The role of AI in the diagnosis of speech and language disorders: A systematic mapping study
These videos have been matched automatically. Contact us if they are not relevant.
These videos have been matched automatically. Contact us if they are not relevant.
View abstract on PubMed
Summary
This summary is machine-generated.Artificial intelligence (AI) machine learning algorithms show potential for diagnosing speech and language disorders (SLDs), but current research is limited. Further development is needed for comprehensive automation across all diagnostic phases, especially for conditions like developmental language disorders.
Area Of Science
- Medical Informatics
- Computational Linguistics
- Artificial Intelligence
Background
- Speech and language disorders (SLDs) affect a significant portion of the population, impacting communication and quality of life.
- Accurate and timely diagnosis of SLDs is crucial for effective intervention and management.
- Current diagnostic processes for SLDs can be time-consuming and may benefit from technological advancements.
Purpose Of The Study
- To systematically map the existing research on the effectiveness of artificial intelligence (AI) machine learning algorithms in diagnosing SLDs.
- To assess the extent to which AI algorithms can automate the diagnostic process for SLDs.
- To identify research gaps in the application of AI for SLD diagnosis.
Main Methods
- A systematic mapping study (SMS) was conducted following Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines.
- A comprehensive literature search screened 19,774 research papers.
- 70 studies were included based on predefined inclusion and exclusion criteria.
Main Results
- A significant disparity exists in AI algorithm application for SLD diagnosis (91.43% vs. 8.57%).
- There is a lack of AI algorithms for diagnosing prevalent language disorders, such as developmental language disorders in children.
- Most AI algorithms focus on binary classification (e.g., healthy vs. pathological) rather than detailed diagnostics and predominantly automate only the assessment phase (76%) rather than diagnosis determination (24%).
Conclusions
- The effectiveness of AI in automating SLD diagnosis requires larger population datasets.
- A research gap exists in developing AI models to automate all four phases of the SLD diagnostic process.
- Future AI models should aim to integrate diagnosis automation with treatment protocols for clinical settings.
These videos have been matched automatically. Contact us if they are not relevant.
These videos have been matched automatically. Contact us if they are not relevant.
