RESUMO
BACKGROUND AND OBJECTIVE: Morphological identification of peripheral leukocytes is a complex and time-consuming task, having especially high requirements for personnel expertise. This study is to investigate the role of artificial intelligence (AI) in assisting the manual leukocyte differentiation of peripheral blood. METHODS: A total of 102 blood samples that triggered the review rules of hematology analyzers were enrolled. The peripheral blood smears were prepared and analyzed by Mindray MC-100i digital morphology analyzers. Two hundreds leukocytes were located and their cell images were collected. Two senior technologists labeled all cells to form standard answers. Afterward, the digital morphology analyzer unitized AI to pre-classify all cells. Ten junior and intermediate technologists were selected to review the cells with the AI pre-classification, yielding the AI-assisted classifications. Then the cell images were shuffled and re-classified without AI. The accuracy, sensitivity and specificity of the leukocyte differentiation with or without AI assistance were analyzed and compared. The time required for classification by each person was recorded. RESULTS: For junior technologists, the accuracy of normal and abnormal leukocyte differentiation increased by 4.79% and 15.16% with the assistance of AI. And for intermediate technologists, the accuracy increased by 7.40% and 14.54% for normal and abnormal leukocyte differentiation, respectively. The sensitivity and specificity also significantly increased with the help of AI. In addition, the average time for each individual to classify each blood smear was shortened by 215 s with AI. CONCLUSION: AI can assist laboratory technologists in the morphological differentiation of leukocytes. In particular, it can improve the sensitivity of abnormal leukocyte differentiation and lower the risk of missing detection of abnormal WBCs.
Assuntos
Inteligência Artificial , Leucócitos , Humanos , Sensibilidade e Especificidade , Diferenciação CelularRESUMO
BACKGROUND: A man experienced multiple episodes of macroscopic hematuria following nocturnal exercise. Urinary stones and tumors were considered the two most likely causes. The patient had two hobbies: Consuming health care products in large quantities and engaging in late-night running. CASE SUMMARY: Health care products contain a large amount of calcium phosphate, and we hypothesize that this could induce the formation of small phosphate stones. After exercise, the urinary system is abraded, resulting in bleeding. The patient was advised to stop using the health care products. Consequently, the aforementioned symptoms disappeared immediately. However, the patient resumed the above two habits one year later; correspondingly, the macroscopic hematuria reappeared. CONCLUSION: This finding further confirmed the above inference and allowed for a new avenue to determine the cause of the patient's hematuria.
RESUMO
Nucleic acid detection technology has become a crucial tool in cutting-edge research within the life sciences and clinical diagnosis domains. Its significance is particularly highlighted during the respiratory virus pandemic, where nucleic acid testing plays a pivotal role in accurately detecting the virus. Isothermal amplification technologies have been developed and offer advantages such as rapidity, mild reaction conditions and excellent stability. Among these methods, recombinase polymerase amplification (RPA) has gained significant attention due to its simple primer design and resistance to multiple reaction inhibitors. However, the detection of RPA amplicons hinders the widespread adoption of this technology, leading to a research focus on cost-effective and convenient detection methods for RPA nucleic acid testing. In this study, we propose a novel computational absorption spectrum approach that utilizes the polar GelRed dye to efficiently detect RPA amplicons. By exploiting the asymmetry of GelRed molecules upon binding with DNA, polar electric dipoles are formed, leading to precipitate formation through centrifugal vibration and electrostatic interaction. The quantification of amplicon content is achieved by measuring the residual GelRed concentration in the supernatant. Our proposed portable and integrated microfluidic device successfully detected five respiratory virus genes simultaneously. The optimized linear detection was achieved and the sensitivity for all the targets reached 100 copies/µL. The total experiment could be finished in 27 min. The clinical experiments demonstrated the practicality and accuracy. This cost-effective and convenient detection scheme presents a promising biosensor for rapid virus detection, contributing to the advancement of RPA technology.
RESUMO
This study assessed the severity of the disease through the preoperative clinical manifestations and inflammatory reaction indicators of acute appendicitis, and established a score table to predict complicated appendicitis (CA).The clinical data of 238 patients with acute appendicitis in our hospital were retrospectively analyzed, which included 18 patients with acute simple appendicitis (7.6%), 170 patients with acute purulent appendicitis (72.0%), and 48 patients with acute gangrene and perforation (20.3%). The clinical manifestations and inflammatory reaction indicators were analyzed by univariate logistic regression. Multivariate logistic regression analysis was performed to screen out the independent risk factors of CA. The ß coefficients of independent risk factors entering the multivariate model were assigned by rounding, and the total score was the sum of values of all factors. Finally, verification and analysis were performed for the predictive model, and the operating characteristic curve (ROC) curve was drawn. Then, the area under the curve (AUC) was compared with the THRIVE scale, and the Hosmer-Lemeshow method was used to evaluate whether the model fitted well.The multivariate logistic regression analysis of independent risk factors was performed, and the values were rounded to the variable assignment based on the ß coefficient values. The plotted ROC and AUC was calculated as 0.857 (Pâ<â.001). Using the Hosmer-Lemeshow method, the X-value was 12.430, suggesting that the prediction model fitted well.The scoring system can quickly determine whether this is a CA, allowing for an earlier and correct diagnosis and treatment. Furthermore, the scoring system was convenient, economical, and affordable. Moreover, it is easy to popularized and promote.