Integrating AI and ML in Myelodysplastic Syndrome Diagnosis: State-of-the-Art and Future Prospects

• Published in: Cancers Vol. 16; no. 1; p. 65
• Main Authors: Elshoeibi, Amgad Mohamed, Badr, Ahmed, Elsayed, Basel, Metwally, Omar, Elshoeibi, Raghad, Elhadary, Mohamed Ragab, Elshoeibi, Ahmed, Attya, Mohamed Amro, Khadadah, Fatima, Alshurafa, Awni, Alhuraiji, Ahmad, Yassin, Mohamed
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 22.12.2023; MDPI
• Subjects: Acute myeloid leukemia; Algorithms; Artificial intelligence; Biopsy; Bone marrow; Computer programs; Diagnosis; Flow cytometry; Granulocytes; Hemopoiesis; Learning algorithms; Machine learning; Malignancy; Medical research; Medicine, Experimental; Middleware; Morphology; Myelodysplastic syndrome; Myelodysplastic syndromes; Patients; Peripheral blood; Review; Stem cells; Thrombocytopenia; flow cytometry; peripheral blood smears; myelodysplastic syndrome diagnosis; machine learning; artificial intelligence; bone marrow smears
• ISSN: 2072-6694; 2072-6694
• DOI: 10.3390/cancers16010065

Myelodysplastic syndrome (MDS) is composed of diverse hematological malignancies caused by dysfunctional stem cells, leading to abnormal hematopoiesis and cytopenia. Approximately 30% of MDS cases progress to acute myeloid leukemia (AML), a more aggressive disease. Early detection is crucial to intervene before MDS progresses to AML. The current diagnostic process for MDS involves analyzing peripheral blood smear (PBS), bone marrow sample (BMS), and flow cytometry (FC) data, along with clinical patient information, which is labor-intensive and time-consuming. Recent advancements in machine learning offer an opportunity for faster, automated, and accurate diagnosis of MDS. In this review, we aim to provide an overview of the current applications of AI in the diagnosis of MDS and highlight their advantages, disadvantages, and performance metrics.