Hybrid Diagnosis Models for Autism Patients Based on Medical and Sociodemographic Features Using Machine Learning and Multicriteria Decision-Making (MCDM) Techniques: An Evaluation and Benchmarking Framework

Abstract

Background and Contexts. Autism spectrum disorder (ASD) is difficult to diagnose, prompting researchers to increase their efforts to find the best diagnosis by introducing machine learning (ML). Recently, several available challenges and issues have been highlighted for the diagnosis of ASD. High consideration must be taken into the feature selection (FS) approaches and classification process simultaneously by using medical tests and sociodemographic characteristic features in autism diagnostic. The constructed ML models neglected the importance of medical tests and sociodemographic features in a training and evaluation dataset, especially since some features have different contributions to the processing data and possess more relevancies to the classification information than others. However, the role of the physician’s experience towards feature contributions remains limited. In addition, the presence of many evaluation criteria, criteria trade-offs, and criteria importance categorize the evaluation and benchmarking of diagnosis ML models concerning the intersection between FS approaches and ML classification methods given under complex multicriteria decision-making (MCDM) problems. To date, no study has presented an evaluation framework for benchmarking the best hybrid diagnosis models to classify autism patients’ emergency levels considering multicriteria evaluation solutions. Method. The three-phase framework integrated the MCDM and ML to develop the diagnosis models and evaluate and benchmark the best. Firstly, the new ASD-dataset-combined medical tests and sociodemographic characteristic features is identified and preprocessed. Secondly, developing the hybrid diagnosis models using the intersection process between three FS techniques and five ML algorithms introduces 15 models. The selected medical tests and sociodemographic features from each FS technique are weighted before feeding the five ML algorithms using the fuzzy-weighted zero-inconsistency (FWZIC) method based on four psychiatry experts. Thirdly, (i) formulate a dynamic decision matrix for all developed models based on seven evaluation metrics, including classification accuracy, precision, F1 score, recall, test time, train time, and AUC. (ii) The fuzzy decision by opinion score method (FDOSM) is used to evaluate and benchmark the 15 models concerning the seven evaluation metrics. Results. Results reveal that (i) the three FS techniques have obtained a size different from the others in the number of the selected features; the sets were 39, 38, and 41 out of 48 features. Each set has its weights constructed by FWIZC. Considered sociodemographic features have been mostly selected more than medical tests within FS techniques. (ii) The first three best hybrid models were “ReF-decision tree,” “IG-decision tree,” and “Chi2-decision tree,” with score values 0.15714, 0.17539, and 0.29444. The best diagnosis model (ReF-decision tree) has obtained 0.4190, 0.0030, 0.9946, 0.9902, 0.9902, 0.9902, 0.9902, and 0.9951 for the C1=train time, C2=test time, C3=AUC, C4=CA, C5=F1 score, C6=precision, and C7=recall, respectively. The developed framework would be beneficial in advancing, accelerating, and selecting diagnosis tools in therapy with ASD. The selected model can identify severity as light, medium, or intense based on medical tests and sociodemographic weighted features.

Evaluation of the Routing Algorithms for NoC-Based MPSoC: A Fuzzy Multi-Criteria Decision-Making Approach

“…FWZIC method is a recent advanced method for weighting criteria with zero inconsistency [20]. The use of FWZIC to weight criteria is not only effective, but it also offers several key advantages that make it a highly persuasive method for decision-makers [28]. One of the most notable benefits of FWZIC is its ability to handle inconsistencies within the decision-making process, which is a common challenge that can significantly impact the accuracy and reliability of decisions.…”

“…The problem is that TFN is limited in dealing with ambiguity and uncertainty [33]. When confronted with realworld challenges, the complexities lie in their inherent vagueness, indeterminacy, and ambiguity, thereby amplifying the intricacies of decision-making [28], [43].…”

“…Alqaysi et al [28] introduced basic FDOSM & FWZIC as an assessment methodology for evaluating the most effective hybrid diagnostic models for autism patient classification.…”

A Systematic Review of Using Deep Learning Technology in the Steady-State Visually Evoked Potential-Based Brain-Computer Interface Applications: Current Trends and Future Trust Methodology

“…Therefore, developing a comprehensive evaluation framework using MCDM methods is necessary to address these challenges and benchmark the developed SSVEP-based BCI applications. This framework would involve decision-makers providing qualitative and/or quantitative assessments to determine the performance of each alternative concerning each criterion and the relative importance of the evaluation criteria concerning the overall objective [ 96 – 101 ]. Therefore, the propose solution for the above issues is explained in the next section.…”

Unlocking the Potential of Autism Detection: Integrating Traditional Feature Selection and Machine Learning Techniques

“…The financial burden of autism highlights the urgent need for the creation of simple, practical, and efficient early detection techniques [29]. Recent studies on detecting autism using ML have focused on assigning weights to ASD features constructed by physicians and applying these weights to the ASD dataset [30]- [32] However, this study adopts a different approach, focusing on traditional feature selection methods rather than constructing an ML model based on weighted features or the intersection of different ML methods and feature selection approaches. Several reasons justify this approach.…”