Novel Preoperative Risk Stratification Using Digital Phenotyping Applying a Scalable Machine-Learning Approach.

BACKGROUND: Classification of perioperative risk is important for patient care, resource allocation, and guiding shared decision-making. Using discriminative features from the electronic health record (EHR), machine-learning algorithms can create digital phenotypes among heterogenous populations, representing distinct patient subpopulations grouped by shared characteristics, from which we can personalize care, anticipate clinical care trajectories, and explore therapies. We hypothesized that digital phenotypes in preoperative settings are associated with postoperative adverse events including in-hospital and 30-day mortality, 30-day surgical redo, intensive care unit (ICU) admission, and hospital length of stay (LOS). METHODS: We identified all laminectomies, colectomies, and thoracic surgeries performed over a 9-year period from a large hospital system. Seventy-seven readily extractable preoperative features were first selected from clinical consensus, including demographics, medical history, and lab results. Three surgery-specific datasets were built and split into derivation and validation cohorts using chronological occurrence. Consensus k -means clustering was performed independently on each derivation cohort, from which phenotypes' characteristics were explored. Cluster assignments were used to train a random forest model to assign patient phenotypes in validation cohorts. We reconducted descriptive analyses on validation cohorts to confirm the similarity of patient characteristics with derivation cohorts, and quantified the association of each phenotype with postoperative adverse events by using the area under receiver operating characteristic curve (AUROC). We compared our approach to American Society of Anesthesiologists (ASA) alone and investigated a combination of our phenotypes with the ASA score. RESULTS: A total of 7251 patients met inclusion criteria, of which 2770 were held out in a validation dataset based on chronological occurrence. Using segmentation metrics and clinical consensus, 3 distinct phenotypes were created for each surgery. The main features used for segmentation included urgency of the procedure, preoperative LOS, age, and comorbidities. The most relevant characteristics varied for each of the 3 surgeries. Low-risk phenotype alpha was the most common (2039 of 2770, 74%), while high-risk phenotype gamma was the rarest (302 of 2770, 11%). Adverse outcomes progressively increased from phenotypes alpha to gamma, including 30-day mortality (0.3%, 2.1%, and 6.0%, respectively), in-hospital mortality (0.2%, 2.3%, and 7.3%), and prolonged hospital LOS (3.4%, 22.1%, and 25.8%). When combined with the ASA score, digital phenotypes achieved higher AUROC than the ASA score alone (hospital mortality: 0.91 vs 0.84; prolonged hospitalization: 0.80 vs 0.71). CONCLUSIONS: For 3 frequently performed surgeries, we identified 3 digital phenotypes. The typical profiles of each phenotype were described and could be used to anticipate adverse postoperative events.

Incidence of Intraoperative Vasoplegic Syndrome in Lung Transplantation.

OBJECTIVES: Severe hypotension and low systemic vascular resistance in the setting of adequate cardiac output, known as "vasoplegic syndrome" (VS), is a physiologic disturbance reported in 9% to 44% of cardiac surgery patients. Although this phenomenon is well-documented in cardiac surgery, there are few studies on its occurrence in lung transplantation. The goal of this study was to characterize the incidence of VS in lung transplantation, as well as identify associated risk factors and outcomes. DESIGN: Retrospective study of single and bilateral lung transplants from April 2013 to September 2021. SETTING: The study was conducted at an academic hospital. PARTICIPANTS: Patients ≥18 years of age who underwent lung transplantation. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: The authors defined VS as mean arterial pressure <65 mmHg, cardiac index ≥2.2 L/min/m2, and ≥30 minutes of vasopressor administration after organ reperfusion. The association between VS and risk factors or outcomes was assessed using t tests, Mann-Whitney U, and chi-square tests. The authors ran multivariate logistic regression models to determine factors independently associated with VS. The incidence of VS was 13.9% (CI 10.4%-18.4%). In the multivariate model, male sex (odds ratio 2.85, CI 1.07-7.58, p = 0.04) and cystic fibrosis (odds ratio 5.76, CI 1.43-23.09, p = 0.01) were associated with VS. CONCLUSIONS: The incidence of VS in lung transplantation is comparable to that of cardiac surgery. Interestingly, male sex and cystic fibrosis are strong risk factors. Identifying lung transplant recipients at increased risk of VS may be crucial to anticipating intraoperative complications.

Regional Anesthesia for Neonates.

Pain management in neonates and infants has many unique and important facets, particularly in former preterm infants. Untreated pain and surgical stress in neonates are associated with myriad negative sequelae, including deleterious inflammatory, autonomic, hormonal, metabolic, and neurologic effects. Meanwhile, opioid side effects are also very impactful and affect multiple systems and pathways, particularly in the neonatal and infant population. Regional anesthesia presents a unique opportunity to provide highly effective analgesia; prevent deleterious signaling cascade pathways within the endocrine, immune, and nervous systems from occurring; and create conditions to facilitate reduced reliance on opioids and other analgesics. In some cases, clinicians can completely avoid general anesthesia and systemic anesthetics. This review will discuss some of the unique aspects of pain management in neonates and infants and provide an overview of the different regional anesthetic options available, namely, spinal anesthesia, epidural anesthesia, and peripheral nerve blocks.

A Least Absolute Shrinkage and Selection Operator-Derived Predictive Model for Postoperative Respiratory Failure in a Heterogeneous Adult Elective Surgery Patient Population.

BACKGROUND: Postoperative respiratory failure (PRF) is associated with increased hospital charges and worse patient outcomes. Reliable prediction models can help to guide postoperative planning to optimize care, to guide resource allocation, and to foster shared decision-making with patients. RESEARCH QUESTION: Can a predictive model be developed to accurately identify patients at high risk of PRF? STUDY DESIGN AND METHODS: In this single-site proof-of-concept study, we used structured query language to extract, transform, and load electronic health record data from 23,999 consecutive adult patients admitted for elective surgery (2014-2021). Our primary outcome was PRF, defined as mechanical ventilation after surgery of > 48 h. Predictors of interest included demographics, comorbidities, and intraoperative factors. We used logistic regression to build a predictive model and the least absolute shrinkage and selection operator procedure to select variables and to estimate model coefficients. We evaluated model performance using optimism-corrected area under the receiver operating curve and area under the precision-recall curve and calculated sensitivity, specificity, positive and negative predictive values, and Brier scores. RESULTS: Two hundred twenty-five patients (0.94%) demonstrated PRF. The 18-variable predictive model included: operations on the cardiovascular, nervous, digestive, urinary, or musculoskeletal system; surgical specialty orthopedic (nonspine); Medicare or Medicaid (as the primary payer); race unknown; American Society of Anesthesiologists class ≥ III; BMI of 30 to 34.9 kg/m2; anesthesia duration (per hour); net fluid at end of the operation (per liter); median intraoperative FIO2, end title CO2, heart rate, and tidal volume; and intraoperative vasopressor medications. The optimism-corrected area under the receiver operating curve was 0.835 (95% CI,0.808-0.862) and the area under the precision-recall curve was 0.156 (95% CI, 0.105-0.203). INTERPRETATION: This single-center proof-of-concept study demonstrated that a structured query language extract, transform, and load process, based on readily available patient and intraoperative variables, can be used to develop a prediction model for PRF. This PRF prediction model is scalable for multicenter research. Clinical applications include decision support to guide postoperative level of care admission and treatment decisions.

Machine Learning, Deep Learning, and Closed Loop Devices-Anesthesia Delivery.

With the tremendous volume of data captured during surgeries and procedures, critical care, and pain management, the field of anesthesiology is uniquely suited for the application of machine learning, neural networks, and closed loop technologies. In the past several years, this area has expanded immensely in both interest and clinical applications. This article provides an overview of the basic tenets of machine learning, neural networks, and closed loop devices, with emphasis on the clinical applications of these technologies.

Acute Kidney Injury and Outcomes in Children Undergoing Noncardiac Surgery: A Propensity-Matched Analysis.

BACKGROUND: Acute kidney injury (AKI) has been well documented in adults after noncardiac surgery and demonstrated to be associated with adverse outcomes. We report the prevalence of AKI after pediatric noncardiac surgery, the perioperative factors associated with postoperative AKI, and the association of AKI with postoperative outcomes in children undergoing noncardiac surgery. METHODS: Patients ≤18 years of age who underwent noncardiac surgery with serum creatinine during the 12 months preceding surgery and no history of end-stage renal disease were included in this retrospective observational study at a single tertiary academic hospital. Patients were evaluated during the first 7 days after surgery for development of any stage of AKI, according to Kidney Disease: Improving Global Outcomes (KDIGO) criteria. Patients were classified into stages of KDIGO AKI for the purposes of describing prevalence. For further analyses, patients were grouped into those who developed any stage of AKI postoperatively and those who did not. Additionally, the time point at which each patient was first diagnosed with stage I AKI or greater was also assessed. Pre-, intra-, and postoperative factors were compared between the 2 groups. A multivariable Cox proportional hazards regression model was created to examine the time to first diagnosis of AKI using all nonredundant covariates. Analysis of the association of AKI with postoperative outcomes, mortality and 30-day readmission, was undertaken utilizing propensity score-matched controls and a multivariable Cox proportional hazards regression model. RESULTS: A total of 25,203 cases between 2013 and 2018 occurred; 8924 met inclusion criteria. Among this cohort, the observed prevalence of postoperative AKI was 3.2% (288 cases; confidence interval [CI], 2.9-3.6). The multivariable Cox model showed American Society of Anesthesiologists (ASA) status to be associated with the development of postoperative AKI. Several other factors, including intraoperative hypotension, were significantly associated with postoperative AKI in univariable models but found not to be significantly associated after adjustment. The multivariable Cox analyses with propensity-matched controls showed an estimated hazard ratio of 3.28 for mortality (CI, 1.71-6.32, P < .001) and 1.55 for 30-day readmission (CI, 1.08-2.23, P = .018) in children who developed AKI versus those who did not. CONCLUSIONS: In children undergoing noncardiac surgery, postoperative AKI occurred in 3.2% of patients. Several factors, including intraoperative hypotension, were significantly associated with postoperative AKI in univariable models. After adjustment, only ASA status was found to be significantly associated with AKI in children after noncardiac surgery. Postoperative AKI was found to be associated with significantly higher rates of mortality and 30-day readmission in multivariable, time-varying models with propensity-matched controls.

Preoperative Anemia as a Risk Factor for Postoperative Outcomes in Patients Undergoing Lung Transplantation.

OBJECTIVES: The aim of this study was to evaluate the effect of preoperative anemia on early postoperative outcomes in a population of patients undergoing lung transplantation. DESIGN: Single-center retrospective study of lung transplantation recipients between April 2013 and June 2018. The primary outcome was hospital length of stay. SETTING: Ronald Reagan UCLA Medical Center, Los Angeles, CA, a tertiary academic medical center. PARTICIPANTS: Patients presenting from home for lung transplantation. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: A total of 435 patients underwent lung transplantation during the study period. After exclusion, 342 were included in the analysis. The prevalence of preoperative anemia was 54% (n = 183); however, only 11% of anemic patients received treatment for anemia before transplantation. Multivariate regression analysis indicated that lower hemoglobin levels were associated with longer hospital lengths of stay (p = 0.049). Preoperative anemia also was independently associated with an increased risk for redo surgery for bleeding (odds ratio 4.89; p = 0.007). No association between preoperative anemia and any of the other postoperative outcomes examined was found. CONCLUSIONS: Preoperative anemia in patients undergoing lung transplantation is undertreated and independently associated with an increased risk for redo surgery for bleeding. Additional studies regarding reasons for this association and effect of treatment are necessary to improve outcomes.

Preoperative Diastolic Dysfunction and Postoperative Outcomes after Noncardiac Surgery.

OBJECTIVE: To determine if diastolic dysfunction is independently associated with increased mortality, acute kidney injury, and hospital length of stay after noncardiac surgery. DESIGN: Retrospective observational cohort. SETTING: Academic referral center. PARTICIPANTS: All patients undergoing noncardiac and nonliver-transplant surgeries at University of California - Los Angeles between April 2013 and October 2017, who also had transthoracic echocardiograms performed within 6 months preceding their procedures. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: Patients' demographic, comorbidity, echocardiographic, and perioperative data were queried from the electronic health record. Diastolic dysfunction was graded by automated application of 2016 American Society of Echocardiography guidelines to queried echocardiographic measurements. During the study period, 12,871 eligible records were identified, of which 7,312 represented unique procedures with complete information. Twenty-three percent of patients had echocardiographic evidence of diastolic dysfunction (7.0% grade 1, 8.1% grade 2, 0.6% grade 3, and 7.5% nonspecific). Patients with diastolic dysfunction tended to be older and have higher American Society of Anesthesiologists scores with more comorbidities. Overall, 166 patients (2.3%) experienced an in-hospital death. After adjustment for potentially confounding variables, diastolic dysfunction was not significantly associated with increased in-hospital mortality, acute kidney injury, or hospital length of stay. CONCLUSIONS: Diastolic dysfunction does not appear to be associated with increased in-hospital mortality, acute kidney injury, or hospital length of stay in a cohort of noncardiac surgical patients at an academic medical center. These results highlight uncertainties in perioperative risk determination.

BayesCCE: a Bayesian framework for estimating cell-type composition from DNA methylation without the need for methylation reference.

We introduce a Bayesian semi-supervised method for estimating cell counts from DNA methylation by leveraging an easily obtainable prior knowledge on the cell-type composition distribution of the studied tissue. We show mathematically and empirically that alternative methods which attempt to infer cell counts without methylation reference only capture linear combinations of cell counts rather than provide one component per cell type. Our approach allows the construction of components such that each component corresponds to a single cell type, and provides a new opportunity to investigate cell compositions in genomic studies of tissues for which it was not possible before.