Diagnosing Coronavirus Disease 2019 (COVID-19): Efficient Harris Hawks-Inspired Fuzzy K-Nearest Neighbor Prediction Methods.

This study is devoted to proposing a useful intelligent prediction model to distinguish the severity of COVID-19, to provide a more fair and reasonable reference for assisting clinical diagnostic decision-making. Based on patients' necessary information, pre-existing diseases, symptoms, immune indexes, and complications, this article proposes a prediction model using the Harris hawks optimization (HHO) to optimize the Fuzzy K-nearest neighbor (FKNN), which is called HHO-FKNN. This model is utilized to distinguish the severity of COVID-19. In HHO-FKNN, the purpose of introducing HHO is to optimize the FKNN's optimal parameters and feature subsets simultaneously. Also, based on actual COVID-19 data, we conducted a comparative experiment between HHO-FKNN and several well-known machine learning algorithms, which result shows that not only the proposed HHO-FKNN can obtain better classification performance and higher stability on the four indexes but also screen out the key features that distinguish severe COVID-19 from mild COVID-19. Therefore, we can conclude that the proposed HHO-FKNN model is expected to become a useful tool for COVID-19 prediction.

Twelve out of 117 recovered COVID-19 patients retest positive in a single-center study of China.

BACKGROUND: It has been reported that a fraction of recovered coronavirus disease 2019(COVID-19) patients have retested positive for SARS-CoV-2. Clinical characteristics and risk factors for retesting positive have not been studied extensively. METHODS: In this retrospective, single-center cohort study, we included adult patients (≥ 18 years old) diagnosed as COVID-19 in Affiliated Yueqing Hospital, Wenzhou Medical University, Zhejiang, China. All the patients were discharged before March 31, 2020, and were re-tested for SARS-CoV-2 RNA by real-time reverse-transcriptase polymerase-chain-reaction (RT-PCR) after meeting the discharge criteria. We retrospectively analyzed this cohort of 117 discharged patients and analyzed the differences between retest positive and negative patients in terms of demographics, clinical characteristics, laboratory findings, chest computed tomography (CT) features and treatment procedures. FINDINGS: Compared with the negative group, the positive group had a higher proportion of patients with comorbidities (Odds Ratio(OR) =2·12, 95% Confidence Interval(CI) 0·48-9·46; p = 0·029), longer hospital stay (OR=1·21, 95% CI 1·07-1·36; p = 0·008), a higher proportion of patients with lymphocytopenia (p = 0·036), a higher proportion of antibiotics treatment (p = 0·008) and glucocorticoids treatment (p = 0·003). Multivariable regression showed increasing odds of positive SARS-CoV-2 retest after discharge associated with longer hospital stay (OR=1·22, 95% CI 1·08-1·38; p = 0·001), and lymphocytopenia (OR=7·74, 95% CI 1·70-35·21; p = 0·008) on admission. INTERPRETATION: Patients with COVID-19 who met discharge criteria could still test positive for SARS-CoV-2 RNA. Longer hospital stay and lymphopenia could be potential risk factors for positive SARS-CoV-2 retest in COVID-19 patients after hospital discharge. FUNDING: Natural Science Foundation of Zhejiang Province, Medical Scientific Research Fund of Zhejiang Province, Wenzhou science and technology project.