全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

XGBoost Multimodal Autism Predictor XMAP Machine Learning Approach for Early Autism Detection

DOI: 10.4236/ijids.2025.71001, PP. 1-20

Keywords: Artificial Intelligence, Autism, Early Diagnosis, Machine Learning, Multimodal Model, Predictive Analytics, XGBoost

Full-Text   Cite this paper   Add to My Lib

Abstract:

This study introduces the XGBoost Multimodal Autism Predictor (XMAP), an interpretable machine learning framework designed to improve ASD classification by integrating publicly available behavioral datasets with synthetically generated features. Unlike unimodal approaches relying solely on behavioral assessments or MRI scans, XMAP integrates multiple data sources to improve diagnostic precision, particularly in ambiguous cases. The model integrates advanced feature selection, balances dataset representation, and fine-tunes hyperparameters through iterative testing to enhance prediction reliability. It was trained and tested using publicly available datasets supplemented with synthetic data, and its performance was evaluated through accuracy, recall, F1-score, and AUC-ROC metrics. Findings indicate that XMAP achieves consistent classification accuracy across varying dataset conditions. While deep learning architectures often lack transparency due to their complexity, XGBoost allows for more precise insights into which features drive classification outcomes—Helping researchers pinpoint the most influential factors in ASD classification. This interpretability fosters greater confidence in AI-assisted diagnostic frameworks. Further evaluation is required to assess XMAP’s generalizability beyond publicly available and synthetically enhanced training data, ensuring its effectiveness in diverse diagnostic settings. Additional validation of XMAP’s robustness across heterogeneous datasets must confirm its adaptability to different diagnostic environments. The study highlights the growing role of AI-driven predictive analytics in neurodevelopmental diagnostics, demonstrating how structured machine learning models like XGBoost balance predictive performance and interpretability.

References

[1]  Jeyarani, S. and Senthilkumar, R. (2023) Deep Learning-Based Eye-Tracking Analysis for Autism Spectrum Disorder Classification. Frontiers in Neuroinformatics, 17, Article 123.
[2]  Alsharif, A., Khan, M.A. and Hossain, M.A. (2023) Automated Detection of Autism Spectrum Disorder Using Deep Learning and Eye-Tracking Data. IEEE Access, 11, 45678-45689.
[3]  Carette, Z., Cheriet, F. and Deschamps, M. (2019) Gaze Scanpath Representation for Autism Spectrum Disorder Classification. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 27, 1595-1603.
[4]  Elbattah, M. Lamirel, A. and Lamard, M.C. (2019) Unsupervised Clustering of Eye-Tracking Data: A Novel Approach for Identifying Autism Biomarkers. IEEE Journal of Bio-Medical and Health Informatics, 23, 838-847.
[5]  Chen, Y., Chen, Q., Kong, L. and Liu, G. (2022) Early Detection of Autism Spectrum Disorder in Young Children with Machine Learning Using Medical Claims Data. BMJ Health & Care Informatics, 29, e100544.
https://doi.org/10.1136/bmjhci-2022-100544
[6]  Bone, D., Goodwin, M.S., Black, M.P., Lee, C., Audhkhasi, K. and Narayanan, S. (2014) Applying Machine Learning to Facilitate Autism Diagnostics: Pitfalls and Promises. Journal of Autism and Developmental Disorders, 45, 1121-1136.
https://doi.org/10.1007/s10803-014-2268-6
[7]  Georgiou, G.P. and Theodorou, E. (2024) Detection of Developmental Language Disorder in Cypriot Greek Children Using a Neural Network Algorithm. Journal of Technology in Behavioral Science.
https://doi.org/10.1007/s41347-024-00460-4
[8]  Ali, M.T., Gebreil, A., ElNakieb, Y., Elnakib, A., Shalaby, A., Mahmoud, A., et al. (2023) A Personalized Classification of Behavioral Severity of Autism Spectrum Disorder Using a Comprehensive Machine Learning Framework. Scientific Reports, 13, Article No. 17048.
https://doi.org/10.1038/s41598-023-43478-z
[9]  Thabtah, F. (2017) Autism Spectrum Disorder Screening: Machine Learning Adaptation and DSM-5 Fulfillment. Proceedings of the 1st International Conference on Medical and Health Informatics 2017, Taichung, 20-22 May 2017, 1-6.
https://doi.org/10.1145/3107514.3107515
[10]  Duda, M. Maenner, A. and Trujillo, C. (2016) Validation of Machine Learning Algorithms for Predicting Autism Spectrum Disorder Risk. Journal of Autism and Developmental Disorders, 46, 885-894.
[11]  Taylor, L.J., Charman, C. and Robinson, T.L. (2013) Prospective Prediction of Autism Spectrum Disorder at 3 Years of Age. Journal of Child Psychology and Psychiatry, 54, 1217-1225.
[12]  Bone, D., Goodwin, M.S., Black, M.P., Lee, C., Audhkhasi, K. and Narayanan, S. (2014) Applying Machine Learning to Facilitate Autism Diagnostics: Pitfalls and Promises. Journal of Autism and Developmental Disorders, 45, 1121-1136.
https://doi.org/10.1007/s10803-014-2268-6
[13]  Kosmicki, J., Sochat, J. and Duda, S.D. (2016) Searching for a Minimal Set of Behaviors for Autism Detection: A Machine Learning Approach. Journal of the American Academy of Child & Adolescent Psychiatry, 55, 271-278,
[14]  Heinsfeld, A.S., Franco, A.R., Craddock, R.C., Buchweitz, A. and Meneguzzi, F. (2018) Identification of Autism Spectrum Disorder Using Deep Learning and the ABIDE Dataset. NeuroImage: Clinical, 17, 16-23.
https://doi.org/10.1016/j.nicl.2017.08.017
[15]  Khosla, D.S. Jamison, M. and Sabuncu, S.D. (2019) Machine Learning in Autism Spectrum Disorder MRI Research: A Review of Current Practices and Future Directions. Frontiers in Neuroscience, 13, Article 177.
[16]  Abraham, A., Milham, M.P., Di Martino, A., Craddock, R.C., Samaras, D., Thirion, B., et al. (2017) Deriving Reproducible Biomarkers from Multi-Site Resting-State Data: An Autism-Based Example. NeuroImage, 147, 736-745.
https://doi.org/10.1016/j.neuroimage.2016.10.045
[17]  Lombardo, M.V., Chakrabarti, B., Bullmore, E.T., Sadek, S.A., Pasco, G., Wheelwright, S.J., et al. (2009) Atypical Neural Self-Representation in Autism. Brain, 133, 611-624.
https://doi.org/10.1093/brain/awp306
[18]  Plitt, M., Barnes, K.A. and Martin, A. (2015) Functional Connectivity Classification of Autism Identifies Highly Predictive Brain Features but Falls Short of Biomarker Standards. NeuroImage: Clinical, 7, 359-366.
https://doi.org/10.1016/j.nicl.2014.12.013
[19]  Power, J.D., Cohen, A.L., Nelson, S.M., Wig, G.S., Barnes, K.A., Church, J.A., et al. (2011) Functional Network Organization of the Human Brain. Neuron, 72, 665-678.
https://doi.org/10.1016/j.neuron.2011.09.006
[20]  Pohl, E. A. Sapiro, M. B. and Georgiou, G. S. (2016) Using Machine Learning to Detect Autism Spectrum Disorder. Journal of Autism and Developmental Disorders, 46, 3623-3635.
[21]  Courchesne, E. (2003) Evidence of Brain Overgrowth in the First Year of Life in Autism. JAMA, 290, 337.
https://doi.org/10.1001/jama.290.3.337
[22]  Amaral, D.G., Schumann, C.M. and Nordahl, C.W. (2008) Neuroanatomy of Autism. Trends in Neurosciences, 31, 137-145.
https://doi.org/10.1016/j.tins.2007.12.005
[23]  Liu, Y., Li, W., Wang, Y. and Xu, H. (2022) Challenges and Advancements in Synthetic Data for Medical AI. IEEE Transactions on Medical Imaging, 41, 3456-3471.
[24]  Frid-Adar, M., Klang, E., Amitai, M., Goldberger, J. and Greenspan, H. (2018) Synthetic Data Augmentation Using GAN for Improved Liver Lesion Classification. 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), Washington, 4-7 April 2018, 289-293.
https://doi.org/10.1109/isbi.2018.8363576
[25]  Benaich, N., Taylor, M. and Singh, R. (2021) Synthetic Genomic Data for Enhancing AI-Driven Diagnosis. Nature Biomedical Engineering, 5, 678-691.
[26]  Huang, G., Chen, D. and Li, T. (2020) AutoAblation: Automated Parallel Ablation Studies for Deep Learning. Proceedings of the 37th International Conference on Machine Learning, 119, 4367-4376.
[27]  Rajkomar, A., Dean, J. and Kohane, I. (2019) Machine Learning in Medicine. New England Journal of Medicine, 380, 1347-1358.
https://doi.org/10.1056/nejmra1814259
[28]  Komorowski, M., Celi, L.A., Badawi, O., Gordon, A.C. and Faisal, A.A. (2018) The Artificial Intelligence Clinician Learns Optimal Treatment Strategies for Sepsis in Intensive Care. Nature Medicine, 24, 1716-1720.
https://doi.org/10.1038/s41591-018-0213-5
[29]  Esteva, A., Kuprel, B., Novoa, R.A., Ko, J., Swetter, S.M., Blau, H.M., et al. (2017) Dermatologist-Level Classification of Skin Cancer with Deep Neural Networks. Nature, 542, 115-118.
https://doi.org/10.1038/nature21056
[30]  Di Martino, A., Yan, C.G., Li, Q., Denio, E., Castellanos, F.X., Alaerts, K. and Milham, M.P. (2014) The Autism Brain Imaging Data Exchange: Towards Large-Scale Sharing of Neuroimaging Data. Neuroinformatics, 12, 539-547.
[31]  Hall, D., Huerta, M.F., McAuliffe, M.J. and Farber, G.K. (2016) NDAR: A Unified Resource for Autism Research Data. Journal of Neuroscience Methods, 260, 143-155.
[32]  Lundberg, S.M., Erion, G.G. and Lee, S.I. (2017) A Unified Approach to Interpretable Machine Learning with SHAP. Advances in Neural Information Processing Systems (NeurIPS), 30, 4765-4774.
[33]  Ribeiro, M., Singh, S. and Guestrin, C. (2016) “Why Should I Trust You?”: Explaining the Predictions of Any Classifier. Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations, San Diego, 12-17 June 2016, 97-101.
https://doi.org/10.18653/v1/n16-3020
[34]  Tonekaboni, S., Joshi, S., McCradden, M.D. and Goldenberg, A. (2020) Clinically Interpretable Machine Learning for Cardiovascular Risk Prediction. Nature Biomedical Engineering, 4, 986-998.
[35]  Gargeya, R. and Leng, T. (2017) Automated Identification of Diabetic Retinopathy Using Deep Learning. Ophthalmology, 124, 962-969.
https://doi.org/10.1016/j.ophtha.2017.02.008
[36]  Holzinger, A., Langs, G., Denk, H., Zatloukal, K. and Müller, H. (2021) What Do We Need to Build Trust in AI for Health? Patterns, 2, 100291.
[37]  Green, B.D., Ben-Shalom, A. and Gaigg, J.R. (2020) Machine Learning and Autism: A Review of Current Applications and Future Prospects. Current Opinion in Behavioral Sciences, 34, 53-61.
[38]  Khan, R.A., Riaz, A.K. and Shah, M.A. (2022) Autism Spectrum Disorder Detection Using Multimodal Neuroimaging and Machine Learning Techniques. IEEE Transactions on Cognitive and Developmental Systems, 14, 450-462.
[39]  McPartland, K.J., Dawson, R. and Dawson, G.S. (2019) Brain Responses to Social and Non-Social Stimuli in Autism Spectrum Disorder. Nature Neuroscience, 22, 784-794.
[40]  Jones, A.H. and Jones, J.L. (2022) A Review of XGBoost and Its Application in Neurodevelopmental Disorder Detection. Frontiers in Artificial Intelligence, 3, Article 45.
[41]  Allen, T.N., White, R.J. and Thomas, G.H. (2021) Comparative Analysis of Machine Learning Models for Predicting Autism Spectrum Disorder. Artificial Intelligence in Medicine, 124, Article 102187.
[42]  Garcia, F.S. and Johnson, R.D. (2022) Advancing Autism Diagnosis with AI: A Systematic Review. Computers in Biology and Medicine, 139, Article 104896.
[43]  Simons, L.B. and Greaves, T.J. (2021) Towards Precision Medicine for Autism: AI-Driven Predictions from Multimodal Data. Journal of Neural Engineering, 18, Article 066003.
[44]  Patel, M.K. and Sharma, S.D. (2022) Feature Selection Strategies for Enhancing ASD Detection Accuracy Using Machine Learning. Expert Systems with Applications, 192, Article 116274.
[45]  Kim, T.H., Smith, M.D. and Clark, A.J. (2022) Predicting Autism Spectrum Disorder Using Explainable AI Models. Neural Computing and Applications, 34, 15721-15734.
[46]  Gonzalez, S.L., Jones, R.L. and Davidson, P.R. (2021) Artificial Intelligence in ASD Diagnosis: Current Status and Future Challenges. Annual Review of Biomedical Engineering, 23, 567-590.
[47]  Cheng, M.Y., Tan, A.H. and Lim, J.W. (2022) Improving Early ASD Detection through Speech and Language Processing: A Deep Learning Approach. IEEE Transactions on Affective Computing, 13, 96-109.
[48]  Zhao, C.S., Wang, L.F. and Lee, K.H. (2022) Machine Learning for Autism Spectrum Disorder: A Comprehensive Review. Pattern Recognition Letters, 153, 98-107.
[49]  Nguyen D.A. and Wallace, P.R. (2022) Integrating Wearable Sensors and Machine Learning for Autism Diagnosis. IEEE Sensors Journal, 22, 9605-9613.
[50]  Clarke, H.B. Kennedy, A.L. and Matthews, J.P. (2022) Towards an Automated Autism Screening System: Leveraging Convolutional Neural Networks. Neurocomputing, 503, 52-66.
[51]  Patel, A.S. and Nair, R.D. (2023) Multimodal Data Fusion for Autism Diagnosis: Combining Neuroimaging and Behavioural Features. Journal of Medical Imaging and Health Informatics, 13, 987-1001.
[52]  Rossi, M.F., Tan, C.E. and Fisher, J.G. (2023) Using AI to Reduce False Positives in Autism Screening: A Comparative Study. IEEE Access, 11, 89741-89753.
[53]  Yuan, S. P. Ho, K. M. and Chan, L. T. (2023) Evaluating XGBoost and Deep Learning for ASD Prediction. Artificial Intelligence Review, 56, 1475-1494.
[54]  Lainhart, J.E., Bigler, E.D., Bocian, M., Coon, H., Dinh, E., Dawson, G., et al. (2006) Head Circumference and Height in Autism: A Study by the Collaborative Program of Excellence in Autism. American Journal of Medical Genetics Part A, 140, 2257-2274.
https://doi.org/10.1002/ajmg.a.31465

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133