeled as serious games. We hypothesize that one of the main reasons is the difficulty for a medical educator to systematically and accurately evaluate key aspects of serious games.ObjectiveThis study aimed to identify markers that can evaluate serious games and distinguish between serious games, entertainment games, and e-learning.MethodsJabareen's eight-phase framework-building procedure was used to identify the core markers of a serious game. The procedure was modified slightly to elicit "diagnostic criteria" as opposed to its original purpose of a conceptual framework. Following the identification of purported markers, the newly developed markers were tested on a series of freely available health care serious games-Dr. Game Surgeon Trouble, Staying Alive, and Touch Surgery-and the results were compared to the published test validity for each game.ResultsDiagnostic criteria for serious games were created, comprising the clusters of User Experience (UX), Play, and Learning. Each cluster was formed from six base markers, a minimum of four of which were required for a cluster to be considered present. These criteria were tested on the three games, and Dr. Game Surgeon Trouble and Staying Alive fit the criteria to be considered a serious game. Touch Surgery did not meet the criteria, but fit the definition of an e-learning module.ConclusionsThe diagnostic criteria appear to accurately distinguish between serious games and mediums commonly misidentified as serious games, such as e-learning modules. However, the diagnostic criteria do not determine if a serious game will be efficacious; they only determine if it is a serious game. Future research should include a much larger sample of games designed specifically for health care purposes.

Project description:BACKGROUND:The idea of using serious games to effectuate better outcomes in health care has gained significant traction among a growing community of researchers, developers, and health care professionals. Many now recognize the importance of creating evidence-based games that are purposefully designed to address physical and mental health challenges faced by end users. To date, no regulatory resources have been established to guide the development of serious games for health (SGH). Developers must therefore look elsewhere for guidance. Although a more robust level of evidence exists in the research literature, it is neither structured nor is there any clear consensus. Developers currently use a variety of approaches and methodologies. The establishment of a well-defined framework that represents the consensus views of the SGH research community would help developers improve the efficiency of internal development processes, as well as chances of success. A consensus framework would also enhance the credibility of SGH and help provide quality evidence of their effectiveness. OBJECTIVE:This research aimed to (1) identify and evaluate the requirements, recommendations, and guidelines proposed by the SGH community in the research literature, and; (2) develop a consensus framework to guide developers, designers, researchers, and health care professionals in the development of evidence-based SGH. METHODS:A critical review of the literature was performed in October to November 2018. A 3-step search strategy and a predefined set of inclusion criteria were used to identify relevant articles in PubMed, ScienceDirect, Institute of Electrical and Electronics Engineers Xplore, CiteSeerX, and Google Scholar. A supplemental search of publications from regulatory authorities was conducted to capture their specific requirements. Three researchers independently evaluated the identified articles. The evidence was coded and categorized for analysis. RESULTS:This review identified 5 categories of high-level requirements and 20 low-level requirements suggested by the SGH community. These advocate a methodological approach that is multidisciplinary, iterative, and participatory. On the basis of the requirements identified, we propose a framework for developing theory-driven, evidence-based SGH. It comprises 5 stages that are informed by various stakeholders. It focuses on building strong scientific and design foundations that guide the creative and technical development. It includes quantitative trials to evaluate whether the SGH achieve the intended outcomes, as well as efforts to disseminate trial findings and follow-up monitoring after the SGH are rolled out for use. CONCLUSIONS:This review resulted in the formulation of a framework for developing theory-driven, evidence-based SGH that represents many of the requirements set out by SGH stakeholders in the literature. It covers all aspects of the development process (scientific, technological, and design) and is transparently described in sufficient detail to allow SGH stakeholders to implement it in a wide variety of projects, irrespective of discipline, health care segments, or focus.

Project description:The field of serious games for people with dementia (PwD) is mostly driven by game-design principals typically applied to games created by and for younger individuals. Little has been done developing serious games to help PwD maintain cognition and to support functionality.We aimed to create a theory-based serious game for PwD, with input from a multi-disciplinary team familiar with aging, dementia, and gaming theory, as well as direct input from end users (the iterative process). Targeting enhanced self-efficacy in daily activities, the goal was to generate a game that is acceptable, accessible and engaging for PwD.The theory-driven game development was based on the following learning theories: learning in context, errorless learning, building on capacities, and acknowledging biological changes-all with the aim to boost self-efficacy. The iterative participatory process was used for game screen development with input of 34 PwD and 14 healthy community dwelling older adults, aged over 65 years. Development of game screens was informed by the bio-psychological aging related disabilities (ie, motor, visual, and perception) as well as remaining neuropsychological capacities (ie, implicit memory) of PwD. At the conclusion of the iterative development process, a prototype game with 39 screens was used for a pilot study with 24 PwD and 14 healthy community dwelling older adults. The game was played twice weekly for 10 weeks.Quantitative analysis showed that the average speed of successful screen completion was significantly longer for PwD compared with healthy older adults. Both PwD and controls showed an equivalent linear increase in the speed for task completion with practice by the third session (P<.02). Most important, the rate of improved processing speed with practice was not statistically different between PwD and controls. This may imply that some form of learning occurred for PwD at a nonsignificantly different rate than for controls. Qualitative results indicate that PwD found the game engaging and fun. Healthy older adults found the game too easy. Increase in self-reported self-efficacy was documented with PwD only.Our study demonstrated that PwD's speed improved with practice at the same rate as healthy older adults. This implies that when tasks are designed to match PwD's abilities, learning ensues. In addition, this pilot study of a serious game, designed for PwD, was accessible, acceptable, and enjoyable for end users. Games designed based on learning theories and input of end users and a multi-disciplinary team familiar with dementia and aging may have the potential of maintaining capacity and improving functionality of PwD. A larger longer study is needed to confirm our findings and evaluate the use of these games in assessing cognitive status and functionality.

Project description:IntroductionSerious educational games are digital games designed to support teaching or learning objectives that have become popular among children. However, a set of principles is needed to develop a successful educational game. Therefore, this study aimed to provide a comprehensive and valid framework for designing children's serious educational games.MethodsThe conceptual framework is developed in two phases. First, a scoping review was conducted in PubMed, Ovid (APA PsycInfo), EMBASE, Scopus, Web of Science, ProQuest, and gray literature on August 1, 2022. Papers in English that reported the serious educational games' principles for children were included. Second, the extracted data from the previous step was reviewed and discussed by the research team to develop the initial framework. Then, it was distributed to 20 experts with relevant knowledge and experience in two rounds to validate and apply their comments within the framework.ResultsOf the 12916 papers identified, 15 were included in this study. In the proposed framework named CoDHP, the results were classified into four topics, including (a) content aspects, (b) design requirements, (c) highlighted attributes, and (d) children's preferences. Content aspects comprise four classes (goals and limits, child learning content, learning context, and a long-term program) with 16 principles. Design requirements contain 11 classes (stories and storylines, player characters, game mechanics, interactivity, game challenge, game rules, game help, entertaining games, user interface, accessibility, and setting) with 47 principles, of which 15 are highlighted. Regarding children's preferences for the game elements, various similarities and differences were extracted. For instance, both girls and boys prefer fun and popular games. Based on experts' comments, 21 supplementary principles were recommended to complete the content and design requirements.ConclusionGame designers or researchers can use the proposed framework as a formative guide to design successful serious games or evaluate children's digital games.