RESUMEN

Virtual assistants, broadly defined as digital services designed to simulate human conversation and provide personalized responses based on user input, have the potential to improve health care by supporting clinicians and patients in terms of diagnosing and managing disease, performing administrative tasks, and supporting medical research and education. These tasks are particularly helpful in vascular surgery, where the clinical and administrative burden is high due to the rising incidence of vascular disease, the medical complexity of the patients, and the potential for innovation and care advancement. The rapid development of artificial intelligence, machine learning, and natural language processing techniques have facilitated the training of large language models, such as GPT-4 (OpenAI), which can support the development of increasingly powerful virtual assistants. These tools may support holistic, multidisciplinary, and high-quality vascular care delivery throughout the pre-, intra-, and postoperative stages. Importantly, it is critical to consider the design, safety, and challenges related to virtual assistants, including data security, ethical, and equity concerns. By combining the perspectives of patients, clinicians, data scientists, and other stakeholders when developing, implementing, and monitoring virtual assistants, there is potential to harness the power of this technology to care for vascular surgery patients more effectively. In this comprehensive review article, we introduce the concept of virtual assistants, describe potential applications of virtual assistants in vascular surgery for clinicians and patients, highlight the benefits and drawbacks of large language models, such as GPT-4, and discuss considerations around the design, safety, and challenges associated with virtual assistants in vascular surgery.

Asunto(s)

RESUMEN

BACKGROUND: Delirium is a common and potentially serious complication after major surgery. A previous history of depression is a known risk factor for experiencing delirium in patients admitted to the hospital, but the generalised risk has not been estimated in surgical patients. METHODS: We conducted a systematic review and meta-analysis of studies reporting the incidence or relative risk (or relative odds) of delirium in the immediate postoperative period for adults with pre-operative depression. We included studies that defined depression as either a formal pre-existing diagnosis or having clinically important depressive symptoms measured using a patient-reported instrument before surgery. Multilevel random effects meta-analyses were used to estimate the pooled incidences and pooled relative risks. We also conducted subgroup analyses by various study-level characteristics to identify important moderators of pooled estimates. RESULTS: Forty-two studies (n = 4,664,051) from five continents were included. The pooled incidence of postoperative delirium for patients with pre-operative depression was 29% (95%CI 17-43%, I2 = 99.0%), compared with 15% (95%CI 6-28%, I2 = 99.8%) in patients without pre-operative depression and 21% (95% CI 11-33%, I2 = 99.8%) in the cohorts overall. For patients with pre-operative depression, the risk of delirium was 1.91 times greater (95%CI 1.68-2.17, I2 = 42.0%) compared with patients without pre-operative depression. CONCLUSIONS: Patients with a previous diagnosis of depression or clinically important depressive symptoms before surgery have substantially greater risk of experiencing delirium after surgery. Clinicians and patients should be informed of these increased risks. Robust screening and other risk mitigation strategies for postoperative delirium are warranted, especially for patients with pre-operative depression.

RESUMEN

BACKGROUND: Transfemoral carotid artery stenting (TFCAS) carries important perioperative risks. Outcome prediction tools may help guide clinical decision-making but remain limited. We developed machine learning algorithms that predict 1-year stroke or death following TFCAS. METHODS AND RESULTS: The VQI (Vascular Quality Initiative) database was used to identify patients who underwent TFCAS for carotid artery stenosis between 2005 and 2024. We identified 112 features from the index hospitalization (82 preoperative [demographic/clinical], 13 intraoperative [procedural], and 17 postoperative [in-hospital course/complications]). The primary outcome was 1-year postprocedural stroke or death. The data were divided into training (70%) and test (30%) sets. Six machine learning models were trained using preoperative features with 10-fold cross-validation. The primary model evaluation metric was area under the receiver operating characteristic curve. The algorithm with the best performance was further trained using intra- and postoperative features. Model robustness was assessed using calibration plots and Brier scores. Overall, 35 214 patients underwent TFCAS during the study period and 3257 (9.2%) developed 1-year stroke or death. The best preoperative prediction model was extreme gradient boosting, achieving an area under the receiver operating characteristic curve of 0.94 (95% CI, 0.93-0.95). In comparison, logistic regression had an AUROC of 0.65 (95% CI, 0.63-0.67). The extreme gradient boosting model maintained excellent performance at the intra- and postoperative stages, with area under the receiver operating characteristic curve values of 0.94 (95% CI, 0.93-0.95) and 0.98 (95% CI, 0.97-0.99), respectively. Calibration plots showed good agreement between predicted/observed event probabilities with Brier scores of 0.11 (preoperative), 0.11 (intraoperative), and 0.09 (postoperative). CONCLUSIONS: Machine learning can accurately predict 1-year stroke or death following TFCAS, performing better than logistic regression.

Asunto(s)

Asunto(s)

RESUMEN

Importance: Identifying disparities in health outcomes related to modifiable patient factors can improve patient care. Objective: To compare likelihood of withdrawal of life-supporting treatment (WLST) and mortality in patients with complete cervical spinal cord injury (SCI) with different types of insurance. Design, Setting, and Participants: This retrospective cohort study collected data between 2013 and 2020 from 498 trauma centers participating in the Trauma Quality Improvement Program. Participants included adult patients (older than 16 years) with complete cervical SCI. Data were analyzed from November 1, 2023, through May 18, 2024. Exposure: Uninsured or public insurance compared with private insurance. Main Outcomes and Measures: Coprimary outcomes were WLST and mortality. The adjusted odds ratio (aOR) of each outcome was estimated using hierarchical logistic regression. Propensity score matching was used as an alternative analysis to compare public and privately insured patients. Process of care outcomes, including the occurrence of a hospital complication and length of stay, were compared between matched patients. Results: The study included 8421 patients with complete cervical SCI treated across 498 trauma centers (mean [SD] age, 49.1 [20.2] years; 6742 male [80.1%]). Among the 3524 patients with private insurance, 503 had WLST (14.3%) and 756 died (21.5%). Among the 3957 patients with public insurance, 906 had WLST (22.2%) and 1209 died (30.6%). Among the 940 uninsured patients, 156 had WLST (16.6%) and 318 died (33.8%). A significant difference was found between uninsured and privately insured patients in the adjusted odds of WLST (aOR, 1.49; 95% CI, 1.11-2.01) and mortality (aOR, 1.98; 95% CI, 1.50-2.60). Similar results were found in subgroup analyses. Matched public compared with private insurance patients were found to have significantly greater odds of hospital complications (odds ratio, 1.27; 95% CI, 1.14-1.42) and longer hospital stay (mean difference 5.90 days; 95% CI, 4.64-7.20), which was redemonstrated on subgroup analyses. Conclusions and Relevance: Health insurance type was associated with significant differences in the odds of WLST, mortality, hospital complications, and days in hospital among patients with complete cervical SCI in this study. Future work is needed to incorporate patient perspectives and identify strategies to close the quality gap for the large number of patients without private insurance.

RESUMEN

OBJECTIVE: Inferior vena cava (IVC) filter placement is associated with important long-term complications. Predictive models for filter-related complications may help guide clinical decision-making but remain limited. We developed machine learning (ML) algorithms that predict 1-year IVC filter complications using preoperative data. METHODS: The Vascular Quality Initiative database was used to identify patients who underwent IVC filter placement between 2013 and 2024. We identified 77 preoperative demographic and clinical features from the index hospitalization when the filter was placed. The primary outcome was 1-year filter-related complications (composite of filter thrombosis, migration, angulation, fracture, and embolization or fragmentation, vein perforation, new caval or iliac vein thrombosis, new pulmonary embolism, access site thrombosis, or failed retrieval). The data were divided into training (70%) and test (30%) sets. Six ML models were trained using preoperative features with 10-fold cross-validation (Extreme Gradient Boosting, random forest, Naïve Bayes classifier, support vector machine, artificial neural network, and logistic regression). The primary model evaluation metric was area under the receiver operating characteristic curve (AUROC). Model robustness was assessed using calibration plot and Brier score. Performance was evaluated across subgroups based on age, sex, race, ethnicity, rurality, median Area Deprivation Index, planned duration of filter, landing site of filter, and presence of prior IVC filter placement. RESULTS: Overall, 14,476 patients underwent IVC filter placement and 584 (4.0%) experienced 1-year filter-related complications. Patients with a primary outcome were younger (59.3 ± 16.7 years vs 63.8 ± 16.0 years; P < .001) and more likely to have thrombotic risk factors including thrombophilia, prior venous thromboembolism (VTE), and family history of VTE. The best prediction model was Extreme Gradient Boosting, achieving an AUROC of 0.93 (95% confidence interval, 0.92-0.94). In comparison, logistic regression had an AUROC of 0.63 (95% confidence interval, 0.61-0.65). Calibration plot showed good agreement between predicted/observed event probabilities with a Brier score of 0.07. The top 10 predictors of 1-year filter-related complications were (1) thrombophilia, (2) prior VTE, (3) antiphospholipid antibodies, (4) factor V Leiden mutation, (5) family history of VTE, (6) planned duration of IVC filter (temporary), (7) unable to maintain therapeutic anticoagulation, (8) malignancy, (9) recent or active bleeding, and (10) age. Model performance remained robust across all subgroups. CONCLUSIONS: We developed ML models that can accurately predict 1-year IVC filter complications, performing better than logistic regression. These algorithms have potential to guide patient selection for filter placement, counselling, perioperative management, and follow-up to mitigate filter-related complications and improve outcomes.

RESUMEN

Importance: Withdrawal of life-sustaining therapy (WLST) decisions for critically injured trauma patients are complicated and multifactorial, with potential for patients' insurance status to affect decision-making. Objectives: To determine if patient insurance type (private insurance, Medicaid, and uninsured) is associated with time to WLST in critically injured adults cared for at US trauma centers. Design, Setting, and Participants: This retrospective registry-based cohort study included reported data from level I and level II trauma centers in the US that participated in the American College of Surgeons Trauma Quality Improvement Program (TQIP) registry. Participants included adult trauma patients who were injured between January 1, 2017, and December 31, 2020, and required an intensive care unit stay. Patients were excluded if they died on arrival or in the emergency department or had a preexisting do not resuscitate directive. Analyses were performed on December 12, 2023. Exposures: Insurance type (private insurance, Medicaid, uninsured). Main Outcomes and Measures: An adjusted time-to-event analysis for association between insurance status and time to WLST was performed, with analyses accounting for clustering by hospital. Results: This study included 307 731 patients, of whom 160 809 (52.3%) had private insurance, 88 233 (28.6%) had Medicaid, and 58 689 (19.1%) were uninsured. The mean (SD) age was 40.2 (14.1) years, 232 994 (75.7%) were male, 59 551 (19.4%) were African American or Black patients, and 201 012 (65.3%) were White patients. In total, 12 962 patients (4.2%) underwent WLST during their admission. Patients who are uninsured were significantly more likely to undergo earlier WLST compared with those with private insurance (HR, 1.54; 95% CI, 1.46-1.62) and Medicaid (HR, 1.47; 95% CI, 1.39-1.55). This finding was robust to sensitivity analysis excluding patients who died within 48 hours of presentation and after accounting for nonwithdrawal death as a competing risk. Conclusions and Relevance: In this cohort study of US adult trauma patients who were critically injured, patients who were uninsured underwent earlier WLST compared with those with private or Medicaid insurance. Based on our findings, patient's ability to pay was may be associated with a shift in decision-making for WLST, suggesting the influence of socioeconomics on patient outcomes.

Asunto(s)

RESUMEN

INTRODUCTION: Intraoperative hypotension is associated with increased risks of postoperative complications. Consequently, a variety of blood pressure optimization strategies have been tested to prevent or promptly treat intraoperative hypotension. We performed a systematic review to summarize randomized controlled trials that evaluated the efficacy of blood pressure optimization interventions in either mitigating exposure to intraoperative hypotension or reducing risks of postoperative complications. METHODS: Medline, Embase, PubMed, and Cochrane Controlled Register of Trials were searched from database inception to August 2, 2023, for randomized controlled trials (without language restriction) that evaluated the impact of any blood pressure optimization intervention on intraoperative hypotension and/or postoperative outcomes. RESULTS: The review included 48 studies (N = 46,377), which evaluated 10 classes of blood pressure optimization interventions. Commonly assessed interventions included hemodynamic protocols using arterial waveform analysis, preoperative withholding of antihypertensive medications, continuous blood pressure monitoring, and adjuvant agents (vasopressors, anticholinergics, anticonvulsants). These same interventions reduced intraoperative exposure to hypotension. Conversely, low blood pressure alarms had an inconsistent impact on exposure to hypotension. Aside from limited evidence that higher prespecified intraoperative blood pressure targets led to a reduced risk of complications, there were few data suggesting that these interventions prevented postoperative complications. Heterogeneity in interventions and outcomes precluded meta-analysis. CONCLUSIONS: Several different blood pressure optimization interventions show promise in reducing exposure to intraoperative hypotension. Nonetheless, the impact of these interventions on clinical outcomes remains unclear. Future trials should assess promising interventions in samples sufficiently large to identify clinically plausible treatment effects on important outcomes.

RESUMEN

Introduction: Cannabis use has been associated with reduced physical activity and increased sedentary behavior in adolescents. In adults, however, there is no conclusive evidence of such an association, and existing studies have primarily relied on self-reported activity measures. As cannabis use increases globally, a deeper understanding of its relationship with activity levels may inform clinical counseling and guidelines. This study investigated the association between recent cannabis use and accelerometer-measured activity. Methods: Data were obtained from the National Health and Nutrition Examination Survey (NHANES) from 2011 to 2014. We included adults in the United States who responded to a cannabis questionnaire and had at least 4 days of activity data from an ActiGraph GT3X+ accelerometer, which comprised participants from 18 to 59 years. The primary exposure was any self-reported cannabis use in the past 30 days. The primary outcome was daily sedentary time and secondary outcomes were daily light physical activity (LPA) and moderate-to-vigorous physical activity (MVPA). Analyses were performed with multivariable quasi-Poisson regression models. Results: Of 4666 included adults, 658 (14.1%) reported recent cannabis use. After covariate adjustment, recent cannabis use was not associated with daily sedentary time (adjusted incidence rate ratio [aIRR] 0.99, 95% confidence interval [CI]: 0.98-1.01) or daily MVPA time (aIRR 1.01, 95% CI: 0.98-1.04). Daily LPA time was 4% greater with recent cannabis use (aIRR 1.04, 95% CI: 1.01-1.06). Conclusion: Recent cannabis use in young to midlife adults was not associated with accelerometer-measured sedentary or MVPA time, but it was associated with a marginal increase in LPA time of unclear clinical significance. Our findings provide evidence against existing concerns that cannabis use independently promotes sedentary behavior and decreases physical activity. Future prospective studies are needed to determine if these findings generalize to specific populations using cannabis including chronic pain patients.

RESUMEN

OBJECTIVE: To characterize the association between ambulatory cardiology or general internal medicine (GIM) assessment prior to surgery and outcomes following scheduled major vascular surgery. BACKGROUND: Cardiovascular risk assessment and management prior to high-risk surgery remains an evolving area of care. METHODS: This is population-based retrospective cohort study of all adults who underwent scheduled major vascular surgery in Ontario, Canada, April 1, 2004-March 31, 2019. Patients who had an ambulatory cardiology and/or GIM assessment within 6 months prior to surgery were compared to those who did not. The primary outcome was 30-day mortality. Secondary outcomes included: composite of 30-day mortality, myocardial infarction or stroke; 30-day cardiovascular death; 1-year mortality; composite of 1-year mortality, myocardial infarction or stroke; and 1-year cardiovascular death. Cox proportional hazard regression using inverse probability of treatment weighting (IPTW) was used to mitigate confounding by indication. RESULTS: Among 50,228 patients, 20,484 (40.8%) underwent an ambulatory assessment prior to surgery: 11,074 (54.1%) with cardiology, 8,071 (39.4%) with GIM and 1,339 (6.5%) with both. Compared to patients who did not, those who underwent an assessment had a higher Revised Cardiac Risk Index (N with Index over 2= 4,989[24.4%] vs. 4,587[15.4%], P<0.001) and more frequent pre-operative cardiac testing (N=7,772[37.9%] vs. 6,113[20.6%], P<0.001) but, lower 30-day mortality (N=551[2.7%] vs. 970[3.3%], P<0.001). After application of IPTW, cardiology or GIM assessment prior to surgery remained associated with a lower 30-day mortality (weighted Hazard Ratio [95%CI] = 0.73 [0.65-0.82]) and a lower rate of all secondary outcomes. CONCLUSIONS: Major vascular surgery patients assessed by a cardiology or GIM physician prior to surgery have better outcomes than those who are not. Further research is needed to better understand potential mechanisms of benefit.

RESUMEN

BACKGROUND: Research shows women experience higher mortality than men after cardiac surgery but information on sex-differences during postoperative recovery is limited. Days alive and out of hospital (DAH) combines death, readmission and length of stay, and may better quantify sex-differences during recovery. This main objective is to evaluate (i) how DAH at 30-days varies between sex and surgical procedure, (ii) DAH responsiveness to patient and surgical complexity, and (iii) longer-term prognostic value of DAH. METHODS: We evaluated 111,430 patients (26% female) who underwent one of three types of cardiac surgery (isolated coronary artery bypass [CABG], isolated non-CABG, combination procedures) between 2009 - 2019. Primary outcome was DAH at 30 days (DAH30), secondary outcomes were DAH at 90 days (DAH90) and 180 days (DAH180). Data were stratified by sex and surgical group. Unadjusted and risk-adjusted analyses were conducted to determine the association of DAH with patient-, surgery-, and hospital-level characteristics. Patients were divided into two groups (below and above the 10th percentile) based on the number of days at DAH30. Proportion of patients below the 10th percentile at DAH30 that remained in this group at DAH90 and DAH180 were determined. RESULTS: DAH30 were lower for women compared to men (22 vs. 23 days), and seen across all surgical groups (isolated CABG 23 vs. 24, isolated non-CABG 22 vs. 23, combined surgeries 19 vs. 21 days). Clinical risk factors including multimorbidity, socioeconomic status and surgical complexity were associated with lower DAH30 values, but women showed lower values of DAH30 compared to men for many factors. Among patients in the lowest 10th percentile at DAH30, 80% of both females and males remained in the lowest 10th percentile at 90 days, while 72% of females and 76% males remained in that percentile at 180 days. CONCLUSION: DAH is a responsive outcome to differences in patient and surgical risk factors. Further research is needed to identify new care pathways to reduce disparities in outcomes between male and female patients.

Asunto(s)

RESUMEN

BACKGROUND: Lower extremity endovascular revascularization for peripheral artery disease carries nonnegligible perioperative risks; however, outcome prediction tools remain limited. Using machine learning, we developed automated algorithms that predict 30-day outcomes following lower extremity endovascular revascularization. METHODS AND RESULTS: The National Surgical Quality Improvement Program targeted vascular database was used to identify patients who underwent lower extremity endovascular revascularization (angioplasty, stent, or atherectomy) for peripheral artery disease between 2011 and 2021. Input features included 38 preoperative demographic/clinical variables. The primary outcome was 30-day postprocedural major adverse limb event (composite of major reintervention, untreated loss of patency, or major amputation) or death. Data were split into training (70%) and test (30%) sets. Using 10-fold cross-validation, 6 machine learning models were trained using preoperative features. The primary model evaluation metric was area under the receiver operating characteristic curve. Overall, 21 886 patients were included, and 30-day major adverse limb event/death occurred in 1964 (9.0%) individuals. The best performing model for predicting 30-day major adverse limb event/death was extreme gradient boosting, achieving an area under the receiver operating characteristic curve of 0.93 (95% CI, 0.92-0.94). In comparison, logistic regression had an area under the receiver operating characteristic curve of 0.72 (95% CI, 0.70-0.74). The calibration plot showed good agreement between predicted and observed event probabilities with a Brier score of 0.09. The top 3 predictive features in our algorithm were (1) chronic limb-threatening ischemia, (2) tibial intervention, and (3) congestive heart failure. CONCLUSIONS: Our machine learning models accurately predict 30-day outcomes following lower extremity endovascular revascularization using preoperative data with good discrimination and calibration. Prospective validation is warranted to assess for generalizability and external validity.

Asunto(s)

RESUMEN

Preoperative depression is prevalent among patients undergoing metabolic and bariatric surgery (MBS) and is a potentially modifiable risk factor. However, the impact of preoperative depression on MBS outcomes has not been systematically reviewed. A search of MEDLINE, Embase, Cochrane, and PsychINFO (inception to June 2023) was conducted for studies reporting associations between preoperative depression and any clinical or patient-reported outcomes after MBS. Eighteen studies (5 prospective and 13 retrospective) reporting on 5933 participants were included. Most participants underwent gastric bypass or sleeve gastrectomy. Meta-analyses were not conducted due to heterogeneity in reported outcomes; findings were instead synthesized using a narrative and tabular approach. Across 13 studies (n = 3390) the associations between preoperative depression and weight loss outcomes at 6-72 months were mixed overall. This may be related to differences in cohort characteristics, outcome definitions, and instruments used to measure depression. A small number of studies reported that preoperative depression was associated with lower quality of life, worse acute pain, and more perioperative complications after surgery. Most of the included studies were deemed to be at high risk of bias, resulting in low or very low certainty of evidence according to the Risk of Bias In Non-randomized Studies - of Exposure (ROBINS-E) tool. While the impact of preoperative depression on weight loss after MBS remains unclear, there is early evidence that depression has negative consequences on other patient-important outcomes. Adequately powered studies using more sophisticated statistical methods are needed to accurately estimate these associations.

Asunto(s)

RESUMEN

BACKGROUND: The amount of same-day surgery has increased markedly worldwide in recent decades, but there remains limited evidence on chronic postsurgical pain in this setting. METHODS: This study assessed pain 90 days after ambulatory surgery in an international, multicenter prospective cohort study of patients at least 45 yr old with comorbidities or at least 65 yr old. Pain was assessed using the Brief Pain Inventory. Chronic postsurgical pain was defined as a change of more than 1 point in self-rated average pain at the surgical site between baseline and 90 days, and moderate to severe chronic postsurgical pain was defined as a score greater than 4 in self-rated average pain at the surgical site at 90 days. Risk factors for chronic postsurgical pain were identified using multivariable logistic regression. RESULTS: Between November 2021 and January 2023, a total of 2,054 participants were included, and chronic postsurgical pain occurred in 12% of participants, of whom 93.1% had new chronic pain at the surgical site (i.e., participants without pain before surgery). Moderate to severe chronic postsurgical pain occurred in 9% of overall participants. Factors associated with chronic postsurgical pain were active smoking (odds ratio, 1.82; 95% CI, 1.20 to 2.76), orthopedic surgery (odds ratio, 4.7; 95% CI, 2.24 to 9.7), plastic surgery (odds ratio, 4.3; 95% CI, 1.97 to 9.2), breast surgery (odds ratio, 2.74; 95% CI, 1.29 to 5.8), vascular surgery (odds ratio, 2.71; 95% CI, 1.09 to 6.7), and ethnicity (i.e., for Hispanic/Latino ethnicity, odds ratio, 3.41; 95% CI, 1.68 to 6.9 and for First Nations/native persons, odds ratio, 4.0; 95% CI, 1.05 to 15.4). CONCLUSIONS: Persistent postsurgical pain after same-day surgery is common, is usually moderate to severe in nature, and occurs mostly in patients without chronic pain before surgery.

Asunto(s)

RESUMEN

Importance: Central venous catheters (CVCs) are commonly used but are associated with complications. Quantifying complication rates is essential for guiding CVC utilization decisions. Objective: To summarize current rates of CVC-associated complications. Data Sources: MEDLINE, Embase, CINAHL, and CENTRAL databases were searched for observational studies and randomized clinical trials published between 2015 to 2023. Study Selection: This study included English-language observational studies and randomized clinical trials of adult patients that reported complication rates of short-term centrally inserted CVCs and data for 1 or more outcomes of interest. Studies that evaluated long-term intravascular devices, focused on dialysis catheters not typically used for medication administration, or studied catheters placed by radiologists were excluded. Data Extraction and Synthesis: Two reviewers independently extracted data and assessed risk of bias. Bayesian random-effects meta-analysis was applied to summarize event rates. Rates of placement complications (events/1000 catheters with 95% credible interval [CrI]) and use complications (events/1000 catheter-days with 95% CrI) were estimated. Main Outcomes and Measures: Ten prespecified complications associated with CVC placement (placement failure, arterial puncture, arterial cannulation, pneumothorax, bleeding events requiring action, nerve injury, arteriovenous fistula, cardiac tamponade, arrhythmia, and delay of ≥1 hour in vasopressor administration) and 5 prespecified complications associated with CVC use (malfunction, infection, deep vein thrombosis [DVT], thrombophlebitis, and venous stenosis) were assessed. The composite of 4 serious complications (arterial cannulation, pneumothorax, infection, or DVT) after CVC exposure for 3 days was also assessed. Results: Of 11 722 screened studies, 130 were included in the analyses. Seven of 15 prespecified complications were meta-analyzed. Placement failure occurred at 20.4 (95% CrI, 10.9-34.4) events per 1000 catheters placed. Other rates of CVC placement complications (per 1000 catheters) were arterial canulation (2.8; 95% CrI, 0.1-10), arterial puncture (16.2; 95% CrI, 11.5-22), and pneumothorax (4.4; 95% CrI, 2.7-6.5). Rates of CVC use complications (per 1000 catheter-days) were malfunction (5.5; 95% CrI, 0.6-38), infection (4.8; 95% CrI, 3.4-6.6), and DVT (2.7; 95% CrI, 1.0-6.2). It was estimated that 30.2 (95% CrI, 21.8-43.0) in 1000 patients with a CVC for 3 days would develop 1 or more serious complication (arterial cannulation, pneumothorax, infection, or DVT). Use of ultrasonography was associated with lower rates of arterial puncture (risk ratio [RR], 0.20; 95% CrI, 0.09-0.44; 13.5 events vs 68.8 events/1000 catheters) and pneumothorax (RR, 0.25; 95% CrI, 0.08-0.80; 2.4 events vs 9.9 events/1000 catheters). Conclusions and Relevance: Approximately 3% of CVC placements were associated with major complications. Use of ultrasonography guidance may reduce specific risks including arterial puncture and pneumothorax.

Asunto(s)

RESUMEN

Importance: Endovascular intervention for peripheral artery disease (PAD) carries nonnegligible perioperative risks; however, outcome prediction tools are limited. Objective: To develop machine learning (ML) algorithms that can predict outcomes following endovascular intervention for PAD. Design, Setting, and Participants: This prognostic study included patients who underwent endovascular intervention for PAD between January 1, 2004, and July 5, 2023, with 1 year of follow-up. Data were obtained from the Vascular Quality Initiative (VQI), a multicenter registry containing data from vascular surgeons and interventionalists at more than 1000 academic and community hospitals. From an initial cohort of 262 242 patients, 26 565 were excluded due to treatment for acute limb ischemia (n = 14 642) or aneurysmal disease (n = 3456), unreported symptom status (n = 4401) or procedure type (n = 2319), or concurrent bypass (n = 1747). Data were split into training (70%) and test (30%) sets. Exposures: A total of 112 predictive features (75 preoperative [demographic and clinical], 24 intraoperative [procedural], and 13 postoperative [in-hospital course and complications]) from the index hospitalization were identified. Main Outcomes and Measures: Using 10-fold cross-validation, 6 ML models were trained using preoperative features to predict 1-year major adverse limb event (MALE; composite of thrombectomy or thrombolysis, surgical reintervention, or major amputation) or death. The primary model evaluation metric was area under the receiver operating characteristic curve (AUROC). After selecting the best performing algorithm, additional models were built using intraoperative and postoperative data. Results: Overall, 235 677 patients who underwent endovascular intervention for PAD were included (mean [SD] age, 68.4 [11.1] years; 94 979 [40.3%] female) and 71 683 (30.4%) developed 1-year MALE or death. The best preoperative prediction model was extreme gradient boosting (XGBoost), achieving the following performance metrics: AUROC, 0.94 (95% CI, 0.93-0.95); accuracy, 0.86 (95% CI, 0.85-0.87); sensitivity, 0.87; specificity, 0.85; positive predictive value, 0.85; and negative predictive value, 0.87. In comparison, logistic regression had an AUROC of 0.67 (95% CI, 0.65-0.69). The XGBoost model maintained excellent performance at the intraoperative and postoperative stages, with AUROCs of 0.94 (95% CI, 0.93-0.95) and 0.98 (95% CI, 0.97-0.99), respectively. Conclusions and Relevance: In this prognostic study, ML models were developed that accurately predicted outcomes following endovascular intervention for PAD, which performed better than logistic regression. These algorithms have potential for important utility in guiding perioperative risk-mitigation strategies to prevent adverse outcomes following endovascular intervention for PAD.

Asunto(s)

RESUMEN

Lower extremity open revascularization is a treatment option for peripheral artery disease that carries significant peri-operative risks; however, outcome prediction tools remain limited. Using machine learning (ML), we developed automated algorithms that predict 30-day outcomes following lower extremity open revascularization. The National Surgical Quality Improvement Program targeted vascular database was used to identify patients who underwent lower extremity open revascularization for chronic atherosclerotic disease between 2011 and 2021. Input features included 37 pre-operative demographic/clinical variables. The primary outcome was 30-day major adverse limb event (MALE; composite of untreated loss of patency, major reintervention, or major amputation) or death. Our data were split into training (70%) and test (30%) sets. Using tenfold cross-validation, we trained 6 ML models. Overall, 24,309 patients were included. The primary outcome of 30-day MALE or death occurred in 2349 (9.3%) patients. Our best performing prediction model was XGBoost, achieving an area under the receiver operating characteristic curve (95% CI) of 0.93 (0.92-0.94). The calibration plot showed good agreement between predicted and observed event probabilities with a Brier score of 0.08. Our ML algorithm has potential for important utility in guiding risk mitigation strategies for patients being considered for lower extremity open revascularization to improve outcomes.

Asunto(s)

RESUMEN

Background: Post-operative acute kidney injury (PO-AKI) is a common surgical complication consistently associated with subsequent morbidity and mortality. Prior kidney dysfunction is a major risk factor for PO-AKI, however it is unclear whether serum creatinine, the conventional kidney function marker, is optimal in this population. Serum cystatin C is a kidney function marker less affected by body composition and might provide better prognostic information in surgical patients. Methods: This was a pre-defined, secondary analysis of a multi-centre prospective cohort study of pre-operative functional capacity. Participants were aged ≥40 years, undergoing non-cardiac surgery. We assessed the association of pre-operative estimated glomerular filtration rate (eGFR) calculated using both serum creatinine and serum cystatin C with PO-AKI within 3 days after surgery, defined by KDIGO creatinine changes. The adjusted analysis accounted for established AKI risk factors. Results: A total of 1347 participants were included (median age 65 years, interquartile range 56-71), of whom 775 (58%) were male. A total of 82/1347 (6%) patients developed PO-AKI. These patients were older, had higher prevalence of cardiovascular disease and related medication, were more likely to have intra-abdominal procedures, had more intraoperative transfusion, and were more likely to be dead at 1 year after surgery 6/82 (7.3%) vs 33/1265 (2.7%) (P = .038). Pre-operative eGFR was lower in AKI than non-AKI patients using both creatinine and cystatin C. When both measurements were considered in a single age- and sex-adjusted model, eGFR-Cysc was strongly associated with PO-AKI, with increasing risk of AKI as eGFR-Cysc decreased below 90, while eGFR-Cr was no longer significantly associated. Conclusions: Data from over 1000 prospectively recruited surgical patients confirms pre-operative kidney function as major risk factor for PO-AKI. Of the kidney function markers available, compared with creatinine, cystatin C had greater strength of association with PO-AKI and merits further assessment in pre-operative assessment of surgical risk.

RESUMEN

BACKGROUND: Clinical presentation of postoperative myocardial infarction (POMI) is often silent. Several international guidelines recommend routine troponin surveillance in patients at risk. We compared how these different guidelines select patients for surveillance after noncardiac surgery with our established risk stratification model. METHODS: We used outcome data from two prospective studies: Measurement of Exercise Tolerance before Surgery (METS) and Troponin Elevation After Major non-cardiac Surgery (TEAMS). We compared the major American, Canadian, and European guideline recommendations for troponin surveillance with our established risk stratification model. For each guideline and model, we quantified the number of patients requiring monitoring, % POMI detected, sensitivity, specificity, diagnostic odds ratio, and number needed to screen (NNS). RESULTS: METS and TEAMS contributed 2350 patients, of whom 319 (14%) had myocardial injury, 61 (2.5%) developed POMI, and 14 (0.6%) died. Our risk stratification model selected fewer patients for troponin monitoring (20%), compared with the Canadian (78%) and European (79%) guidelines. The sensitivity to detect POMI was highest with the Canadian and European guidelines (0.85; 95% confidence interval [CI] 0.74-0.92). Specificity was highest using the American guidelines (0.91; 95% CI 0.90-0.92). Our risk stratification model had the best diagnostic odds ratio (2.5; 95% CI 1.4-4.2) and a lower NNS (21 vs 35) compared with the guidelines. CONCLUSIONS: Most postoperative myocardial infarctions were detected by the Canadian and European guidelines but at the cost of low specificity and a higher number of patients undergoing screening. Patient selection based on our risk stratification model was optimal.

Asunto(s)