Related Experiment Video
Updated: Jul 23, 2025
12:05
Database-guided Flow-cytometry for Evaluation of Bone Marrow Myeloid Cell Maturation
Published on: November 3, 2018
11.7K
Artificial Intelligence-Assisted Diagnostic Cytology and Genomic Testing for Hematologic Disorders
Lealem Gedefaw1, Chia-Fei Liu1, Rosalina Ka Ling Ip2
1Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hong Kong, China.
Cells
|July 14, 2023
Summary
Artificial intelligence (AI) enhances hematology diagnostics by identifying patterns in data for applications like digital pathology and patient screening. Challenges like data bias and privacy must be addressed for AI to fully revolutionize patient care.
Area of Science:
- Hematology
- Artificial Intelligence (AI)
- Machine Learning
- Deep Learning
Background:
- Artificial intelligence (AI) involves creating computational programs that mimic human intelligence.
- Machine learning and deep learning models excel at identifying and grouping patterns within data.
- AI applications are increasingly being explored in various hematology subfields.
Purpose of the Study:
- To review the applications of AI in hematology.
- To highlight the potential benefits of AI-assisted methods in improving diagnostic accuracy and efficiency.
- To discuss the limitations and challenges of implementing AI in clinical hematology settings.
Main Methods:
- Review of AI applications in digital pathology, alpha thalassemia patient screening, cytogenetics, immunophenotyping, and sequencing.
- Analysis of AI's role in identifying novel biomarkers and predicting treatment outcomes.
- Examination of limitations including database size, validation, standardization, errors, and bias.
Main Results:
- AI-assisted methods show promise in enhancing diagnostic accuracy and efficiency in hematology.
- AI can aid in identifying novel biomarkers and predicting patient treatment outcomes.
- Current limitations, such as data scarcity and bias, prevent AI from fully replacing manual diagnosis.
Conclusions:
- AI holds significant potential to revolutionize hematology and improve patient outcomes.
- Addressing challenges related to data privacy, ethical concerns, and system validation is crucial.
- Continued research and development are necessary to overcome existing hurdles and realize AI's full potential in clinical hematology.
