Use of machine learning to assess the prognostic utility of radiomic features for in-hospital COVID-19 mortality.

As portable chest X-rays are an efficient means of triaging emergent cases, their use has raised the question as to whether imaging carries additional prognostic utility for survival among patients with COVID-19. This study assessed the importance of known risk factors on in-hospital mortality and investigated the predictive utility of radiomic texture features using various machine learning approaches. We detected incremental improvements in survival prognostication utilizing texture features derived from emergent chest X-rays, particularly among older patients or those with a higher comorbidity burden. Important features included age, oxygen saturation, blood pressure, and certain comorbid conditions, as well as image features related to the intensity and variability of pixel distribution. Thus, widely available chest X-rays, in conjunction with clinical information, may be predictive of survival outcomes of patients with COVID-19, especially older, sicker patients, and can aid in disease management by providing additional information.

Prognostic Value of Histidine-Rich Glycoprotein for Community-Acquired Pneumonia.

PURPOSE: Histidine-rich glycoprotein (HRG) is abundant in serum and has been implicated in several processes including blood coagulation and immune response. This prospective study is aimed at exploring HRG as a biomarker in patients hospitalized for community-acquired pneumonia (CAP). METHODS: A total of 160 patients (73 severe CAP, 57 nonsevere CAP), and 30 healthy controls were enrolled in 2019. Demographic and clinical data were recorded for all patients. Serum HRG concentration was measured upon admission using ELISA. RESULTS: HRG levels were significantly lower in severe CAP patients compared with other groups, regardless of etiology, and were negatively correlated with serum interleukin-6 and disease severity index scores. Combination of CURB-65, PSI, and APACHE II scores with HRG values significantly improved the accuracy of predicting 30-day mortality in these patients. Cox regression analysis showed that HRG could serve as an independent risk factor for 30-day mortality. Notably, patients with HRG ≤ 16.92 µg/mL had significantly lower cumulative survival than those with HRG > 16.92 µg/mL. CONCLUSION: Serum HRG levels are lower in patients with severe CAP and are negatively correlated with disease severity scores. Measurement of HRG upon admission can provide valuable prognostic information for patients with CAP.

Comprehensive evaluation of COVID-19 patient short- and long-term outcomes: Disparities in healthcare utilization and post-hospitalization outcomes.

BACKGROUND: Understanding risk factors for short- and long-term COVID-19 outcomes have implications for current guidelines and practice. We study whether early identified risk factors for COVID-19 persist one year later and through varying disease progression trajectories. METHODS: This was a retrospective study of 6,731 COVID-19 patients presenting to Michigan Medicine between March 10, 2020 and March 10, 2021. We describe disease progression trajectories from diagnosis to potential hospital admission, discharge, readmission, or death. Outcomes pertained to all patients: rate of medical encounters, hospitalization-free survival, and overall survival, and hospitalized patients: discharge versus in-hospital death and readmission. Risk factors included patient age, sex, race, body mass index, and 29 comorbidity conditions. RESULTS: Younger, non-Black patients utilized healthcare resources at higher rates, while older, male, and Black patients had higher rates of hospitalization and mortality. Diabetes with complications, coagulopathy, fluid and electrolyte disorders, and blood loss anemia were risk factors for these outcomes. Diabetes with complications, coagulopathy, fluid and electrolyte disorders, and blood loss were associated with lower discharge and higher inpatient mortality rates. CONCLUSIONS: This study found differences in healthcare utilization and adverse COVID-19 outcomes, as well as differing risk factors for short- and long-term outcomes throughout disease progression. These findings may inform providers in emergency departments or critical care settings of treatment priorities, empower healthcare stakeholders with effective disease management strategies, and aid health policy makers in optimizing allocations of medical resources.

Predictive and Prognostic Utility of the Serum Level of Resistin-Like Molecule Beta for Risk Stratification in Patients with Community-Acquired Pneumonia.

Despite progress in intensive care, the morbidity and mortality of patients with community-acquired pneumonia (CAP) remains high. Furthermore, the predictive and prognostic utility of resistin-like molecule beta (RELM-ß) in patients with CAP is uncertain. This study investigated the role of RELM-ß in patients with CAP and evaluated its correlation with disease severity and the risk of death. A prospective, multicenter study was conducted in 2017, and admission serum levels of RELM-ß were detected using quantitative enzyme-linked immunosorbent assay. A total of 114 and 112 patients with severe CAP (SCAP) and non-severe CAP (NSCAP) were enrolled, respectively, with 15 healthy controls. Patients with SCAP, especially non-survivors, had significantly higher levels of serum RELM-ß than patients with NSCAP. RELM-ß levels positively correlated with severity scores and consistently predicted SCAP in patients with CAP (area under the curve = 0.794). Increased levels of RELM-ß were closely related to the severity and prognosis of patients with CAP. The accuracy of 30-day mortality predictions of CURB-65 (confusion, urea, respiratory rate, blood pressure, and age ≥ 65 years) can be significantly improved when combined with RELM-ß levels. The level of RELM-ß can assist clinicians in risk stratification of patients with CAP in early stages.