BACKGROUND
Perioperative mortality in children is relatively rare; however, accurate preoperative risk stratification is critical, as it enables anticipatory planning to mitigate the risk of death. This study aims to use machine learning (ML) to develop and internally validate a predictive model for 30-day mortality in children undergoing noncardiac surgery and compare model performance to the regression-based Pediatric Risk Assessment (PRAm) score.
METHODS
A retrospective study of the National Surgical Quality Improvement Program (NSQIP)-Pediatric database from 2012 to 2022, excluding 2020, was performed. Patients <18 years undergoing multispecialty surgical procedures except cardiac surgery were included. Clinically meaningful risk factors for mortality were included in the random forest and XGBoost ML models. The primary outcome was 30-day mortality.
RESULTS
A total of 1,023,639 unique patient encounters were included in the final analysis; 3522 (0.34%) resulted in 30-day mortality. Most patients of the 1,023,639 were ≥12 years (307,930, 30.1%), followed by 6 to 12 years (263,241, 25.7%). The majority was inpatient (596,642, 58.3%) and underwent an elective procedure (736,163, 71.9%). The most common comorbid conditions were neurologic disease (209,384, 20.5%), gastrointestinal disease (177,888, 17.4%), and central nervous system tumor or acquired abnormality (129,711, 12.7%). A total of 3.2% (33,103) were mechanically ventilated and 0.6% (6032) supported with inotropes. ML models were developed on the 70% training set (n = 716,662) and evaluated using the 30% validation set (n = 306,977). The XGBoost model demonstrated the best performance in the validation set (area under the receiver operating characteristic curve [AUC-ROC] = 0.956, area under the precision-recall curve [AUC-PR] = 0.179). The accuracy was 99.4% and the precision was 0.247, meaning that a positive prediction was associated with a 24.7% risk of mortality. The model demonstrated good calibration (Brier score = 0.003) between observed and expected probabilities. The AUC-ROC for the XGBoost model was 0.956 and for the PRAm score 0.958. There was no substantial increase in net benefit of the XGBoost model versus the PRAm score across the range of threshold probabilities.
CONCLUSIONS
ML can be leveraged to develop clinical prediction tools with excellent predictive performance for rare but critical outcomes like postoperative mortality. However, the ML-based models in the current study performed similarly to the regression-based PRAm score, highlighting the need to consider whether their added complexity yields meaningful clinical benefit.
S. Staffa, Eleonore Valencia, V. Tangel et al.· Anesthesia and Analgesia· 0 citations
BACKGROUND
Post-extubation emergence agitation (EA) is common in pediatric ear, nose, and throat (ENT) procedures and may lead to serious complications.
AIMS
To assess the efficacy of low-dose propofol administered before extubation, compared with placebo, for preventing EA, using meta-analysis with trial sequential analysis (TSA).
METHODS
We searched PubMed, Embase, and the Cochrane Central Register of Controlled Trials for randomized controlled trials (RCTs) comparing low-dose propofol versus placebo administered before extubation in pediatric ENT procedures. The primary outcomes were laryngospasm, severity of EA, assessed by the Pediatric Anesthesia Emergence Delirium (PAED) scale score, and incidence of EA. Secondary outcomes included post-anesthesia care unit (PACU) length of stay, time to recovery, and time to extubation. Random-effects models were used to pool effect estimates with 95% confidence intervals (CIs). TSA was performed for all outcomes to assess the robustness of the evidence.
RESULTS
Ten RCTs were included in the review, of which six (414 pediatric patients) contributed to the meta-analysis. Compared with control, propofol significantly reduced the incidence of EA (risk ratio [RR] = 0.57; 95% CI, 0.42-0.78) and lowered agitation severity (mean difference [MD] = -3.94; 95% CI, -5.74 to -2.13). Time to extubation was slightly longer (MD = 1.8 min; 95% CI, 1.4-2.3), whereas time to recovery (MD = 0.9 min; 95% CI, -1.9 to 3.6) and PACU length of stay (MD = -0.63 min; 95% CI, -3.2 to 1.9) did not differ. TSA confirmed the robustness of the findings for incidence of EA, severity of EA, and time to extubation. However, the certainty of evidence was very low for severity of EA and moderate for EA incidence and time to extubation. Laryngospasm outcomes were not pooled due to substantial heterogeneity.
CONCLUSIONS
Our findings suggest that pre-extubation propofol probably reduces the incidence of EA in pediatric ENT surgery, supported by moderate-certainty evidence, and may lower EA severity measured by PAED scale scores, for which the certainty of evidence was very low. Propofol was also associated with a slightly longer time to extubation, with no difference in overall recovery time or PACU length of stay.
Rafaela Silva, Raphaela G. Mendes, João Mário M.F. Borges et al.· Paediatric anaesthesia· 0 citations
Endometriosis is a chronic inflammatory condition that affects an estimated 1 in 10 women but is often mis- and underdiagnosed due to its non-specific symptoms and the lack of a non-invasive diagnostic test. This study aimed to identify and validate a potential non-invasive biomarker for endometriosis. This study applied quantitative proteomics discovery approaches to identify and validate non-invasive biomarkers of endometriosis with a long-term goal of leveraging them for purposes of diagnosis and therapeutic monitoring. Isobaric tags for relative and absolute quantification (iTRAQ) combined with mass spectrometry were used to identify and quantitate proteins and peptides in urine samples from participants with surgically-confirmed endometriosis (n = 73) and 1:1 age-matched participants never diagnosed with endometriosis (n = 73). Among those aged 25–47 at urine collection, Epidermal Growth Factor (EGF) (validated using monospecific enzyme-linked immunosorbent assays (ELISA)) was present at significantly lower levels in the urine of participants with surgically-confirmed endometriosis compared to controls (P = 0.02) and had an excellent negative predictive value (NPV) of 94.3% with a cutoff of > 800 pg/ug as determined by Bayes’ formula. Urinary EGF levels were also significantly lower in the urine of participants aged 25–47 with endometriosis who experience acyclic pelvic pain compared to samples from age-matched controls who did not report acyclic pelvic pain (P = 0.007) such that the presence of acyclic pelvic pain increased the NPV of EGF to 96.8% as determined by Bayes’ formula. These data demonstrate that urinary EGF has potential as a novel, non-invasive, accurate and objective biomarker for endometriosis diagnosis and prognosis of this disease.
Emma R. Rashes Gertel, Cassandra C. Daisy, K. Kaplan et al.· Biomarker Research· 0 citations