Defining predictors for successful mechanical ventilation weaning, using a data-mining process and artificial intelligence.

Mechanical ventilation weaning within intensive care units (ICU) is a difficult process, while crucial when considering its impact on morbidity and mortality. Failed extubation and prolonged mechanical ventilation both carry a significant risk of adverse events. We aimed to determine predictive factors of extubation success using data-mining and artificial intelligence. A prospective physiological and biomedical signal data warehousing project. A 21-beds medical Intensive Care Unit of a University Hospital. Adult patients undergoing weaning from mechanical ventilation. Hemodynamic and respiratory parameters of mechanically ventilated patients were prospectively collected and combined with clinical outcome data. One hundred and eight patients were included, for 135 spontaneous breathing trials (SBT) allowing to identify physiological parameters either measured before or during the trial and considered as predictive for extubation success. The Early-Warning Score Oxygen (EWSO2) enables to discriminate patients deemed to succeed extubation, at 72-h and 7-days. Cut-off values for EWSO2 (AUC = 0.80; Se = 0.75; Sp = 0.76), mean arterial pressure and heart-rate variability parameters were determined. A predictive model for extubation success was established including body-mass index (BMI) on inclusion, occlusion pressure at 0,1 s. (P0.1) and heart-rate analysis parameters (LF/HF) both measured before SBT, and heart rate during SBT (global performance 62%; 83%). The data-mining process enabled to detect independent predictive factors for extubation success and to develop a dynamic predictive model using artificial intelligence. Such predictive tools may help clinicians to better discriminate patients deemed to succeed extubation and thus improve clinical performance.

Transfusion-related respiratory complications in intensive care: A diagnosis challenge.

Transfusion-related respiratory complications can be challenging to diagnose especially in mechanically-ventilated patients in the intensive care unit (ICU) due to the concurrent respiratory symptoms associated with the patients' primary diagnoses. In this narrative review, transfusion-related respiratory complications, including transfusion-associated dyspnea (TAD), transfusion-related acute lung injury (TRALI), transfusion-associated circulatory overload (TACO), and transfusion-related allergic reaction (TRAR), are briefly presented in light of the recent consensus or experts' definitions; and the diagnosis issues for ICU patients are discussed. Acute respiratory failure occurring during, or within 6 to 24hours, of transfusion might be a transfusion-related respiratory complication. The recent updated definitions for TRALI and TACO should assist clinicians to differentiate between possible diagnoses. The issues for ICU clinicians are first to recognize the acute respiratory deterioration and the possible causality between the deterioration and blood transfusion and secondly to make the proper diagnosis. This remains challenging for mechanically-ventilated patients. Clinical assessment to identify ICU patients at particular risk of transfusion-related respiratory complications and non-invasive investigation tools could be beneficial and may help to remind clinicians to be alert to the link between transfusion and worsening of respiratory symptoms in these vulnerable critically ill patients.

Henoch-Schönlein Purpura Associated with Lung Cancer: When Paraneoplastic Manifestations Impede Oncological Management.

BACKGROUND: Henoch-Schönlein purpura (HSP) is an uncommon syndrome that mostly occurs in children, in whom it is frequently triggered by infections. In contrast, HSP in adults is more frequently of neoplastic origin. Case Presentation. We report HSP associated with a locally advanced lung squamous cell carcinoma that was considered a paraneoplastic syndrome. Systemic corticosteroids were given because a kidney biopsy revealed active glomerulonephritis. Concomitant chemoradiotherapy achieved a partial response of the lung tumor. Consolidation immunotherapy (programmed death protein-1-ligand-1 (PD-L1) inhibitor) was cancelled because HSP is known to be an autoimmune vasculitis, and long-term corticosteroid therapy was pursued. CONCLUSION: Further prospective studies are needed to evaluate the effect of anti-PD-(L) 1 immunotherapies on autoimmune manifestations.