Natural airway as an alternative to intubation for pediatric endoscopic esophageal foreign body removal: A retrospective cohort study of 326 patients.

BACKGROUND: Anesthesia is required for endoscopic removal of esophageal foreign bodies (EFBs) in children. Historically, endotracheal intubation has been the de facto gold standard for airway management in these cases. However, as more elective endoscopic procedures are now performed under propofol sedation with natural airway, there has been a move toward using similar Monitored Anesthesia Care (MAC) for select patients who require endoscopic removal of an EFB. METHODS: In this single-center retrospective cohort study, we compared endoscopic EFB removal with either MAC or endotracheal intubation. Descriptive statistics summarized factors stratified by initial choice of airway technique, including intra- and postanesthesia complications and the frequency of mid-procedure conversion to endotracheal intubation in those initially managed with MAC. To demonstrate the magnitude of associations between these factors and the anesthesiologist's choice of airway technique, univariable Firth logistic and quantile regressions were used to estimate odds ratios (95% CI) and beta coefficients (95% CI). RESULTS: From the initial search, 326 patients were identified. Among them, 23% (n = 75) were planned for intubation and 77% (n = 251) were planned for MAC. Three patients (0.9%) who were initially planned for MAC required conversion to endotracheal intubation after induction. Two (0.6%) of these children were admitted to the hospital after the procedure and treated for ongoing airway reactivity. No patient experienced reflux of gastric contents to the mouth or dislodgement of the foreign body to the airway, and no patient required administration of vasoactive medications or cardiopulmonary resuscitation. Patients had higher odds that the anesthesiologist chose to utilize MAC if the foreign body was a coin (OR, 3.3; CI, 1.9-5.7, p < .001) or if their fasting time was >6 h. Median total operating time was 15 min greater in intubated patients (11 vs. 26 min, p < .001). CONCLUSIONS: This study demonstrates that MAC may be considered for select pediatric patients undergoing endoscopic removal of EFB, especially those who have ingested coins, who do not have reactive airways, who have fasted for >6 h, and in whom the endoscopic procedure is expected to be short and uncomplicated. Prospective multi-site studies are needed to confirm these findings.

Machine Vision and Image Analysis in Anesthesia: Narrative Review and Future Prospects.

Machine vision describes the use of artificial intelligence to interpret, analyze, and derive predictions from image or video data. Machine vision-based techniques are already in clinical use in radiology, ophthalmology, and dermatology, where some applications currently equal or exceed the performance of specialty physicians in areas of image interpretation. While machine vision in anesthesia has many potential applications, its development remains in its infancy in our specialty. Early research for machine vision in anesthesia has focused on automated recognition of anatomical structures during ultrasound-guided regional anesthesia or line insertion; recognition of the glottic opening and vocal cords during video laryngoscopy; prediction of the difficult airway using facial images; and clinical alerts for endobronchial intubation detected on chest radiograph. Current machine vision applications measuring the distance between endotracheal tube tip and carina have demonstrated noninferior performance compared to board-certified physicians. The performance and potential uses of machine vision for anesthesia will only grow with the advancement of underlying machine vision algorithm technical performance developed outside of medicine, such as convolutional neural networks and transfer learning. This article summarizes recently published works of interest, provides a brief overview of techniques used to create machine vision applications, explains frequently used terms, and discusses challenges the specialty will encounter as we embrace the advantages that this technology may bring to future clinical practice and patient care. As machine vision emerges onto the clinical stage, it is critically important that anesthesiologists are prepared to confidently assess which of these devices are safe, appropriate, and bring added value to patient care.

A machine-learning approach for decision support and risk stratification of pediatric perioperative patients based on the APRICOT dataset.

BACKGROUND: Pediatric anesthesia has evolved to a high level of patient safety, yet a small chance remains for serious perioperative complications, even in those traditionally considered at low risk. In practice, prediction of at-risk patients currently relies on the American Society of Anesthesiologists Physical Status (ASA-PS) score, despite reported inconsistencies with this method. AIMS: The goal of this study was to develop predictive models that can classify children as low risk for anesthesia at the time of surgical booking and after anesthetic assessment on the procedure day. METHODS: Our dataset was derived from APRICOT, a prospective observational cohort study conducted by 261 European institutions in 2014 and 2015. We included only the first procedure, ASA-PS classification I to III, and perioperative adverse events not classified as drug errors, reducing the total number of records to 30 325 with an adverse event rate of 4.43%. From this dataset, a stratified train:test split of 70:30 was used to develop predictive machine learning algorithms that could identify children in ASA-PS class I to III at low risk for severe perioperative critical events that included respiratory, cardiac, allergic, and neurological complications. RESULTS: Our selected models achieved accuracies of >0.9, areas under the receiver operating curve of 0.6-0.7, and negative predictive values >95%. Gradient boosting models were the best performing for both the booking phase and the day-of-surgery phase. CONCLUSIONS: This work demonstrates that prediction of patients at low risk of critical PAEs can be made on an individual, rather than population-based, level by using machine learning. Our approach yielded two models that accommodate wide clinical variability and, with further development, are potentially generalizable to many surgical centers.

Paediatric cannabinoid hyperemesis.

PURPOSE OF REVIEW: The prevalence of adolescent cannabinoid hyperemesis syndrome (CHS) continues to grow, as clinicians increasingly recognize the presenting features of cyclical nausea, emesis, abdominal pain and relief of symptoms with hot showers, in the setting of chronic cannabinoid use. RECENT FINDINGS: Our understanding of the contributory mechanisms continues to grow, but high-quality evidence of effective treatment in adolescents remains lacking. Current best evidence in the treatment of acute paediatric CHS suggests intravenous rehydration and electrolyte correction, followed by 0.05 mg/kg haloperidol with or without a benzodiazepine. The only long-term treatment remains complete cessation of cannabinoid use. SUMMARY: This article reviews our growing knowledge of adolescent CHS and provides practical guidance for diagnosis, treatment and understanding the underlying mechanisms of the condition.

Machine Learning Applied to Registry Data: Development of a Patient-Specific Prediction Model for Blood Transfusion Requirements During Craniofacial Surgery Using the Pediatric Craniofacial Perioperative Registry Dataset.

BACKGROUND: Craniosynostosis is the premature fusion of ≥1 cranial sutures and often requires surgical intervention. Surgery may involve extensive osteotomies, which can lead to substantial blood loss. Currently, there are no consensus recommendations for guiding blood conservation or transfusion in this patient population. The aim of this study is to develop a machine-learning model to predict blood product transfusion requirements for individual pediatric patients undergoing craniofacial surgery. METHODS: Using data from 2143 patients in the Pediatric Craniofacial Surgery Perioperative Registry, we assessed 6 machine-learning classification and regression models based on random forest, adaptive boosting (AdaBoost), neural network, gradient boosting machine (GBM), support vector machine, and elastic net methods with inputs from 22 demographic and preoperative features. We developed classification models to predict an individual's overall need for transfusion and regression models to predict the number of blood product units to be ordered preoperatively. The study is reported according to the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) checklist for prediction model development. RESULTS: The GBM performed best in both domains, with an area under receiver operating characteristic curve of 0.87 ± 0.03 (95% confidence interval) and F-score of 0.91 ± 0.04 for classification, and a mean squared error of 1.15 ± 0.12, R-squared (R) of 0.73 ± 0.02, and root mean squared error of 1.05 ± 0.06 for regression. GBM feature ranking determined that the following variables held the most information for prediction: platelet count, weight, preoperative hematocrit, surgical volume per institution, age, and preoperative hemoglobin. We then produced a calculator to show the number of units of blood that should be ordered preoperatively for an individual patient. CONCLUSIONS: Anesthesiologists and surgeons can use this continually evolving predictive model to improve clinical care of patients presenting for craniosynostosis surgery.

Acute Treatment of Adolescent Cannabinoid Hyperemesis Syndrome With Haloperidol, Lorazepam, and/or Capsaicin: A Single Institution Case Series.

Cannabinoid hyperemesis syndrome (CHS), an under-recognized and seemingly paradoxical condition, arises in some adolescents and adults who chronically use cannabis. It presents acutely with intractable nausea, vomiting, and abdominal pain but standard antiemetic therapy leads to improvement for only a minority of patients. Randomized controlled trial evidence in adults indicates the superiority of haloperidol over ondansetron in alleviating the acute symptoms of CHS, but safe and effective treatment for adolescents with the disorder is currently unknown. The successful use of topical capsaicin has also been reported. We report a case series of 6 adolescent patients with CHS who presented to Johns Hopkins All Children's Hospital and were treated with haloperidol, lorazepam, and/or capsaicin. Four patients given 5 mg intravenous (IV) haloperidol and 2 mg IV lorazepam and 1 patient treated with 5 mg IV haloperidol and peri-umbilical topical capsaicin (0.025%) experienced full acute symptomatic relief. One patient, treated only with topical capsaicin, reported improvement of symptoms with some persistent nausea. Haloperidol/lorazepam, haloperidol/capsaicin, and topical capsaicin alone appear safe and effective in adolescents, but larger studies are required to confirm our findings.

Pediatric Cannabinoid Hyperemesis: A Single Institution 10-Year Case Series.

PURPOSE: Cannabis hyperemesis (CH) is an under-recognized condition in patients with chronic or cyclic vomiting and who regularly use cannabis. Once thought to be rare, it is now increasingly recognized in both adults and children. We report a case series of adolescent patients with CH who presented at a single institution over 10 years. METHODS: Patients were included if they had a diagnosis code of cannabis-related or cyclic vomiting, experienced the onset of regular vomiting after starting to regularly use cannabis, and if no other diagnosis was found to better explain the presentation. Thirty-four patients aged 13-20 years (median 17 years) met the inclusion criteria. RESULTS: The presenting clinical features were broadly similar to adult CH: cyclic nausea and emesis after at least 3 months of regular cannabis use, abdominal pain, change in bowel habit, and symptomatic relief from hot showers or baths. No antiemetic was found to be of particular benefit. Follow-up was recorded in under half of the patients; documentation of drug history was also frequently incomplete. Clinicians should consider CH when assessing any adolescent with cyclic or chronic vomiting. CONCLUSIONS: A detailed drug history, preferably taken in the absence of parents or other involved adults and corroborated by urine drug screening, is helpful in substantiating the diagnosis. Further prospective studies are needed to confirm the incidence, prevalence, presenting features, and the effectiveness of treatments, including drug counseling and cessation. Based on our findings, we propose pragmatic criteria to aid in the diagnosis of pediatric CH.

Deep Learning for Improved Risk Prediction in Surgical Outcomes.

The Norwood surgical procedure restores functional systemic circulation in neonatal patients with single ventricle congenital heart defects, but this complex procedure carries a high mortality rate. In this study we address the need to provide an accurate patient specific risk prediction for one-year postoperative mortality or cardiac transplantation and prolonged length of hospital stay with the purpose of assisting clinicians and patients' families in the preoperative decision making process. Currently available risk prediction models either do not provide patient specific risk factors or only predict in-hospital mortality rates. We apply machine learning models to predict and calculate individual patient risk for mortality and prolonged length of stay using the Pediatric Heart Network Single Ventricle Reconstruction trial dataset. We applied a Markov Chain Monte-Carlo simulation method to impute missing data and then fed the selected variables to multiple machine learning models. The individual risk of mortality or cardiac transplantation calculation produced by our deep neural network model demonstrated 89 ± 4% accuracy and 0.95 ± 0.02 area under the receiver operating characteristic curve (AUROC). The C-statistics results for prediction of prolonged length of stay were 85 ± 3% accuracy and AUROC 0.94 ± 0.04. These predictive models and calculator may help to inform clinical and organizational decision making.

Quality Initiative Using Theory of Change and Visual Analytics to Improve Controlled Substance Documentation Discrepancies in the Operating Room.

BACKGROUND: Discrepancies in controlled substance documentation are common and can lead to legal and regulatory repercussions. We introduced a visual analytics dashboard to assist in a quality improvement project to reduce the discrepancies in controlled substance documentation in the operating room (OR) of our free-standing pediatric hospital. METHODS: Visual analytics were applied to collected documentation discrepancy audit data and were used to track progress of the project, to motivate the OR team, and in analyzing where further improvements could be made. This was part of a seven-step improvement plan based on the Theory of Change with a logic model framework approach. RESULTS: The introduction of the visual analytics dashboard contributed a 24% improvement in controlled substance documentation discrepancy. The project overall reduced documentation errors by 71% over the studied period. CONCLUSION: We used visual analytics to simultaneously analyze, monitor, and interpret vast amounts of data and present them in an appealing format. In conjunction with quality-improvement principles, this led to a significant improvement in controlled substance documentation discrepancies.