Overview and Clinical Applications of Artificial Intelligence and Machine Learning in Cardiac Anesthesiology.

Artificial intelligence- (AI) and machine learning (ML)-based applications are becoming increasingly pervasive in the healthcare setting. This has in turn challenged clinicians, hospital administrators, and health policymakers to understand such technologies and develop frameworks for safe and sustained clinical implementation. Within cardiac anesthesiology, challenges and opportunities for AI/ML to support patient care are presented by the vast amounts of electronic health data, which are collected rapidly, interpreted, and acted upon within the periprocedural area. To address such challenges and opportunities, in this article, the authors review 3 recent applications relevant to cardiac anesthesiology, including depth of anesthesia monitoring, operating room resource optimization, and transthoracic/transesophageal echocardiography, as conceptual examples to explore strengths and limitations of AI/ML within healthcare, and characterize this evolving landscape. Through reviewing such applications, the authors introduce basic AI/ML concepts and methodologies, as well as practical considerations and ethical concerns for initiating and maintaining safe clinical implementation of AI/ML-based algorithms for cardiac anesthesia patient care.

Effects of Intra-operative Cardiopulmonary Variability On Post-operative Pulmonary Complications in Major Non-cardiac Surgery: A Retrospective Cohort Study.

Intraoperative cardiopulmonary variables are well-known predictors of postoperative pulmonary complications (PPC), traditionally quantified by median values over the duration of surgery. However, it is unknown whether cardiopulmonary instability, or wider intra-operative variability of the same metrics, is distinctly associated with PPC risk and severity. We leveraged a retrospective cohort of adults (n = 1202) undergoing major non-cardiothoracic surgery. We used multivariable logistic regression to evaluate the association of two outcomes (1)moderate-or-severe PPC and (2)any PPC with two sets of exposure variables- (a)variability of cardiopulmonary metrics (inter-quartile range, IQR) and (b)median intraoperative cardiopulmonary metrics. We compared predictive ability (receiver operating curve analysis, ROC) and parsimony (information criteria) of three models evaluating different aspects of the intra-operative cardiopulmonary metrics: Median-based: Median cardiopulmonary metrics alone, Variability-based: IQR of cardiopulmonary metrics alone, and Combined: Medians and IQR. Models controlled for peri-operative/surgical factors, demographics, and comorbidities. PPC occurred in 400(33%) of patients, and 91(8%) experienced moderate-or-severe PPC. Variability in multiple intra-operative cardiopulmonary metrics was independently associated with risk of moderate-or-severe, but not any, PPC. For moderate-or-severe PPC, the best-fit predictive model was the Variability-based model by both information criteria and ROC analysis (area under the curve, AUCVariability-based = 0.74 vs AUCMedian-based = 0.65, p = 0.0015; AUCVariability-based = 0.74 vs AUCCombined = 0.68, p = 0.012). For any PPC, the Median-based model yielded the best fit by information criteria. Predictive accuracy was marginally but not significantly higher for the Combined model (AUCCombined = 0.661) than for the Median-based (AUCMedian-based = 0.657, p = 0.60) or Variability-based (AUCVariability-based = 0.649, p = 0.29) models. Variability of cardiopulmonary metrics, distinct from median intra-operative values, is an important predictor of moderate-or-severe PPC.

Correlations of Opioid Intake During Different Predischarge Time Frames with Postdischarge Opioid Use Following Inpatient Surgery.

Previous work has shown that predischarge opioid use is the most reliable and practical predictor of postdischarge opioid intake after inpatient surgery. However, the most appropriate predischarge time frame for operationalizing this relationship into more individualized prescriptions is unknown. We compared the correlations between the quantity of opioids taken during 5 predischarge time frames and self-reported postdischarge opioid intake in 604 adult surgery patients. We found that the 24-hour predischarge time frame was most strongly correlated (ρ= 0.60, P < .001) with postdischarge opioid use and may provide actionable information for predicting opioid use after discharge.

Barriers and Facilitators of Surrogates Providing Consent for Critically Ill Patients in Clinical Trials: A Qualitative Study.

BACKGROUND: Enrollment into critical care clinical trials is often hampered by the need to rely on surrogate decision-makers. To identify potential interventions facilitating enrollment into critical care clinical trials, a better understanding of surrogate decision-making for critical care clinical trial enrollment is needed. RESEARCH QUESTION: What are the barriers and facilitators of critical care trial enrollment? What are surrogate decision-makers' perspectives on proposed interventions to facilitate trial enrollment? STUDY DESIGN AND METHODS: We conducted semistructured interviews with 20 surrogate decision-makers of critically ill patients receiving mechanical ventilation. The interviews were recorded and transcribed verbatim, and analyzed for themes using an inductive approach. RESULTS: Twenty surrogate decision-makers of critically ill patients participated in the semistructured interviews. Thematic analysis confirmed previous research showing that trust in the system, assessing the risks and benefits of trial participation, the desire to help others, and building medical knowledge as important motivating factors for trial enrollment. Two previously undescribed concerns among surrogate decision-makers of critically ill patients were identified, including the potential to interfere with clinical treatment decisions and negative sentiment about placebos. Surrogates viewed public recognition and charitable donations for participation as favorable potential interventions to encourage trial enrollment. However, participants viewed direct financial incentives and prioritizing research participants during medical rounds negatively. INTERPRETATION: This study confirms and extends previous findings that health system trust, study risks and benefits, altruism, knowledge generation, interference with clinical care, and placebos are key concerns and barriers for surrogate decision-makers to enroll patients in critical care trials. Future studies are needed to evaluate if charitable giving on the patient's behalf and public recognition are effective strategies to promote enrollment into critical care trials.

Rethinking ketamine as a panacea: adverse effects on oxygenation and postoperative outcomes.

Ketamine is receiving renewed interest in perioperative medicine as an anaesthetic adjunct and a treatment for chronic conditions, including depression. Ketamine's complex pharmacologic profile results not only in several desirable effects, such as anaesthesia and analgesia, but also multiple adverse effects affecting the central nervous, cardiovascular, and respiratory systems. In addition to defining patient-centred outcomes in future clinical studies on the perioperative uses of ketamine, careful monitoring for its numerous adverse effects will be paramount.

Best Practice Alerts Informed by Inpatient Opioid Intake to Reduce Opioid Prescribing after Surgery (PRIOR): A Cluster Randomized Multiple Crossover Trial.

BACKGROUND: Overprescription of opioids after surgery remains common. Residual and unnecessarily prescribed opioids can provide a reservoir for nonmedical use. This study therefore tested the hypothesis that a decision-support tool embedded in electronic health records guides clinicians to prescribe fewer opioids at discharge after inpatient surgery. METHODS: This study included 21,689 surgical inpatient discharges in a cluster randomized multiple crossover trial from July 2020 to June 2021 in four Colorado hospitals. Hospital-level clusters were randomized to alternating 8-week periods during which an electronic decision-support tool recommended tailored discharge opioid prescriptions based on previous inpatient opioid intake. During active alert periods, the alert was displayed to clinicians when the proposed opioid prescription exceeded recommended amounts. No alerts were displayed during inactive periods. Carryover effects were mitigated by including 4-week washout periods. The primary outcome was oral morphine milligram equivalents prescribed at discharge. Secondary outcomes included combination opioid and nonopioid prescriptions and additional opioid prescriptions until day 28 after discharge. A vigorous state-wide opioid education and awareness campaign was in place during the trial. RESULTS: The total postdischarge opioid prescription was a median [quartile 1, quartile 3] of 75 [0, 225] oral morphine milligram equivalents among 11,003 patients discharged when the alerts were active and 100 [0, 225] morphine milligram equivalents in 10,686 patients when the alerts were inactive, with an estimated ratio of geometric means of 0.95 (95% CI, 0.80 to 1.13; P = 0.586). The alert was displayed in 28% (3,074 of 11,003) of the discharges during the active alert period. There was no relationship between the alert and prescribed opioid and nonopioid combination medications or additional opioid prescriptions written after discharge. CONCLUSIONS: A decision-support tool incorporated into electronic medical records did not reduce discharge opioid prescribing for postoperative patients in the context of vigorous opioid education and awareness efforts. Opioid prescribing alerts might yet be valuable in other contexts.(Anesthesiology 2023; 139:186-96).

Reversal of neuromuscular block: what are the costs?

Patients requiring neuromuscular block for anaesthesia have a higher risk of adverse postoperative outcomes. The choice of reversal drug and its corresponding dose is critical for improving clinical outcomes. Although drug costs are higher for sugammadex relative to neostigmine, additional factors need to be considered when choosing one drug over the other. New data from a recent study in the British Journal of Anaesthesia indicate cost advantages for sugammadex in low-risk and ambulatory patients, but for neostigmine in high-risk patients. These findings highlight the need to take local and temporal factors into consideration in addition to clinical effectiveness when performing cost analyses for administrative decision-making.

Meeting Report: First Cardiovascular Outcomes Research in Perioperative Medicine Conference.

The first Cardiovascular Outcomes Research in Perioperative Medicine (COR-PM) conference took place on May 13, 2022, in Palm Springs, CA, and online. Here, we: (1) summarize the background, objective, and aims of the COR-PM meeting; (2) describe the conduct of the meeting; and (3) outline future directions for scientific meetings aimed at fostering high-quality clinical research in the broader perioperative medicine community.

Personal Financial Wellness Curricula for Medical Trainees: A Systematic Review.

PURPOSE: Education debt, poor financial literacy, and a late start to retirement savings can cause financial stress among physicians. This systematic review identifies methods for curriculum development, methods for curriculum delivery, and outcome measures to evaluate the effectiveness of personal financial wellness curricula for medical students, residents, and fellows. METHOD: The authors searched the Embase, MEDLINE (via EBSCO), Scopus, Education Resources Information Center (via EBSCO), and Cochrane Library databases and MedEdPORTAL (via PubMed) on July 28, 2022. Studies must have reported the outcome of at least 1 postcourse assessment to be included. RESULTS: Of the 1,996 unique citations identified, 13 studies met the inclusion criteria. Three curricula (23.1%) were designed for medical students, 8 (61.5%) for residents, 1 (7.7%) for internal medicine fellows, and 1 (7.7%) for obstetrics-gynecology residents and fellows. The most frequently discussed personal finance topics included student loans, investment options, disability insurance, life insurance, retirement savings, budgeting, debt management, and general personal finance. A median (interquartile range) of 3.5 (1.4-7.0) hours was spent on personal finance topics. Eleven curricula (85.6%) relied on physicians to deliver the content. Four studies (30.8%) reported precourse and postcourse financial literacy evaluations, each showing improved financial literacy after the course. Four studies (30.8%) assessed actual or planned financial behavior changes, each credited with encouraging or assisting with financial behavioral changes. One study (7.7%) assessed participants' well-being using the Expanded Well-Being Index, which showed an improvement after the course. CONCLUSIONS: Given the impact educational debt and other financial stressors can have on the wellness of medical trainees, institutions should consider investments in teaching financial literacy. Future studies should report more concrete outcome measures, including financial behavior change and validated measures of wellness.

Airway and Hemodynamic Considerations for the Anesthetic Management of an Intraluminal Tracheal Plasmacytoma.

Central airway obstruction due to tracheal tumors presents unique challenges to the anesthesiologist. We present the case of a 44-year-old male taken to the OR for biopsy and resection of an undiagnosed tracheal mass. Intraoperative management was complicated by bleeding and significant hemodynamic instability, necessitating rapid surgical and anesthetic intervention. This ultimately led to abortion of surgical resection. Pathologic examination revealed a primary tracheal plasmacytoma, a rare type of tracheal tumor. Here, we describe anesthetic and hemodynamic considerations for a tracheal plasmacytoma. We discuss the approach to airway management in variable intrathoracic tracheal obstruction and the unpredictability of tracheal tumors.

Venovenous extracorporeal membrane oxygenation support in patients with COVID-19 respiratory failure: A multicenter study.

Objective: The COVID-19 pandemic presents a high mortality rate amongst patients who develop severe acute respiratory distress syndrome (ARDS). The purpose of this study was to evaluate the outcomes of venovenous extracorporeal membrane oxygenation (VV-ECMO) in COVID-19-related ARDS and identify the patients who benefit the most from this procedure. Methods: Adult patients with COVID-19 and severe ARDS requiring VV-ECMO support at 4 academic institutions between March and October 2020 were included. Data were collected through retrospective chart reviews. Bivariate and multivariable analyses were performed with the primary outcome of in-hospital mortality. Results: Fifty-one consecutive patients underwent VV-ECMO with a mean age of 50.4 years; 64.7% were men. Survival to hospital discharge was 62.8%. Median intensive care unit and hospitalization duration were 27.4 days (interquartile range [IQR], 17-37 days) and 34.5 days (IQR, 23-43 days), respectively. Survivors and nonsurvivors had a median ECMO cannulation time of 11 days (IQR, 8-18) and 17 days (IQR, 12-25 days). The average postdecannulation length of stay was 17.5 days (IQR, 12.4-25 days) for survivors and 0 days for nonsurvivors (IQR, 0-6 days). Only 1 nonsurvivor was able to be decannulated. Clinical characteristics associated with mortality between nonsurviors and survivors included increasing age (P = .0048), hemorrhagic stroke (P = .0014), and postoperative dialysis (P = .0013) were associated with mortality in a bivariate model and retained statistical significance in a multivariable model. Conclusions: This multicenter study confirms the effectiveness of VV-ECMO in selected critically ill patients with COVID-19-related severe ARDS. The survival of these patients is comparable to non-COVID-19-related ARDS.

Cardiac surgery's long opioid dependency: time to recalibrate pain therapy?

Opioid analgesia is the cornerstone of anaesthetic management during cardiac surgery. However, a subset of patients use opioids persistently after three months of surgery. We discuss a recent meta-analysis and systematic review by Liu and colleagues describing both patient and peri-procedural risk factors that contribute to this phenomenon in the context of chronic pain after cardiac surgery. Anaesthetists for cardiac surgery should consider opioid alternatives and individual patient risk factors to optimise recovery and pain control.

Shared Decision-Making Tool for Opioid Prescribing After Ambulatory Orthopedic Surgery in Veterans: A Randomized Controlled Clinical Trial.

Purpose: We examined whether an educational, shared-decision-making tool designed to empower patients, individualize pain management, and maximize use of nonopioid, over-the-counter analgesics reduces opioid use and waste while maintaining adequate pain relief. Methods: We developed an educational, shared-decision-making tool regarding postoperative pain medication for outpatient hand surgery. Patients randomized to groups with and without the tool were surveyed for 4 weeks after surgery. Survey variables included Patient-Reported Outcomes Measurement Information System pain intensity and pain interference scores, as well as the number of oxycodone or over-the-counter pills taken. Results were compared using chi-squared, Wilcoxon rank-sum, and Welch's t tests. Results: Fifty-three patients participated: 25 in the shared-tool group and 28 in the no-tool group. The mean age was 60 years, with more women in the no-tool group than the shared-tool group (n =17 versus 11, respectively). The shared-tool group averaged 6.4 prescribed oxycodone pills, versus 10 for the no-tool group (P < .01). The median numbers of oxycodone pills taken the first week after surgery were 2 (interquartile range, 6) for the shared-tool group and 3 (interquartile range, 6) for the no-tool group (P = .97). Patient-reported outcome measures for pain intensity and pain interference were not significantly different for weeks 1, 3, and 4 after surgery. Pain interference was significantly lower in week 2 in the shared-tool group (difference, -4.4; 95% confidence interval, -8.57 to -0.30; P = .04). Conclusions: The shared-tool group had equivalent or better pain control and were prescribed a lower number of opioid pain pills than the no-tool group. Both groups used nonopioid medications, with no difference in the types of over-the-counter medications used. Shared decision-making strategies could be applied to other outpatient orthopedic surgical settings, and may reduce the amount of opioids prescribed without compromising pain control. Type of study/level of evidence: Therapeutic II.