Year: 2024
Type: article
Abstract: The increasing integration of artificial intelligence (AI)-based predictive models in clinical pathology has created new opportunities to optimize diagnostic accuracy and workflow efficiency. This study addresses the effective synergy between pathologists and predictive models, proposing a collaborative approach where automated systems act as assistants to human experts, rather than replacing them. The benefits of com bining clinical expertise with deep learning algorithms for histological image interpretation are analyzed, highlighting improvements in sensitivity, specificity, and a reduction in diagnostic errors. A mixed-methods approach is employed, integrating clinical validation, comparative performance analysis, and workflow simulations, allowing for the quantitative evaluation of the predictive models’ contribution. The results show that collaboration between pathologists and predictive models increases efficiency in sample review, optimizes decision-making, and reduces interobserver variability. Challenges related to data standardization, model interpretation, and professional acceptance are also identified. The discussion emphasizes the need for regulatory frameworks, ethical protocols, and adequate training for the integration of AI into clinical practice. This study supports a hybrid approach, where the interaction between a human expert and a predictive model maximizes diagnostic benefits and strengthens trust in automated systems.
Author: Zakariya, Ahmad Masruhan
Institution: Universitas Muhammadiyah Malang
Language: English
Subfield: Health Informatics
Field: Medicine
Domain: Health Sciences
Open Access status: diamond
OpenAlex ID: W7220280903
