Machine learning and predictive models: 2 years of Sars-CoV-2 pandemic in a single-center retrospective analysis.

BACKGROUND: Since January 2020, coronavirus disease 19 (COVID-19) has rapidly spread all over the world. An early assessment of illness severity is crucial for the stratification of patients in order to address them to the right intensity path of care. We performed an analysis on a large cohort of COVID-19 patients (n=581) hospitalized between March 2020 and May 2021 in our intensive care unit (ICU) at Policlinico Riuniti di Foggia hospital. Through an integration of the scores, demographic data, clinical history, laboratory findings, respiratory parameters, a correlation analysis, and the use of machine learning our study aimed to develop a model to predict the main outcome. METHODS: We deemed eligible for analysis all adult patients (age >18 years old) admitted to our department. We excluded all the patients with an ICU length of stay inferior to 24 h and the ones that declined to participate in our data collection. We collected demographic data, medical history, D-dimers, NEWS2, and MEWS scores on ICU admission and on ED admission, PaO2/FiO2 ratio on ICU admission, and the respiratory support modalities before the orotracheal intubation and the intubation timing (early vs late with a 48-h hospital length of stay cutoff). We further collected the ICU and hospital lengths of stay expressed in days of hospitalization, hospital location (high dependency unit, HDU, ED), and length of stay before and after ICU admission; the in-hospital mortality; and the in-ICU mortality. We performed univariate, bivariate, and multivariate statistical analyses. RESULTS: SARS-CoV-2 mortality was positively correlated to age, length of stay in HDU, MEWS, and NEWS2 on ICU admission, D-dimer value on ICU admission, early orotracheal intubation, and late orotracheal intubation. We found a negative correlation between the PaO2/FiO2 ratio on ICU admission and NIV. No significant correlations with sex, obesity, arterial hypertension, chronic obstructive pulmonary disease, chronic kidney disease, cardiovascular disease, diabetes mellitus, dyslipidemia, and neither MEWS nor NEWS on ED admission were observed. Considering all the pre-ICU variables, none of the machine learning algorithms performed well in developing a prediction model accurate enough to predict the outcome although a secondary multivariate analysis focused on the ventilation modalities and the main outcome confirmed how the choice of the right ventilatory support with the right timing is crucial. CONCLUSION: In our cohort of COVID patients, the choice of the right ventilatory support at the right time has been crucial, severity scores, and clinical judgment gave support in identifying patients at risk of developing a severe disease, comorbidities showed a lower weight than expected considering the main outcome, and machine learning method integration could be a fundamental statistical tool in the comprehensive evaluation of such complex diseases.

Circulating stem cells, HIF-1, and SDF-1 in septic abdominal surgical patients: randomized controlled study protocol.

BACKGROUND: Sepsis caused by complicated intra-abdominal infection is associated with high mortality. Loss of endothelial barrier integrity, inflammation, and impaired cellular oxygen have been shown to be primary contributors to sepsis. To date, little is known regarding the pathway for the mobilization of endothelial progenitor cells (EPCs) from the bone marrow in sepsis whereas stromal-cell-derived factor 1a (SDF-1a) and hypoxia inducible factor 1 (HIF-1) seem to have a role in the EPC response to hypoxic microenvironments. The aims of the study are: (a) to determine the time course of the levels of circulating EPCs (CD133/CD34), SDF-1a, and HIF-1 in septic patients undergoing major abdominal surgery (group S), (b) to investigate the relationship between CD133/CD34, HIF-1, and SDF-1a, and (c) to investigate the relationship of these factors with the outcome of group S patients treated with standard conventional therapy alone (CT) or with the addition of extracorporeal hemoperfusion therapy (HCT). METHODS/DESIGN: Patients undergoing major abdominal surgery will be allocated into groups: postoperative non-septic patients in an emergency surgical ward (group C) and postoperative septic patients in an intensive care unit (group S). The latter will be randomized to receive CT alone (S1) or with HCT (S2). Healthy volunteers (group H) will be recruited at University Hospital Foggia. Peripheral blood (PB) samples will be collected preoperatively (T0), at 24 h (T1), 72 h (T2), 7 (T3), and 10 (T4) postoperative days in groups S and C, and at T0 in group H. The CD34/133 cells and HIF-1 counts will be determined by flow cytometer analysis. The concentration of SDF-1a in plasma will be calculated by enzyme-linked immunosorbent assay analysis (ELISA). DISCUSSION: This prospective randomized clinical trial is designed to investigate circulating stem cells, levels of HIF-1 and SDF-1a, and their interrelationship in septic postoperative abdominal surgical patients treated with CT alone or with HCT. The rationale is that an integrated understanding of the role of hypoxia-related factors and EPCs in PB of septic patients could indicate which molecular processes need to be regulated to recover the innate immunity homeostasis. Understanding the function of EPCs in sepsis may provide innovative diagnostic and therapeutic approaches to improve the prognosis of this syndrome. TRIAL REGISTRATION: ClinicalTrials.gov: NCT02589535 . Registered on 28 October 2015.

Reference values for coagulation assessment in full-term newborns.

BACKGROUND: Most data in the literature report reduced coagulation activities in the first few days of life with respect to adults and the effects of these differences must be considered when diagnosing and treating hemostatic disorders. The management of pediatric population is further complicated by the lack of age-related reference values and by the unreliability of currently-used hemostatic tests, while an accurate interpretation of results is required to reduce the cases of inappropriate investigation. Thromboelastography (TEG®) is a point-of-care test that provides an efficient analysis of the dynamic viscoelastic properties of whole blood that may provide superior evaluation and management of coagulopathies in newborn. This study was designed to determine reference values for kaolin-activated TEG in full-term healthy newborn by taking small blood samples from the umbilical cord and facilitate accurate interpretation of neonatal TEG results. METHODS: Kaolin-activated TEG was performed in 85 full-term healthy newborn and 40 healthy adults. TEG data analyzed were: reaction time, clot formation time, α-angle, maximum amplitude, clot lysis at 30 minutes, Functional Fibrinogen and coagulation index. RESULTS: Reference values for kaolin-activated TEG in healthy full-term newborn are presented, despite a large variability in reaction time, clot formation time and in coagulation index, not significant impact on range values was evident and no significant differences between neonates and adults were observed. CONCLUSIONS: Neonatal coagulation tests are closer to adult standards and although significant age-related differences in kaolin-activated TEG variables do not appear to be present, the usefulness of TEG for pediatric population is an open field that needs to be further evaluated, the results of this study can be used to interpret the data for newborn.