Hemodynamic Analysis and Diagnosis Based on Multi-Deep Learning Models

This study employs nine distinct deep learning models to categorize 12,444 blood cell images and automatically extract from them relevant information with an accuracy that is beyond that achievable with traditional techniques.The work is intended to improve current methods for the assessment of human health through measurement of the distribution of four types of blood cells,namely,eosinophils,neutrophils,monocytes,and lymphocytes,known for their relationship with human body damage,inflammatory regions,and organ illnesses,in particular,and with the health of the immune system and other hazards,such as cardiovascular disease or infections,more in general.The results of the experiments show that the deep learning models can automatically extract features from the blood cell images and properly classify them with an accuracy of 98%,97%,and 89%,respectively,with regard to the training,verification,and testing of the corresponding datasets.

Comparison of Hematological Parameters and Critical Value Analysis in the Prevention and Control of Thalassaemia in Hainan Li and Han Nationalities

Objective: To compare the distribution of “mean corpuscular hemoglobin”-MCV, “mean corpuscular volume”-MCH, “hemoglobin”-HGB, “hemoglobin A”-HbA and “hemoglobin A2”-HbA2 in α and β thalassemia hematology screening between Li and Han nationality, and analyze the best diagnostic cut-off value. Methods: Select 7816 middle school students from Li nationality area as the research object, collect peripheral blood for blood cell analysis, hemoglobin electrophoresis and thalassaemia gene detection, and compare the difference in hematological parameters of common thalassemia genotype between Li and Han nationalities. Taking the genetic test results as the gold standard, construct the receiver operator characteristic curve (ROC curve) of relevant hematology parameters, calculate the Youden index and take its maximum diagnostic cut-off point as the best critical value. Results: Comparison of hematological parameters of common thalassemia genotypes showed that the average value of MCH and MCV of -α3.7/-α4.2 type in Li nationality was lower than that of Han nationality, and the average value of HbA2 of CD41-42/βN type was higher than that of Han nationality, there was no significant difference among other genotypes. ROC curve analysis shows that the MCH, MCV, and HGB values have poor diagnostic efficiency for thalassaemia, HbA has a slightly better diagnostic efficiency for α thalassaemia, and the optimal cut-off values of HbA for Li and Han nationalities are 96.95% and 97.75%, respectively;HbA2 has better screening efficiency for β-thalassemia, and the optimal cut-off values of HbA2 for Li and Han nationalities are 4.20% and 3.45% respectively. Conclusion: In the prevention and control screening of thalassaemia in the Li and Han nationalities, hemoglobin electrophoresis technology has a better diagnostic efficiency.