Game-Based Diagnosing of Children with Autism Spectrum Disorder
Bibliographic record
Abstract
Purpose: To develop a diagnostic application game targeting children, aiming to streamline the diagnostic process and facilitate early intervention in children with Autism Spectrum Disorder (ASD). Methods: This work was built around two key components: a gaming interface based on real-life scenarios that a child with ASD would encounter, and a Convolutional Neural Network (CNN) model that takes photographs of the children’s faces and determines whether they are autistic or not. Combining these two methodologies, we created a video game that categorizes the youngsters who play it as autistic or non-autistic based on their reactions and choices during the game scenarios and their facial structures (Aldridge et al., 2011). The scenarios in the game were inspired by diagnostic questionnaires used in clinics for diagnostic purposes (Sadek et al., 2020). We sought to add the cultural background influence in ASD diagnosis because several research studies have revealed that children from different cultures can have varied symptoms depending on their cultural background (Golson et al., 2021). We used the AQ-10 questionnaire (Allison et al., 2012) and distributed it to parents of autistic children to evaluate how they see their child and if social norms influence it. In addition, we spoke with a Turkish specialist who works with Turkish autistic children and included her thoughts on the game’s situations. Results: After experimenting with various models on the same dataset (Gerry, 2020), the efficientNet B3 model attained the highest accuracy of 87.5%. The ultimate results presented to the game’s player were a combination of the model results and the outcomes of the scenarios he chose throughout his play. If the player reacts to four out of eight circumstances in the same way that an autistic child diagnosed by specialists would, the player will be tagged as autistic as well. All participants identified as autistic by this test should be checked by a specialist for a final diagnosis. Conclusions: ASD lacks a simple medical test for diagnosis, necessitating observation and questioning by trained professionals, especially in children. Conventional diagnostic approaches are time-consuming and financially demanding, making them less accessible for many families. Given the critical importance of early ASD diagnosis and its impact on learning and development, we were able to create a tool that will help in the diagnosis process, which will lead to solving many problems.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.002 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".