A Reproducible Rule-Execution and Sensitivity-Analysis Workflow for Synthetic Child-Day Records: A Software-Verification Study
DOI:
https://doi.org/10.65417/ljere.v2i2.118Keywords:
autism spectrum disorder, behavioral observation, rule-based decision support, synthetic data; software verification, digital health, explainable artificial intelligence, reproducible researchAbstract
Families and clinical teams may record daily observations about sleep, environmental stimulation, routine changes, activity, and behavior when supporting children with autism spectrum disorder (ASD). Such records can be difficult to structure and interpret, particularly when observations are incomplete or defined differently across days. A transparent rule-based workflow can serve as a testable engineering approach to organizing these observations, but synthetic demonstrations must not be presented as clinical evidence.
This study aims to develop and evaluate a reproducible rule-based workflow for organizing and analyzing synthetic daily records of children with autism spectrum disorder (ASD). A simulated dataset was generated for three hypothetical children over 90 consecutive days per child, resulting in 270 child-day records, using an explicit generation model based on predefined rules and behavioral and environmental variables.
The system utilized nine rules to calculate a risk score and performed verification and sensitivity analyses, including permutation testing, rule-ablation analysis, and Monte Carlo simulations. The results showed a descriptive association between the rule-based score and the simulated severity level (r = 0.3687), with relatively consistent findings across multiple simulation runs.
The study demonstrates the feasibility of using interpretable, rule-based methodologies with software-verification procedures for organizing synthetic behavioral data. However, these findings should not be interpreted as clinical evidence or predictive performance. Future applications require validation using real de-identified longitudinal data and evaluation by clinical experts.
References
1. American Psychiatric Association. Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition. Washington, DC: American Psychiatric Association; 2013. https://www.psychiatry.org/psychiatrists/practice/dsm
2. Cohen S, Conduit R, Lockley SW, Rajaratnam SMW, Cornish KM. The relationship between sleep and behavior in autism spectrum disorder (ASD): a review. Journal of Neurodevelopmental Disorders. 2014;6:44. https://doi.org/10.1186/1866-1955-6-44
3. Cortese S, Wang F, Angriman M, Masi G, Bruni O. Sleep disorders in children and adolescents with autism spectrum disorder: diagnosis, epidemiology, and management. CNS Drugs. 2020;34:415–423. https://doi.org/10.1007/s40263-020-00710-y
4. Royal Children’s Hospital Melbourne. Autism and developmental disability: management of distress/agitation. Clinical Practice Guideline. Updated June 2022. https://www.rch.org.au/clinicalguide/guideline_index/Autism_and_developmental_disability__Management_of_distress/agitation/
5. Chen Y, Xi Z, Greene T, Mandy W. A systematic review of ecological momentary assessment in autism research. Autism. 2025;29(6):1374–1389. Published online 18 December 2024. https://doi.org/10.1177/13623613241305722
6. Hacohen M, Levy A, Kaiser H, et al. An open science resource for accelerating scalable digital health research in autism and other neurodevelopmental conditions. Nature Neuroscience. 2026;29:467–478. https://doi.org/10.1038/s41593-025-02146-3
7. Simons Foundation Autism Research Initiative. Simons Sleep Project: open-science data resource. https://www.sfari.org/resource/simons-sleep-project/
8. Collins GS, Moons KGM, Dhiman P, et al. TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods. BMJ. 2024;385:e078378. https://doi.org/10.1136/bmj-2023-078378
9. Debray TPA, Collins GS, Riley RD, et al. Transparent reporting of multivariable prediction models developed or validated using clustered data: TRIPOD-Cluster checklist. BMJ. 2023;380:e071018. https://doi.org/10.1136/bmj-2022-071018
10. Vasey B, Nagendran M, Campbell B, et al. Reporting guideline for the early-stage clinical evaluation of decision support systems driven by artificial intelligence: DECIDE-AI. Nature Medicine. 2022;28:924–933. https://doi.org/10.1038/s41591-022-01772-9
11. Romani PW, D’Mello SK, Moulder RM, Berkowitz LN. Using wearable technology to predict the occurrence of severe behavior problems among neurodiverse individuals: a systematic review. Perspectives on Behavior Science. 2026;49:361–383. https://doi.org/10.1007/s40614-026-00497-1
12. Goncalves A, Ray P, Soper B, Stevens J, Coyle L, Sales AP. Generation and evaluation of synthetic patient data. BMC Medical Research Methodology. 2020;20:108. https://doi.org/10.1186/s12874-020-00977-1
Amna Ahmed Juma Awheedah. (2026). Psychological and Social Stress among Families of Children with Autism Spectrum Disorder and the Role of Psychological Support. Libyan Journal of Educational Research and E-Learning (LJERE), 2(1), 27-43. https://doi.org/10.65417/ljere.v2i1.62
Najat Nouri Naseer, & Farhat Al-Mabrouk Ali Zayed. (2025). Parenting Styles and Their Relationship to Aggressive Behavior Among Children: A Field Study. Journal of Libyan Academy Bani Walid, 1(4), 230–246. https://doi.org/10.61952/jlabw.v1i4.274
