RESUMEN

Background: During surgery, intraoperative hypotension is associated with postoperative morbidity and should therefore be avoided. Predicting the occurrence of hypotension in advance may allow timely interventions to prevent hypotension. Previous prediction models mostly use high-resolution waveform data, which is often not available. Methods: We utilised a novel temporal fusion transformer (TFT) algorithm to predict intraoperative blood pressure trajectories 7 min in advance. We trained the model with low-resolution data (sampled every 15 s) from 73,009 patients who were undergoing general anaesthesia for non-cardiothoracic surgery between January 1, 2017, and December 30, 2020, at the General Hospital of Vienna, Austria. The data set contained information on patient demographics, vital signs, medication, and ventilation. The model was evaluated using an internal (n = 8113) and external test set (n = 5065) obtained from the openly accessible Vital Signs Database. Findings: In the internal test set, the mean absolute error for predicting mean arterial blood pressure was 0.376 standard deviations-or 4 mmHg-and 0.622 standard deviations-or 7 mmHg-in the external test set. We also adapted the TFT model to binarily predict the occurrence of hypotension as defined by mean arterial blood pressure < 65 mmHg in the next one, three, five, and 7 min. Here, model discrimination was excellent, with a mean area under the receiver operating characteristic curve (AUROC) of 0.933 in the internal test set and 0.919 in the external test set. Interpretation: Our TFT model is capable of accurately forecasting intraoperative arterial blood pressure using only low-resolution data showing a low prediction error. When used for binary prediction of hypotension, we obtained excellent performance. Funding: No external funding.

RESUMEN

INTRODUCTION: Intraoperative Hypotension (IOH) poses a substantial risk during surgical procedures. The integration of Artificial Intelligence (AI) in predicting IOH holds promise for enhancing detection capabilities, providing an opportunity to improve patient outcomes. This systematic review and meta analysis explores the intersection of AI and IOH prediction, addressing the crucial need for effective monitoring in surgical settings. METHOD: A search of Pubmed, Scopus, Web of Science, and Embase was conducted. Screening involved two-phase assessments by independent reviewers, ensuring adherence to predefined PICOS criteria. Included studies focused on AI models predicting IOH in any type of surgery. Due to the high number of studies evaluating the hypotension prediction index (HPI), we conducted two sets of meta-analyses: one involving the HPI studies and one including non-HPI studies. In the HPI studies the following outcomes were analyzed: cumulative duration of IOH per patient, time weighted average of mean arterial pressure < 65 (TWA-MAP < 65), area under the threshold of mean arterial pressure (AUT-MAP), and area under the receiver operating characteristics curve (AUROC). In the non-HPI studies, we examined the pooled AUROC of all AI models other than HPI. RESULTS: 43 studies were included in this review. Studies showed significant reduction in IOH duration, TWA-MAP < 65 mmHg, and AUT-MAP < 65 mmHg in groups where HPI was used. AUROC for HPI algorithms demonstrated strong predictive performance (AUROC = 0.89, 95CI). Non-HPI models had a pooled AUROC of 0.79 (95CI: 0.74, 0.83). CONCLUSION: HPI demonstrated excellent ability to predict hypotensive episodes and hence reduce the duration of hypotension. Other AI models, particularly those based on deep learning methods, also indicated a great ability to predict IOH, while their capacity to reduce IOH-related indices such as duration remains unclear.

Asunto(s)

RESUMEN

PURPOSE: Intraoperative hypotension is associated with adverse outcomes. Predicting and proactively managing hypotension can reduce its incidence. Previously, hypotension prediction algorithms using artificial intelligence were developed for invasive arterial blood pressure monitors. This study tested whether routine non-invasive monitors could also predict intraoperative hypotension using deep learning algorithms. METHODS: An open-source database of non-cardiac surgery patients ( https://vitadb.net/dataset ) was used to develop the deep learning algorithm. The algorithm was validated using external data obtained from a tertiary Korean hospital. Intraoperative hypotension was defined as a systolic blood pressure less than 90 mmHg. The input data included five monitors: non-invasive blood pressure, electrocardiography, photoplethysmography, capnography, and bispectral index. The primary outcome was the performance of the deep learning model as assessed by the area under the receiver operating characteristic curve (AUROC). RESULTS: Data from 4754 and 421 patients were used for algorithm development and external validation, respectively. The fully connected model of Multi-head Attention architecture and the Globally Attentive Locally Recurrent model with Focal Loss function were able to predict intraoperative hypotension 5 min before its occurrence. The AUROC of the algorithm was 0.917 (95% confidence interval [CI], 0.915-0.918) for the original data and 0.833 (95% CI, 0.830-0.836) for the external validation data. Attention map, which quantified the contributions of each monitor, showed that our algorithm utilized data from each monitor with weights ranging from 8 to 22% for determining hypotension. CONCLUSIONS: A deep learning model utilizing multi-channel non-invasive monitors could predict intraoperative hypotension with high accuracy. Future prospective studies are needed to determine whether this model can assist clinicians in preventing hypotension in patients undergoing surgery with non-invasive monitoring.

Asunto(s)

RESUMEN

Background: Acute kidney injury (AKI) is a common surgical complication and is associated with intraoperative hypotension. However, the total duration and magnitude of intraoperative hypotension associated with AKI remains unknown. In this study, the causal relationship between the intraoperative arterial pressure and postoperative AKI was investigated among chronic hypertension patients undergoing non-cardiac surgery. Methods: A retrospective cohort study of 6552 hypertension patients undergoing non-cardiac surgery (2011 to 2019) was conducted. The primary outcome was AKI as diagnosed with the Kidney Disease-Improving Global Outcomes criteria and the primary exposure was intraoperative hypotension. Patients' baseline demographics, pre- and post-operative data were harvested and then analyzed with multivariable logistic regression to assess the exposure-outcome relationship. Results: Among 6552 hypertension patients, 579 (8.84%) had postoperative AKI after non-cardiac surgery. The proportions of patients admitted to ICU (3.97 vs. 1.24%, p < 0.001) and experiencing all-cause death (2.76 vs. 0.80%, p < 0.001) were higher in the patients with postoperative AKI. Moreover, the patients with postoperative AKI had longer hospital stays (13.50 vs. 12.00 days, p < 0.001). Intraoperative mean arterial pressure (MAP) < 60 mmHg for >20 min was an independent risk factor of postoperative AKI. Furthermore, MAP <60 mmHg for >10 min was also an independent risk factor of postoperative AKI in patients whose MAP was measured invasively in the subgroup analysis. Conclusions: Our work suggested that MAP < 60 mmHg for >10 min measured invasively or 20 min measured non-invasively during non-cardiac surgery may be the threshold of postoperative AKI development in hypertension patients. This work may serve as a perioperative management guide for chronic hypertension patients. Trial registration: clinical trial number: ChiCTR2100050209 (8/22/2021). http://www.chictr.org.cn/showproj.aspx?proj=132277.

RESUMEN

Intraoperative hypotension (IOH) is a common issue associated with acute kidney injury, myocardial injury, stroke, and death. IOH may be avoided with the incorporation of newer advanced hemodynamic monitoring technologies. This case study examines the use of advanced hemodynamic monitoring with an early warning system for the intraoperative hemodynamic management of a patient presenting for pancreaticoduodenectomy. Incorporating the hypotension prediction index and other hemodynamic parameters to anticipate impending hypotension and treat potential causative factors is an emerging technological advancement. Understanding and embracing the potential for new advanced hemodynamic technology to reduce intraoperative hypotension's severity, duration, and occurrence is key to reducing negative patient outcomes.

Asunto(s)

RESUMEN

BACKGROUND: Off-pump coronary artery bypass grafting (OPCABG) presents distinct hemodynamic characteristics, yet the relationship between intraoperative hypotension and short-term adverse outcomes remains clear. Our study aims to investigate association between intraoperative hypotension and postoperative acute kidney injury (AKI), mortality and length of stay in OPCABG patients. METHODS: Retrospective data of 494 patients underwent OPCABG from January 2016 to July 2023 were collected. We analyzed the relationship between intraoperative various hypotension absolute values (MAP > 75, 65 < MAP ≤ 75, 55 < MAP ≤ 65, MAP ≤ 55 mmHg) and postoperative AKI, mortality and length of stay. Logistic regression assessed the impacts of exposure variable on AKI and postoperative mortality. Linear regression was used to analyze risk factors on the length of intensive care unit stay (ICU) and hospital stay. RESULTS: The incidence of AKI was 31.8%, with in-hospital and 30-day mortality at 2.8% and 3.5%, respectively. Maintaining a MAP greater than or equal 65 mmHg [odds ratio (OR) 0.408; p = 0.008] and 75 mmHg (OR 0.479; p = 0.024) was significantly associated with a decrease risk of AKI compared to MAP less than 55 mmHg for at least 10 min. Prolonged hospital stays were linked to low MAP, while in-hospital mortality and 30-day mortality were not linked to IOH but exhibited correlation with a history of myocardial infarction. AKI showed correlation with length of ICU stay. CONCLUSIONS: MAP > 65 mmHg emerges as a significant independent protective factor for AKI in OPCABG and IOH is related to length of hospital stay. Proactive intervention targeting intraoperative hypotension may provide a potential opportunity to reduce postoperative renal injury and hospital stay. TRIAL REGISTRATION: ChiCTR2400082518. Registered 31 March 2024. https://www.chictr.org.cn/bin/project/edit?pid=225349 .

Asunto(s)

Asunto(s)

RESUMEN

BACKGROUND: Intraoperative hypotension is a common side effect of general anesthesia. Here we examined whether the Hypotension Prediction Index (HPI), a novel warning system, reduces the severity and duration of intraoperative hypotension during general anesthesia. METHODS: This randomized controlled trial was conducted in a tertiary referral hospital. We enrolled patients undergoing general anesthesia with invasive arterial monitoring. Patients were randomized 1:1 either to receive hemodynamic management with HPI guidance (intervention) or standard of care (control) treatment. Intraoperative hypotension treatment was initiated at HPI > 85 (intervention) or mean arterial pressure (MAP) < 65 mmHg (control). The primary outcome was hypotension severity, defined as a time-weighted average (TWA) MAP < 65 mmHg. Secondary outcomes were TWA MAP < 60 and < 55 mmHg. RESULTS: Of the 60 patients who completed the study, 30 were in the intervention group and 30 in the control group. The patients' median age was 62 years, and 48 of them were male. The median duration of surgery was 490 min. The median MAP before surgery presented no significant difference between the two groups. The intervention group showed significantly lower median TWA MAP < 65 mmHg than the control group (0.02 [0.003, 0.08] vs. 0.37 [0.20, 0.58], P < 0.001). Findings were similar for TWA MAP < 60 mmHg and < 55 mmHg. The median MAP during surgery was significantly higher in the intervention group than that in the control group (87.54 mmHg vs. 77.92 mmHg, P < 0.001). CONCLUSIONS: HPI guidance appears to be effective in preventing intraoperative hypotension during general anesthesia. Further investigation is needed to assess the impact of HPI on patient outcomes. TRIAL REGISTRATION: ClinicalTrials.gov (NCT04966364); 202105065RINA; Date of registration: July 19, 2021; The recruitment date of the first patient: July 22, 2021.

RESUMEN

STUDY OBJECTIVES: Evaluation of the association between intraoperative hypotension (IOH) and important postoperative outcomes after liver transplant such as incidence and severity of acute kidney injury (AKI), MACE and early allograft dysfunction (EAD). DESIGN: Retrospective, single institution study. SETTINGS: Operating room. PATIENTS: 1576 patients who underwent liver transplant in our institution between January 2005 and February 2022. MEASUREMENTS: IOH was measured as the time, area under the threshold (AUT), or time-weighted average (TWA) of mean arterial pressure (MAP) less than certain thresholds (55,60 and 65 mmHg). Associations between IOH exposures and AKI severity were assessed via proportional odds models. The odds ratio from the proportional odds model estimated the relative odds of having higher stage of AKI for higher exposure to IOH. Associations between exposures and MACE and EAD were assessed through logistic regression models. Potential confounding variables including patient baseline and surgical characteristics were adjusted for all models. MAIN RESULTS: The primary analysis included 1576 surgeries that met the inclusion and exclusion criteria. Of those, 1160 patients (74%) experienced AKI after liver transplant surgery, with 780 (49%), 248(16%), and 132 (8.4%) experiencing mild, moderate, and severe injury, respectively. No significant association between hypotension exposure and postoperative AKI (yes or no) nor severity of AKI was observed. The odds ratios (95% CI) of having more severe AKI were 1.02 (0.997, 1.04) for a 50-mmHg·min increase in AUT of MAP <55 mmHg (P = 0.092); 1.03 (0.98, 1.07) for a 15-min increase in time spent under MAP <55 mmHg (P = 0.27); and 1.24 (0.98, 1.57) for a 1 mmHg increase in TWA of MAP <55 mmHg (P = 0.068). The associations between IOH and the incidence of MACE or EAD were not significant. CONCLUSION: Our results did not show the association between IOH and investigated outcomes.

Asunto(s)

RESUMEN

BACKGROUND: The Saint Louis University Score (SLUScore) was developed to quantify intraoperative blood pressure trajectories and their associated risk for adverse outcomes. This study examines the prevalence and severity of intraoperative hypotension described by the SLUScore and its relationship with 30-day mortality in surgical subtypes. METHODS: This retrospective analysis of perioperative data included surgical cases performed between January 1, 2010, and December 31, 2020. The SLUScore is calculated from cumulative time-periods for which the mean arterial pressure is below a range of hypotensive thresholds. After calculating the SLUScore for each surgical procedure, we quantified the prevalence and severity of intraoperative hypotension for each surgical procedure and the association between intraoperative hypotension and 30-day mortality. We used binary logistic regression to quantify the potential contribution of intraoperative hypotension to mortality. RESULTS: We analysed 490 982 cases (57.7% female; mean age 57 yr); 33.2% of cases had a SLUScore>0, a median SLUScore of 13 (inter-quartile range [IQR] 7-21), with 1.19% average mortality. The SLUScore was associated with mortality in 12/14 surgical groups. The increases in the odds ratio for death within 30 days of surgery per SLUScore increment were: all surgery types 3.5% (95% confidence interval [95% CI] 3.2-3.9); abdominal/transplant surgery 6% (95% CI 1.5-10.7); thoracic surgery1.5% (95% CI 1-3.3); vascular surgery 3.01% (95% CI 1.9-4.05); spine/neurosurgery 1.1% (95% CI 0.1-2.1); orthopaedic surgery 1.4% (95% CI 0.7-2.2); gynaecological surgery 6.3% (95% CI 2.5-10.1); genitourinary surgery 4.84% (95% CI 3.5-6.15); gastrointestinal surgery 5.2% (95% CI 3.9-6.4); gastroendoscopy 5.5% (95% CI 4.4-6.7); general surgery 6.3% (95% CI 5.5-7.1); ear, nose, and throat surgery 1.6% (95% CI 0-3.27); and cardiac electrophysiology (including pacemaker procedures) 6.6% (95% CI 1.1-12.4). CONCLUSIONS: The SLUScore was independently, but variably, associated with 30-day mortality after noncardiac surgery.

Asunto(s)

RESUMEN

INTRODUCTION: Intraoperative goal-directed hemodynamic therapy (GDHT) is a cornerstone of enhanced recovery protocols. We hypothesized that use of an advanced noninvasive intraoperative hemodynamic monitoring system to guide GDHT may decrease intraoperative hypotension (IOH) and improve perfusion during pancreatic resection. METHODS: The monitor uses machine learning to produce the Hypotension Prediction Index to predict hypotensive episodes. A clinical decision-making algorithm uses the Hypotension Prediction Index and hemodynamic data to guide intraoperative fluid versus pressor management. Pre-implementation (PRE), patients were placed on the monitor and managed per usual. Post-implementation (POST), anesthesia teams were educated on the algorithm and asked to use the GDHT guidelines. Hemodynamic data points were collected every 20 s (8942 PRE and 26,638 POST measurements). We compared IOH (mean arterial pressure <65 mmHg), cardiac index >2, and stroke volume variation <12 between the two groups. RESULTS: 10 patients were in the PRE and 24 in the POST groups. In the POST group, there were fewer minimally invasive resections (4.2% versus 30.0%, P = 0.07), more pancreaticoduodenectomies (75.0% versus 20.0%, P < 0.01), and longer operative times (329.0 + 108.2 min versus 225.1 + 92.8 min, P = 0.01). After implementation, hemodynamic parameters improved. There was a 33.3% reduction in IOH (5.2% ± 0.1% versus 7.8% ± 0.3%, P < 0.01, a 31.6% increase in cardiac index >2.0 (83.7% + 0.2% versus 63.6% + 0.5%, P < 0.01), and a 37.6% increase in stroke volume variation <12 (73.2% + 0.3% versus 53.2% + 0.5%, P < 0.01). CONCLUSIONS: Advanced intraoperative hemodynamic monitoring to predict IOH combined with a clinical decision-making tree for GDHT may improve intraoperative hemodynamic parameters during pancreatectomy. This warrants further investigation in larger studies.

Asunto(s)

Asunto(s)

RESUMEN

INTRODUCTION: Kidney transplantation is a definitive treatment for end-stage renal disease. It is associated with improved life expectancy and quality of life. One of the most common complications following kidney transplantation is graft rejection. To our knowledge, no previous study has identified rejection risk factors in kidney transplant recipients in Saudi Arabia. Therefore, this study aimed to determine the specific risk factors of graft rejection. METHODS: A multicenter case-control study was conducted at four transplant centers in Saudi Arabia. All adult patients who underwent a renal transplant between January 1, 2015 and December 31, 2021 were screened for eligibility. Included patients were categorized into two groups (cases and control) based on the occurrence of biopsy-proven rejection within 2 years. The primary outcome was to determine the risk factors for rejection within the 2 years of transplant. Exact matching was utilized using a 1:4 ratio based on patients' age, gender, and transplant year. RESULTS: Out of 1,320 screened renal transplant recipients, 816 patients were included. The overall prevalence of 2-year rejection was 13.9%. In bivariate analysis, deceased donor status, the presence of donor-specific antibody (DSA), intraoperative hypotension, Pseudomonas aeruginosa, Candida, and any infection within 2 years were linked with an increased risk of 2-year rejection. However, in the logistic regression analysis, the presence of DSA was identified as a significant risk for 2-year rejection (adjusted OR: 2.68; 95% CI: 1.10, 6.49, p = 0.03). Furthermore, blood infection, infected with Pseudomonas aeruginosa or BK virus within 2 years of transplant, were associated with higher odds of 2-year rejection (adjusted OR: 3.10; 95% CI: 1.48, 6.48, p = 0.003, adjusted OR: 3.23; 95% CI: 0.87, 11.97, p = 0.08 and adjusted OR: 2.76; 95% CI: 0.89, 8.48, p = 0.07, respectively). CONCLUSION: Our findings emphasize the need for appropriate prevention and management of infections following kidney transplantation to avoid more serious problems, such as rejection, which could significantly raise the likelihood of allograft failure and probably death. Further studies with larger sample sizes are needed to investigate the impact of serum chloride levels prior to transplant and intraoperative hypotension on the risk of graft rejection and failure.

Asunto(s)

Asunto(s)

Asunto(s)

RESUMEN

BACKGROUND: Intraoperative hypotension during cesarean section has become a serious complication for maternal and fetal healthy. It is commonly encountered by subarachnoid anesthesia. However, currently used control methods have varying degrees of side effects, such as drugs. The Root Cause Analysis (RCA) - Plan, Do, Check, Act (PDCA) is a new model of care that identifies the root causes of problems. The study aimed to demonstrate the usefulness of RCA-PDCA nursing methods in preventing intraoperative hypotension during cesarean section and to predict the occurrence of intraoperative hypotension through a machine learning model. METHODS: Patients who underwent cesarean section at Traditional Chinese Medicine of Southwest Medical University from January 2023 to December 2023 were retrospectively screened, and the data of their gestational times, age, height, weight, history of allergies, intraoperative vital signs, fetal condition, operative time, fluid out and in, adverse effects, use of vasopressor drugs, anxiety-depression-pain scores, and satisfaction were collected and analyzed. The statistically different features were screened and five machine learning models were used as predictive models to assess the usefulness of the RCA-PDCA model of care. RESULTS: (1) Compared with the general nursing model, the RCA-PDCA nursing model significantly reduces the incidence of intraoperative hypotension and postoperative complications in cesarean delivery, and the patient experience is comfortable and satisfactory. (2) Among the five machine learning models, the RF model has the best predictive performance, and the accuracy of the random forest model in preventing intraoperative hypotension is as high as 90%. CONCLUSION: Through computer machine learning model analysis, we prove the importance of the RCA-PDCA nursing method in the prevention of intraoperative hypotension during cesarean section, especially the Random Forest model which performed well and promoted the application of artificial intelligence computer learning methods in the field of medical analysis.

Asunto(s)

RESUMEN

BACKGROUND: With the increasing use of immune checkpoint inhibitors (ICIs) in cancer therapy, perioperative healthcare professionals need to be vigilant about potential immune-related adverse events (irAEs). We report a case of severe postinduction hypotension in a patient undergoing laparotomy due to suspected intraabdominal bleeding from gastric cancer and Krukenberg tumors, caused by unrecognized hypothyroidism precipitated by ICIs. CASE PRESENTATION: A 65-year-old Chinese female with a history of gastric adenocarcinoma and Krukenberg tumors, previously treated with nivolumab, presented to the emergency room with abdominal pain and hypotension. Despite ruling out other causes, including hypovolemia and anaphylaxis, her hypotension persisted. The patient was found to have severe hypothyroidism, likely an irAE from the use of nivolumab. Thyroxine replacement therapy resolved the hypotension, and the patient recovered uneventfully after surgery. CONCLUSIONS: This case underscores the importance of considering irAEs, such as hypothyroidism, in patients treated with ICIs. Perioperative healthcare providers must remain vigilant for potential complications and promptly recognize and manage irAEs to optimize patient outcomes.

Asunto(s)