National Implementation of an Artificial Intelligence-Based Virtual Dietitian for Patients With Cancer.

PURPOSE: Nutritional status is an established driver of cancer outcomes, but there is an insufficient workforce of registered dietitians to meet patient needs for nutritional counseling. Artificial intelligence (AI) and machine learning (ML) afford the opportunity to expand access to guideline-based nutritional support. METHODS: An AI-based nutrition assistant called Ina was developed on the basis of a learning data set of >100,000 expert-curated interventions, peer-reviewed literature, and clinical guidelines, and provides a conversational text message-based patient interface to guide dietary habits and answer questions. Ina was implemented nationally in partnership with 25 advocacy organizations. Data on demographics, patient-reported outcomes, and utilization were systematically collected. RESULTS: Between July 2019 and August 2023, 3,310 users from all 50 states registered to use Ina. Users were 73% female; median age was 57 (range, 18-91) years; most common cancer types were genitourinary (22%), breast (21%), gynecologic (19%), GI (14%), and lung (12%). Users were medically complex, with 50% reporting Stage III to IV disease, 37% with metastases, and 50% with 2+ chronic conditions. Nutritional challenges were highly prevalent: 58% had overweight/obese BMIs, 83% reported barriers to good nutrition, and 42% had food allergies/intolerances. Levels of engagement were high: 68% texted questions to Ina; 79% completed surveys; median user retention was 8.8 months; 94% were satisfied with the platform; and 98% found the guidance helpful. In an evaluation of outcomes, 84% used the advice to guide diet; 47% used recommended recipes, 82% felt the program improved quality of life (QoL), and 88% reported improved symptom management. CONCLUSION: Implementation of an evidence-based AI virtual dietitian is feasible and is reported by patients to be beneficial on diet, QoL, and symptom management. Ongoing evaluations are assessing impact on other outcomes.

Does Non-Neurologic Multiorgan Dysfunction After Out-of-Hospital Cardiac Arrest among Children Admitted in Coma Predict Outcome 1 Year Later?

In this article, we investigated whether non-neurologic multiorgan dysfunction syndrome (MODS) following out-of-hospital cardiac arrest (OHCA) predicts poor 12-month survival. We conducted a secondary data analysis of therapeutic hypothermia after pediatric cardiac arrest out-of-hospital randomized trial involving children who remained unconscious and intubated after OHCA ( n = 237). Associations between MODS and 12-month outcomes were assessed using multivariable logistic regression. Non-neurologic MODS was present in 95% of patients and sensitive (97%; 95% confidence interval [CI]: 93-99%) for 12-month survival but had poor specificity (10%; 95% CI: 4-21%). Development of non-neurologic MODS is not helpful to predict long-term neurologic outcome or survival after OHCA.

Trends in Imaging Findings, Interventions, and Outcomes Among Children With Isolated Head Trauma.

OBJECTIVE: The aim was to analyze the impact of decreased head computed tomography (CT) imaging on detection of abnormalities and outcomes for children with isolated head trauma. METHODS: The study involves a multicenter retrospective cohort of patients younger than 19 years presenting for isolated head trauma to emergency departments in the Pediatric Health Information System database from 2003 to 2015. Patients directly admitted or transferred to another facility and those with a discharge diagnosis code for child maltreatment were excluded. Outcomes were ascertained from administrative and billing data. Trends were tested using mixed effects logistic regression, accounting for clustering within hospitals and adjusted for age, sex, insurance type, race, presence of a complex chronic condition, and hospital-level case mix index. RESULTS: Between 2003 and 2015, 306,041 children presented for isolated head trauma. The proportion of children receiving head CT imaging was increasing until 2008, peaking at just under 40%, before declining to 25% by 2015. During the recent period of decreased head CT imaging, the detection of skull fractures (odds ratio [OR]/year, 0.96; 95% confidence interval [CI], 0.95-0.97) and intracranial bleeds (OR/year, 0.96; 95% CI, 0.94-0.97), hospitalization (OR/year, 0.96; 95% CI, 0.95-0.96), neurosurgery (OR/year, 0.91; 95% CI, 0.87-0.95), and revisit (OR/year, 0.98; 95% CI, 0.96-1.00) also decreased, without significant changes in mortality (OR/year, 0.93; 95% CI, 0.84-1.04) or persistent neurologic impairment (OR/year, 1.03; 95% CI, 0.92-1.15). CONCLUSIONS: The recent decline in CT scanning in children with isolated head trauma was associated with a reduction in detection of intracranial abnormalities, and a concomitant decrease in interventions, without measurable patient harm.

External validation of the Pediatric Extracorporeal Membrane Oxygenation Prediction model for risk adjusting mortality.

INTRODUCTION: The Pediatric Extracorporeal Membrane Oxygenation Prediction (PEP) model was created to provide risk stratification for all pediatric patients requiring extracorporeal life support (ECLS). Our purpose was to externally validate the model using contemporaneous cases submitted to the Extracorporeal Life Support Organization (ELSO) registry. METHODS: This multicenter, retrospective analysis included pediatric patients (<19 years) during their initial ECLS run for all indications between January 2012 and September 2014. Median values from the BATE dataset for activated partial thromboplastin time and internationalized normalized ratio were used as surrogates as these were missing in the ELSO group. Model discrimination was evaluated using area under the receiver operating characteristic curve (AUC), and goodness-of-fit was evaluated using the Hosmer-Lemeshow test. RESULTS: A total of 4,342 patients in the ELSO registry were compared to 514 subjects from the bleeding and thrombosis on extracorporeal membrane oxygenation (BATE) dataset used to develop the PEP model. Overall mortality was similar (42% ELSO vs. 45% BATE). The c-statistic after external validation decreased from 0.75 to 0.64 and model calibration decreases most in the highest risk deciles. CONCLUSION: Discrimination of the PEP model remains modest after external validation using the largest pediatric ECLS cohort. While the model overestimates mortality for the highest risk patients, it remains the only prediction model applicable to both neonates and pediatric patients who require ECLS for any indication and thus maintains potential for application in research and quality benchmarking.

Guidelines for the Management of Severe Traumatic Brain Injury: 2020 Update of the Decompressive Craniectomy Recommendations.

When the fourth edition of the Brain Trauma Foundation's Guidelines for the Management of Severe Traumatic Brain Injury were finalized in late 2016, it was known that the results of the RESCUEicp (Trial of Decompressive Craniectomy for Traumatic Intracranial Hypertension) randomized controlled trial of decompressive craniectomy would be public after the guidelines were released. The guideline authors decided to proceed with publication but to update the decompressive craniectomy recommendations later in the spirit of "living guidelines," whereby topics are updated more frequently, and between new editions, when important new evidence is published. The update to the decompressive craniectomy chapter presented here integrates the findings of the RESCUEicp study as well as the recently published 12-mo outcome data from the DECRA (Decompressive Craniectomy in Patients With Severe Traumatic Brain Injury) trial. Incorporation of these publications into the body of evidence led to the generation of 3 new level-IIA recommendations; a fourth previously presented level-IIA recommendation remains valid and has been restated. To increase the utility of the recommendations, we added a new section entitled Incorporating the Evidence into Practice. This summary of expert opinion provides important context and addresses key issues for practitioners, which are intended to help the clinician utilize the available evidence and these recommendations. The full guideline can be found at: https://braintrauma.org/guidelines/guidelines-for-the-management-of-severe-tbi-4th-ed#/.

Characteristics of pediatric patients with traumatic epidural hematomas who can be safely observed: a clinical validation study.

OBJECTIVE: The study aimed to validate admission clinical and radiographic features of pediatric patients with traumatic epidural hematoma (EDH) that lead to safe observation. METHODS: A Level I trauma center radiology and electronic medical record databases were retrospectively queried for pediatric patients with EDH on CT scan between 1/1/2016 and 10/1/2016. Patient imaging, treatment and outcome variables were abstracted. Characteristics of the cohort were compared to an external cohort used to develop prediction rules for surgical intervention. External validity of the prediction rules was assessed. RESULTS: 195 eligible subjects were included in the study, 37 of which failed observation and required surgery while 158 underwent successful observation. The surgical cohort had significantly thicker (p < .001) and higher volume (p < .001) EDH, increased midline shift (p < .001) and higher likelihood of mass effect (p < .001). There was significantly higher residual neurologic deficit rate (54% vs 23%, p < .001) and hospital mortality (5% vs 0%, p = .035) amongst the surgical group. There were significant differences in patient demographic, clinical and imaging characteristics between the internal and external cohorts. The predictive rules externally developed yielded positive predictive value of 97.7% (95% CI = 93.3-99.5%), negative predictive value of 24.5% (95% CI = 16.2-34.4%), specificity of 88.5% (95% CI = 69.9-97.6%), and sensitivity of 63.8% (95% CI = 56.6-70.5%) for successful observation. CONCLUSION: The current study validates previously developed prediction rules for safe observation of pediatric EDH in a cohort with distinct characteristics from the external cohort. Specifically, patients with no mass effect, EDH volume <15 ml and no neurological deficits are less likely to fail observation. ADVANCES IN KNOWLEDGE: The current study validates prediction rules for safe observation of pediatric EDH in a distinct pediatric cohort that provides further support to conservative management in these circumstances.

Current Epidemiology of Vocal Cord Dysfunction After Congenital Heart Surgery in Young Infants.

OBJECTIVES: Surgery of the aortic arch poses risk of recurrent laryngeal nerve injury due to the anatomic proximity and can manifest as vocal cord dysfunction after surgery. We assessed risk factors for vocal cord dysfunction and calculated surgical procedure associated rates in young infants after congenital heart surgery. DESIGN: Cross section analysis. SETTING: Forty-four children's hospitals reporting administrative data to Pediatric Health Information System. PARTICIPANTS: Cardiac surgical patients less than or equal to 90 days old and discharged between January 2004 and June 2014. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: Overall, 2,319 of 46,567 subjects (5%) had vocal cord dysfunction, increasing from 4% to 7% over the study period. Of those with vocal cord dysfunction, 75% had unilateral partial paralysis. Vocal cord dysfunction was significantly more common in newborn infants (74%), those with aortic arch procedures (77%) and with greater surgical complexity. Rates of vocal cord dysfunction ranged from 0.7% to 22.4% across surgical procedure groups. Vocal cord dysfunction was significantly associated with greater use of: prolonged mechanical ventilation (53% vs 40%), diaphragmatic plication (3% vs 1%), feeding tube use (32% vs 8%), surgical airways (4% vs 2%), and prolonged length of stay (44 vs 21 d). Vocal cord dysfunction testing increased significantly over the study (6-14 %), and vocal cord dysfunction diagnosis increased almost two-fold (odds ratio, 1.9; 95% CI, 1.7-2.1) comparing the last to first study quarters with the increase in vocal cord dysfunction diagnosis occurring predominately in surgeries to the aortic arch supported by cardiopulmonary bypass. However, aortic procedures without cardiopulmonary bypass and nonaortic arch procedures were common surgeries accounting for 27% and 23% of vocal cord dysfunction cases despite low overall vocal cord dysfunction rates (3.7% and 2.6%). CONCLUSIONS: Vocal cord dysfunction complicated all cardiac surgical procedures among infants including those without aortic arch involvement. Increased efforts to determine appropriate indications for prevention, screening and treatment of vocal cord dysfunction among young infants after congenital heart surgery are needed.

Management of Pediatric Severe Traumatic Brain Injury: 2019 Consensus and Guidelines-Based Algorithm for First and Second Tier Therapies.

OBJECTIVES: To produce a treatment algorithm for the ICU management of infants, children, and adolescents with severe traumatic brain injury. DATA SOURCES: Studies included in the 2019 Guidelines for the Management of Pediatric Severe Traumatic Brain Injury (Glasgow Coma Scale score ≤ 8), consensus when evidence was insufficient to formulate a fully evidence-based approach, and selected protocols from included studies. DATA SYNTHESIS: Baseline care germane to all pediatric patients with severe traumatic brain injury along with two tiers of therapy were formulated. An approach to emergent management of the crisis scenario of cerebral herniation was also included. The first tier of therapy focuses on three therapeutic targets, namely preventing and/or treating intracranial hypertension, optimizing cerebral perfusion pressure, and optimizing partial pressure of brain tissue oxygen (when monitored). The second tier of therapy focuses on decompressive craniectomy surgery, barbiturate infusion, late application of hypothermia, induced hyperventilation, and hyperosmolar therapies. CONCLUSIONS: This article provides an algorithm of clinical practice for the bedside practitioner based on the available evidence, treatment protocols described in the articles included in the 2019 guidelines, and consensus that reflects a logical approach to mitigate intracranial hypertension, optimize cerebral perfusion, and improve outcomes in the setting of pediatric severe traumatic brain injury.

Guidelines for the Management of Pediatric Severe Traumatic Brain Injury, Third Edition: Update of the Brain Trauma Foundation Guidelines, Executive Summary.

OBJECTIVES: The purpose of this work is to identify and synthesize research produced since the second edition of these Guidelines was published and incorporate new results into revised evidence-based recommendations for the treatment of severe traumatic brain injury in pediatric patients. METHODS AND MAIN RESULTS: This document provides an overview of our process, lists the new research added, and includes the revised recommendations. Recommendations are only provided when there is supporting evidence. This update includes 22 recommendations, nine are new or revised from previous editions. New recommendations on neuroimaging, hyperosmolar therapy, analgesics and sedatives, seizure prophylaxis, temperature control/hypothermia, and nutrition are provided. None are level I, three are level II, and 19 are level III. The Clinical Investigators responsible for these Guidelines also created a companion algorithm that supplements the recommendations with expert consensus where evidence is not available and organizes possible interventions into first and second tier utilization. The purpose of publishing the algorithm as a separate document is to provide guidance for clinicians while maintaining a clear distinction between what is evidence based and what is consensus based. This approach allows, and is intended to encourage, continued creativity in treatment and research where evidence is lacking. Additionally, it allows for the use of the evidence-based recommendations as the foundation for other pathways, protocols, or algorithms specific to different organizations or environments. The complete guideline document and supplemental appendices are available electronically from this journal. These documents contain summaries and evaluations of all the studies considered, including those from prior editions, and more detailed information on our methodology. CONCLUSIONS: New level II and level III evidence-based recommendations and an algorithm provide additional guidance for the development of local protocols to treat pediatric patients with severe traumatic brain injury. Our intention is to identify and institute a sustainable process to update these Guidelines as new evidence becomes available.

Guidelines for the Management of Pediatric Severe Traumatic Brain Injury, Third Edition: Update of the Brain Trauma Foundation Guidelines, Executive Summary.

The purpose of this work is to identify and synthesize research produced since the second edition of these Guidelines was published and incorporate new results into revised evidence-based recommendations for the treatment of severe traumatic brain injury in pediatric patients. This document provides an overview of our process, lists the new research added, and includes the revised recommendations. Recommendations are only provided when there is supporting evidence. This update includes 22 recommendations, 9 are new or revised from previous editions. New recommendations on neuroimaging, hyperosmolar therapy, analgesics and sedatives, seizure prophylaxis, temperature control/hypothermia, and nutrition are provided. None are level I, 3 are level II, and 19 are level III. The Clinical Investigators responsible for these Guidelines also created a companion algorithm that supplements the recommendations with expert consensus where evidence is not available and organizes possible interventions into first and second tier utilization. The complete guideline document and supplemental appendices are available electronically (https://doi.org/10.1097/PCC.0000000000001735). The online documents contain summaries and evaluations of all the studies considered, including those from prior editions, and more detailed information on our methodology. New level II and level III evidence-based recommendations and an algorithm provide additional guidance for the development of local protocols to treat pediatric patients with severe traumatic brain injury. Our intention is to identify and institute a sustainable process to update these Guidelines as new evidence becomes available.

Predictors of extracorporeal membrane oxygenation support after surgery for adult congenital heart disease in children's hospitals.

OBJECTIVE: Adult congenital heart disease (ACHD) patients who undergo cardiac surgery are at risk for poor outcomes, including extracorporeal membrane oxygenation support (ECMO) and death. Prior studies have demonstrated risk factors for mortality, but have not fully examined risk factors for ECMO or death without ECMO (DWE). We sought to identify risk factors for ECMO and DWE in adults undergoing congenital heart surgery in tertiary care children's hospitals. DESIGN: All adults (≥18 years) undergoing congenital heart surgery in the Pediatric Health Information System (PHIS) database between 2003 and 2014 were included. Patients were classified into three groups: ECMO-free survival, requiring ECMO, and DWE. Univariate analyses were performed, and multinomial logistic regression models were constructed examining ECMO and DWE as independent outcomes. SETTING: Tertiary care children's hospitals. RESULTS: A total of 4665 adult patients underwent ACHD surgery in 39 children's hospitals with 51 (1.1%) patients requiring ECMO and 64 (1.4%) patients experiencing DWE. Of the 51 ECMO patients, 34 (67%) died. Increasing patient age, surgical complexity, diagnosis of single ventricle heart disease, preoperative hospitalization, and the presence of noncardiac complex chronic conditions (CCC) were risk factors for both outcomes. Additionally, low and medium hospital ACHD surgical volume was associated with an increased risk of DWE in comparison with ECMO. CONCLUSIONS: There are overlapping but separate risk factors for ECMO support and DWE among adults undergoing congenital heart surgery in pediatric hospitals.

Development of the Pediatric Extracorporeal Membrane Oxygenation Prediction Model for Risk-Adjusting Mortality.

OBJECTIVES: To develop a prognostic model for predicting mortality at time of extracorporeal membrane oxygenation initiation for children which is important for determining center-specific risk-adjusted outcomes. DESIGN: Multivariable logistic regression using a large national cohort of pediatric extracorporeal membrane oxygenation patients. SETTING: The ICUs of the eight tertiary care children's hospitals of the Collaborative Pediatric Critical Care Research Network. PATIENTS: Five-hundred fourteen children (< 19 yr old), enrolled with an initial extracorporeal membrane oxygenation run for any indication between January 2012 and September 2014. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: A total of 514 first extracorporeal membrane oxygenation runs were analyzed with an overall mortality of 45% (n = 232). Weighted logistic regression was used for model selection and internal validation was performed using cross validation. The variables included in the Pediatric Extracorporeal Membrane Oxygenation Prediction model were age (pre-term neonate, full-term neonate, infant, child, and adolescent), indication for extracorporeal membrane oxygenation (extracorporeal cardiopulmonary resuscitation, cardiac, or respiratory), meconium aspiration, congenital diaphragmatic hernia, documented blood stream infection, arterial blood pH, partial thromboplastin time, and international normalized ratio. The highest risk of mortality was associated with the presence of a documented blood stream infection (odds ratio, 5.26; CI, 1.90-14.57) followed by extracorporeal cardiopulmonary resuscitation (odds ratio, 4.36; CI, 2.23-8.51). The C-statistic was 0.75 (95% CI, 0.70-0.80). CONCLUSIONS: The Pediatric Extracorporeal Membrane Oxygenation Prediction model represents a model for predicting in-hospital mortality among children receiving extracorporeal membrane oxygenation support for any indication. Consequently, it holds promise as the first comprehensive pediatric extracorporeal membrane oxygenation risk stratification model which is important for benchmarking extracorporeal membrane oxygenation outcomes across many centers.

Pyr-GC/MS analysis of microplastics extracted from the stomach content of benthivore fish from the Texas Gulf Coast.

Fish ingestion of microplastic has been widely documented throughout freshwater, marine, and estuarine species. While numerous studies have quantified and characterized microplastic particles, analytical methods for polymer identification are limited. This study investigated the applicability of pyr-GC/MS for polymer identification of microplastics extracted from the stomach content of marine fish from the Texas Gulf Coast. A total of 43 microplastic particles were analyzed, inclusive of 30 fibers, 3 fragments, and 10 spheres. Polyvinyl chloride (PVC) and polyethylene terephthalate (PET) were the most commonly identified polymers (44.1%), followed by nylon (9.3%), silicone (2.3%), and epoxy resin (2.3%). Approximately 42% of samples could not be classified into a specific polymer class, due to a limited formation of pyrolytic products, low product abundance, or a lack of comparative standards. Diethyl phthalate, a known plasticizer, was found in 16.3% of the total sample, including PVC (14.3%), silicone (14.3%), nylon (14.3%), and sample unknowns (57.2%).