Haturusinghe, RGunathilake, BAbeysundara, SSenadeera, SThelijjagoda, SJayalath, T2026-08-192026-06-26R. Haturusinghe, B. Gunathilake, S. Abeysundara, S. Senadeera, S. Thelijjagoda and T. Jayalath, "Machine Learning-Based Early Detection Of Autism Using Multimodal Conversational Features," 2026 IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS), Kuala Lumpur, Malaysia, 2026, pp. 149-154, doi: 10.1109/I2CACIS69435.2026.11600351.979-833156170-3https://rda.sliit.lk/handle/123456789/5244Early and reliable screening for autism spectrum disorder (ASD) remains challenging in low-resource and high-variance conversational settings. This paper presents an end-to-end multimodal screening system that analyzes child-caregiver interaction data from audio recordings, CHAT-format transcripts, and text inputs to estimate ASD likelihood and provide clinician-facing explanations. The system integrates three feature families: pragmatic-conversational, acoustic-prosodic, and syntactic-semantic, supporting component-wise classification and late-fusion strategies with modality-aware weighting. Beyond prediction, the platform provides transcript-level behavioral annotations, global and local feature attributions, and counterfactual what-if analysis. Experiments on cross-validated ASDBank data show multimodal fusion achieving 87.2% accuracy (ROC-AUC 0.92), outperforming unimodal baselines by 2-4%.enacoustic prosodyASDBankautism spectrum disordercounterfactual explanationsexplainable AIpragmatic featuresspeech analysisTalkBankArticleDOI: 10.1109/I2CACIS69435.2026.11600351