Hybrid CNN and random forest model with late fusion for detection of autism spectrum disorder in Toddlers
Accurate and early diagnosis of Autism Spectrum Disorder (ASD) in toddlers is crucial for effective intervention. Traditional models have shown limited success, while deep learning approaches achieve higher accuracies. Our study proposes a hybrid model combining VGG16, a pre-trained deep CNN, with a...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-06-01
|
| Series: | MethodsX |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2215016125001244 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849419509924888576 |
|---|---|
| author | Pushpmala Nawghare Jayashree Prasad |
| author_facet | Pushpmala Nawghare Jayashree Prasad |
| author_sort | Pushpmala Nawghare |
| collection | DOAJ |
| description | Accurate and early diagnosis of Autism Spectrum Disorder (ASD) in toddlers is crucial for effective intervention. Traditional models have shown limited success, while deep learning approaches achieve higher accuracies. Our study proposes a hybrid model combining VGG16, a pre-trained deep CNN, with an RF classifier to leverage high-level image feature extraction using the ACD image dataset on Kaggle alongside robust decision-making on the ACD Questionnaire dataset. The proposed model achieves an accuracy of 88.34 %, outperforming both standalone deep learning models like VGG16, EfficientNetB0, and AlexNet-based models as well as conventional ML models. This improvement demonstrates the effectiveness of combining feature-rich deep learning outputs with RF's ensemble-based classification. Our findings suggest that this hybrid approach is highly suitable for ASD classification tasks, enhancing the reliability of predictions in clinical settings. This research not only establishes the model as an option for ASD diagnosis but also underscores the potential of hybrid architectures that fuse deep learning with machine learning. Future research will focus on integrating multi-modal data (e.g., genetic and socio-demographic) and further testing on diverse datasets to improve generalizability. The study contributes to the growing body of evidence supporting advanced ML techniques in healthcare diagnostics, especially in neurodevelopmental disorders like ASD. |
| format | Article |
| id | doaj-art-8aa40083e9b14eaf96cbaed7661dab2c |
| institution | Kabale University |
| issn | 2215-0161 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | MethodsX |
| spelling | doaj-art-8aa40083e9b14eaf96cbaed7661dab2c2025-08-20T03:32:03ZengElsevierMethodsX2215-01612025-06-011410327810.1016/j.mex.2025.103278Hybrid CNN and random forest model with late fusion for detection of autism spectrum disorder in ToddlersPushpmala Nawghare0Jayashree Prasad1Corresponding author.; Department of Computer Science and Engineering, MIT School of Computing, MIT Art, Design and Technology University, Pune, Maharashtra 412201, IndiaDepartment of Computer Science and Engineering, MIT School of Computing, MIT Art, Design and Technology University, Pune, Maharashtra 412201, IndiaAccurate and early diagnosis of Autism Spectrum Disorder (ASD) in toddlers is crucial for effective intervention. Traditional models have shown limited success, while deep learning approaches achieve higher accuracies. Our study proposes a hybrid model combining VGG16, a pre-trained deep CNN, with an RF classifier to leverage high-level image feature extraction using the ACD image dataset on Kaggle alongside robust decision-making on the ACD Questionnaire dataset. The proposed model achieves an accuracy of 88.34 %, outperforming both standalone deep learning models like VGG16, EfficientNetB0, and AlexNet-based models as well as conventional ML models. This improvement demonstrates the effectiveness of combining feature-rich deep learning outputs with RF's ensemble-based classification. Our findings suggest that this hybrid approach is highly suitable for ASD classification tasks, enhancing the reliability of predictions in clinical settings. This research not only establishes the model as an option for ASD diagnosis but also underscores the potential of hybrid architectures that fuse deep learning with machine learning. Future research will focus on integrating multi-modal data (e.g., genetic and socio-demographic) and further testing on diverse datasets to improve generalizability. The study contributes to the growing body of evidence supporting advanced ML techniques in healthcare diagnostics, especially in neurodevelopmental disorders like ASD.http://www.sciencedirect.com/science/article/pii/S2215016125001244Late Fusion Model |
| spellingShingle | Pushpmala Nawghare Jayashree Prasad Hybrid CNN and random forest model with late fusion for detection of autism spectrum disorder in Toddlers MethodsX Late Fusion Model |
| title | Hybrid CNN and random forest model with late fusion for detection of autism spectrum disorder in Toddlers |
| title_full | Hybrid CNN and random forest model with late fusion for detection of autism spectrum disorder in Toddlers |
| title_fullStr | Hybrid CNN and random forest model with late fusion for detection of autism spectrum disorder in Toddlers |
| title_full_unstemmed | Hybrid CNN and random forest model with late fusion for detection of autism spectrum disorder in Toddlers |
| title_short | Hybrid CNN and random forest model with late fusion for detection of autism spectrum disorder in Toddlers |
| title_sort | hybrid cnn and random forest model with late fusion for detection of autism spectrum disorder in toddlers |
| topic | Late Fusion Model |
| url | http://www.sciencedirect.com/science/article/pii/S2215016125001244 |
| work_keys_str_mv | AT pushpmalanawghare hybridcnnandrandomforestmodelwithlatefusionfordetectionofautismspectrumdisorderintoddlers AT jayashreeprasad hybridcnnandrandomforestmodelwithlatefusionfordetectionofautismspectrumdisorderintoddlers |