Discrimination of β-thalassemia and iron deficiency anemia through extreme learning machine and regularized extreme learning machine based decision support system

Machine Learning-Based Prediction of Hemoglobinopathies Using Complete Blood Count Data

BACKGROUND

Hemoglobinopathies, the most common inherited blood disorder, are frequently underdiagnosed. Early identification of carriers is important for genetic counseling of couples at risk. The aim of this study was to develop and validate a novel machine learning model on a multicenter data set, covering a wide spectrum of hemoglobinopathies based on routine complete blood count (CBC) testing.

METHODS

Hemoglobinopathy test results from 10 322 adults were extracted retrospectively from 8 Dutch laboratories. eXtreme Gradient Boosting (XGB) and logistic regression models were developed to differentiate negative from positive hemoglobinopathy cases, using 7 routine CBC parameters. External validation was conducted on a data set from an independent Dutch laboratory, with an additional external validation on a Spanish data set (n = 2629) specifically for differentiating thalassemia from iron deficiency anemia (IDA).

RESULTS

The XGB and logistic regression models achieved an area under the receiver operating characteristic (AUROC) of 0.88 and 0.84, respectively, in distinguishing negative from positive hemoglobinopathy cases in the independent external validation set. Subclass analysis showed that the XGB model reached an AUROC of 0.97 for β-thalassemia, 0.98 for α0-thalassemia, 0.95 for homozygous α+-thalassemia, 0.78 for heterozygous α+-thalassemia, and 0.94 for the structural hemoglobin variants Hemoglobin C, Hemoglobin D, Hemoglobin E. Both models attained AUROCs of 0.95 in differentiating IDA from thalassemia.

CONCLUSIONS

Both the XGB and logistic regression model demonstrate high accuracy in predicting a broad range of hemoglobinopathies and are effective in differentiating hemoglobinopathies from IDA. Integration of these models into the laboratory information system facilitates automated hemoglobinopathy detection using routine CBC parameters.

Third-generation sequencing identified two rare α-chain variants leading to hemoglobin variants in Chinese population

BACKGROUND

Rare and novel variants of HBA1/2 and HBB genes resulting in thalassemia and hemoglobin (Hb) variants have been increasingly identified. Our goal was to identify two rare Hb variants in Chinese population using third-generation sequencing (TGS) technology.

METHODS

Enrolled in this study were two Chinese families from Fujian Province. Hematological screening was conducted using routine blood analysis and Hb capillary electrophoresis analysis. Routine thalassemia gene testing was carried out to detect the common mutations of α- and β-thalassemia in Chinese population. Rare or novel α- and β-globin gene variants were further investigated by TGS.

RESULTS

The proband of family 1 was a female aged 32, with decreased levels of mean corpuscular volume (MCV), mean corpuscular hemoglobin (MCH), Hb A2, and abnormal Hb bands in zone 5 and zone 12. No common thalassemia mutations were detected by routine thalassemia analysis, while a rare α-globin gene variant Hb Jilin [α139(HC1)Lys>Gln (AAA>CAA); HBA2:c.418A>C] was identified by TGS. Subsequent pedigree analysis showed that the proband's son also harbored the Hb Jilin variant with slightly low levels of MCH, Hb A2, and abnormal Hb bands. The proband of family 2 was a male at 41 years of age, exhibiting normal MCV and MCH, but a low level of Hb A2 and an abnormal Hb band in zone 12 without any common α- and β-thalassemia mutations. The subsequent TGS detection demonstrated a rare Hb Beijing [α16(A14)Lys>Asn (AAG>AAT); HBA2:c.51G>T] variant in HBA2 gene.

CONCLUSION

In this study, for the first time, we present two rare Hb variants of Hb Jilin and Hb Beijing in Fujian Province, Southeast China, using TGS technology.

Predicting Thalassemia Using Feature Selection Techniques: A Comparative Analysis

Thalassemia represents one of the most common genetic disorders worldwide, characterized by defects in hemoglobin synthesis. The affected individuals suffer from malfunctioning of one or more of the four globin genes, leading to chronic hemolytic anemia, an imbalance in the hemoglobin chain ratio, iron overload, and ineffective erythropoiesis. Despite the challenges posed by this condition, recent years have witnessed significant advancements in diagnosis, therapy, and transfusion support, significantly improving the prognosis for thalassemia patients. This research empirically evaluates the efficacy of models constructed using classification methods and explores the effectiveness of relevant features that are derived using various machine-learning techniques. Five feature selection approaches, namely Chi-Square (χ2), Exploratory Factor Score (EFS), tree-based Recursive Feature Elimination (RFE), gradient-based RFE, and Linear Regression Coefficient, were employed to determine the optimal feature set. Nine classifiers, namely K-Nearest Neighbors (KNN), Decision Trees (DT), Gradient Boosting Classifier (GBC), Linear Regression (LR), AdaBoost, Extreme Gradient Boosting (XGB), Random Forest (RF), Light Gradient Boosting Machine (LGBM), and Support Vector Machine (SVM), were utilized to evaluate the performance. The χ2 method achieved accuracy, registering 91.56% precision, 91.04% recall, and 92.65% f-score when aligned with the LR classifier. Moreover, the results underscore that amalgamating over-sampling with Synthetic Minority Over-sampling Technique (SMOTE), RFE, and 10-fold cross-validation markedly elevates the detection accuracy for αT patients. Notably, the Gradient Boosting Classifier (GBC) achieves 93.46% accuracy, 93.89% recall, and 92.72% F1 score.

Using artificial intelligence to improve body iron quantification: A scoping review

This scoping review explores the potential of artificial intelligence (AI) in enhancing the screening, diagnosis, and monitoring of disorders related to body iron levels. A systematic search was performed to identify studies that utilize machine learning in iron-related disorders. The search revealed a wide range of machine learning algorithms used by different studies. Notably, most studies used a single data type. The studies varied in terms of sample sizes, participant ages, and geographical locations. AI's role in quantifying iron concentration is still in its early stages, yet its potential is significant. The question is whether AI-based diagnostic biomarkers can offer innovative approaches for screening, diagnosing, and monitoring of iron overload and anemia.

Applications of Artificial Intelligence in Thalassemia: A Comprehensive Review

Thalassemia is an autosomal recessive genetic disorder that affects the beta or alpha subunits of the hemoglobin structure. Thalassemia is classified as a hypochromic microcytic anemia and a definitive diagnosis of thalassemia is made by genetic testing of the alpha and beta genes. Thalassemia carries similar features to the other diseases that lead to microcytic hypochromic anemia, particularly iron deficiency anemia (IDA). Therefore, distinguishing between thalassemia and other causes of microcytic anemia is important to help in the treatment of the patients. Different indices and algorithms are used based on the complete blood count (CBC) parameters to diagnose thalassemia. In this article, we review how effective artificial intelligence is in aiding in the diagnosis and classification of thalassemia.

A New Artificial Intelligence Approach Using Extreme Learning Machine as the Potentially Effective Model to Predict and Analyze the Diagnosis of Anemia

The procedure to diagnose anemia is time-consuming and resource-intensive due to the existence of a multitude of symptoms that can be felt physically or seen visually. Anemia also has several forms, which can be distinguished based on several characteristics. It is possible to diagnose anemia through a quick, affordable, and easily accessible laboratory test known as the complete blood count (CBC), but the method cannot directly identify different kinds of anemia. Therefore, further tests are required to establish a gold standard for the type of anemia in a patient. These tests are uncommon in settings that offer healthcare on a smaller scale because they require expensive equipment. Moreover, it is also difficult to discern between beta thalassemia trait (BTT), iron deficiency anemia (IDA), hemoglobin E (HbE), and combination anemias despite the presence of multiple red blood cell (RBC) formulas and indices with differing optimal cutoff values. This is due to the existence of several varieties of anemia in individuals, making it difficult to distinguish between BTT, IDA, HbE, and combinations. Therefore, a more precise and automated prediction model is proposed to distinguish these four types to accelerate the identification process for doctors. Historical data were retrieved from the Laboratory of the Department of Clinical Pathology and Laboratory Medicine, Faculty of Medicine, Public Health, and Nursing, Universitas Gadjah Mada, Yogyakarta, Indonesia for this purpose. Furthermore, the model was developed using the algorithm for the extreme learning machine (ELM). This was followed by the measurement of the performance using the confusion matrix and 190 data representing the four classes, and the results showed 99.21% accuracy, 98.44% sensitivity, 99.30% precision, and an F1 score of 98.84%.

A Novel Automatic Audiometric System Design Based on Machine Learning Methods Using the Brain's Electrical Activity Signals

This study uses machine learning to perform the hearing test (audiometry) processes autonomously with EEG signals. Sounds with different amplitudes and wavelengths given to the person tested in standard hearing tests are assigned randomly with the interface designed with MATLAB GUI. The person stated that he heard the random size sounds he listened to with headphones but did not take action if he did not hear them. Simultaneously, EEG (electro-encephalography) signals were followed, and the waves created in the brain by the sounds that the person attended and did not hear were recorded. EEG data generated at the end of the test were pre-processed, and then feature extraction was performed. The heard and unheard information received from the MATLAB interface was combined with the EEG signals, and it was determined which sounds the person heard and which they did not hear. During the waiting period between the sounds given via the interface, no sound was given to the person. Therefore, these times are marked as not heard in EEG signals. In this study, brain signals were measured with Brain Products Vamp 16 EEG device, and then EEG raw data were created using the Brain Vision Recorder program and MATLAB. After the data set was created from the signal data produced by the heard and unheard sounds in the brain, machine learning processes were carried out with the PYTHON programming language. The raw data created with MATLAB was taken with the Python programming language, and after the pre-processing steps were completed, machine learning methods were applied to the classification algorithms. Each raw EEG data has been detected by the Count Vectorizer method. The importance of each EEG signal in all EEG data has been calculated using the TF-IDF (Term Frequency-Inverse Document Frequency) method. The obtained dataset has been classified according to whether people can hear the sound. Naïve Bayes, Light Gradient Strengthening Machine (LGBM), support vector machine (SVM), decision tree, k-NN, logistic regression, and random forest classifier algorithms have been applied in the analysis. The algorithms selected in our study were preferred because they showed superior performance in ML and succeeded in analyzing EEG signals. Selected classification algorithms also have features of being used online. Naïve Bayes, Light Gradient Strengthening Machine (LGBM), support vector machine (SVM), decision tree, k-NN, logistic regression, and random forest classifier algorithms were used. In the analysis of EEG signals, Light Gradient Strengthening Machine (LGBM) was obtained as the best method. It was determined that the most successful algorithm in prediction was the prediction of the LGBM classification algorithm, with a success rate of 84%. This study has revealed that hearing tests can also be performed using brain waves detected by an EEG device. Although a completely independent hearing test can be created, an audiologist or doctor may be needed to evaluate the results.

A Novel Expert System for Diagnosis of Iron Deficiency Anemia

Diagnosis of a disease is one of the most important processes in the field of medicine. Thus, computer-aided detection systems are becoming increasingly important to assist physicians. The iron deficiency anemia (IDA) is a serious health problem that requires careful diagnosis. Diagnosis of IDA is a classification problem, and there are various studies conducted. Researchers also use feature selection approaches to detect significant variables. Studies so far investigate different classification problems such as outliers, class imbalance, presence of noise, and multicollinearity. However, datasets are usually affected by more than one of these problems. In this study, we aimed to create multiple systems that can separate diseased and healthy individuals and detect the variables that have a significant effect on these diseases considering influential classification problems. For this, we prepared different datasets based on the original dataset whose outliers were removed using different outlier detection methods. Then, a multistep classification algorithm was proposed for each dataset to see the results under irregular and regulated conditions. In each step, a different classification problem is handled. The results showed that it is important to consider each question together as it can and should change the outcome. Dataset and R codes used in the study are available as supplementary files online.

Performance analysis of machine learning algorithms and screening formulae for β-thalassemia trait screening of Indian antenatal women

BACKGROUND

Currently, more than forty discrimination formulae based on red blood cell (RBC) parameters and some supervised machine learning algorithms (MLAs) have been recommended for β-thalassemia trait (BTT) screening. The present study was aimed to evaluate and compare the performance of 26 such formulae and 13 MLAs on antenatal woman data with a recently developed formula SCS_BTT, which is available for evaluation in over seventy countries as an Android app, called SUSOKA[16].

METHODS

A diagnostic database of 2942 antenatal females were collected from PGIMER, Chandigarh, India and was used for this analysis. The data set consists of hypochromic microcytic anemia, BTT, Hemoglobin E trait, double heterozygote for Hemoglobin S and BTT, heterozygote for Hemoglobin D Punjab and normal subjects. Performance of the formulae and the MLAs were assessed by Sensitivity, Specificity, Youden's Index, and AUC-ROC measures. A final recommendation was made from the ranking obtained through two Multiple Criteria Decision-Making (MCDM) techniques, namely, Simultaneous Evaluation of Criteria and Alternatives (SECA) and TOPSIS.

RESULTS

It was observed that Extreme Learning Machine (ELM) and Gradient Boosting Classifier (GBC) showed maximum Youden's index and AUC-ROC measures compared to all discriminating formulae. Sensitivity remains maximum for SCS_BTT. K-means clustering and the ranking from MCDM methods show that SCS_BTT, Shine & Lal and Ravanbakhsh-F4 formula ensures higher performance among all formulae. The discriminant power of some MLAs and formulae was found considerably lower than that reported in original studies.

CONCLUSION

Comparative information on MLAs can aid researchers in developing new discriminating formulae that simultaneously ensure higher sensitivity and specificity. More multi-centric verification of the formulae on heterogeneous data is indispensable. SCS_BTT and Shine & Lal formula, and ELM and GBC are recommended for screening BTT based on MCDM. SCS_BTT can be used with certainty as a tangible cost-saving screening tool for mass screening for antenatal women in India and other countries.

Peripheral Blood Erythrocyte Parameters in Β-Thalassemia Minor with Coexistent Iron Deficiency: Comparisons between Iron-Deficient and -Sufficient Carriers

Changes in erythrocyte parameters are well known in both β-thalassemia minor (BTM) and iron deficiency (ID) when either is present alone; however, to our knowledge, there has been no study showing the changes when the two conditions coexist. We herein assessed erythrocyte parameters in BTM with coexistent ID. The BTM cases were divided into two groups based on ferritin levels as ID+ and ID−; the ID+ group was then further divided based on hemoglobin (Hb) levels as iron-deficient carriers with (IDA+) and without (IDA−) anemia. When compared to the ID− group, all parameters were significantly different in the IDA+ group except mean corpuscular volume (MCV) and red blood cells (RBC). All parameters except RBC were significantly different between the IDA+ and IDA− groups. Hb, hematocrit (Hct), MCV, and mean corpuscular hemoglobin (MCH) levels in the IDA− group were found to be lower than in the ID− group. Changes in erythrocyte parameters in iron-deficient carriers are critical in screening for BT, particularly for correct formulation of mathematical algorithms utilized by artificial intelligence programs.

Can laboratory parameters be an alternative to CT and RT-PCR in the diagnosis of COVID-19? A machine learning approach

In this study, a machine learning-based decision support system that uses routine laboratory parameters has been proposed in order to increase the diagnostic success in COVID-19. The main goal of the proposed method was to reduce the number of misdiagnoses in the RT-PCR and CT scans and to reduce the cost of testing. In this study, we retrospectively reviewed the files of patients who presented to the coronavirus outpatient. The demographic, thoracic CT, and laboratory data of the individuals without any symptoms of the disease, who had negative RT-PCR test and who had positive RT-PCR test were analyzed. CT images were classified using hybrid CNN methods to show the superiority of the decision support system using laboratory parameters. Detection of COVID-19 from CT images achieved an accuracy of 97.56% with the AlexNet-SVM hybrid method, while COVID-19 was classified with an accuracy of 97.86% with the proposed method using laboratory parameters.

An online alpha-thalassemia carrier discrimination model based on random forest and red blood cell parameters for low HbA2 cases

BACKGROUND

Since screening of α-thalassemia carriers by low HbA₂ has a low positive predictive value (PPV), the PPV was as low as 40.97% in our laboratory, other more effective screening methods need to be devised. This study aimed at developing a machine learning model by using red blood cell parameters to identify α-thalassemia carriers from low HbA₂ patients.

METHODS

Laboratory data of 1213 patients with low HbA₂ used for modeling was randomly divided into the training set (849 of 1213, 70%) and the internal validation set (364 of 1213, 30%). In addition, an external data set (n = 399) was used for model validation. Fourteen machine learning methods were applied to construct a discriminant model. Performance was evaluated with accuracy, sensitivity, specificity, etc. and compared with 7 previously published discriminant function formulae.

RESULTS

The optimal model was based on random forest with 5 clinical features. The PPV of the model was more than twice the PPV of HbA₂, and the model had a high negative predictive value (NPV) at the same time. Compared with seven formulae in screening of α-thalassemia carriers, the model had a better accuracy (0.915), specificity (0.967), NPV (0.901), PPV (0.942) and area under the receiver operating characteristic curve (AUC, 0.948) in the independent test set.

CONCLUSION

Use of a random forest-based model enables rapid discrimination of α-thalassemia carriers from low HbA₂ cases.

A decision support scheme for beta thalassemia and HbE carrier screening

The most effective way to combat β-thalassemias is to prevent the birth of children with thalassemia major. Therefore, a cost-effective screening method is essential to identify β-thalassemia traits (BTT) and differentiate normal individuals from carriers. We considered five hematological parameters to formulate two separate scoring mechanisms, one for BTT detection, and another for joint determination of hemoglobin E (HbE) trait and BTT by employing decision trees, Naïve Bayes classifier, and Artificial neural network frameworks on data collected from the Postgraduate Institute of Medical Education and Research, Chandigarh, India. We validated both the scores on two different data sets and found 100% sensitivity of both the scores with their respective threshold values. The results revealed the specificity of the screening scores to be 79.25% and 91.74% for BTT and 58.62% and 78.03% for the joint score of HbE and BTT, respectively. A lower Youden’s index was measured for the two scores compared to some existing indices. Therefore, the proposed scores can obviate a large portion of the population from expensive high-performance liquid chromatography (HPLC) analysis during the screening of BTT, and joint determination of BTT and HbE, respectively, thereby saving significant resources and cost currently being utilized for screening purpose.