简介：无

简介：AbstractPurpose:Traumatic brain injury (TBI) generally causes mortality and disability, particularly in children. Machine learning (ML) is a computer algorithm, applied as a clinical prediction tool. The present study aims to assess the predictability of ML for the functional outcomes of pediatric TBI.Methods:A retrospective cohort study was performed targeting children with TBI who were admitted to the trauma center of southern Thailand between January 2009 and July 2020. The patient was excluded if he/she (1) did not undergo a CT scan of the brain, (2) died within the first 24 h, (3) had unavailable complete medical records during admission, or (4) was unable to provide updated outcomes. Clinical and radiologic characteristics were collected such as vital signs, Glasgow coma scale score, and characteristics of intracranial injuries. The functional outcome was assessed using the King's Outcome Scale for Childhood Head Injury, which was thus dichotomized into favourable outcomes and unfavourable outcomes: good recovery and moderate disability were categorized as the former, whereas death, vegetative state, and severe disability were categorized as the latter. The prognostic factors were estimated using traditional binary logistic regression. By data splitting, 70% of data were used for training the ML models and the remaining 30% were used for testing the ML models. The supervised algorithms including support vector machines, neural networks, random forest, logistic regression, naive Bayes and k-nearest neighbor were performed for training of the ML models. Therefore, the ML models were tested for the predictive performances by the testing datasets.Results:There were 828 patients in the cohort. The median age was 72 months (interquartile range 104.7 months, range 2-179 months). Road traffic accident was the most common mechanism of injury, accounting for 68.7%. At hospital discharge, favourable outcomes were achieved in 97.0% of patients, while the mortality rate was 2.2%. Glasgow coma scale score, hypotension, pupillary light reflex, and subarachnoid haemorrhage were associated with TBI outcomes following traditional binary logistic regression; hence, the 4 prognostic factors were used for building ML models and testing performance. The support vector machine model had the best performance for predicting pediatric TBI outcomes: sensitivity 0.95, specificity 0.60, positive predicted value 0.99, negative predictive value 1.0; accuracy 0.94, and area under the receiver operating characteristic curve 0.78.Conclusion:The ML algorithms of the present study have a high sensitivity; therefore they have the potential to be screening tools for predicting functional outcomes and counselling prognosis in general practice of pediatric TBIs.

简介：AbstractBackground:Conventional pressure support ventilation (PSP) is triggered and cycled off by pneumatic signals such as flow. Patient-ventilator asynchrony is common during pressure support ventilation, thereby contributing to an increased inspiratory effort. Using diaphragm electrical activity, neurally controlled pressure support (PSN) could hypothetically eliminate the asynchrony and reduce inspiratory effort. The purpose of this study was to compare the differences between PSN and PSP in terms of patient-ventilator synchrony, inspiratory effort, and breathing pattern.Methods:Eight post-operative patients without respiratory system comorbidity, eight patients with acute respiratory distress syndrome (ARDS) and obvious restrictive acute respiratory failure (ARF), and eight patients with chronic obstructive pulmonary disease (COPD) and mixed restrictive and obstructive ARF were enrolled. Patient-ventilator interactions were analyzed with macro asynchronies (ineffective, double, and auto triggering), micro asynchronies (inspiratory trigger delay, premature, and late cycling), and the total asynchrony index (AI). Inspiratory efforts for triggering and total inspiration were analyzed.Results:Total AI of PSN was consistently lower than that of PSP in COPD (3% vs. 93%, P = 0.012 for 100% support level; 8% vs. 104%, P = 0.012 for 150% support level), ARDS (8% vs. 29%, P = 0.012 for 100% support level; 16% vs. 41%, P = 0.017 for 150% support level), and post-operative patients (21% vs. 35%, P = 0.012 for 100% support level; 15% vs. 50%, P = 0.017 for 150% support level). Improved support levels from 100% to 150% statistically increased total AI during PSP but not during PSN in patients with COPD or ARDS. Patients’ inspiratory efforts for triggering and total inspiration were significantly lower during PSN than during PSP in patients with COPD or ARDS under both support levels (P < 0.05). There was no difference in breathing patterns between PSN and PSP.Conclusions:PSN improves patient-ventilator synchrony and generates a respiratory pattern similar to PSP independently of any level of support in patients with different respiratory system mechanical properties. PSN, which reduces the trigger and total patient’s inspiratory effort in patients with COPD or ARDS, might be an alternative mode for PSP.Trial Registration:ClinicalTrials.gov, NCT01979627; https://clinicaltrials.gov/ct2/show/record/NCT01979627.