A MALDI-TOF mass spectrometry-based haemoglobin chain quantification method for rapid screen of thalassaemia

Can some algorithms of machine learning identify osteoporosis patients after training and testing some clinical information about patients?

OBJECTIVE

This study was designed to establish a diagnostic model for osteoporosis by collecting clinical information from patients with and without osteoporosis. Various machine learning algorithms were employed for training and testing the model, evaluating its performance, and conducting validations to explore the most suitable machine learning algorithm.

METHODS

Clinical information, including demographic data, examination results, medical history, and laboratory test results, was collected from inpatients with and without osteoporosis. The LASSO algorithm was utilized for feature selection, and multiple machine learning algorithms were applied to calculate the model's accuracy, precision, recall, F1 score, and average precision (AP) value. Receiver operating characteristic (ROC) curves for each algorithm were plotted, and a comprehensive evaluation was conducted to identify the most suitable machine learning model. Finally, the model's predictive accuracy was validated using corresponding information from other patients.

RESULTS

A total of 1063 patients were included; 562 had osteoporosis, and 501 did not. After LASSO feature selection, the most important features for the model's predictive results were determined to be age, height, weight, alkaline phosphatase activity, and osteocalcin. Evaluation of the accuracy, precision, recall, F1 score, and AP value for each algorithm, along with ROC curves, led to the selection of the light gradient boosting machine (LGBM) algorithm as the best algorithm for the model. The validation results confirmed the model's excellent predictive ability.

CONCLUSION

This study established a preliminary diagnostic model for osteoporosis, contributing to increased efficiency in diagnosing the disease.

A reliable and high throughput HPLC-HRMS method for the rapid screening of β-thalassemia and hemoglobinopathy in dried blood spots

OBJECTIVES

Traditional methods for β-thalassemia screening usually rely on the structural integrity of hemoglobin (Hb), which can be affected by the hemolysis of red blood cells and Hb degradation. Here, we aim to develop a reliable and high throughput method for rapid detection of β-thalassemia using dried blood spots (DBS).

METHODS

Hb components were extracted from a disc (3.2 mm diameter) punched from the DBS samples and digested by trypsin to produce a series of Hb-specific peptides. An analytical system combining high-resolution mass spectrometry and high-performance liquid chromatography was used for biomarker selection. The selected marker peptides were used to calculate delta/beta (δ/β) and beta-mutated/beta (β_M/β) globin ratios for disease evaluation.

RESULTS

Totally, 699 patients and 629 normal individuals, aged 3 days to 89 years, were recruited for method construction. Method assessment showed both the inter-assay and intra-assay relative standard deviation values were less than 10.8%, and the limits of quantitation for the proteo-specific peptides were quite low (1.0-5.0 μg/L). No appreciable matrix effects or carryover rates were observed. The extraction recoveries ranged from 93.8 to 128.7%, and the method was shown to be stable even when the samples were stored for 24 days. Prospective applications of this method in 909 participants also indicated good performance with a sensitivity of 100% and a specificity of 99.6%.

CONCLUSIONS

We have developed a fast, high throughput and reliable method for screening of β-thalassemia and hemoglobinopathy in children and adults, which is expected to be used as a first-line screening assay.

Advances in screening of thalassaemia

Thalassaemia is a common hereditary haemolytic anaemia. Mild cases of this disease may be asymptomatic, while patients with severe thalassaemias require high-dose blood transfusions and regular iron removal to maintain life or haematopoietic stem cell transplantation to be cured, imposing an enormous familial and social burden. Therefore, early, timely, and accurate screening of patients is of great importance. In recent years, with the continuous development of thalassaemia screening technologies, the accuracy of thalassaemia screening has also improved significantly. This article reviews the current research on thalassaemia screening.