Background The 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. Objective Our 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. Methods Spanning 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. Results In 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. Conclusions A deep-learning model based on a 12-lead ECG may help physicians promptly recognize severe dyskalemias and thereby potentially reduce cardiac events.

Currently the local P. vivax was sharply decreased while the imported vivax malaria increased in China. Despite Southeast Asia was still the main import source of vivax malaria, the trend of Africa become serious, especially for west and central Africa. Herein we have clarified the trend of P. vivax in China from 2004–2012, and made some analysis for the differences of imported vivax back from different regions. There are significantly different of P. vivax between Southeast Asia and Africa, also the difference was observed for different regions in Africa. Additionally, we have explored the possibility for the difference of the P. vivax between migrant workers back from west and central Africa and the prevalence of local population. This reminds us that surveillance and training should be strengthened by medical staffs on the imported P. vivax cases reported especially from west and central Africa, in order to reduce the risk of malaria reintroduction and, specific tools should be developed, as well as the epidemiological study to avoid the misdiagnosis such as P. ovale and P. vivax.

Recent studies have suggested that polymorphisms in toll-like receptor 9 (TLR-9), an endosomal TLR, are associated with knee osteoarthritis (OA). TLR-3, -7, and -8 are also found on the surface of endosomes and to investigate whether similar associations exist with polymorphisms in these TLR genes we performed a two-stage case-control study and genotyped 11 TLR single nucleotide polymorphisms (SNPs) in 823 OA cases and 594 healthy controls by polymerase chain reaction restriction fragment length polymorphism assays. Real-time PCR was performed to assess the functional expression of an identified promoter polymorphism in TLR-3 following dexamethasone stimulation of articular chondrocytes. An association between TLR-3 SNPs at rs3775296 and rs3775290 and OA was identified in both populations. In males the allelic frequencies of TLR-7 rs179010 and TLR-8 rs5744080 were significantly different between OA cases and healthy controls. The ATCA, CTCA, and CCTA haplotypes of TLR-3 were associated with OA susceptibility. A significant difference in TLR-3 gene expression following dexamethasone treatment was seen among the various genotypes of rs3775296 (p ¼ 0.004). Our findings indicate that a SNP in the promoter region of TLR-3 is associated with elevated TLR-3 gene expression and susceptibility to knee OA in a Chinese Han population.

No abstract

Background Bone 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. Objective The 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. Methods From 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. Results In 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. Conclusions Our 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.

No abstract

Background Longitudinal integrated clerkships (LICs) are a model of clinical education growing rapidly in Western contexts. LICs use educational continuity to benefits students’ clinical learning and professional identity formation. Patient-centered care is a core component of medical professionalism in the West. To support patient-centered care, education leaders in Taiwan restructured clinical education and implemented the first longitudinal integrated clerkship in East Asia. We aimed to investigate patients’ perceptions of longitudinal relationships with the LIC students within Taiwan’s Confucian cultural and social context. Methods We invited patients or their family members who were cared for longitudinally by a LIC student to participate in the study. Participating patients or their family members undertook semi-structured interviews. We analyzed data qualitatively using a general inductive approach to identify themes in the patients’ descriptions of their experiences interacting with the LIC students. Results Twenty-five patients and family members participated in interviews: 16 patients and 9 family members. Qualitative analysis of interview transcripts identified three themes from patients’ experience receiving care from their LIC students: care facilitation, companionship, and empathy. To provide care facilitation, LIC students served as a bridge between the physicians and patients. Students served patients by reminding, consulting, tracking disease progression, and researching solutions for problems. To provide companionship, students accompanied patients interpersonally like a friend or confidant who listens and provides a presence for patients. To provide empathy, patients reported that students showed sincere concern for patients’ experience, feelings, and mood. Conclusion In our study, Taiwanese patients’ perspectives of LIC students suggested the value of care facilitation, companionship, and empathy. We discuss these themes within the context of Confucian culture and the Taiwanese context of care.

Introduction: This study aimed to investigate the baseline level of malaria awareness in residents in 20 malaria-endemic provinces from October 2010 to January 2011 at the beginning of the implementation of the China National Malaria Elimination Programme (NMEP). Methodology: A structured questionnaire about basic malaria knowledge was administrated to residents in rural areas from 20 provinces, municipalities, and autonomous regions. Results: A total of 182,085 residents no younger than 15 years of age took part in the cross-sectional investigation; 3,232 were excluded because of incomplete survey responses. Of the respondents, 56.86% were aware of malaria, 18.03% responded correctly to all five questions, and 5.57% answered all the questions incorrectly. Malaria awareness among different age groups was statistically significant (p < 0.001), males had a better understanding of malaria than did females (p < 0.001), and Type I counties had a better understanding than did Type II counties (p < 0.001). Conclusions: The level of malaria awareness was low among residents at the beginning of the NMEP, especially about malaria pathogenicity and preventive methods. Health education campaigns should be developed and implemented to increase the public perceptions about malaria prevention and treatment, and to promote malaria elimination in China.