Establishment and verification of the model in diagnosis of thalassemia trait based on red blood cell parameters: A two-center retrospective study

Objectives Thalassemia trait (TT) screening in resource-limited settings is hampered by reliance on expensive and complex tests. This study aimed to develop and validate a highly accessible machine learning-based tool using only routine blood parameters to accurately differentiate TT from non-TT and its major subtypes. Methods The retrospective study included 987 individuals (221 α-TT, 211 β-TT and 555 non-TT) from two medical centers. Seven machine learning methods—Logistic Regression, Gaussian Naive Bayes, Decision Tree, Random Forest, Multilayer Perceptron, XGBoost, and CatBoost—were employed to develop diagnostic models, which were evaluated using accuracy, sensitivity, specificity, AUC, PPV, NPV, and F1 score. Results The CatBoost model emerged as superior for differentiating TT from non-TT, achieving an AUC of 0.976, accuracy of 0.940, and specificity of 0.981. It also outperformed other models in distinguishing α-TT from β-TT (AUC = 0.842). Critically, this high-performance model was successfully deployed as a user-friendly WeChat mini-program AI Lab, for real-world clinical application. Conclusion The deployed ML-based AI Lab represents a robust, interpretable, and scalable tool poised to enhance TT screening efficiency and accessibility, particularly in underserved healthcare environments.

• Publication year

  2025

• Venue

  Digital Health

• Publication date

  2025-05-01

• Fields of study

  Medicine

• Identifiers
  DOI 10.1177/20552076251393429PMID 41229930PMCID 12602979
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• Responsible CVD screening with a blockchain assisted chatbot powered by explainable AI

  2025cited by this paper
• Multiclass classification of thalassemia types using complete blood count and HPLC data with machine learning

  2025cited by this paper
• Deep learning driven interpretable and informed decision making model for brain tumour prediction using explainable AI

  2025cited by this paper
• A comprehensive case study of deep learning on the detection of alpha thalassemia and beta thalassemia using public and private datasets

  2025cited by this paper
• Development and validation of HBV surveillance models using big data and machine learning

  2024cited by this paper
• Artificial Intelligence in Pharmaceutical and Healthcare Research

  2023cited by this paper
• TT@MHA: A Machine Learning-based Webpage Tool for Discriminating Thalassemia Trait from Microcytic Hypochromic Anemia Patients.

  2023cited by this paper
• Inherited disorders of hemoglobin: A review of old and new diagnostic methods.

  2023cited by this paper
• Artificial Intelligence-Assisted Diagnostic Cytology and Genomic Testing for Hematologic Disorders

  2023cited by this paper
• Advances in Machine Learning for Big Data Analysis

  2022cited by this paper
• A comparative analysis of K-Nearest Neighbour, Genetic, Support Vector Machine, Decision Tree, and Long Short Term Memory algorithms in machine learning

  2022cited by this paper
• Thalassaemia.

  2022cited by this paper
• 2021 Thalassaemia International Federation Guidelines for the Management of Transfusion-dependent Thalassemia

  2022cited by this paper
• Performance analysis of machine learning algorithms and screening formulae for β-thalassemia trait screening of Indian antenatal women

  2022cited by this paper
• Artificial Intelligence for Electricity Supply Chain automation

  2022cited by this paper
• Towards deep phenotyping pregnancy: a systematic review on artificial intelligence and machine learning methods to improve pregnancy outcomes

  2021cited by this paper
• The TVGH-NYCU Thal-Classifier: Development of a Machine-Learning Classifier for Differentiating Thalassemia and Non-Thalassemia Patients

  2021influential reference
• Basic Tenets of Classification Algorithms K-Nearest-Neighbor, Support Vector Machine, Random Forest and Neural Network: A Review

  2020cited by this paper
• Role of Red Cell Indices in Screening for Beta Thalassemia Trait: an Assessment of the Individual Indices and Application of Machine Learning Algorithm

  2020cited by this paper
• Thalassaemia.

  2019cited by this paper
• Evaluation and accurate diagnoses of pediatric diseases using artificial intelligence

  2019cited by this paper
• Effects of lipid-based nutrient supplements and infant and young child feeding counseling with or without improved water, sanitation, and hygiene (WASH) on anemia and micronutrient status: results from 2 cluster-randomized trials in Kenya and Bangladesh

  2019cited by this paper
• Artificial search agents with cognitive intelligence for binary optimization problems

  2019cited by this paper
• Clinical Classification, Screening and Diagnosis for Thalassemia.

  2018cited by this paper
• [How I treat thalassemia].

  2018cited by this paper
• Renal complications in thalassemia

  2018cited by this paper
• New challenges in diagnosis of haemoglobinopathies: Migration of populations

  2018cited by this paper
• Thalassaemia.

  2018cited by this paper
• Iron overload correlates with serum liver fibrotic markers and liver dysfunction: Potential new methods to predict iron overload-related liver fibrosis in thalassemia patients

  2017cited by this paper
• Naïve Induced Pluripotent Stem Cells Generated From β‐Thalassemia Fibroblasts Allow Efficient Gene Correction With CRISPR/Cas9

  2016cited by this paper
• Thalassaemia.

  2012cited by this paper
• Thalassemia

  2012cited by this paper
• How I treat thalassemia.

  2011cited by this paper
• Thalassaemia classification by neural networks and genetic programming

  2007cited by this paper
• Thalassemia.

  2004cited by this paper
• A Real-Time Classification System of Thalassemic Pathologies Based on Artificial Neural Networks

  2002cited by this paper
• The population genetics of the haemoglobinopathies.

  1993cited by this paper
• Mediterranean Journal of Hematology and Infectious Diseases Β-thalassemia Distribution in the Old World: an Ancient Disease Seen from a Historical Standpoint

  year unknowncited by this paper

• No citing papers are available for this paper.