Comparing different machine learning techniques for predicting COVID-19 severity.

BACKGROUND: Coronavirus disease 2019 (COVID-19) is still ongoing spreading globally, machine learning techniques were used in disease diagnosis and to predict treatment outcomes, which showed favorable performance. The present study aims to predict COVID-19 severity at admission by different machine learning techniques including random forest (RF), support vector machine (SVM), and logistic regression (LR). Feature importance to COVID-19 severity were further identified. METHODS: A retrospective design was adopted in the JinYinTan Hospital from January 26 to March 28, 2020, eighty-six demographic, clinical, and laboratory features were selected with LassoCV method, Spearman's rank correlation, experts' opinions, and literature evaluation. RF, SVM, and LR were performed to predict severe COVID-19, the performance of the models was compared by the area under curve (AUC). Additionally, feature importance to COVID-19 severity were analyzed by the best performance model. RESULTS: A total of 287 patients were enrolled with 36.6% severe cases and 63.4% non-severe cases. The median age was 60.0 years (interquartile range: 49.0-68.0 years). Three models were established using 23 features including 1 clinical, 1 chest computed tomography (CT) and 21 laboratory features. Among three models, RF yielded better overall performance with the highest AUC of 0.970 than SVM of 0.948 and LR of 0.928, RF also achieved a favorable sensitivity of 96.7%, specificity of 69.5%, and accuracy of 84.5%. SVM had sensitivity of 93.9%, specificity of 79.0%, and accuracy of 88.5%. LR also achieved a favorable sensitivity of 92.3%, specificity of 72.3%, and accuracy of 85.2%. Additionally, chest-CT had highest importance to illness severity, and the following features were neutrophil to lymphocyte ratio, lactate dehydrogenase, and D-dimer, respectively. CONCLUSIONS: Our results indicated that RF could be a useful predictive tool to identify patients with severe COVID-19, which may facilitate effective care and further optimize resources.

The effect of Huashibaidu formula on the blood oxygen saturation status of severe COVID-19: A retrospective cohort study.

BACKGROUND: Huashibaidu Formula (HSBD) for the COVID-19 treatment has been supported by the China's Diagnosis and Treatment Protocol for Novel Coronavirus Pneumonia. However, it is not clear whether HSBD can improve blood oxygen saturation and when it should be used with conventional therapies. PURPOSE: To access the effect of HSBD combined with conventional treatment on blood oxygen saturation of COVID-19 patients. METHODS: A single-center retrospective cohort study was conducted to collect the confirmed severe COVID-19 patients' information, treated by the National Traditional Chinese Medicine Medical Team at the Jinyintan hospital between January 24 and March 31, 2020. According to whether HSBD was used during hospitalization, participants were separated into the conventional treatment group and the HSBD group (HSBD and conventional treatment). The primary observation indicators included the time for relieving blood oxygen saturation and the improvement ratio of blood oxygen saturation in each group. RESULTS: Of 111 patients with severe COVID-19, 53.2% (59/111) received HSBD, and 46.8% (52/111) only received conventional treatment, respectively. No statistically significant difference was found in image, clinical symptoms, and past medical history between the two groups (p > 0.05). Notably, the median time for relieving blood oxygen saturation in the conventional treatment group was 11 days (IQR, 8-14.25), while that in the HSBD group was only 6 days (IQR, 3.25-10.75), which was significantly shortened by 4.09 days (95%CI, 2.07-6.13; p= 0.0001), compared with the conventional treatment group. After repeated measurement design analysis, the main effect within times (p< 0.001) and the main effect were significantly different under the oxygen saturation dimension between two groups (p= 0.004). However, time and group interaction were observed no significant difference (p= 0.094). After 14 days of treatment, the improvement ratio of the HSBD group over the conventional treatment group was 1.20 (95%CI, 0.89-1.61). CONCLUSION: For severe COVID-19 patients, the HSBD has a tendency to shorten the time for relieving blood oxygen saturation. After taking a course of HSBD, the effect can be more obvious.

High-Dose Intravenous Immunoglobulin in Severe Coronavirus Disease 2019: A Multicenter Retrospective Study in China.

BACKGROUND: The effective treatment of coronavirus disease 2019 (COVID-19) remains unclear. We reported successful use of high-dose intravenous immunoglobulin (IVIg) in cases of severe COVID-19, but evidence from larger case series is still lacking. METHODS: A multi-center retrospective study was conducted to evaluate the effectiveness of IVIg administered within two weeks of disease onset at a total dose of 2 g/kg body weight, in addition to standard care. The primary endpoint was 28-day mortality. Efficacy of high-dose IVIg was assessed by using the Cox proportional hazards regression model and the Kaplan-Meier curve adjusted by inverse probability of treatment weighting (IPTW) analysis, and IPTW after multiple imputation (MI) analysis. RESULTS: Overall, 26 patients who received high-dose IVIg with standard therapy and 89 patients who received standard therapy only were enrolled in this study. The IVIg group was associated with a lower 28-day mortality rate and less time to normalization of inflammatory markers including IL-6, IL-10, and ferritin compared with the control. The adjusted HR of 28-day mortality in high-dose IVIg group was 0.24 (95% CI 0.06-0.99, p<0.001) in IPTW model, and 0.27 (95% CI 0.10-0.57, p=0.031) in IPTW-MI model. In subgroup analysis, patients with no comorbidities or treated in the first week of disease were associated with more benefit from high-dose IVIg. CONCLUSIONS: High-dose IVIg administered in severe COVID-19 patients within 14 days of onset was linked to reduced 28-day mortality, more prominent with those having no comorbidities or treated at earlier stage.

Epidemiological, Virological and Serological Features of Coronavirus Disease 2019 (COVID-19) Cases in People Living With Human Immunodeficiency Virus in Wuhan: A Population-based Cohort Study.

BACKGROUND: We aimed to describe the epidemiological, virological, and serological features of coronavirus disease 2019 (COVID-19) cases in people living with human immunodeficiency virus (HIV; PLWH). METHODS: This population-based cohort study identified all COVID-19 cases among all PLWH in Wuhan, China, by 16 April 2020. The epidemiological, virological, and serological features were analyzed based on the demographic data, temporal profile of nucleic acid test for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) during the disease, and SARS-CoV-2-specific immunoglobin (Ig) M and G after recovery. RESULTS: From 1 January to 16 April 2020, 35 of 6001 PLWH experienced COVID-19, with a cumulative incidence of COVID-19 of 0.58% (95% confidence interval [CI], .42-.81%). Among the COVID-19 cases, 15 (42.86) had severe illness, with 2 deaths. The incidence, case-severity, and case-fatality rates of COVID-19 in PLWH were comparable to those in the entire population in Wuhan. There were 197 PLWH who had discontinued combination antiretroviral therapy (cART), 4 of whom experienced COVID-19. Risk factors for COVID-19 were age ≥50 years old and cART discontinuation. The median duration of SARS-CoV-2 viral shedding among confirmed COVID-19 cases in PLWH was 30 days (interquartile range, 20-46). Cases with high HIV viral loads (≥20 copies/mL) had lower IgM and IgG levels than those with low HIV viral loads (<20 copies/ml; median signal value divided by the cutoff value [S/CO] for IgM, 0.03 vs 0.11, respectively [P < .001]; median S/CO for IgG, 10.16 vs 17.04, respectively [P = .069]). CONCLUSIONS: Efforts are needed to maintain the persistent supply of antiretroviral treatment to elderly PLWH aged 50 years or above during the COVID-19 epidemic. The coinfection of HIV and SARS-CoV-2 might change the progression and prognosis of COVID-19 patients in PLWH.

Combination of Hua Shi Bai Du granule (Q-14) and standard care in the treatment of patients with coronavirus disease 2019 (COVID-19): A single-center, open-label, randomized controlled trial.

OBJECTIVE: To evaluate the efficacy and safety of Hua Shi Bai Du Granule (Q-14) plus standard care compared with standard care alone in adults with coronavirus disease (COVID-19). STUDY DESIGN: A single-center, open-label, randomized controlled trial. SETTING: Wuhan Jinyintan Hospital, Wuhan, China, February 27 to March 27, 2020. PARTICIPANTS: A total of 204 patients with laboratory-confirmed COVID-19 were randomized into the treatment group and control group, consisting of 102 patients in each group. INTERVENTIONS: In the treatment group, Q-14 was administered at 10 g (granules) twice daily for 14 days, plus standard care. In the control group, patients were provided standard care alone for 14 days. MAIN OUTCOME MEASURE: The primary outcome was the conversion time for the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) viral assay. Adverse events were analyzed in the safety population. RESULTS: Among the 204 patients, 195 were analyzed according to the intention-to-treat principle. A total of 149 patients (71 vs. 78 in the treatment and control groups, respectively) tested negative via the SARS-CoV-2 viral assay. There was no statistical significance in the conversion time between the treatment group and control group (Full analysis set: Median [interquartile range]: 10.00 [9.00-11.00] vs. 10.00 [9.00-11.00]; Mean rank: 67.92 vs. 81.44; P = 0.051). The recovery time for fever was shorter in the treatment group than in the control group. The disappearance rate of symptoms like cough, fatigue, and chest discomfort was significantly higher in the treatment group. In chest computed tomography (CT) examinations, the overall evaluation of chest CT examination after treatment compared with baseline showed that more patients improved in the treatment group. There were no significant differences in the other outcomes. CONCLUSION: The combination of Q-14 and standard care for COVID-19 was useful for the improvement of symptoms (such as fever, cough, fatigue, and chest discomfort), but did not result in a significantly higher probability of negative conversion in the SARS-CoV-2 viral assay. No serious adverse events were observed. TRIAL REGISTRATION: ChiCTR2000030288.

Patients with Prolonged Positivity of SARS-CoV-2 RNA Benefit from Convalescent Plasma Therapy: A Retrospective Study.

Convalescent plasma therapy has been implemented in a few cases of severe coronavirus disease 2019. No report about convalescent plasma therapy in treating patients with prolonged positivity of SARS-CoV-2 RNA has been published. In this study, we conducted a retrospective observational study in 27 patients with prolonged positivity of SARS-CoV-2 RNA, the clinical benefit of convalescent plasma therapy were analyzed. qRT-PCR test of SARS-CoV-2 RNA turned negative (≤ 7 days) in a part of patients (early negative group, n = 15) after therapy, others (late negative group, n = 12) turned negative in more than 7 days. Pulmonary imaging improvement was confirmed in 7 patients in early negative group and 8 in late negative group after CP therapy. Viral load decreased in early negative group compared with late negative group at day 3, 5, 7 after implementing convalescent plasma therapy. Patients in early negative group had a shorter median length of hospital stay. In conclusion, convalescent plasma therapy might help eliminate virus and shorten length of hospital stay in patients with prolonged positivity of SARS-CoV-2 RNA.

Corrigendum: High-Dose Intravenous Immunoglobulin in Severe Coronavirus Disease 2019: A Multicenter Retrospective Study in China.

[This corrects the article DOI: 10.3389/fimmu.2021.627844/full.].

Efficacy and safety assessment of severe COVID-19 patients with Chinese medicine: A retrospective case series study at early stage of the COVID-19 epidemic in Wuhan, China.

ETHNOPHARMACOLOGICAL RELEVANCE: The coronavirus disease 2019 (COVID-19) has formed a global pandemic since late 2019. Benefitting from the application experience of Chinese Medicine (CM) for influenza and SARS, CM has been used to save patients at the early stage of COVID-19 outbreak in China. AIM OF THE STUDY: In order to evaluate the efficacy and safety of CM, and compare with Western Medicine (WM) for COVID-19, we conducted a retrospective case series study based on the patients in Wuhan Jinyintan Hospital, Wuhan, China. METHODS: The inclusion and exclusion criteria of data extraction were set for this retrospective study. All patients who were admitted by the Wuhan Jinyintan Hospital between January 17th and February 25th 2020 were considered. In addition, patients enrolled met the severe defined by the guidelines released by the National Health Commission of the People's Republic of China. In these cases included in the study, CM or WM treatment was selected according to the wishes of the patients at the beginning of hospitalization. The patients in CM group were treated with Huashi Baidu granule (137 g po, bid) combined with the injections of Xiyanping (100 mg iv, bid), Xuebijing (100 ml iv, bid) and Shenmai (60 ml iv, qd) according to the syndrome of epidemic toxin blocking the lung in the theory of Traditional Chinese Medicine. The WM group received antiviral therapy (including abidor capsule 0.2 g po, tid; Lopinavir-Ritonavir tablets, 500 mg po, bid), antibiotics (such as cefoperazone 2 g iv, bid; moxifloxacin hydrochloride tablets, 0.4 g po, qd) or corticosteroid therapy (such as methylprednisolone succinate sodium 40 mg iv, qd; prednisone, 30 mg po, qd). In addition, patients in both groups received routine supportive treatment, including oxygen inhalation, symptomatic therapy, and/or human intravenous immunoglobulin, and/or serum albumin, and treatment for underlying diseases. The clinical outcomes were evaluated based on changes related with clinical manifestations, computer tomography (CT) scan images, and laboratory examinations before and after the treatment. RESULTS: 55 severe COVID-19 patients, with 23 in CM group and 32 in WM group, were included for analyzed. There was no case of death, being transferred to ICU, or receiving invasive mechanical ventilation in two groups during hospitalization. The median time of SARS-CoV-2 RNA clearance in CM and WM group were 12 days and 15.5 days respectively, the ratio of nucleic acid negative conversion of CM group at different follow-up time points was significantly higher than that of WM group (HR: 2.281, P = 0.018). Further, the chest CT imaging showed more widely lung lesion opacity absorbed in the CM group. The high sensitivity C-reactive protein and serum ferritin decreased significantly in the CM group (P<0.05). There was no significant difference in adverse events in terms of liver function and renal function between the two groups. CONCLUSION: Based on this retrospective analysis from Wuhan Jinyintan Hospital, CM has better effects in SARS-CoV-2 RNA clearance, promoting lung lesion opacity absorbed and reducing inflammation in severe COVID-19 patients, which is effective and safe therapy for treating severe COVID-19 and reducing mortality.

Prolonged presence of viral nucleic acid in clinically recovered COVID-19 patients was not associated with effective infectiousness.

Prolonged presence of viral nucleic acid was reported in certain patients with coronavirus disease 2019 (COVID-19), with unclear clinical and epidemiological significance. We here described the clinical and epidemiological characteristics of 37 recovered COVID-19 patients with prolonged presence of viral RNA in Wuhan, China. For those who had been discharged and re-admitted, their close contacts outside the hospital were traced and evaluated. The median age of the 37 patients was 62 years (IQR 50, 68), and 24 (64.9%) were men. They had common or severe COVID-19. With prolonged positive RT-PCR, most patients were clinically stable, 29 (78.4%) denied any symptoms. A total of 431 PCR tests were carried out, with each patient at a median of 8 time points. The median time of PCR positivity to April 18 was 78 days (IQR 67.7, 84.5), and the longest 120 days. 22 of 37 patients had been discharged at a median of 44 days (IQR 22.3, 50) from disease onset, and 9 had lived with their families without personal protections for a total of 258 person-days and no secondary infection was identified through epidemiological investigation, nucleic acid and antibody screening. Infectiousness in COVID-19 patients with prolonged presence of viral nucleic acid should not solely be evaluated by RT-PCR. Those patients who have clinically recovered and whose disease course has exceeded four weeks were associated with very limited infectiousness. Reconsideration of disease control in such patients is needed.

Efficacy and safety of Lianhuaqingwen capsules, a repurposed Chinese herb, in patients with coronavirus disease 2019: A multicenter, prospective, randomized controlled trial.

BACKGROUND: Coronavirus disease 2019 (Covid-19) has resulted in a global outbreak. Few existing targeted medications are available. Lianhuaqingwen (LH) capsule, a repurposed marketed Chinese herb product, has been proven effective for influenza. PURPOSE: To determine the safety and efficacy of LH capsule in patients with Covid-19. METHODS: We did a prospective multicenter open-label randomized controlled trial on LH capsule in confirmed cases with Covid-19. Patients were randomized to receive usual treatment alone or in combination with LH capsules (4 capsules, thrice daily) for 14 days. The primary endpoint was the rate of symptom (fever, fatigue, coughing) recovery. RESULTS: We included 284 patients (142 each in treatment and control group) in the full-analysis set. The recovery rate was significantly higher in treatment group as compared with control group (91.5% vs. 82.4%, p = 0.022). The median time to symptom recovery was markedly shorter in treatment group (median: 7 vs. 10 days, p < 0.001). Time to recovery of fever (2 vs. 3 days), fatigue (3 vs. 6 days) and coughing (7 vs. 10 days) was also significantly shorter in treatment group (all p < 0.001). The rate of improvement in chest computed tomographic manifestations (83.8% vs. 64.1%, p < 0.001) and clinical cure (78.9% vs. 66.2%, p = 0.017) was also higher in treatment group. However, both groups did not differ in the rate of conversion to severe cases or viral assay findings (both p > 0.05). No serious adverse events were reported. CONCLUSION: In light of the safety and effectiveness profiles, LH capsules could be considered to ameliorate clinical symptoms of Covid-19.

High-Dose Intravenous Immunoglobulin as a Therapeutic Option for Deteriorating Patients With Coronavirus Disease 2019.

The outbreak of coronavirus disease 2019 (COVID-19) has spread rapidly in China. Until now, no definite effective treatment has been identified. We reported on 3 patients with severe COVID-19 who received high-dose intravenous immunoglobulin (IVIg) with satisfactory recovery. Based on these observations, randomized studies of high-dose IVIg should be considered in deteriorating patients infected with COVID-19.

A Trial of Lopinavir-Ritonavir in Adults Hospitalized with Severe Covid-19.

BACKGROUND: No therapeutics have yet been proven effective for the treatment of severe illness caused by SARS-CoV-2. METHODS: We conducted a randomized, controlled, open-label trial involving hospitalized adult patients with confirmed SARS-CoV-2 infection, which causes the respiratory illness Covid-19, and an oxygen saturation (Sao2) of 94% or less while they were breathing ambient air or a ratio of the partial pressure of oxygen (Pao2) to the fraction of inspired oxygen (Fio2) of less than 300 mm Hg. Patients were randomly assigned in a 1:1 ratio to receive either lopinavir-ritonavir (400 mg and 100 mg, respectively) twice a day for 14 days, in addition to standard care, or standard care alone. The primary end point was the time to clinical improvement, defined as the time from randomization to either an improvement of two points on a seven-category ordinal scale or discharge from the hospital, whichever came first. RESULTS: A total of 199 patients with laboratory-confirmed SARS-CoV-2 infection underwent randomization; 99 were assigned to the lopinavir-ritonavir group, and 100 to the standard-care group. Treatment with lopinavir-ritonavir was not associated with a difference from standard care in the time to clinical improvement (hazard ratio for clinical improvement, 1.31; 95% confidence interval [CI], 0.95 to 1.80). Mortality at 28 days was similar in the lopinavir-ritonavir group and the standard-care group (19.2% vs. 25.0%; difference, -5.8 percentage points; 95% CI, -17.3 to 5.7). The percentages of patients with detectable viral RNA at various time points were similar. In a modified intention-to-treat analysis, lopinavir-ritonavir led to a median time to clinical improvement that was shorter by 1 day than that observed with standard care (hazard ratio, 1.39; 95% CI, 1.00 to 1.91). Gastrointestinal adverse events were more common in the lopinavir-ritonavir group, but serious adverse events were more common in the standard-care group. Lopinavir-ritonavir treatment was stopped early in 13 patients (13.8%) because of adverse events. CONCLUSIONS: In hospitalized adult patients with severe Covid-19, no benefit was observed with lopinavir-ritonavir treatment beyond standard care. Future trials in patients with severe illness may help to confirm or exclude the possibility of a treatment benefit. (Funded by Major Projects of National Science and Technology on New Drug Creation and Development and others; Chinese Clinical Trial Register number, ChiCTR2000029308.).