Classifying Microscopic Images of Reactive Lymphocytosis Using Two-Step Tandem AI Models

The practical applications of automatic recognition and categorization technology for next-generation systems are desired in the clinical laboratory. We approached the identification of reactive lymphocytosis using artificial intelligence (AI) technology and studied its clinical usefulness for blood smear screening. This study created one- and two-step AI models for the identification of reactive lymphocytosis. The ResNet-101 model was applied for deep learning. The original image set for supervised AI training consisted of 5765 typical nucleated blood cell images. The subjects for clinical assessment were 25 healthy cases, 25 erythroblast cases, and 25 reactive lymphocytosis cases. The total accuracy (mean ± standard deviation) of the one- and two-step models were 0.971 ± 0.047 and 0.977 ± 0.024 in healthy, 0.938 ± 0.040 and 0.978 ± 0.018 in erythroblast, and 0.856 ± 0.056 and 0.863 ± 0.069 in reactive lymphocytosis cases, respectively. The two-step AI model showed a sensitivity of 0.960 and a specificity of 1.000 between healthy and reactive lymphocytosis cases. As our two-step tandem AI model showed high performance for identifying reactive lymphocytosis in blood smear screening, we plan to apply this method to the development of AI models to differentiate reactive and neoplastic lymphocytosis.

Comprehensive evaluation of bronchoalveolar lavage from patients with severe COVID-19 and correlation with clinical outcomes.

Information on bronchoalveolar lavage (BAL) in patients with COVID-19 is limited, and clinical correlation has not been reported. This study investigated the key features of BAL fluids from COVID-19 patients and assessed their clinical significance. A total of 320 BAL samples from 83 COVID-19 patients and 70 non-COVID-19 patients (27 patients with other respiratory viral infections) were evaluated, including cell count/differential, morphology, flow cytometric immunophenotyping, and immunohistochemistry. The findings were correlated with clinical outcomes. Compared to non-COVID-19 patients, BAL from COVID-19 patients was characterized by significant lymphocytosis (p < 0.001), in contrast to peripheral blood lymphopenia commonly observed in COVID-19 patients and the presence of atypical lymphocytes with plasmacytoid/plasmablastic features (p < 0.001). Flow cytometry and immunohistochemistry demonstrated that BAL lymphocytes, including plasmacytoid and plasmablastic cells, were composed predominantly of T cells with a mixture of CD4+ and CD8+ cells. Both populations had increased expression of T-cell activation markers, suggesting important roles of helper and cytotoxic T-cells in the immune response to SARS-CoV-2 infection in the lung. More importantly, BAL lymphocytosis was significantly associated with longer hospital stay (p < 0.05) and longer requirement for mechanical ventilation (p < 0.05), whereas the median atypical (activated) lymphocyte count was associated with shorter hospital stay (p < 0.05), shorter time on mechanical ventilation (p < 0.05) and improved survival. Our results indicate that BAL cellular analysis and morphologic findings provide additional important information for diagnostic and prognostic work-up, and potential new therapeutic strategies for patients with severe COVID-19.

Development of infectious mononucleosis as an unusual manifestation of COVID-19.

It has generally been reported that patients with COVID-19 show a fever, cough, and/or respiratory failure as the most common clinical symptoms but some have unusual symptoms, such as anosmia, diarrhea, and throat pain. We herein report a 26-year-old woman with chief complaints of lymphadenopathy and a fever. First, she underwent a laboratory examination, which showed a high proportion of atypical lymphocytes (19%) and an increase in hepatic enzyme activities, and was then hospitalized with a diagnosis of infectious mononucleosis (IM). However, the blood examination did not show any increase in anti-Epstein-Barr virus VCM-IgM. Subsequently, she developed tonsillar hypertrophy with purulent plugs. An additional examination for infection of other pathogens revealed positivity only for SARS-CoV-2 in a loop-mediated isothermal amplification (LAMP) test. The patient was transferred to the COVID-19-specific isolation ward, and none of the ward staff, patients, or either of the two otolaryngologists who had directly examined this patient showed positive signs for SARS-CoV-2 in a LAMP test. Consequently, this case suggests that even if patients show clinical symptoms and signs of common diseases for otolaryngologists, such as IM, we should keep in mind the possibility of COVID-19 without arbitrarily assuming that IM is caused by Epstein-Barr virus.

Differential Diagnosis of COVID-19: Importance of Measuring Blood Lymphocytes, Serum Electrolytes, and Olfactory and Taste Functions.

Coronavirus disease 2019 (COVID-19) is associated with various symptoms and changes in hematological and biochemical variables. However, clinical features, which can differentiate COVID-19 from non-COVID-19, are not clear. We therefore examined the key clinical features of COVID-19 and non-COVID-19 patients. This study included 60 COVID-19 patients and 100 non-COVID-19 patients, diagnosed by PCR, and no significant differences in the age and sex were seen between the two groups. The frequencies of fatigue, loose stool, diarrhea, nasal obstruction, olfactory dysfunction, taste dysfunction, underlying hyperlipidemia, and the prescription of angiotensin II receptor blocker (ARB) were significantly higher in COVID-19 patients than those in non-COVID-19 patients. The counts of leucocytes, neutrophils, lymphocytes, eosinophils, monocytes, and basophils and the levels of chloride and calcium in blood of COVID-19 patients were significantly lower than those of non-COVID-19 patients. The frequencies of atypical lymphocytes and the levels of lactate dehydrogenase (LDH) and potassium were significantly higher in COVID-19 than those in non-COVID-19. The C-reactive protein (CRP) level in COVID-19 patients was significantly lower than that in non-COVID-19 patients, when we compared CRP levels among patients with elevated CRP. This study is the first to indicate that electrolyte levels and the frequency of atypical lymphocytes in COVID-19 are significantly different from those in non-COVID-19. Fatigue, loose stool, diarrhea, nasal obstruction, olfactory dysfunction, and taste dysfunction were the key symptoms of COVID-19. Furthermore, hyperlipidemia and ARB may be risk factors of COVID-19. In conclusion, leucocytes, leucocyte fractions, CRP, LDH, and electrolytes are useful indicators for COVID-19 diagnosis.