Background: Iron deficiency (ID) and hemoglobinopathies are highly prevalent in Southeast Asia. Accurate estimation of reference intervals (RIs) for red cell parameters is complicated by the need to exclude individuals with these conditions from the reference population. Indirect RI estimations using machine learning could help overcome these challenges. Methods: We developed a binary classification model using eXtreme Gradient Boosting (XGB) to distinguish normal individuals from those with ID, hemoglobinopathies, or other anemias. The model was trained on an annotated dataset comprising 5,520 complete blood count (CBC) results and validated with a holdout dataset of 2,367 CBC results. An independent dataset of 64,100 CBC results was used to identify individuals predicted to be normal, from which RIs were estimated using the refineR algorithm. Results: The XGB model achieved an area under the ROC of 0.97 (95% confidence interval: 0.96–0.97) for distinguishing between individuals with normal versus abnormal values. Among individuals within the independent dataset, 40,300 (62.9%) were predicted to be normal. The refineR-based reference limits (RLs) derived from this subset approximated those obtained through a direct approach. Improvements in the accuracy of indirect RL estimates were most evident for hematocrit, hemoglobin, and red cell concentrations. Conclusions Combining XGB with refineR to indirectly derive RIs for red cell parameters improved the accuracy and yielded results comparable with those of directly derived RIs. A further benefit was the capacity to generate sex- and age-specific ranges, which has remained difficult to achieve through direct approaches.

Adult T-cell leukaemia/lymphoma (ATLL) is a rare T lymphoproliferative disorder which is aetiologically linked with human T-cell lymphotropic virus type-1 (HTLV-1). HTLV-1 is endemic in Japan, Caribbean and Africa. The highest incidence of ATLL is in Japan although sporadic cases have been reported elsewhere in the world. We describe a case of ATLL with an unusual presentation which we believe is the first reported case of ATLL in Malaysia based on our literature search. A 51-year-old Indian lady was referred to University Malaya Medical Centre for an incidental finding of lymphocytosis while being investigated for pallor and giddiness. Clinical examination revealed bilateral shotty cervical lymph nodes with no hepato-splenomegaly or skin lesions. Laboratory investigations showed absolute lymphocytosis (38 x 10(9)/L) with a mildly increased serum lactate dehydrogenase. The peripheral blood smear showed the presence of predominantly small to medium sized, non-flower lymphocytes. The bone marrow showed similar findings of prominent lymphocytosis. Immunophenotyping of the bone marrow mononuclear cells showed CD3+, CD4+, CD5+, CD7- and CD25+ which is characteristic of ATLL phenotype. HTLV-1 infection was confirmed by the presence of HTLV-1 proviral DNA in the tumor cells using conventional Polymerase Chain Reaction (PCR) and real-time PCR. Here, we discuss the pathogenesis and characteristics of ATLL as well as the detection of HTLV-1 by real time PCR.
Leukemia-Lymphoma, T-Cell, Acute, HTLV-I-Associated ; Human T-lymphotropic virus 1 ; Polymerase Chain Reaction ; T-Lymphocytes ; Lymphocytosis