RAPIDMINER-GENERATED ALGORITHM USING MEAN CORPUSCULAR HEMOGLOBIN & HEMATOCRIT & HEMOLYSIA AREA : A NEW PREDICTION TOOL FOR CARRIERS OF αO-THALASSEMIA (SOUTHEAST ASIAN TYPE) AMONG MICROCYTIC BLOOD SAMPLES
DOI:
https://doi.org/10.55766/sujst8272Keywords:
Rapidminer algorithm, Screening tests, SEA-αO-thalassemia, Thalassemia carriers, α-thalassemiaAbstract
The SEA-αO thalassemia is common in Thailand. Carriers of this type of thalassemia can be found in microcytic blood samples. Although several laboratory tests are performed to screen the carriers of this type of thalassemia, it is questioned if only RBC parameters can effectively screen the carriers of SEA-aO-thalassemia. This study was aimed to evaluate the effectiveness of IC strip, OFT, HbH-IB test, Hemolysis Area and RBC parameters in screening for SEA-αO thalassemia carriers in microcytic blood samples. Fifty-four (54) non-anemic blood samples having MCV <80 fL were tested for OFT, HbH-IB test, HA, IC strip test and RBC indices. An algorithm of RBC indices for the SEA-αO-thalassemia carrier screening was established by the RapidMiner software. The Gap-PCR was carried out to detect the SEA-αO thalassemia genotype. A variety of RBC indices was observed. In screening for SEA-aO thalassemia, the OFT, HA and IC strip tests had 95.47%, 95.4% and 100% sensitivity, and 53.1%, 50%, and 43.7% specificity, respectively, while the conventional and modified HbH inclusion body tests had 45.4%, 69.1% sensitivity and 100%, 93.7% specificity, respectively. A newly established algorithm [MCH(£23.0 pg) -> Hct(>36.5 %) ->HA(£70.0 units)] was found to have 80% sensitivity, 100% specificity, 100% PPV and 92.8% NPV, infinite positive LR and 0.002 negative LR in screening for SEA-aO thalassemia. Therefore, OFT, HA, IC strip, but not HbH-IB test, were still effective in screening for carriers of SEA-aO-thalassemia in the microcytic blood samples. Due to its ease of use, the newly established algorithm was an additional means to predict the carriers of SEA-aO thalassemia in the microcytic cohort.
References
Amirhajlou, L., Sohrabi, Z., Alebouyeh, M. R., Tavakoli, N., Haghighi, R. Z., Hashemi, A., and Asoodeh, A. (2019). Application of data mining techniques for predicting residents’ performance on pre-board examinations: A case study. Journal of Education and Health Promotion, 8:108. https://doi.org/10.4103/jehp.jehp_394_18
Bunkall, C., Ghallyan, N., Elliott, C., Van de Water, N., and Chan, G. (2018). Evaluation of an immunochromatographic strip test for α-thalassaemia screening. International Journal of Laboratory Hematology, 40(6):691-696. https://doi.org/10.1111/ijlh.12905
Chan, A.Y., So, C.K., and Chan, L.C. (1996). Comparison of the HbH inclusion test and a PCR test in routine screening for α-thalassaemia in Hong Kong. Journal of Clinical Pathology, 49(5):411-412. https://doi.org/10.1136/jcp.49.5.411
CheshmehSohrabi, M. and Mashhadi, A. (2023). Using data mining, text mining, and bibliometric techniques to the research trends and gaps in the field of language and linguistics. Journal of Psycholinguistic Research, 52(2):607-630. https://doi.org/10.1007/s10936-022-09911-6
Feng, P., Li, Y., Liao, Z., Yao, Z., Lin, W., Xie, S., Hu, B., Huang, C., Liu, W., Xu, H., Liu, M., and Gan, W. (2022). An online α-thalassemia carrier discrimination model based on random forest and red blood cell parameters for low HbA2 cases. Clinica Chimica Acta, 525:1-5. https://doi.org/10.1016/j.cca.2021.12.003
Fu, Y.K., Liu, H.M., Lee, L.H., Chen, Y.J., Chien, S.H., Lin, J.S., Chen, W.C., Cheng, M.H., Lin, P.H., Lai, J.Y., Chen, C.M., and Liu, C.Y. (2021). The TVGH–NYCU Thal-Classifier: Development of a machine-learning classifier for differentiating thalassemia and non-thalassemia patients. Diagnostics, 11(9):1725. https://doi.org/10.3390/diagnostics11091725
Harteveld, C.L. and Higgs, D.R. (2010). α-thalassaemia. Orphanet Journal of Rare Diseases, 5:13. https://doi.org/10.1186/1750-1172-5-13
Hockham, C., Ekwattanakit, S., Bhatt, S., Penman, B.S., Gupta, S., Viprakasit, V., and Piel, F.B. (2019). Estimating the burden of α-thalassaemia in Thailand using a comprehensive prevalence database for Southeast Asia. eLife, 8:e40580. https://doi.org/10.7554/eLife.40580
Jomoui, W., Fucharoen, G., Sanchaisuriya, K., and Fucharoen, S. (2017). Screening of (–SEA) α-thalassaemia using an immunochromatographic strip assay for the ζ-globin chain in a population with a high prevalence and heterogeneity of haemoglobinopathies. Journal of Clinical Pathology, 70(1):63-68. https://doi.org/10.1136/jclinpath-2016-203765
Lachover-Roth, I., Peretz, S., Zoabi, H., Harel, E., Livshits, L., Filon, D., Levin, C., and Koren, A. (2024). Support vector machine-based formula for detecting suspected α-thalassemia carriers: A path toward universal screening. International Journal of Molecular Sciences, 25(12):6446. https://doi.org/10.3390/ijms25126446
Laengsri, V., Shoombuatong, W., Adirojananon, W., Nantasenamat, C., Prachayasittikul, V., and Nuchnoi, P. (2019). ThalPred: A web-based prediction tool for discriminating thalassemia trait and iron deficiency anemia. BMC Medical Informatics and Decision Making, 19(1):212. https://doi.org/10.1186/s12911-019-0929-2
Martins, B., Ferreira, D., Neto, C., Abelha, A., and Machado, J. (2021). Data mining for cardiovascular disease prediction. Journal of Medical Systems, 45(1):6. https://doi.org/10.1007/s10916-020-01682-8
Mir, A., Ur Rehman, A., Ali, T.M., Javaid, S., Almufareh, M.F., Humayun, M., and Shaheen, M. (2024). A novel approach for the effective prediction of cardiovascular disease using applied artificial intelligence techniques. ESC Heart Failure,11(6):3742-3756. https://doi.org/10.1002/ehf2.14942
Mo, D., Zheng, Q., Xiao, B., and Li, L. (2023). Predicting thalassemia using deep neural network based on red blood cell indices. Clinica Chimica Acta, 543:117329. https://doi.org/10.1016/j.cca.2023.117329
Nelson, A.C., Motum, P.I., and Emeto, T.I. (2019). Evaluation of an immunochromatographic test for α-thalassaemia screening in a multi-ethnic population. International Journal of Laboratory Hematology, 41(3):397-403. https://doi.org/10.1111/ijlh.12994
Old, J.M. (2003). Screening and genetic diagnosis of haemoglobin disorders. Blood Reviews, 17(1):43-53. https://doi.org/10.1016/S0268-960X(02)00061-9
Phirom, K., Charoenkwan, P., Shoombuatong, W., Sirichotiyakul, S., and Tongsong, T. (2022). DeepThal: A deep learning-based framework for the large-scale prediction of the α⁺-thalassemia trait using red blood cell parameters. Journal of Clinical Medicine, 11(21):6305. https://doi.org/10.3390/jcm11216305
Pranpanus, S., Sirichotiyakul, S., Srisupundit, K., and Tongsong, T. (2009). Sensitivity and specificity of mean corpuscular hemoglobin for screening of α-thalassemia-1 trait and β-thalassemia trait. Journal of the Medical Association of Thailand, 92(6):739-743.
Prayalaw, P., Fucharoen, G., and Fucharoen, S. (2014). Routine screening for α-thalassaemia using an immunochromatographic strip assay for haemoglobin Bart’s. Journal of Medical Screening, 21(3):120-125. https://doi.org/10.1177/0969141314538611
Rustam, F., Ashraf, I., Jabbar, S., Tutusaus, K., Mazas, C., Barrera, A.E.P., and de la Torre Díez, I. (2022). Prediction of β-thalassemia carriers using complete blood count features. Scientific Reports, 12(1):19999. https://doi.org/10.1038/s41598-022-22011-8
Saha, S., Sharma, P., Jain, A.K., Dutta, B., Martínez, L., Saleh, S., Dolai, T.K., Kaviraj, A., Sanyal, T., Nielsen, I., and Das, R. (2025). Detection of β-thalassemia trait from a heterogeneous population with red cell indices and parameters. Computers in Biology and Medicine, 192(PartA):110151. https://doi.org/10.1016/j.compbiomed.2025.110151
Saleem, M., Aslam, W., Lali, M.I.U., Rauf, H.T., and Nasr, E.A. (2023). Predicting thalassemia using feature selection techniques: A comparative analysis. Diagnostics, 13(22):3441. https://doi.org/10.3390/diagnostics13223441
Schipper, A., Rutten, M., van Gammeren, A., Harteveld, C.L., Urrechaga, E., Weerkamp, F., den Besten, G., Krabbe, J., Schoonen, L., Broeren, M., van Wijnen, M., Huijskens, M. J.A.J., Koopmann, T., van Ginneken, B., Kusters, R., and Kurstjens, S. (2024). Machine learning-based prediction of hemoglobinopathies using complete blood count data. Clinical Chemistry, 70(8):1064-1075. https://doi.org/10.1093/clinchem/hvae081
Sirichotiyakul, S., Maneerat, J., Sa-nguansermsri, T., Dhananjayanonda, P., and Tongsong, T. (2005). Sensitivity and specificity of mean corpuscular volume testing for screening for α-thalassemia-1 and β-thalassemia traits. Journal of Obstetrics and Gynaecology Research, 31(3):198-201. https://doi.org/10.1111/j.1447-0756.2005.00280.x
Sirichotiyakul, S., Tantipalakorn, C., Sanguansermsri, T., Wanapirak, C., and Tongsong, T. (2004). Erythrocyte osmotic fragility test for screening of α-thalassemia-1 and β-thalassemia trait in pregnancy. International Journal of Gynecology and Obstetrics, 86(3):347-350. https://doi.org/10.1016/j.ijgo.2004.04.037
Sudjaroen, Y. (2015). Efficiency assessment of immunochromatographic strip test for the diagnosis of α-thalassemia-1 carriers. Journal of Laboratory Physicians, 7(1):4-10. https://doi.org/10.4103/0974-2727.157779
Tatu, T. (2020). Laboratory Diagnosis of Beta Thalassemia and HbE. In: Zakaria, M. and Hassan, T. (eds.). Beta Thalassemia. London: IntechOpen, 174p. https://doi.org/10.5772/intechopen.90317
Tatu, T. and Sweatman, D. (2018). Hemolysis area: A new parameter of erythrocyte osmotic fragility for screening of thalassemia trait. Journal of Laboratory Physicians, 10(2):214-220. https://doi.org/10.4103/JLP.JLP_136_17
Tatu, T., Jannoi, S., Jamwuttipreecha, K., and Sa-nguansermsri, T. (2003). Screening for α-thalassemia 1 using the dried brilliant cresyl blue method. Thai Journal of Hematology and Transfusion Medicine, 13(4):315-320.
Tatu, T., Klasamut, S., Sorntham, H., Chantanaskulwong, P., Kaewkhampa, N., and Khantarag, P. (2025). Predicting the double heterozygotes of HbE and α-thalassemia-1 (Southeast Asian Type) using RapidMiner-generated hematologic algorithm. Hemoglobin, 49(6):390-398. https://doi.org/10.1080/03630269.2025.2590224
Tayapiwatana, C., Kuntaruk, S., Tatu, T., Chiampanichayakul, S., Munkongdee, T., Winichagoon, P., Fucharoen, S., and Kasinrerk, W. (2009). Simple method for screening of α-thalassaemia 1 carriers. International Journal of Hematology, 89(5):559-567. https://doi.org/10.1007/s12185-009-0331-4
Tienthavorn, V., Pattanapongsthorn, J., Charoensak, S., Sae-Tung, R., Charoenkwan, P., and Sa-nguansermsri, T. (2006). Prevalence of thalassemia carriers in Thailand (in Thai). Thai Journal of Hematology and Transfusion Medicine, 16:307-312.
Wanapirak, C., Piyamongkol, W., Sirichotiyakul, S., Tayapiwatana, C., Kasinrerk, W., and Tongsong, T. (2011). Accuracy of immunochromatographic strip test in diagnosis of α-thalassemia-1 carrier. Journal of the Medical Association of Thailand, 94(7):761-765.
Wang, W., Ye, R., Tang, B., and Qi, Y. (2025). MultiThal-classifier: A machine learning-based multi-class model for thalassemia diagnosis and classification. Clinica Chimica Acta, 567:120025. https://doi.org/10.1016/j.cca.2024.120025
Winichagoon, P., Kumpan, P., Holmes, P., Finlayson, J., Newbound, C., Kabral, A., Li, B., Nuinoon, M., Fawcett, T., Tayapiwatana, C., Kasinrerk, W., and Fucharoen, S. (2015). Validation of the immunochromatographic strip for α-thalassemia screening: A multicenter study. Translational Research, 165(6):689-695. https://doi.org/10.1016/j.trsl.2014.10.013
Zhang, F., Yang, J., Wang, Y., Cai, M., Ouyang, J., and Li, J. (2023). TT@MHA: A machine learning-based webpage tool for discriminating thalassemia trait from microcytic hypochromic anemia patients. Clinica Chimica Acta, 545:117368. https://doi.org/10.1016/j.cca.2023.117368
