ASD Diagnostic Model Using ML for Early Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The diagnosis of Autism Spectrum Disorder (ASD) is challenging due to its complex nature, heterogeneity in expression, and the difficulty in distinguishing it from other comorbidities, leading to delayed or missed diagnoses, especially in underserved communities, which can result in inadequate early intervention and poorer outcomes.
Innovation Solution
A computing-based method and system utilizing a machine-learning model that evaluates demographic, comorbidity, observational assessment, and interview data to determine the presence or absence of ASD and classify it, providing a more accessible and efficient diagnostic tool.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional diagnostic methods are used for ASD, then diagnostic accuracy may be maintained through multiple phases and differential diagnosis by clinicians, but the diagnostic process becomes challenging and elaborate, leading to delayed diagnoses especially in underserved communities
Solution Approach 1:
The patent applies preliminary action by implementing automated screening tools and machine learning models that can perform initial ASD identification before formal clinical diagnosis. This preliminary assessment filters candidates and prepares data structures, enabling clinicians to focus on complex cases and reducing overall diagnostic time while maintaining accuracy through structured evaluation protocols
2Measurement precision
If comprehensive evaluation data including demographic, comorbidity, observational assessment and interview data is collected, then diagnostic accuracy improves, but the complexity of the evaluation process increases
Solution Approach 1:
The patent merges multiple evaluation components (demographic data collection, comorbidity assessment, observational checks, and interview protocols) into a unified digital platform. This integration consolidates data streams and evaluation criteria into a single coherent system, reducing procedural complexity while comprehensively capturing all necessary diagnostic information through standardized digital workflows
Solution Approach 2:
The patent introduces an intermediary computational layer that processes and integrates diverse evaluation data. This intermediary system includes algorithms that harmonize data from multiple sources, apply diagnostic criteria automatically, and present synthesized results to clinicians, thereby managing evaluation complexity while maintaining comprehensive data collection for accurate diagnosis
3Reliability
If early and accurate ASD diagnosis is achieved, then prognosis and quality of life improve with better cognitive, language, and adaptive behavior gains, but the diagnostic process must overcome challenges in distinguishing ASD from other comorbidities and heterogeneous presentations
Solution Approach 1:
The patent segments the diagnostic process into distinct analytical components: differential diagnosis modules that evaluate specific symptom clusters, comorbidity detection algorithms that identify co-occurring conditions, and severity classification systems that assess functional impact. This segmentation allows systematic evaluation of heterogeneous presentations while maintaining comprehensive differential diagnosis capabilities, improving detection accuracy without overwhelming the diagnostic workflow
Data Source
AI summary
A method implemented via a computing device. The method may include receiving, by the computing device, data associated with a subject. The data associated with the subject may include two or more of demographic data, comorbidity data, observational assessment and interview data, and medication data. The method may also include evaluating, by the computing device, the data associated with the subject via an autism spectrum disorder (ASD) model. The ASD model may evaluate the data associated with the subject to determine the presence or absence of an ASD and, based upon a determination of the presence of an ASD, classify the ASD. The evaluation of the data associated with the subject by the ASD model may yield an evaluation result. The evaluation result may indicate the presence or absence of the ASD.