Background: The prevalence of clinical manifestations in severe patients with COVID-19 was highly variable across region, populations, and assessment methods. We investigated the characteristics in patients with COVID-19 and the risk factors associated with severe cases and progression to severe patients during hospitalization. Methods: In this retrospective, multicenter observational study, we collected the clinical manifestations and laboratory regarding from 125 patients with laboratory-confirmed COVID-19 in Liaoning province, China. The collected COVID-19 patients were divided into two groups, including nonsevere group and severe group which were according to the Chinese national guideline for COVID-19 diagnosis and treatment. Results: One hundred and twenty-five laboratory-confirmed COVID-19 patients from three centralized diagnosis and treatment centers were enrolled. The median age was 44 years old, 68 (54.4%) were male. One hundred and twelve (81.6%) patients were in nonsevere group and 23 (18.4%) were in severe group. The overall hospital mortality is 1.6%. About 34% patients had been to Wuhan, 35.2%patients had contact with confirmed COVID-19 patient in Wuhan. Thirty-five (28%) patients were local and 11 (8.8%) patients had a history of direct contact with wildlife. About 20.8% of the patients had comorbidity, hypertension was the most common comorbidity (14.4%). Four patients changed from nonsevere to severe during hospitalization. Most patients were admitted in January and February (98.4%). The median hospital stay was 16 days (interquartile range [IQR]: 12–21). On admission, fever was the most common symptom (60.8%). Duration from onset symptom to hospitalization was 5 days (IQR, 2–8). Compared with nonsevere group, severe cases were associated with significant increased NE (74.19 ± 13.87 vs. 62.32 ± 12.80, P = 0.001), C-reactive protein (CRP) (33.27 ± 38.60 vs. 15.53 ± 29.35, P = 0.003), D2 (1.52 ± 2.83 vs. 0.44 ± 0.93, P = 0.021), lower lymphocyte count (0.81 ± 0.41 vs. 2.32 ± 6.63, P = 0.042), and lymphocyte percentage (LY%) (15.94 ± 10.47 vs. 28.83 ± 11.66, P < 0.001). Kaletra and Chinese medicine were most widely used, the proportion was 61.6% and 66.4%, respectively. Age (odds ratio [OR] = 1.030, 95% confidence interval [CI], 0.99–1.09; P = 0.042), fever on admission (OR = 5.23, 95% CI, 1.32–20.79; P = 0.019), increased NE (OR = 10.53, 95% CI, 3.55–31.25; P = 0.000), and decreased LY% (OR = 7.72, 95% CI, 2.61–22.83; P = 0.000) were independently associated with the severe COVID-19. Age (OR, 1.12; 95% CI, 1.01–1.23; P = 0.025), myalgia (OR, 30.82; 95% CI, 1.58–600.16; P = 0.024), and CRP (OR = 1.04, 95% CI, 1.004–1.073; P = 0.030) were associated with higher risk of development to severe COVID-19 cases. Conclusions: 1. Identification of individuals at risk for severe COVID-19 after severe acute respiratory syndrome coronavirus 2 infection is important 2. The effects of conventional methods on predicting those patients who will go on to develop severe COVID-19 are limited 3. Age, fever on admission, increased NE, and decreased LY% were independently associated with the severe COVID-19 4. Age, myalgia, and CRP were independent risk factors associated with development to severe COVID-19.

Objective: Postoperative cognitive dysfunction (POCD) and neurologic deficit continues to be an important neuropsychological adverse affecting patients' outcome. We conducted this systematic review to investigate the relationship between regional cerebral oxygen saturation (rSO2) and early POCD in postoperative patients. Materials and Methods: Our search included MEDLINE (PubMed) and Cochrane library, from inception to October 31, 2018. We included studies reporting values of rSO2 at the beginning of and/or during surgery, and the primary outcome was POCD, and excluded articles who do not put postoperative cognitive function as the main observation. Two reviewers assessed the quality of the included articles using the Newcastle-Ottawa Scale and extracted the data. Results: Seven prospective cohort studies that included 532 patients incorporate into this systematic review. About 37.78% (201/532) patients achieved POCD. POCD was associated with significantly lower overall values of rSO2 during surgery compared to the population that did not achieve POCD (mean difference [MD] −1.98; 95% confidence interval [CI] −3.30 to −0.66; P = 0.003). In the subgroup, the lowest rSO2 values intraoperative period were a better predictor of POCD (MD −2.91; 95% CI −4.37 to − 1.46; P < 0.0001) than the mean rSO2 values (MD − 2.94; 95% CI −5.71 to − 0.17; P = 0.04). However, all of two were proved superior to baseline rSO2 values (MD −0.13; 95% CI -1.33 to 1.07; P = 0.83); patients with intraoperative cerebral oxygen <50% are nearly four times more likely to have early POCD (odds ratio = 3.65; 95% CI 1.62–8.23, P = 0.002). Conclusions: Patients with POCD have significantly lower cerebral oxygenation during operation than their counterparts. The lowest rSO2 values intraoperative period and patients with intraoperative cerebral oxygen <50% were a better predictor of POCD.

Artificial intelligence provides a vast opportunity and conquest of the science of knowledge. Twenty-first-century medicine will be characterized by an extraordinary ability to access and process medical information to provide patient-specific, timely, and effective clinical decision support. The knowledge gained by patient care experience and clinicians' expertise has led to many clinical care advances. Access to a large volume of data, along with ever-growing information and knowledge of diseases, can allow us to optimize diagnoses and management strategies by using advances in machine learning and artificial intelligence. Changing the medical culture from only relying on the experts to use medical informatics advances to improve the experts' clinical judgment would be an uphill battle. It is necessary to overcome the clinicians' traditional training to empower them into moving in the data science, statistics, and artificial intelligence era. As the incorporation of artificial intelligence in clinical practice seems inevitable, a thorough understanding of its capacities and flaws is essential to the emergence of a new clinical practice world. This review paper describes some of the nuances of past, current, and future clinical decision support systems and artificial intelligence's impact on this process.

Coagulopathy is common in critically ill patients. Under pathogenic factors, the homeostasis of coagulation, anticoagulation, and fibrinolytic system is disrupted, causing a series of cascade reactions that ultimately lead to coagulopathy. The pathophysiology of coagulopathy markedly varies according to the etiology. For sepsis-induced coagulopathy, inflammation interacts with coagulation. This process involves various cells, including endothelial cells, neutrophils, and platelets. Thrombocytopenia, as a common coagulopathy disorder among intensive care unit (ICU) patients, is indicative of poor outcome, and its differential diagnosis is crucial. However, the standardized diagnostic criteria for disseminated intravascular coagulation are yet to be established, and the existing ones have limitations. Therefore, we used PubMed to search literature related to “thrombocytopenia,” “sepsis,” “coagulopathy,” “disseminated intravascular coagulation,” and “coagulation biomarkers” and expected ICU doctors to fully understand knowledgeable of the pathophysiology of Coagulopathy. The traditional coagulation indicators can be combined with novel coagulation-related biomarkers for the accurate diagnosis and treatment of coagulopathy.