Search

Editor’s Perspective What We Already Know about This Topic What This Article Tells Us That Is New Background Hypotension is a risk factor for adverse perioperative outcomes. Machine-learning methods allow large amounts of data for development of robust predictive analytics. The authors hypothesized that machine-learning methods can provide prediction for the risk of postinduction hypotension. Methods Data was extracted from the electronic health record of a single quaternary care center from November 2015 to May 2016 for patients over age 12 that underwent general anesthesia, without procedure exclusions. Multiple supervised machine-learning classification techniques were attempted, with postinduction hypotension (mean arterial pressure less than 55 mmHg within 10 min of induction by any measurement) as primary outcome, and preoperative medications, medical comorbidities, induction medications, and intraoperative vital signs as features. Discrimination was assessed using cross-validated area under the receiver operating characteristic curve. The best performing model was tuned and final performance assessed using split-set validation. Results Out of 13,323 cases, 1,185 (8.9%) experienced postinduction hypotension. Area under the receiver operating characteristic curve using logistic regression was 0.71 (95% CI, 0.70 to 0.72), support vector machines was 0.63 (95% CI, 0.58 to 0.60), naive Bayes was 0.69 (95% CI, 0.67 to 0.69), k-nearest neighbor was 0.64 (95% CI, 0.63 to 0.65), linear discriminant analysis was 0.72 (95% CI, 0.71 to 0.73), random forest was 0.74 (95% CI, 0.73 to 0.75), neural nets 0.71 (95% CI, 0.69 to 0.71), and gradient boosting machine 0.76 (95% CI, 0.75 to 0.77). Test set area for the gradient boosting machine was 0.74 (95% CI, 0.72 to 0.77). Conclusions The success of this technique in predicting postinduction hypotension demonstrates feasibility of machine-learning models for predictive analytics in the field of anesthesiology, with performance dependent on model selection and appropriate tuning.

Background As specialists in perioperative medicine, anesthesiologists are well equipped to design and oversee the preoperative patient preparation process; however, the impact of an anesthesiologist-led preoperative evaluation clinic (PEC) on clinical outcomes has yet to be fully elucidated. The authors compared the incidence of in-hospital postoperative mortality in patients who had been evaluated in their institution’s PEC before elective surgery to the incidence in patients who had elective surgery without being seen in the PEC. Methods A retrospective review of an administrative database was performed. There were 46 deaths from 64,418 patients (0.07%): 22 from 35,535 patients (0.06%) seen in PEC and 24 from 28,883 patients (0.08%) not seen in PEC. After propensity score matching, there were 13,964 patients within each matched set; there were 34 deaths (0.1%). There were 11 deaths from 13,964 (0.08%) patients seen in PEC and 23 deaths from 13,964 (0.16%) patients not seen in PEC. A subanalysis to assess the effect of a PEC visit on deaths as a result of failure to rescue (FTR) was also performed. Results A visit to PEC was associated with a reduction in mortality (odds ratio, 0.48; 95% CI, 0.22 to 0.96, P = 0.04) by comparison of the matched cohorts. The FTR subanalysis suggested that the proportion of deaths attributable to an unanticipated surgical complication was not significantly different between the two groups (P = 0.141). Conclusions An in-person assessment at the PEC was associated with a reduction in in-hospital mortality. It was difficult to draw conclusions about whether a difference exists in the proportion of FTR deaths between the two cohorts due to small sample size.

Background The authors sought to identify the incidence, risk factors, and mortality impact of acute kidney injury (AKI) after general surgery using a large and representative national clinical data set. Methods The 2005-2006 American College of Surgeons-National Surgical Quality Improvement Program participant use data file is a compilation of outcome data from general surgery procedures performed in 121 US medical centers. The primary outcome was AKI within 30 days, defined as an increase in serum creatinine of at least 2 mg/dl or acute renal failure necessitating dialysis. A variety of patient comorbidities and operative characteristics were evaluated as possible predictors of AKI. A logistic regression full model fit was used to create an AKI model and risk index. Thirty-day mortality among patients with and without AKI was compared. Results Of 152,244 operations reviewed, 75,952 met the inclusion criteria, and 762 (1.0%) were complicated by AKI. The authors identified 11 independent preoperative predictors: age 56 yr or older, male sex, emergency surgery, intraperitoneal surgery, diabetes mellitus necessitating oral therapy, diabetes mellitus necessitating insulin therapy, active congestive heart failure, ascites, hypertension, mild preoperative renal insufficiency, and moderate preoperative renal insufficiency. The c statistic for a simplified risk index was 0.80 in the derivation and validation cohorts. Class V patients (six or more risk factors) had a 9% incidence of AKI. Overall, patients experiencing AKI had an eightfold increase in 30-day mortality. Conclusions Approximately 1% of general surgery cases are complicated by AKI. The authors have developed a robust risk index based on easily identified preoperative comorbidities and patient characteristics.

The authors sought to identify the incidence, risk factors, and mortality impact of acute kidney injury (AKI) after general surgery using a large and representative national clinical data set.The 2005-2006 American College of Surgeons-National Surgical Quality Improvement Program participant use data file is a compilation of outcome data from general surgery procedures performed in 121 US medical centers. The primary outcome was AKI within 30 days, defined as an increase in serum creatinine of at least 2 mg/dl or acute renal failure necessitating dialysis. A variety of patient comorbidities and operative characteristics were evaluated as possible predictors of AKI. A logistic regression full model fit was used to create an AKI model and risk index. Thirty-day mortality among patients with and without AKI was compared.Of 152,244 operations reviewed, 75,952 met the inclusion criteria, and 762 (1.0%) were complicated by AKI. The authors identified 11 independent preoperative predictors: age 56 yr or older, male sex, emergency surgery, intraperitoneal surgery, diabetes mellitus necessitating oral therapy, diabetes mellitus necessitating insulin therapy, active congestive heart failure, ascites, hypertension, mild preoperative renal insufficiency, and moderate preoperative renal insufficiency. The c statistic for a simplified risk index was 0.80 in the derivation and validation cohorts. Class V patients (six or more risk factors) had a 9% incidence of AKI. Overall, patients experiencing AKI had an eightfold increase in 30-day mortality.Approximately 1% of general surgery cases are complicated by AKI. The authors have developed a robust risk index based on easily identified preoperative comorbidities and patient characteristics.

Background The authors sought to determine the incidence and risk factors for perioperative cardiac adverse events (CAEs) after noncardiac surgery using detailed preoperative and intraoperative hemodynamic data. Methods The authors conducted a prospective observational study at a single university hospital from 2002 to 2006. All American College of Surgeons-National Surgical Quality Improvement Program patients undergoing general, vascular, and urological surgery were included. The CAE outcome definition included cardiac arrest, non-ST elevation myocardial infarction, Q-wave myocardial infarction, and new clinically significant cardiac dysrhythmia within the first 30 postoperative days. Results Four years of data demonstrated that of 7,740 noncardiac operations, 83 patients (1.1%) experienced a CAE within 30 days. Nine independent predictors were identified (P < or = 0.05): age > or = 68, body mass index > or = 30, emergent surgery, previous coronary intervention or cardiac surgery, active congestive heart failure, cerebrovascular disease, hypertension, operative duration > or = 3.8 h, and the administration of 1 or more units of packed red blood cells intraoperatively. The c-statistic of this model was 0.81 +/- 0.02. Univariate analysis demonstrated that high-risk patients experiencing a CAE were more likely to experience an episode of mean arterial pressure < 50 mmHg (6% vs. 24%, P = 0.02), experience an episode of 40% decrease in mean arterial pressure (26% vs. 53%, P = 0.01), and an episode of heart rate > 100 (22% vs. 34%, P = 0.05). Conclusions In comparison with current risk stratification indices, the inclusion of intraoperative elements improves the ability to predict a perioperative CAE after noncardiac surgery.

Background The authors investigated the incidence and risk factors for postoperative acute renal failure after major noncardiac surgery among patients with previously normal renal function. Methods Adult patients undergoing major noncardiac surgery with a preoperative calculated creatinine clearance of 80 ml/min or greater were included in a prospective, observational study at a single tertiary care university hospital. Patients were followed for the development of acute renal failure (defined as a calculated creatinine clearance of 50 ml/min or less) within the first 7 postoperative days. Patient preoperative characteristics and intraoperative anesthetic management were evaluated for associations with acute renal failure. Thirty-day, 60-day, and 1-yr all-cause mortality was also evaluated. Results A total of 65,043 cases between 2003 and 2006 were reviewed. Of these, 15,102 patients met the inclusion criteria; 121 patients developed acute renal failure (0.8%), and 14 required renal replacement therapy (0.1%). Seven independent preoperative predictors were identified (P < 0.05): age, emergent surgery, liver disease, body mass index, high-risk surgery, peripheral vascular occlusive disease, and chronic obstructive pulmonary disease necessitating chronic bronchodilator therapy. Several intraoperative management variables were independent predictors of acute renal failure: total vasopressor dose administered, use of a vasopressor infusion, and diuretic administration. Acute renal failure was associated with increased 30-day, 60-day, and 1-yr all-cause mortality. Conclusions Several preoperative predictors previously reported to be associated with acute renal failure after cardiac surgery were also found to be associated with acute renal failure after noncardiac surgery. The use of vasopressor and diuretics is also associated with acute renal failure.

Background The incidence of acute lung injury (ALI) in hypoxic patients undergoing surgery is currently unknown. Previous studies have identified lung protective ventilation strategies that are beneficial in the treatment of ALI. The authors sought to determine the incidence and examine the use of lung protective ventilation strategies in patients receiving anesthetics with a known history of ALI. Methods The ventilation parameters that were used in all patients were reviewed, with an average preoperative PaO₂/Fio₂ [corrected] ratio of ≤ 300 between January 1, 2005 and July 1, 2009. This dataset was then merged with a dataset of patients screened for ALI. The median tidal volume, positive end-expiratory pressure, peak inspiratory pressures, fraction inhaled oxygen, oxygen saturation, and tidal volumes were compared between groups. Results A total of 1,286 patients met criteria for inclusion; 242 had a diagnosis of ALI preoperatively. Comparison of patients with ALI versus those without ALI found statistically yet clinically insignificant differences between the ventilation strategies between the groups in peak inspiratory pressures and positive end-expiratory pressure but no other category. The tidal volumes in cc/kg predicted body weight were approximately 8.7 in both groups. Peak inspiratory pressures were found to be 27.87 cm H₂O on average in the non-ALI group and 29.2 in the ALI group. Conclusion Similar ventilation strategies are used between patients with ALI and those without ALI. These findings suggest that anesthesiologists are not using lung protective ventilation strategies when ventilating patients with low PaO₂/Fio₂ [corrected] ratios and ALI, and instead are treating hypoxia and ALI with higher concentrations of oxygen and peak pressures.