Comparison of the HbH inclusion test and a PCR test in routine screening for alpha thalassaemia in Hong Kong

Artificial Intelligence-Assisted Diagnostic Cytology and Genomic Testing for Hematologic Disorders

Artificial intelligence (AI) is a rapidly evolving field of computer science that involves the development of computational programs that can mimic human intelligence. In particular, machine learning and deep learning models have enabled the identification and grouping of patterns within data, leading to the development of AI systems that have been applied in various areas of hematology, including digital pathology, alpha thalassemia patient screening, cytogenetics, immunophenotyping, and sequencing. These AI-assisted methods have shown promise in improving diagnostic accuracy and efficiency, identifying novel biomarkers, and predicting treatment outcomes. However, limitations such as limited databases, lack of validation and standardization, systematic errors, and bias prevent AI from completely replacing manual diagnosis in hematology. In addition, the processing of large amounts of patient data and personal information by AI poses potential data privacy issues, necessitating the development of regulations to evaluate AI systems and address ethical concerns in clinical AI systems. Nonetheless, with continued research and development, AI has the potential to revolutionize the field of hematology and improve patient outcomes. To fully realize this potential, however, the challenges facing AI in hematology must be addressed and overcome.

Image Analysis Using Machine Learning for Automated Detection of Hemoglobin H Inclusions in Blood Smears - A Method for Morphologic Detection of Rare Cells

Background

Morphologic rare cell detection is a laborious, operator-dependent process which has the potential to be improved by the use of image analysis using artificial intelligence. Detection of rare hemoglobin H (HbH) inclusions in red cells in the peripheral blood is a common screening method for alpha-thalassemia. This study aims to develop a convolutional neural network-based algorithm for the detection of HbH inclusions.

Methods

Digital images of HbH-positive and HbH-negative blood smears were used to train and test the software. The software performance was tested on images obtained at various magnifications and on different scanning platforms. Another model was developed for total red cell counting and was used to confirm HbH cell frequency in alpha-thalassemia trait. The threshold minimum red cells to image for analysis was determined by Poisson modeling and validated on image sets.

Results

The sensitivity and specificity of the software for HbH+ cells on images obtained at ×100, ×60, and ×40 objectives were close to 91% and 99%, respectively. When an AI-aided diagnostic model was tested on a pilot of 40 whole slide images (WSIs), good inter-rater reliability and high sensitivity and specificity of slide-level classification were obtained. Using the lowest frequency of HbH+ cells (1 in 100,000) observed in our study, we estimated that a minimum of 2.4 × 10⁶ red cells would need to be analyzed to reduce misclassification at the slide level. The minimum required smear size was validated on 78 image sets which confirmed its validity.

Conclusions

WSI image analysis can be utilized effectively for morphologic rare cell detection. The software can be further developed on WISs and evaluated in future clinical validation studies comparing AI-aided diagnosis with the routine diagnostic method.

Evaluation of Thalassaemia Screening Tests in the Antenatal and Non-Antenatal Populations in Singapore

Introduction: Haemoglobinopathy testing is performed for carrier screening and evaluation of microcytic anaemia. We evaluated the effectiveness of thalassaemia screening tests at our institution and suggest ways of improving the testing algorithm. Materials and Methods: A total of 10,084 non-antenatal and 11,364 antenatal samples with alkaline gel electrophoresis (AGE), capillary electrophoresis (CE), haemoglobin H (HbH) inclusion test, mean corpuscular haemoglobin (MCH) and mean corpuscular volume (MCV) were retrospectively reviewed. A subgroup of 187 samples with genetic testing was correlated with HbH inclusions and MCH/MCV. The effect of iron deficiency on percentage haemoglobin A2 (HbA2) was studied. Results: HbH inclusion test showed low sensitivity of 21.43% for α-thalassaemia mutations but higher sensitivity of 78.95% for --SEA deletion. Byreceiver operating characteristic (ROC) analysis, MCH ≤28 pg or MCV ≤80 fl for non-antenatal samples and MCH ≤27 pg or MCV ≤81 fl for antenatal samples had >98% sensitivity for HbH inclusions. Above these thresholds, the probability that HbH inclusions would be absent was >99% (negative predictive value [NPV] >99%). MCH ≤28 pg had 100% sensitivity (95% CI 95.63%-100%) for α-thalassaemia mutations and 97.68% calculated NPV in the antenatal population. Detection of haemoglobin variants by CE correlated highly with AGE (99.89% sensitivity, 100% specificity). Severe iron deficiency reduced HbA2 in haemoglobin E (P <0.001) and α-thalassaemia (P = 0.0035), but not in β-thalassaemia. Conclusion: MCH/MCV thresholds have adequate sensitivity for α-thalassaemia in the antenatal population, and genotyping plays an important role as HbH inclusion test shows low sensitivity. CE without AGE, may be used as initial screening for haemoglobin variants. Our study provides contemporary data to guide thalassaemia screening algorithms in Singapore. Key words: Haemoglobinopathy, Mean corpuscular haemoglobin, Mean corpuscular volume

Carrier Testing for Autosomal- Recessive Disorders

The aim of carrier testing is to identify carrier couples at risk of having offspring with a serious genetic (autosomal recessive) disorder. Carrier couples are offered genetic consultation where their reproductive options, including prenatal diagnosis, are explained. The Ashkenazi Jewish population is at increased risk for several recessively inherited disorders (Tay-Sachs disease, Cystic fibrosis, Canavan disease, Gaucher disease, Familial Dysautonomia, Niemann-Pick disease, Fanconi anemia, and Bloom syndrome). Unlike Tay-Sachs disease, there is no simple biochemical or enzymatic test to detect carriers for these other disorders. However, with the rapid identification of disease-causing genes in recent years, DNA-based assays are increasingly available for carrier detection. Approximately 5% of the world's population carries a mutation affecting the globin chains of the hemoglobin molecule. Among the most common of these disorders are the thalassemias. The global birth rate of affected infants is at least 2 per 1000 (in unscreened populations), with the greatest incidence in Southeast Asian, Indian, Mediterranean, and Middle Eastern ethnic groups. Carriers are detected by evaluation of red cell indices and morphology, followed by more sophisticated hematological testing and molecular analyses. The following issues need to be considered in the development of a carrier screening program: (1) test selection based on disease severity and test accuracy; (2) funding for testing and genetic counselling; (3) definition of the target population to be screened; (4) development of a public and professional education program; (5) informed consent for screening; and (6) awareness of community needs.

An improved method for the diagnostic approach of alpha+-thalassaemia

An improved method for the diagnostic approach of alpha(+)-thalassaemia is described. The method is based on five common parameters: absence of iron deficiency, mild morphological abnormalities of erythrocytes, normal or slightly reduced erythrocytic indices MCV and MCH, normal chromatographic findings, and presence of haemoglobin H inclusions in erythrocytes with methyl-violet stain after, but not before, incubation with oxidant agent. We studied by DNA analysis, 58 subjects fulfilling the above mentioned diagnostic criteria and we found that 50 of them (86.2%) had a alpha-globin gene defect. In the remaining eight subjects (13.8%) no alpha-gene defect could be documented with the techniques used in the DNA analysis, which detect the six well-known alpha(+)-thalassaemic defects in the Greek population. We conclude that the improved method, we described has a high sensitivity and accuracy in the screening of alpha(+)-thalassaemia.

α-Thalassemia: Hb H Disease and Hb Barts Hydrops Fetalis

alpha-Thalassemia mutations are one of the most common mutations of man, and they cause Hb H disease and Hb Barts hydrops fetalis. Hb H disease is not necessarily a benign disorder as has been generally thought. Furthermore, in southern China and in Southeast Asia, there are 2-3 times more fetuses afflicted with the invariably fatal Hb Barts hydrops fetalis than with the beta-thalassemia major or intermedia. These findings underscore the public health importance of these hereditary disorders, and they call for better education, diagnosis, treatment, prevention, and research for these diseases.

Should we screen for globin gene mutations in blood samples with mean corpuscular volume (MCV) greater than 80 fL in areas with a high prevalence of thalassaemia?

AIMS

To investigate whether it is worthwhile, in areas where thalassaemia is common, to screen for globin gene mutations in subjects with a mean corpuscular volume (MCV) above 80 fL, especially in partners of known thalassaemia carriers.

METHODS

Blood samples from 95 subjects with MCV between 80 and 85 fL were screened for the presence of alpha globin gene mutations and the haemoglobin (Hb) E mutation.

RESULTS

Thirty four subjects harboured globin gene mutations. Of these, 31 had deletions of one alpha globin gene, one had Hb Constant Spring, and three had Hb E mutations.

CONCLUSION

Based on the above figures and known prevalence rates of thalassaemia carriers, it would seem worthwhile to screen for globin gene mutations in partners of known thalassaemia carriers, regardless of MCV, to identify pregnancies at risk of Hb H disease or Hb E/beta thalassaemia.

Prevalence and genotypes of alpha- and beta-thalassemia carriers in Hong Kong -- implications for population screening

BACKGROUND

The thalassemias are common in southern China. We determined the prevalence of heterozygous carriers of these genetic disorders in Hong Kong and assessed the feasibility of a community-based screening program.

METHODS

An educational and screening program for the thalassemias was carried out in three high schools with a total of 2420 students. Seventy-five percent of the students agreed to undergo screening, which consisted of blood counts, hemoglobin electrophoresis, serum ferritin measurements, and DNA analyses.

RESULTS

Of the 1800 blood samples tested, 150 (8.3 percent) had microcytosis (mean corpuscular volume, <80 microm3). Ninety students (5.0 percent) were carriers of alpha-thalassemia, of whom 81 (4.5 percent) were carriers of the Southeast Asian type of deletion, in which both alpha-globin genes on the same chromosome 16 are deleted. Sixty-one students (3.4 percent) were carriers of either beta-thalassemia or the mutation coding for hemoglobin E. Six students were carriers of both alpha- and beta-thalassemias. On the basis of these figures, the estimated numbers of pregnancies in Hong Kong in which the fetus is at risk for homozygous alpha-thalassemia and beta-thalassemia major or intermedia are 145 and 80 per year, respectively. In Hong Kong the actual numbers of women referred for prenatal diagnoses of these disorders are approximately 95 and 40 per year, respectively.

CONCLUSIONS

Despite the availability of hospital-based screening and prenatal diagnosis for many years in Hong Kong, many women carrying fetuses at risk for thalassemia are not referred for genetic counseling. A community-based program of education, screening, and counseling is needed in Hong Kong and southern China.