The increasing prevalence of autism spectrum disorder (ASD) underscores its significant impact on individuals and the importance of early intervention. ASD affects various aspects of life, including education, emotional development, and social interactions. Besides traditional therapeutic approaches, a novel strategy incorporating digital games has been introduced. Four games developed using Makey Makey and Scratch aim to enhance cognitive skills in children with ASD. This approach facilitates emotional and intellectual development, tracks progress, and offers personalized and engaging interventions. This study demonstrated significant improvements in memory and concentration among participants, with an average improvement of 23.38 points. The most notable enhancements were observed in children aged 10, who showed an average improvement of 25.67 points. Additionally, female participants exhibited a slightly higher average improvement compared to males. The Memory Maze game also effectively enhanced cognitive skills in children with different types of ADHD. Children with the Hyperactive–Impulsive type showed the highest average improvement, with 25.00 points, followed by those with the Combined type, with 24.15 points, and the Inattentive type, with 23.53 points. These findings highlight the potential use of these tools in both ASD and ADHD therapy, providing a structured and enjoyable learning environment that supports cognitive development and therapeutic outcomes.

Quantum machine learning on near-term noisy quantum devices has generated substantial theoretical interest, but rigorous empirical comparisons under realistic noise on practically relevant data remain scarce. This paper compares two paradigmatic quantum learning models, a Quantum Support Vector Machine (QSVM) built on the ZZFeatureMap quantum kernel and a Variational Quantum Classifier (VQC) with an EfficientSU2/RealAmplitudes ansatz, against tuned classical baselines (SVM with four kernels, Random Forest, XGBoost, LightGBM and CatBoost) on the ULB Credit Card Fraud dataset (284,807 transactions, 0.17% fraud). All models share an identical 4-qubit PCA-reduced feature space, evaluated on the full unbalanced test fold over 15 fits (3 folds × 5 seeds) and reported as mean ± standard deviation with bootstrap confidence intervals, AUPRC as the primary metric. Noise robustness is assessed under depolarizing noise $p\in \{0,0.001,0.01,0.05\}$, with ranking preservation measured directly through Spearman $\rho$ and Kendall $\tau$ between the noisy and noiseless decision scores rather than read off AUPRC, alongside the per-paradigm computational cost. At four qubits the classical baselines lead (AUPRC 0.60 to 0.74, CatBoost best), above the VQC (0.494) and the QSVM (0.240); the controlled QSVM-versus-RBF–SVM comparison puts the cost of the quantum kernel at about 0.45 AUPRC. Under noise the QSVM keeps its score ranking ($\rho =0.998$ at $p=0.001$, 0.906 at $p=0.01$) and an operational decision threshold (recall 0.87 to 0.89, stable calibration), while the VQC AUPRC peaks non-monotonically at $p=0.01$ (0.494 rising to 0.654, then easing to 0.569 at $p=0.05$) even as its ranking decays monotonically ($\rho$ from 0.72 to near zero), so average precision on its own misrepresents how noise affects it. The quantum models do not surpass the tuned classical reference at four qubits; the contribution is methodological: under noise, AUPRC has to be read together with a genuine rank statistic, because the two can move in opposite directions.