Search

BackgroundBone marrow aspiration and biopsy remain the gold standard for the diagnosis of hematological diseases despite the development of flow cytometry (FCM) and molecular and gene analyses. However, the interpretation of the results is laborious and operator dependent. Furthermore, the obtained results exhibit inter- and intravariations among specialists. Therefore, it is important to develop a more objective and automated analysis system. Several deep learning models have been developed and applied in medical image analysis but not in the field of hematological histology, especially for bone marrow smear applications. ObjectiveThe aim of this study was to develop a deep learning model (BMSNet) for assisting hematologists in the interpretation of bone marrow smears for faster diagnosis and disease monitoring. MethodsFrom January 1, 2016, to December 31, 2018, 122 bone marrow smears were photographed and divided into a development cohort (N=42), a validation cohort (N=70), and a competition cohort (N=10). The development cohort included 17,319 annotated cells from 291 high-resolution photos. In total, 20 photos were taken for each patient in the validation cohort and the competition cohort. This study included eight annotation categories: erythroid, blasts, myeloid, lymphoid, plasma cells, monocyte, megakaryocyte, and unable to identify. BMSNet is a convolutional neural network with the YOLO v3 architecture, which detects and classifies single cells in a single model. Six visiting staff members participated in a human-machine competition, and the results from the FCM were regarded as the ground truth. ResultsIn the development cohort, according to 6-fold cross-validation, the average precision of the bounding box prediction without consideration of the classification is 67.4%. After removing the bounding box prediction error, the precision and recall of BMSNet were similar to those of the hematologists in most categories. In detecting more than 5% of blasts in the validation cohort, the area under the curve (AUC) of BMSNet (0.948) was higher than the AUC of the hematologists (0.929) but lower than the AUC of the pathologists (0.985). In detecting more than 20% of blasts, the AUCs of the hematologists (0.981) and pathologists (0.980) were similar and were higher than the AUC of BMSNet (0.942). Further analysis showed that the performance difference could be attributed to the myelodysplastic syndrome cases. In the competition cohort, the mean value of the correlations between BMSNet and FCM was 0.960, and the mean values of the correlations between the visiting staff and FCM ranged between 0.952 and 0.990. ConclusionsOur deep learning model can assist hematologists in interpreting bone marrow smears by facilitating and accelerating the detection of hematopoietic cells. However, a detailed morphological interpretation still requires trained hematologists.

BackgroundThe detection of dyskalemias—hypokalemia and hyperkalemia—currently depends on laboratory tests. Since cardiac tissue is very sensitive to dyskalemia, electrocardiography (ECG) may be able to uncover clinically important dyskalemias before laboratory results. ObjectiveOur study aimed to develop a deep-learning model, ECG12Net, to detect dyskalemias based on ECG presentations and to evaluate the logic and performance of this model. MethodsSpanning from May 2011 to December 2016, 66,321 ECG records with corresponding serum potassium (K+) concentrations were obtained from 40,180 patients admitted to the emergency department. ECG12Net is an 82-layer convolutional neural network that estimates serum K+ concentration. Six clinicians—three emergency physicians and three cardiologists—participated in human-machine competition. Sensitivity, specificity, and balance accuracy were used to evaluate the performance of ECG12Net with that of these physicians. ResultsIn a human-machine competition including 300 ECGs of different serum K+ concentrations, the area under the curve for detecting hypokalemia and hyperkalemia with ECG12Net was 0.926 and 0.958, respectively, which was significantly better than that of our best clinicians. Moreover, in detecting hypokalemia and hyperkalemia, the sensitivities were 96.7% and 83.3%, respectively, and the specificities were 93.3% and 97.8%, respectively. In a test set including 13,222 ECGs, ECG12Net had a similar performance in terms of sensitivity for severe hypokalemia (95.6%) and severe hyperkalemia (84.5%), with a mean absolute error of 0.531. The specificities for detecting hypokalemia and hyperkalemia were 81.6% and 96.0%, respectively. ConclusionsA deep-learning model based on a 12-lead ECG may help physicians promptly recognize severe dyskalemias and thereby potentially reduce cardiac events.

Introduction Generalized anxiety disorder (GAD) is characterized by persistent worry associated with a variety of symptoms, including concentration problems, difficulty sleeping, fatigue, irritability, muscle tension and restlessness. It is a [...], Background: Neuroticism personality trait is recognized as an important endophenotypic predictor of generalized anxiety disorder (GAD). Furthermore, endophenotype-based pathway approaches have recently been shown to have greater advantages for gene-finding strategies than traditional case-control studies. In the present study, in addition to conventional case-control methods, we used pathway analyses to test whether the tri-allelic serotonin transporter promoter polymorphism (combining 5-HTTLPR and rs25531) is associated with risk of GAD through its effects on trait neuroticism. Methods: We included 2236 Han Chinese adults in this study, including 736 patients with GAD and 1500 healthy participants. We genotyped the 5-HTTLPR and rs25531 polymorphisms using the polymerase chain reaction restriction fragment length polymorphism method. We used the Neuroticism scale of the Maudsley Personality Inventory (MPI) short version (MPI-Neuroticism) to measure participants' tendency toward neuroticism. Results: Using endophenotype-based path analyses, we found significant indirect effects of the tri-allelic genotype on risk of GAD, mediated by MPI-Neuroticism in both men and women. Compared to women carrying the S'S' genotype, women carrying the L' allele had higher levels of MPI-Neuroticism, which in turn were associated with higher risk of GAD. Men, however, showed the opposite pattern. Using traditional case-control comparisons, we observed that the effect of tri-allelic genotype on GAD was significant, but only in women. Limitations: Participants were restricted to Han Chinese, and we used only 1 questionnaire to assess neuroticism. Conclusion: These findings are the first to show that the triallelic 5-HTTLPR polymorphism is associated with elevated risk of GAD, and that this effect is mediated via increased trait neuroticism, a sex-dependent risk pathway.