
Summary of studies using Al technology with existing ASD assessments
Author | Sample size | Mean age | Date type | Method | AUC (%) | Sensitivity (%) | Specificity (%) | Accuracy (%) |
---|---|---|---|---|---|---|---|---|
Bone et al. [35] | 1264 (ASD) | 6.7-15.9 yrs | ADI-R | SVM | - | 89.2 86.7 | 59 53.4 | - |
Bussu et al. [28] | 32(ASD) | 8.1 m (visiti) | MSEL | SVM | 69.2 (8 m) | 68.8 (8 m) | 64.4 (8 m) | 66.4 (8 m) |
Duda et al. [36] | 2775 (ASD) | 8.1 yrs (ASD) | SRS | SVC, LDA, CL, LR, RF, DT | 93.3-96.5 | - | - | - |
Duda et al. [37] | 248(ASD) | 8.2 yrs (ASD) | SRS | SVC, CL, LR, LDA | 82-89 | - | - | - |
Kosmicki et al. [33] | 1451 ASD (M2) | 68 m ASD (M 2) | ADOS (M2, M3) | SVM, ADTree, FT, LR, NBT, RF | 96.7-99.7 (M2) 96.1-100 (M3) | 96.5-98.6 (M2) 87.1-98.9 (M3) | ||
Levy et al. [32] | 1319 ASD (M 2) | 83 m ASD (M 2) | ADOS (M2, M3) | LR, LDA, SVM | 93 (M2) | 98 (M2) | 58 (M2) | 78 (M2) |
Thabtah et al. [49] | 707(ASD) | 6.3 yrs | AQ | CI | 80-87.3 | 80 80 90 | ||
Wall et al. [34] | 2867 (ASD) | 8.06-8.75 yrs (ASD) | ADI-R | ADTree | - | - | 93.8-99 | 99.9-100 |
ADHD: attention-deficit/hyperactivity disorder, ADI-R: Autism Diagnositc Interview-Revised, ADOS: Autism Diagnostic Observational Schedule, ADTree: alternating decision tree, AI: artificial intelligence, AOSI: Autism Observational Scale for Infants, AQ: Autism Spectrum Quotient, ASD: autism spectrum disorder, AUC: area under the curve, CI: computational intelligence, CL: categorical lasso, DT: decision tree, FT: functional tree, LDA: linear discriminant analysis, LR: logistic regression, m: months, MSEL: Mullen Scales of Early Learning, M2: module 2, M3: module 3, NBT: naïve Bayes tree, RF: random forest, SRS: Social Responsiveness Scale, SVC: support vector classification, SVM: support vector machine, VABS: Vineland Adaptable Behavior Scale, yrs: years