Frontiers in medicine
-
Frontiers in medicine · Jan 2021
Machine Learning Prediction Models for Mechanically Ventilated Patients: Analyses of the MIMIC-III Database.
Background: Mechanically ventilated patients in the intensive care unit (ICU) have high mortality rates. There are multiple prediction scores, such as the Simplified Acute Physiology Score II (SAPS II), Oxford Acute Severity of Illness Score (OASIS), and Sequential Organ Failure Assessment (SOFA), widely used in the general ICU population. We aimed to establish prediction scores on mechanically ventilated patients with the combination of these disease severity scores and other features available on the first day of admission. ⋯ The top five predictors were age, respiratory dysfunction, SAPS II score, maximum hemoglobin, and minimum lactate. Conclusion: The current study indicates that models with the risk of factors on the first day could be successfully established for predicting mortality in ventilated patients. The XGBoost model performs best among the seven machine learning models.
-
Frontiers in medicine · Jan 2021
Predictors of Failed Intrauterine Balloon Tamponade in the Management of Severe Postpartum Hemorrhage.
To identify the factors predicting intrauterine balloon tamponade (IUBT) failure for severe postpartum hemorrhage (PPH) after delivery, we conducted a retrospective cohort study of women who underwent IUBT for severe PPH after delivery from October 1, 2016 until September 30, 2017. The failure of IUBT was defined as the need of additional surgical procedures or uterine embolization. A total of 99,650 deliveries occurred during the study period. ⋯ Ultimately, these models identified multiple gestation, EBL, and PAS as independent risk factors for IUBT failure. In conclusion, IUBT is an effective method for severe PPH. The presence of factors affecting IUBT failure should be recognized early, and other modalities of management should be anticipated.
-
Pulmonary embolism (PE) is a frequent, life-threatening COVID-19 complication, whose diagnosis can be challenging because of its non-specific symptoms. There are no studies assessing the impact of diagnostic delay on COVID-19 related PE. The aim of our exploratory study was to assess the diagnostic delay of PE in COVID-19 patients, and to identify potential associations between patient- or physician-related variables and the delay. ⋯ The overall diagnostic delay significantly correlated with the physician-related delay (p < 0.0001), with the tendency to a worse outcome in long physician-related diagnostic delay (p = 0.04). The delay was related to the presence of fever, respiratory symptoms and high levels of lactate dehydrogenase. It is important to rule out PE as soon as possible, in order to start the right therapy, to improve patient's outcome and to shorten the hospitalization.
-
Frontiers in medicine · Jan 2021
Impact of the Addition of Baricitinib to Standard of Care Including Tocilizumab and Corticosteroids on Mortality and Safety in Severe COVID-19.
Background: Baricitinib is a Janus kinase (JAK) inhibitor with a broader anti-inflammatory activity than tocilizumab and an antiviral potential although no head-to-head trials are available. The benefits of adding baricitinib to patients with COVID-19 experiencing clinical progression despite the standard of care (SOC), including corticosteroids and tocilizumab, are also unknown. Methods: A cohort study included microbiologically confirmed COVID-19 hospitalizations. ⋯ Secondary infections during hospitalization were not different between groups (17.9 vs. 10.5%, respectively; p = 0.212) and thromboembolic events were higher with baricitinib (11.6% vs. 3.2%; p = 0.048), but differences vanished after the adjustment [aHR 1.89 (0.31-11.57), p = 0.490]. Conclusion: The addition of baricitinib did not substantially reduce mortality in hospitalized patients with COVID-19 having clinical progression despite the therapy with tocilizumab and corticosteroids. The combination of baricitinib and tocilizumab was not associated with an increased risk of secondary infections or thromboembolic events.
-
Frontiers in medicine · Jan 2021
The Addition of Other Fecal Biomarkers Does Not Improve the Diagnostic Accuracy of Immunochemical Fecal Occult Blood Test Alone in a Colorrectal Cancer Screening Cohort.
Background: Screening with fecal occult blood test reduces colorectal cancer (CRC) incidence and mortality, and is currently implemented in most countries. However, around 40% of screening colonoscopies are normal. Thus, strategies to avoid these colonoscopies are highly necessary. ⋯ None of the other biomarkers explored or their combinations provided a better diagnostic accuracy. Only hTF showed an acceptable diagnostic accuracy. FC and hLF were not useful in this setting.