Article Metrics
Similar Articles
- Digital Transformation in Medication Safety: A Systematic and Bibliometric Analysis of High-Alert Medication Management in Healthcare Settings
- Efficacy of Neuromuscular Electrical Stimulation in managing patients with Ankle Sprain and Chronic Ankle Instability: A Systematic Review
- Role of EMG Biofeedback Training for Spasticity Reduction in Neurological Disorders: A Narrative Review
- Advances in Rehabilitation for Plantar Fasciitis: A Comprehensive Review of Contemporary Approaches and Emerging Therapies
- Effectiveness of Task-Oriented Training in Improving Motor Function in Post-Stroke Hemiplegia: A Systematic Review
Design Validity and Quantitative Metric Analysis of Artificial Intelligence for the Proficiency of Systematic Review
Abstract
With emergence of Artificial Intelligence (AI) has created opportunities for automation with natural language processing (NLP) and semantic mapping. AI tools can identify relevant literature, classifying evidence, extract data, and evaluate quality.
To explore methodological validation of design and quantitative metrics analysis of artificial intelligence and machine learning tools used in the automated systematic review process.
Electronic databases were searched from 2015 to September 2025. Investigating methodological validation of design and quantitative metrics analysis of AI tools.
8 studies were included in this review for reporting quantitative metrics analysis and design validity of ML tool automation in the systematic review process, and evaluating model performance components.
The findings showed metrics analysis was done across a wide range of simulations and workload savings vary according to task across the included studies.
Keywords: Machine Learning; Natural Language Processing (NLP), Semantic Mapping