Clinical characteristics of COVID-19 patients with clinically diagnosed bacterial co-infection: A multi-center study

Objective To understand the clinical characteristics of COVID-19 patients with clinically diagnosed bacterial co-infection (CDBC), and therefore contributing to their early identification and prognosis estimation. Method 905 COVID-19 patients from 7 different centers were enrolled. The demography data, clinical manifestations, laboratory results, and treatments were collected accordingly for further analyses. Results Around 9.5% of the enrolled COVID-19 patients were diagnosed with CDBC. Older patients or patients with cardiovascular comorbidities have increased CDBC probability. Increased body temperature, longer fever duration, anhelation, gastrointestinal symptoms, illness severity, intensive care unit attending, ventilation treatment, glucocorticoid therapy, longer hospitalization time are correlated to CDBC. Among laboratory results, increased white blood cell counting (mainly neutrophil), lymphocytopenia, increased procalcitonin, erythrocyte sedimentation rate, C-reaction protein, D-dimer, blood urea nitrogen, lactate dehydrogenase, brain natriuretic peptide, myoglobin, blood sugar and decreased albumin are also observed, indicating multiple system functional damage. Radiology results suggested ground glass opacity mixed with high density effusion opacities and even pleural effusion. Conclusion The aged COVID-19 patients with increased inflammatory indicators, worse lymphopenia and cardiovascular comorbidities are more likely to have clinically diagnosed bacterial co-infection. Moreover, they tend to have severer clinical manifestations and increased probability of multiple system functional damage.

Automated White Blood Cell Counting in Nailfold Capillary Using Deep Learning Segmentation and Video Stabilization

White blood cells (WBCs) are essential components of the immune system in the human body. Various invasive and noninvasive methods to monitor the condition of the WBCs have been developed. Among them, a noninvasive method exploits an optical characteristic of WBCs in a nailfold capillary image, as they appear as visual gaps. This method is inexpensive and could possibly be implemented on a portable device. However, recent studies on this method use a manual or semimanual image segmentation, which depends on recognizable features and the intervention of experts, hindering its scalability and applicability. We address and solve this problem with proposing an automated method for detecting and counting WBCs that appear as visual gaps on nailfold capillary images. The proposed method consists of an automatic capillary segmentation method using deep learning, video stabilization, and WBC event detection algorithms. Performances of the three segmentation algorithms (manual, conventional, and deep learning) with/without video stabilization were benchmarks. Experimental results demonstrate that the proposed method improves the performance of the WBC event counting and outperforms conventional approaches.