EUVIMEDSkopri EUVIMED
Crossref

Feasibility of a Model-based HbA2 Prediction for Low-cost Screening of β-thalassemia Trait Using Blood-derived Indices: Opportunities and Challenges

Ramadevi Peraka iD, Pradeep Kumar Reddy M iD, Vanajakshi S iD, Sumedha Avadhanam iD, Manimekhala Parsa iD, Aditya Koppula iD

Journal of The Association of Physicians of India · 2026

DOI: 10.59556/japi.74.1706 ↗

At a glance

Journal article in Journal of The Association of Physicians of India, 2026. Written by Ramadevi Peraka and 5 co-authors. Institution: Associate Professor, Department of Pathology, Apollo Institute of Medical Sciences and Research, Hyderabad, Telangana, India, *Corresponding Author. Major MEDLINE topics: beta-Thalassemia, Hemoglobin A2, Mass Screening. 23 references.

AstrattSubjectsDettalji biblijografiċiCiteRelated studies

Abstract (original language)

Background: β-thalassemia trait (β-TT) is a common genetic condition with significant public health implications, particularly in regions with high prevalence. Diagnosis conventionally relies on HbA2 quantification using high-performance liquid chromatography or Hemoglobin electrophoresis, which are costly and inaccessible in resource-limited settings. Developing low-cost screening/triage tools is therefore essential. Materials and methods: A retrospective single-center cross-sectional study was conducted at the Department of Pathology, Apollo Institute of Medical Sciences & Research, Hyderabad, between February 2023 and December 2025. Data from 129 patients with complete blood counts, iron profiles, and HbA2 measurements were analyzed. LASSO method was applied to identify salient predictors of HbA2 from demographic, hematological, and iron parameters. Two ordinary least squares regression models (OLS) were constructed: one excluding iron parameters (model 1) and another incorporating iron parameters (model 2). LASSO-then-OLS approach was used for both 5-fold cross-validation and final model development. ROC analysis was also done.

Results

Of the 129 patients, 15 (11.6%) had β-TT (HbA2 >3.5%). The 5-fold cross-validation found lower root mean squared error (RMSE) and superior variable selection stability with an iron parameter-inclusive model. Salient predictors in the final model were age, RBC count, MCV, and RDW-CV in model 1, while model 2 additionally included serum ferritin, transferrin saturation, and total iron binding capacity (TIBC). Age and RBC count were positively associated with HbA2, while MCV, RDW-CV, serum ferritin, and TIBC were negatively associated. Model 1 explained 40% of HbA2 variance, while model 2 explained 47% variance. Model imprecision was more pronounced for β-TT cases. ROC analysis showed an area under the curve (AUC) value of 0.868 (0.766-0.969) for model 1 and 0.904 (0.829-0.98) for model 2. Optimal cutoff (3.31% from model 1 and 3.26% from model 2) for β-TT detection was lower than the conventional threshold.

Conclusion

Regression-based machine learning models have the potential to estimate HbA2 using routine blood indices, offering a cost-effective screening/triage before specialized assays. Such models are particularly valuable in populations with prevalent iron deficiency anemia (serum ferritin

Subjects

MeSH terms (MEDLINE)

beta-ThalassemiaHemoglobin A2Mass ScreeningHumansRetrospective StudiesCross-Sectional StudiesFemaleMaleFeasibility StudiesAdultROC CurveIron

Author keywords

Least absolute shrinkage and selection operatorMachine learningOLS regressionROC analysisScreeningβ-thalassemia trait

Substances

Hemoglobin A2Iron

Authors and institutions

  • Associate Professor, Department of Pathology, Apollo Institute of Medical Sciences and Research, Hyderabad, Telangana, India, *Corresponding Author.
  • Assistant Professor, Department of Pathology, Apollo Institute of Medical Sciences and Research, Hyderabad, Telangana, India.
  • Associate Professor, Department of Pathology, Apollo Institute of Medical Sciences and Research, Hyderabad, Telangana, India.
  • Final MBBS Student, Department of Pathology, Apollo Institute of Medical Sciences and Research, Hyderabad, Telangana, India.
  • Professor and Head, Department of Pathology, Apollo Institute of Medical Sciences and Research, Hyderabad, Telangana, India.
  • Assistant Professor, Department of Physiology, ESIC Medical College and Hospital, Hyderabad, Telangana, India.

ORCID profiles: Ramadevi Peraka, Pradeep Kumar Reddy M, Vanajakshi S, Sumedha Avadhanam, Manimekhala Parsa, Aditya Koppula

Cite

APA

Peraka, R., M, P. K. R., S, V., Avadhanam, S., Parsa, M., & Koppula, A. (2026). Feasibility of a Model-based HbA2 Prediction for Low-cost Screening of β-thalassemia Trait Using Blood-derived Indices: Opportunities and Challenges. Journal of The Association of Physicians of India. https://doi.org/10.59556/japi.74.1706

Vancouver

Peraka R, M PKR, S V, Avadhanam S, Parsa M, Koppula A. Feasibility of a Model-based HbA2 Prediction for Low-cost Screening of β-thalassemia Trait Using Blood-derived Indices: Opportunities and Challenges. Journal of The Association of Physicians of India. 2026. doi:10.59556/japi.74.1706

BibTeX
@article{Peraka2026,
  author = {Peraka, Ramadevi and M, Pradeep Kumar Reddy and S, Vanajakshi and Avadhanam, Sumedha and Parsa, Manimekhala and Koppula, Aditya},
  title = {Feasibility of a Model-based HbA2 Prediction for Low-cost Screening of β-thalassemia Trait Using Blood-derived Indices: Opportunities and Challenges},
  journal = {Journal of The Association of Physicians of India},
  year = {2026},
  doi = {10.59556/japi.74.1706}
}
Start for free →