Authors :
Nithya K.
Volume/Issue :
Volume 11 - 2026, Issue 3 - March
Google Scholar :
https://tinyurl.com/5yvfhym7
Scribd :
https://tinyurl.com/3kbmjsum
DOI :
https://doi.org/10.38124/ijisrt/26mar1861
Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.
Abstract :
Sickle Cell Disease (SCD) is a major hereditary hemoglobinopathy disproportionately affecting tribal populations
in India, particularly in Attappadi, Kerala, where prevalence rates are significantly higher than those in the general
population. Early detection plays a crucial role in preventing complica- tions, reducing mortality, and supporting
community-level health interventions. However, confirmatory diagnostic methods such as Hemoglobin Electrophoresis and
High-Performance Liquid Chromatography (HPLC) are often expensive, time-consuming, and inaccessible in remote tribal
regions.
This study presents a machine learning–based predictive model for early identification of SCD (SS genotype) using
routinely available clinical and hematological parameters. A synthetic dataset simulating realistic clinical distributions was
developed, incorporating variables such as hemoglobin levels, RBC indices, RDW, symptoms, and demographic factors.
A Random For- est classifier was trained and evaluated using 10-fold cross- validation, achieving an accuracy of 96.8
The proposed model provides a fast, cost-effective, and reliable screening tool that can support preliminary detection in
resource- limited tribal health centers in Attappadi, enabling timely refer- rals for confirmatory diagnostic testing.
Keywords :
Sickle Cell Disease, Machine Learning, Random Forest, Attappadi, Hemoglobinopathy Detection, Clinical Deci- Sion Support.
References :
- P. Marwah et al., “Prevalence of Sickle Cell Disease in Indian Tribal Populations,” Indian Journal of Medical Research, 2019.
- S. Patel et al., “Machine Learning in Hemoglobinopathy Screening,” BMC Medical Informatics, 2020.
- K. Thomas et al., “Health Challenges in Attappadi Tribal Region,” Kerala Journal of Public Health, 2022.
- L. Breiman, “Random Forests,” Machine Learning, 2001.
Sickle Cell Disease (SCD) is a major hereditary hemoglobinopathy disproportionately affecting tribal populations
in India, particularly in Attappadi, Kerala, where prevalence rates are significantly higher than those in the general
population. Early detection plays a crucial role in preventing complica- tions, reducing mortality, and supporting
community-level health interventions. However, confirmatory diagnostic methods such as Hemoglobin Electrophoresis and
High-Performance Liquid Chromatography (HPLC) are often expensive, time-consuming, and inaccessible in remote tribal
regions.
This study presents a machine learning–based predictive model for early identification of SCD (SS genotype) using
routinely available clinical and hematological parameters. A synthetic dataset simulating realistic clinical distributions was
developed, incorporating variables such as hemoglobin levels, RBC indices, RDW, symptoms, and demographic factors.
A Random For- est classifier was trained and evaluated using 10-fold cross- validation, achieving an accuracy of 96.8
The proposed model provides a fast, cost-effective, and reliable screening tool that can support preliminary detection in
resource- limited tribal health centers in Attappadi, enabling timely refer- rals for confirmatory diagnostic testing.
Keywords :
Sickle Cell Disease, Machine Learning, Random Forest, Attappadi, Hemoglobinopathy Detection, Clinical Deci- Sion Support.
