Public Health Informatics and the Perioperative Physician: Looking to the Future.

The role of informatics in public health has increased over the past few decades, and the coronavirus disease 2019 (COVID-19) pandemic has underscored the critical importance of aggregated, multicenter, high-quality, near-real-time data to inform decision-making by physicians, hospital systems, and governments. Given the impact of the pandemic on perioperative and critical care services (eg, elective procedure delays; information sharing related to interventions in critically ill patients; regional bed-management under crisis conditions), anesthesiologists must recognize and advocate for improved informatic frameworks in their local environments. Most anesthesiologists receive little formal training in public health informatics (PHI) during clinical residency or through continuing medical education. The COVID-19 pandemic demonstrated that this knowledge gap represents a missed opportunity for our specialty to participate in informatics-related, public health-oriented clinical care and policy decision-making. This article briefly outlines the background of PHI, its relevance to perioperative care, and conceives intersections with PHI that could evolve over the next quarter century.

Dose-dependent relationship between intra-procedural hypoxaemia or hypocapnia and postoperative delirium in older patients.

BACKGROUND: Previous studies indicated an association between impaired cerebral perfusion and post-procedural neurological disorders. We investigated whether intra-procedural hypoxaemia or hypocapnia are associated with delirium after surgery. METHODS: Inpatients ≥60 yr of age undergoing anaesthesia for surgical or interventional procedures between 2009 and 2020 at an academic healthcare network in the USA (Massachusetts) were included in this hospital registry study. The primary exposure was intra-procedural hypoxaemia, defined as peripheral oxygen saturation <90% for >2 cohering min. The co-primary exposure was hypocapnia during general anaesthesia, defined as end-tidal carbon dioxide pressure ≤25 mm Hg for >5 cohering min. The primary outcome was delirium within 7 days after surgery. RESULTS: Of 71 717 included patients, 1702 (2.4%) developed postoperative delirium, and hypoxaemia was detected in 2532 (3.5%). Of 42 894 patients undergoing general anaesthesia, 532 (1.2%) experienced hypocapnia. The occurrence of either hypoxaemia (adjusted odds ratio [ORadj]=1.71; 95% confidence interval [CI], 1.40-2.07; P<0.001) or hypocapnia (ORadj=1.77; 95% CI, 1.30-2.41; P<0.001) was associated with a higher risk of delirium within 7 days. Both associations were dependent on the magnitude, and increased with event duration (ORadj=1.03; 95% CI, 1.02-1.04; P<0.001 and ORadj=1.01; 95% CI, 1.00-1.01; P=0.005, for each minute increase in the longest continuous episode, respectively). There was no association between occurrence of hypercapnia and postoperative delirium (ORadj=1.24; 95% CI, 0.90-1.71; P=0.181). CONCLUSIONS: Intra-procedural hypoxaemia and hypocapnia were dose-dependently associated with a higher risk of postoperative delirium. These findings support maintaining normal gas exchange to avoid postoperative neurological disorders.

Association Between Intraoperative Arterial Hypotension and Postoperative Delirium After Noncardiac Surgery: A Retrospective Multicenter Cohort Study.

BACKGROUND: It is unclear whether intraoperative arterial hypotension is associated with postoperative delirium. We hypothesized that intraoperative hypotension within a range frequently observed in clinical practice is associated with increased odds of delirium after surgery. METHODS: Adult noncardiac surgical patients undergoing general anesthesia at 2 academic medical centers between 2005 and 2017 were included in this retrospective cohort study. The primary exposure was intraoperative hypotension, defined as the cumulative duration of an intraoperative mean arterial pressure (MAP) <55 mm Hg, categorized into and short (<15 minutes; median [interquartile range {IQR}], 2 [1-4] minutes) and prolonged (≥15 minutes; median [IQR], 21 [17-31] minutes) durations of intraoperative hypotension. The primary outcome was a new diagnosis of delirium within 30 days after surgery. In secondary analyses, we assessed the association between a MAP decrease of >30% from baseline and postoperative delirium. Multivariable logistic regression adjusted for patient- and procedure-related factors, including demographics, comorbidities, and markers of procedural severity, was used. RESULTS: Among 316,717 included surgical patients, 2183 (0.7%) were diagnosed with delirium within 30 days after surgery; 41.7% and 2.6% of patients had a MAP <55 mm Hg for a short and a prolonged duration, respectively. A MAP <55 mm Hg was associated with postoperative delirium compared to no hypotension (short duration of MAP <55 mm Hg: adjusted odds ratio [ORadj], 1.22; 95% confidence interval [CI], 1.11-1.33; P < .001 and prolonged duration of MAP <55 mm Hg: ORadj, 1.57; 95% CI, 1.27-1.94; P < .001). Compared to a short duration of a MAP <55 mm Hg, a prolonged duration of a MAP <55 mm Hg was associated with greater odds of postoperative delirium (ORadj, 1.29; 95% CI, 1.05-1.58; P = .016). The association between intraoperative hypotension and postoperative delirium was duration-dependent (ORadj for every 10 cumulative minutes of MAP <55 mm Hg: 1.06; 95% CI, 1.02-1.09; P =.001) and magnified in patients who underwent surgeries of longer duration (P for interaction = .046; MAP <55 mm Hg versus no MAP <55 mm Hg in patients undergoing surgery of >3 hours: ORadj, 1.40; 95% CI, 1.23-1.61; P < .001). A MAP decrease of >30% from baseline was not associated with postoperative delirium compared to no hypotension, also when additionally adjusted for the cumulative duration of a MAP <55 mm Hg (short duration of MAP decrease >30%: ORadj, 1.13; 95% CI, 0.91-1.40; P = .262 and prolonged duration of MAP decrease >30%: ORadj, 1.19; 95% CI, 0.95-1.49; P = .141). CONCLUSIONS: In patients undergoing noncardiac surgery, a MAP <55 mm Hg was associated with a duration-dependent increase in odds of postoperative delirium. This association was magnified in patients who underwent surgery of long duration.

Effect of Intraoperative Arterial Hypotension on the Risk of Perioperative Stroke After Noncardiac Surgery: A Retrospective Multicenter Cohort Study.

BACKGROUND: Intraoperative cerebral blood flow is mainly determined by cerebral perfusion pressure and cerebral autoregulation of vasomotor tone. About 1% of patients undergoing noncardiac surgery develop ischemic stroke. We hypothesized that intraoperative hypotension within a range frequently observed in clinical practice is associated with an increased risk of perioperative ischemic stroke within 7 days after surgery. METHODS: Adult noncardiac surgical patients undergoing general anesthesia at Beth Israel Deaconess Medical Center and Massachusetts General Hospital between 2005 and 2017 were included in this retrospective cohort study. The primary exposure was intraoperative hypotension, defined as a decrease in mean arterial pressure (MAP) below 55 mm Hg, categorized into no intraoperative hypotension, short (<15 minutes, median [interquartile range {IQR}], 2 minutes [1-5 minutes]) and prolonged (≥15 minutes, median [IQR], 21 minutes [17-31 minutes]) durations. The primary outcome was a new diagnosis of early perioperative ischemic stroke within 7 days after surgery. In secondary analyses, we assessed the effect of a MAP decrease by >30% from baseline on perioperative stroke. Analyses were adjusted for the preoperative STRoke After Surgery (STRAS) prediction score, work relative value units, and duration of surgery. RESULTS: Among 358,391 included patients, a total of 1553 (0.4%) experienced an early perioperative ischemic stroke. About 42% and 3% of patients had a MAP of below 55 mm Hg for a short and a prolonged duration, and 49% and 29% had a MAP decrease by >30% from baseline for a short and a prolonged duration, respectively. In an adjusted analysis, neither a MAP <55 mm Hg (short duration: adjusted odds ratio [ORadj], 0.95; 95% confidence interval [CI], 0.85-1.07; P = .417 and prolonged duration: ORadj, 1.18; 95% CI, 0.91-1.55; P = .220) nor a MAP decrease >30% (short duration: ORadj, 0.97; 95% CI, 0.67-1.42; P = .883 and prolonged duration: ORadj, 1.30; 95% CI, 0.89-1.90; P = .176) was associated with early perioperative stroke. A high a priori stroke risk quantified based on preoperatively available risk factors (STRAS prediction score) was associated with longer intraoperative hypotension (adjusted incidence rate ratio, 1.04; 95% CI, 1.04-1.05; P < .001 per 5 points of the STRAS prediction score). CONCLUSIONS: This study found no evidence to conclude that intraoperative hypotension within the range studied was associated with early perioperative stroke within 7 days after surgery. These findings emphasize the importance of perioperative cerebral blood flow autoregulation to prevent ischemic stroke.

Adverse Outcomes Associated With Delaying or Withholding ß-Blockers After Cardiac Surgery: A Retrospective Single-Center Cohort Study.

BACKGROUND: Ideal timing of postoperative ß-blockers is unclear. We hypothesized that patients who do not receive ß-blockers immediately after cardiac surgery would have increased in-hospital mortality (primary outcome) and postoperative hemodynamic, pulmonary, neurologic, or respiratory complications (secondary outcomes). METHODS: We performed a retrospective cohort study evaluating patients who underwent cardiac surgery at our institution from January 1, 2013 to September 30, 2017. We compared outcomes between patients who received ß-blockers by postoperative day (POD) 5 with outcomes in patients who did not receive ß-blockers at any time or received them after POD 5. Inverse probability of treatment weighting was used to minimize confounding. Univariate logistic regression analyses were performed on the weighted sets using absent or delayed ß-blockers as the independent variable and each outcome as dependent variables in separate analyses. A secondary analysis was performed in patients prescribed preoperative ß-blockers. E-values were calculated for significant outcomes. RESULTS: All results were confounder adjusted. Among patients presenting for cardiac surgery, not receiving ß-blockers by POD 5 or at any time was not associated with the primary outcome in-hospital mortality, estimated odds ratio (OR; 99.5% confidence interval [CI]) of 1.6 (0.49-5.1), P = .28. Not receiving ß-blockers by POD 5 or at any time was associated with postoperative atrial fibrillation, estimated OR (99.5% CI) of 1.5 (1.1-2.1), P < .001, and pulmonary complications, estimated OR (99.5% CI) of 3.0 (1.8-5.2), P < .001. E-values were 2.4 for postoperative atrial fibrillation and 5.6 for pulmonary complications. Among patients presenting for cardiac surgery taking preoperative ß-blockers, not receiving ß-blockers by POD 5 or at any time was not associated with the primary outcome mortality, with estimated OR (99.5% CI) of 1.3 (0.43-4.1), P = .63. In this subset, not receiving ß-blockers by POD 5 or at any time was associated with increased adjusted ORs of postoperative atrial fibrillation (OR = 1.6; 99.5% CI, 1.1-2.4; P < .001) and postoperative pulmonary complications (OR = 2.8; 99.5% CI, 1.6-5.2; P < .001). Here, e-values were 2.7 for postoperative atrial fibrillation and 5.1 for pulmonary complications. For the sensitivity analyses for secondary outcomes, exposure and outcome periods overlap. Outcomes may have occurred before or after postoperative ß-blocker administration. CONCLUSIONS: Among patients who undergo cardiac surgery, not receiving postoperative ß-blockers within the first 5 days after cardiac surgery or at any time is not associated with in-hospital mortality and is associated with, but may not necessarily cause, postoperative atrial fibrillation and pulmonary complications.

Severity and duration of hypoxemia during outpatient endoscopy in obese patients: a retrospective cohort study.

PURPOSE: We sought to quantify the severity and duration of hypoxemic events in morbidly obese patients during outpatient endoscopy procedures performed under deep sedation. METHODS: This was a retrospective cohort study using intraprocedural pulse oximetry readings from 11,595 American Society of Anesthesiologists physical status score I-III adult patients who underwent deep sedation for elective endoscopy at free standing ambulatory centres between June 2015 and June 2016. Unadjusted and risk-adjusted logistic regression analyses explored the relationship between increasing categories of body mass index (BMI) and intraoperative hypoxemia, severe hypoxemia, and prolonged hypoxemia. RESULTS: Hypoxemia occurred in 600 (13%) patients with normal BMI, 314 (18%) with class I obesity, 159 (27%) with class II obesity, and 24 (19%) with class III obesity. Adjusted odds ratio (AOR) for any occurrence of intraoperative hypoxemia increased from 1.61 (95% confidence interval [CI], 1.35 to 1.90; P < 0.001) in the class I obesity group to 2.61 (95% CI, 2.05 to 3.30; P < 0.001) in patients with class II obesity, when compared with patients with normal BMI. Adjusted odds ratio of severe hypoxemia were significant in the class I obesity group (AOR, 1.47; 95% CI, 1.13 to 1.89; P = 0.003), and the class II obesity group (AOR, 2.59; 95% CI, 1.86 to 3.57; P < 0.001). Adjusted odds ratio of prolonged hypoxemia increased with each category of BMI from 1.97 (95% CI, 1.08 to 3.69) in the overweight group to 9.20 (95% CI, 4.74 to 18.03) in patients with class III obesity. CONCLUSIONS: The incidence of severe hypoxemia increased nearly six-fold in obese patients and 8.5-fold in class III obese patients when compared with those of normal BMI. Intravenous fentanyl was associated with intraoperative hypoxemia independent of BMI. Patients who represent the highest risk for hypoxia should be stratified to procedure locations with adequate resources for the safest care.

RéSUMé: OBJECTIF: Nous avons tenté de quantifier la gravité et la durée des complications hypoxémiques chez les patients obèses morbides pendant les interventions endoscopiques ambulatoires réalisées sous sédation profonde. MéTHODE: Nous avons réalisé une étude de cohorte rétrospective en nous fondant sur les relevés d'oxymétrie de pouls intra-procéduraux de 11 595 patients adultes de statut physique ASA (American Society of Anesthesiologists) I-III ayant subi une sédation profonde pour une endoscopie non urgente dans des centres ambulatoires indépendants entre juin 2015 et juin 2016. Les analyses de régression logistique non ajustées et ajustées en fonction du risque ont examiné la relation entre des catégories croissantes d'indice de masse corporelle (IMC) et l'hypoxémie, l'hypoxémie sévère et l'hypoxémie prolongée peropératoires. RéSULTATS: L'hypoxémie a touché 600 (13 %) patients ayant un IMC normal, 314 (18 %) patients souffrant d'une obésité de classe I, 159 (27 %) patients avec une obésité de classe II, et 24 (19 %) patients souffrant d'obésité de classe III. Le rapport de cotes ajusté (RCA) pour tout épisode d'hypoxémie peropératoire a augmenté de 1,61 (intervalle de confiance [IC] 95 %, 1,35 à 1,90; P < 0,001) dans le groupe obésité de classe I à 2,61 (IC 95 %, 2,05 à 3,30; P < 0,001) chez les patients présentant une obésité de classe II, par rapport aux patients avec un IMC normal. Les rapports de cotes ajustés pour l'hypoxémie sévère étaient significatifs dans le groupe de patients obèses de classe I (RCA, 1,47; IC 95 %, 1,13 à 1,89; P = 0,003) et dans le groupe de patients obèses de classe II (RCA, 2,59; IC 95 %, 1,86 à 3,57; P < 0,001). Les rapports de cotes ajustés pour l'hypoxémie prolongée ont augmenté avec chaque catégorie d'IMC, passant de 1,97 (IC 95 %, 1,08 à 3,69) dans le groupe en surcharge pondérale à 9,20 (IC 95 %, 4,74 à 18,03) chez les patients atteints d'obésité de classe III. CONCLUSION: L'incidence d'hypoxémie sévère a augmenté de près de six fois chez les patients obèses et de 8,5 fois chez les patients obèses de classe III par rapport aux patients ayant un IMC normal. L'administration intraveineuse de fentanyl était associée à une hypoxémie peropératoire indépendante de l'IMC. Les patients qui présentent le risque le plus élevé d'hypoxie devraient être stratifiés à être pris en charge dans des établissements disposant des ressources nécessaires pour offrir les soins les plus sécuritaires possibles.

Relationship Between Preoperative Antidepressant and Antianxiety Medications and Postoperative Hospital Length of Stay.

BACKGROUND: Patients on antidepressant or antianxiety medications often have complex perioperative courses due to difficult pain management, altered coping mechanisms, or medication-related issues. This study examined the relationship between preoperative antidepressants and antianxiety medications on postoperative hospital length of stay while controlling for confounding variables. METHODS: From an administrative database of 48,435 adult patients who underwent noncardiac surgery from 2011 to 2014 at a single, large urban academic institution, multivariable zero-truncated negative binomial regression analyses controlling for age, sex, medical comorbidities, and surgical type were performed to assess whether preoperative exposure to antidepressant or antianxiety medication use was associated with postoperative hospital length of stay. RESULTS: There were 5111 (10.5%) patients on antidepressants and 4912 (10.1%) patients on antianxiety medications. The median length of stay was 3 days (interquartile range = 2-6). After controlling for confounding variables, preoperative antidepressant medication was associated with increased length of stay with an incidence rate ratio of 1.04 (99% confidence interval, 1.0-1.08, P < .001) and antianxiety medication with an incidence rate ratio of 1.1 (99% confidence interval, 1.06-1.14; P < .001). CONCLUSIONS: The association between antidepressants or antianxiety medications and increased postoperative length of stay suggests that these patients may require greater attention in the perioperative period to hasten recovery, which may involve integrating preoperative counseling, postoperative psychiatric consults, or holistic recovery approaches into enhanced recovery protocols.

Preoperative Long-Acting Opioid Use Is Associated with Increased Length of Stay and Readmission Rates After Elective Surgeries.

Objectives To compare postoperative outcomes in patients prescribed long-acting opioids vs opioid-naïve patients who underwent elective noncardiac surgeries. Design Retrospective cohort study. Setting Single urban academic institution. Methods and Subjects We retrospectively compared postoperative outcomes in long-acting opioid users vs opioid-naïve patients who underwent elective noncardiac surgeries. Inpatient and ambulatory surgery cohorts were separately analyzed. Preoperative medication lists were queried for the presence of long-acting opioids or absence of opioids. Multivariable logistic regression was performed to analyze the impact of long-acting opioid use on readmission rate, respiratory failure, and adverse cardiac events. Multivariable zero-truncated negative binomial regression was used to examine length of stay. Results After exclusions, there were 93,644 adult patients in the study population, 23,605 of whom underwent inpatient surgeries and 70,039 of whom underwent ambulatory surgeries. After adjusting for potential confounders and inpatient surgeries, preoperative long-acting opioid use was associated with increased risk of prolonged length of stay (incidence rate ratio = 1.1, 99% confidence interval [CI] = 1.0-1.2, P < 0.01) but not readmission. For ambulatory surgeries, preoperative long-acting opioid use was associated with increased risk of all-cause as well as pain-related readmission (odds ratio [OR] = 2.1, 99% CI = 1.5-2.9, P < 0.001; OR = 2.0, 99% CI = 0.85-4.2, P = 0.02, respectively). There were no significant differences for respiratory failure or adverse cardiac events. Conclusions The use of preoperative long-acting opioids was associated with prolonged length of stay for inpatient surgeries and increased risk of all-cause and pain-related readmission for ambulatory surgeries. Timely interventions for patients on preoperative long-acting opioids may be needed to improve these outcomes.

Supervised Machine-learning Predictive Analytics for Prediction of Postinduction Hypotension.

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.

A retrospective study of opioid prescribing patterns at hospital discharge in surgical patients with obstructive sleep apnea.

PURPOSE: Obstructive sleep apnea (OSA) is a risk factor for complications with postoperative opioid use, and in those patients with known or suspected OSA, minimization of postoperative opioids is recommended. We hypothesize that despite these recommendations, surgical patients with known or suspected OSA are prescribed postoperative opioids at hospital discharge at similar doses to those without OSA. METHODS: This was a retrospective analysis of the electronic health records of surgical patients from 1 November 2016 to 30 April 2017 at a single academic institution. Patients with a known diagnosis of OSA or a STOP-Bang score ≥ 5 were compared with those without OSA for the amount of postoperative discharge opioid medication using multivariable linear regression. RESULTS: Of the 17,671 patients analyzed, 1,692 (9.6%) had known or suspected OSA with 1,450 (86%) of these patients discharged on opioid medications. Of the 15,979 patients without OSA, 12,273 (77%) were discharged on opioid medications. The total median [interquartile range (IQR)] oral morphine equivalents (OME) for all patients was 150 [0-338] mg and for patients with known or suspected OSA was 160 [0-450] mg, an unadjusted comparison showing an 18% difference in OME (95% confidence interval [CI], 3% to 35%; P = 0.02). The analysis, after adjusting for confounders, showed no significant difference in the amount of opioids prescribed to OSA or non-OSA patients (8% difference in total OME; 95% CI, -6% to 25%; P = 0.26). CONCLUSION: This study shows that surgical patients at risk for OSA or confirmed OSA are prescribed opioids at similar rates and doses upon discharge despite guidelines that recommend minimizing opioid use in OSA patients. These findings indicate a need to implement different strategies to reduce the prescription of opioids to patients with OSA.

Preoperative Evaluation Clinic Visit Is Associated with Decreased Risk of In-hospital Postoperative Mortality.

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.

Preoperative Renal Insufficiency: Underreporting and Association With Readmission and Major Postoperative Morbidity in an Academic Medical Center.

BACKGROUND: Making a formal diagnosis of chronic kidney disease (CKD) in the preoperative setting may be challenging because of lack of longitudinal data. We explored the predictive value of a single reduced preoperative estimated glomerular filtration rate (eGFR) value on adverse patient outcomes in the first 30 days after elective surgery. We compared the rate of major postoperative adverse events, including 30-day readmission rate, hospital length of stay, infection, acute kidney injury (AKI), and myocardial infarction across patients with declining preoperative eGFR values. We hypothesized that there is an association between decreasing preoperative eGFR values and major postoperative morbidity including readmission within 30 days of discharge and that the reasons for unplanned readmissions may be associated with poor preoperative renal function. METHODS: This was a retrospective analysis of the electronic health record of 39 989 adult patients who underwent elective surgery between June 2011 and July 2013 at our institution. Patients with reduced eGFR (<60 mL/min/1.73 m) were identified and categorized by the stages of CKD that correlated with the preoperative eGFR value. Odds of readmission to our hospital within 30 days, as well as new diagnosis of AKI, myocardial infarction, and infection, were determined with multivariate logistic regression. The subset of patients who were readmitted within 30 days also were subdivided further into patients who had an eGFR <60 mL/min/1.73 m and those with an eGFR ≥60 mL/min/1.73 m, as well as whether the readmission was planned or unplanned. RESULTS: Of the 4053 patients with eGFR <60 mL/min/1.73 m, 3290 (81.2%) did not carry a preoperative diagnosis of CKD. Adjusted odds ratios of being readmitted were 1.48 (99% confidence interval [CI], 1.18-1.87; P < .001) for eGFR 30 to 44 mL/min/1.73 m to 2.06 (99% CI, 1.32-3.23; P < .001) for eGFR <15 mL/min/1.73 m compared with patients with a preoperative eGFR value ≥60 mL/min/1.73 m. Patients with a lower eGFR also demonstrated increasing odds of AKI from 2.78 (99% CI, 1.86-4.17; P < .001) for eGFR 45 to 59 mL/min/1.73 m to 3.81 (99% CI, 1.68-8.16; P < .001) for eGFR <15 mL/min/1.73 m. CONCLUSIONS: This study highlights that preoperative renal insufficiency may be underreported and appears to be significantly associated with postoperative complications. It extends the association between a single low preoperative eGFR and postoperative morbidity to a broader range of surgical populations than previously described. Our results suggest that preoperative calculation of eGFR may be a relatively low-cost, readily available tool to identify patients who are at an increased risk of readmission within 30 days of surgery and postoperative morbidity in patients presenting for elective surgery.

Machine Learning for the Prediction of Procedural Case Durations Developed Using a Large Multicenter Database: Algorithm Development and Validation Study.

BACKGROUND: Accurate projections of procedural case durations are complex but critical to the planning of perioperative staffing, operating room resources, and patient communication. Nonlinear prediction models using machine learning methods may provide opportunities for hospitals to improve upon current estimates of procedure duration. OBJECTIVE: The aim of this study was to determine whether a machine learning algorithm scalable across multiple centers could make estimations of case duration within a tolerance limit because there are substantial resources required for operating room functioning that relate to case duration. METHODS: Deep learning, gradient boosting, and ensemble machine learning models were generated using perioperative data available at 3 distinct time points: the time of scheduling, the time of patient arrival to the operating or procedure room (primary model), and the time of surgical incision or procedure start. The primary outcome was procedure duration, defined by the time between the arrival and the departure of the patient from the procedure room. Model performance was assessed by mean absolute error (MAE), the proportion of predictions falling within 20% of the actual duration, and other standard metrics. Performance was compared with a baseline method of historical means within a linear regression model. Model features driving predictions were assessed using Shapley additive explanations values and permutation feature importance. RESULTS: A total of 1,177,893 procedures from 13 academic and private hospitals between 2016 and 2019 were used. Across all procedures, the median procedure duration was 94 (IQR 50-167) minutes. In estimating the procedure duration, the gradient boosting machine was the best-performing model, demonstrating an MAE of 34 (SD 47) minutes, with 46% of the predictions falling within 20% of the actual duration in the test data set. This represented a statistically and clinically significant improvement in predictions compared with a baseline linear regression model (MAE 43 min; P<.001; 39% of the predictions falling within 20% of the actual duration). The most important features in model training were historical procedure duration by surgeon, the word "free" within the procedure text, and the time of day. CONCLUSIONS: Nonlinear models using machine learning techniques may be used to generate high-performing, automatable, explainable, and scalable prediction models for procedure duration.

Predicting hypotension in the ICU using noninvasive physiological signals.

Hypotension frequently occurs in Intensive Care Units (ICU), and its early prediction can improve the outcome of patient care. Trends observed in signals related to blood pressure (BP) are critical in predicting future events. Unfortunately, the invasive measurement of BP signals is neither comfortable nor feasible in all bed settings. In this study, we investigate the performance of machine-learning techniques in predicting hypotensive events in ICU settings using physiological signals that can be obtained noninvasively. We show that noninvasive mean arterial pressure (NIMAP) can be simulated by down-sampling the invasively measured MAP. This enables us to investigate the effect of BP measurement frequency on the algorithm's performance by training and testing the algorithm on a large dataset provided by the MIMIC III database. This study shows that having NIMAP information is essential for adequate predictive performance. The proposed predictive algorithm can flag hypotension with a sensitivity of 84%, positive predictive value (PPV) of 73%, and F1-score of 78%. Furthermore, the predictive performance of the algorithm improves by increasing the frequency of BP sampling.

Relation between preoperative benzodiazepines and opioids on outcomes after total joint arthroplasty.

To examine the association of preoperative opioids and/or benzodiazepines on postoperative outcomes in total knee and hip arthroplasty, we retrospectively compared postoperative outcomes in those prescribed preoperative opioids and/or benzodiazepines versus those who were not who underwent elective total knee and hip arthroplasty at a single urban academic institution. Multivariable logistic regression was performed for readmission rate, respiratory failure, infection, and adverse cardiac events. Multivariable zero-truncated negative binomial regression was used for length of stay. After exclusions, there were 4307 adult patients in the study population, 2009 of whom underwent total knee arthroplasty and 2298 of whom underwent total hip arthroplasty. After adjusting for potential confounders, preoperative benzodiazepine use was associated with increased odds of readmission (p < 0.01). Preoperative benzodiazepines were not associated with increased odds of respiratory failure nor increased length of stay. Preoperative opioids were not associated with increased odds of the examined outcomes. There were insufficient numbers of infection and cardiac events for analysis. In this study population, preoperative benzodiazepines were associated with increased odds of readmission. Preoperative opioids were not associated with increased odds of the examined outcomes. Studies are needed to further examine risks associated with preoperative benzodiazepine use.