Clinical Classification, Screening and Diagnosis for Thalassemia

Thalassemia is one of the most widely distributed monogenic disorders in the world and affects the largest number of people. It can manifest a wide spectrum of phenotypes from asymptomatic to fatal, which is associated with the degree of imbalance between α- and β-globin chains. Therefore, individuals with different genotypes could present with a similar phenotype. Genetic analysis is always needed to make a correct diagnosis. However, routine genetic analysis of thalassemia used in the Chinese population identifies only 23 common variants, resulting in many cases undiagnosed or being misdiagnosed. In this study, we applied a long-read sequencing-based approach termed comprehensive analysis of thalassemia alleles (CATSA) to 30 subjects whose hematologic screening results could not be explained by the routine genetic test results. The identification of additional variants and the correction of genotypes allowed the interpretation of the clinical phenotype in 24 subjects, which have been confirmed to be correct by independent experiments. Moreover, we identified a novel 8.4-kb deletion containing the entire HBB and HBD genes as well as part of the HBBP1 gene, expanding the genotype spectrum of β-thalassemia. CATSA showed a great advantage over other genetic tests in the diagnosis of thalassemia caused by rare variants.

Thalassemia is the most common monogenic disorder of red blood cells (RBCs) caused by defects in the synthesis of globin chains. Thalassemia phenotypes have a wide spectrum of clinical manifestations and vary from severe anemia requiring regular blood transfusions to clinically asymptomatic states. Ineffective erythropoiesis and toxicity caused by iron overload are major factors responsible for various complications in thalassemia patients, especially patients with β-thalassemia major (β-TM). Common complications in patients with thalassemia include iron overload, thrombosis, cardiac morbidity, vascular dysfunction, inflammation, and organ dysfunction. Extracellular vesicles (EVs) are small membrane vesicles released from various cells' plasma membranes due to activation and apoptosis. Based on studies, EVs play a role in various processes, including clot formation, vascular damage, and proinflammatory processes. In recent years, they have also been studied as biomarkers in the diagnosis and prognosis of diseases. Considering the high concentration of EVs in thalassemia and their role in cellular processes, this study reviews the role of EVs in the common complications of patients with β-thalassemia for the first time.

Ocular involvement is common in transfusion-dependent beta-thalassemia (TDβ-T) patients. We aimed to investigate the effect of splenectomy on optical coherence tomography angiography (OCTA) findings in TDβ-T patients.

The study is a prospective cross-sectional study. A total of 45 eyes of 23 patients with splenectomy (34.04±8.83 years), 18 eyes of 9 patients without splenectomy (27.44±5.43 years), and 54 eyes of 27 controls (33.22±6.44 years) were included. Vessel density in superficial capillary plexus, deep capillary plexus and radial peripapillary capillary, foveal avascular zone, choriocapillaris flow area, choroidal and retinal thickness detected by OCTA were evaluated. p < 0.05 was considered significant.

Vessel density of superficial capillary plexus and deep capillary plexus were similar in patients with and without splenectomy, and controls. Choriocapillaris flow area was significantly decreased in patients with splenectomy than that in those without splenectomy and controls (2.02±0.12 vs. 2.17±0.1 and 2.14±0.12; p < 0.001). Choroidal thickness was significantly lower in patients without splenectomy than in patients with splenectomy and controls (260.05±61.02 vs. 305.11±42.13 and 298.89±29.14, p = 0.008). Parafoveal and perifoveal thickness of the full retina and outer retina were significantly lower in patients without splenectomy than in patients with splenectomy and controls (301.06±10.0, 279.78±10.28 vs. 311.04±14.89, 290.87±13.67 and 316.63±13.57, 289.56±9.31, p < 0.001 and p = 0.002; 174.72±7.81, 167.17±6.21 vs. 182.87±8.81, 173.60±7.09 and 185.11±9.26, 173.96±6.79, p = 0.001 and p < 0.001, respectively).

OCTA findings can provide information about the microvascular effects of splenectomy on the retina of patients with TDβ-T.

The traditional statistical screening method for thalassemia based on red blood cell (RBC) indices is being replaced by machine learning. Here, we developed deep neural networks (DNNs) that outperformed the traditional method for predicting thalassemia.

Using a dataset of 8693 records comprising genetic tests and other 11 features we constructed 11 DNN models and 4 traditional statistical models and then compared their performances and analysed feature importance for interpreting DNN models.

The area under the receiver operating characteristic curve, accuracy, Youden’s index, F1 score, sensitivity, specificity, positive predictive value and negative predictive value, were 0.960, 0.897, 0.794, 0.897, 0.883, 0.911, 0.914, and 0.882, respectively, for our best model, and compared with the traditional statistical model based on the mean corpuscular volume, these values were increased by 10.22%, 10.09%, 26.55%, 8.92%, 4.13%, 16.90%, 13.86% and 6.07%, respectively, and by 15.38%, 11.70%, 31.70%, 9.89%, 3.05%, 22.13%, 17.11% and 5.94%, respectively, for the mean cellular haemoglobin model. The DNN model performance will reduce without age, RBC distribution width (RDW), sex, or both WBC and PLT.

Our DNN model outperformed the current screening model. In 8 features, RDW and age were the most useful, followed by sex and the combination of WBC and PLT, the remaining nearly useless.