Ability of an Arterial Waveform Analysis-Derived Hypotension Prediction Index to Predict Future Hypotensive Events in Surgical Patients

Impact of Predictive Hemodynamic Monitoring on Intraoperative Hypotension and Postoperative Complications in Multi-level Spinal Fusion Surgery

STUDY DESIGN

Prospective longitudinal comparative cohort.

OBJECTIVES

To determine if the use of predictive hemodynamic monitoring (PHM) during elective multi-level posterior instrumented spine fusions decreases episodes of intraoperative hypotension (IOH) and complications.

BACKGROUND

A recent study showed an association between complications and duration of IOH in patients undergoing multi-level spine fusions. Whether the use of PHM to maintain hemodynamic stability intraoperatively decreases postoperative complications has not been evaluated.

METHODS

Adults undergoing elective multi-level posterior thoracolumbar fusion with arterial line blood pressure monitoring were identified and stratified into those in which predictive hemodynamic monitoring (PHM) was used and those in which it was not. Number of minutes of hypotension (MAP <65 mm Hg) and hypertension (MAP ≥100 mm Hg), volume of fluids, blood products and vasopressors administered intraoperatively and within the first 4 hours postoperatively as well as the number and type of postoperative complications were collected.

RESULTS

The 47 cases in the PHM group and 70 in the non-PHM group had similar demographic and operative characteristics. A shorter duration of IOH was seen in the PHM group (8.13 min) compared with the non-PHM group (13.28 min, P=0.029); and a shorter duration of intraoperative hypertension seen in the PHM group (0.46 min) compared with the non-PHM group (1.38 min, P=0.032). There was a smaller number of patients in the PHM group who had a surgical site infection (2.% vs. 13%, P=0.027), postoperative nausea and vomiting (0 vs. 14%, P=0.004) and postoperative cognitive dysfunction (6% vs. 19%, P=0.049) compared with the non-PHM group. There was also a statistically significant shorter length of hospitalization in the PHM (4.62 d) compared with the non-PHM group (5.99 d, P=0.017).

CONCLUSION

Predictive hemodynamic monitoring to manage intraoperative hemodynamic instability is associated with a shorter duration of intraoperative hypotension, a lower prevalence of complications, and a decreased hospital stay in multi-level spinal fusion surgery.

Machine learning or traditional statistical methods for predictive modelling in perioperative medicine: A narrative review

Prediction of outcomes in perioperative medicine is key to decision-making and various prediction models have been created to help quantify and communicate those risks to both patients and clinicians. Increasingly, machine learning (ML) is being favoured over more traditional techniques to improve prediction of outcomes, however, the studies are of varying quality. It is also not known whether any increase in predictive performance using ML algorithms transpires into a clinically meaningful benefit. This coupled with the difficulty in interrogating ML algorithms is a potential cause of concern within the medical community. In this review, we provide a concise appraisal of studies which develop perioperative predictive ML models and compare predictive performance to traditional statistical models. The search strategy, title and abstract screening, and full-text reviews produced 37 studies for data extraction. Initially designed as a systematic review but due to the heterogeneity of the population and outcomes, was written in the narrative. Perioperative ML and traditional predictive models continue to be developed and published across a range of populations. This review highlights several studies which show that ML can enhance perioperative prediction models, although this is not universal, and performance for both methods remain context dependent. By focusing on relevant patient-centred outcomes, model interpretability, external validation, and maintaining high standards of reporting and methodological transparency, researchers can develop ML models alongside traditional methods to enhance clinical decision-making and improve patient care.

Perioperative goal-directed therapy with artificial intelligence to reduce the incidence of intraoperative hypotension and renal failure in patients undergoing lung surgery: A pilot study

STUDY OBJECTIVE

The aim of this study was to investigate whether goal-directed treatment using artificial intelligence, compared to standard care, can reduce the frequency, duration, and severity of intraoperative hypotension in patients undergoing single lung ventilation, with a potential reduction of postoperative acute kidney injury (AKI).

DESIGN

single center, single-blinded randomized controlled trial.

SETTING

University hospital operating room.

PATIENTS

150 patients undergoing lung surgery with single lung ventilation were included.

INTERVENTIONS

Patients were randomly assigned to two groups: the Intervention group, where a goal-directed therapy based on the Hypotension Prediction Index (HPI) was implemented; the Control group, without a specific hemodynamic protocol.

MEASUREMENTS

The primary outcome measures include the frequency, duration of intraoperative hypotension, furthermore the Area under MAP 65 and the time-weighted average (TWA) of MAP of 65. Other outcome parameters are the incidence of AKI and myocardial injury after non-cardiac surgery (MINS).

MAIN RESULTS

The number of hypotensive episodes was lower in the intervention group compared to the control group (0 [0-1] vs. 1 [0-2]; p = 0.01), the duration of hypotension was shorter in the intervention group (0 min [0-3.17] vs. 2.33 min [0-7.42]; p = 0.01). The area under the MAP of 65 (0 mmHg * min [0-12] vs. 10.67 mmHg * min [0-44.16]; p < 0.01) and the TWA of MAP of 65 (0 mmHg [0-0.08] vs. 0.07 mmHg [0-0.25]; p < 0.01) were lower in the intervention group. The incidence of postoperative AKI showed no differences between the groups (6.7 % vs.4.2 %; p = 0.72). There was a trend to lower incidence of MINS in the intervention group (17.1 % vs. 31.8 %; p = 0.07). A tendency towards reduced postoperative infection was seen in the intervention group (16.0 % vs. 26.8 %; p = 0.16).

CONCLUSIONS

The implementation of a treatment algorithm based on HPI allowed us to decrease the duration and severity of hypotension in patients undergoing lung surgery. It did not result in a significant reduction in the incidence of AKI, however we observed a tendency towards lower incidence of MINS in the intervention group, along with a slight reduction in postoperative infections.

Intraoperative hemodynamic management in abdominal aortic surgery guided by the Hypotension Prediction Index: the Hemas multicentric observational study

BACKGROUND

Intraoperative hypotension (IOH) during non-cardiac surgery is closely associated with postoperative complications. Hypotensive events are more likely during major open vascular surgery. We prospectively investigated whether our institutional algorithm of cardiocirculatory management, which included the Hypotension Prediction Index (HPI), a predictive model of hypotension of the Hemosphere™ platform (Edwards Lifescience, Irwin, CA, USA), was able to reduce the incidence and severity of intraoperative hypotension during open abdominal aortic aneurysm repair.

METHODS

A multi-center observational study was conducted at IRCCS-Humanitas Research Hospital (Milan) and AO Mauriziano Umberto I Hospital (Turin) between July 2022 and September 2023, enrolling patients undergoing elective open abdominal aortic aneurysm repair. A hemodynamic protocol based on the Acumen-HPI Hemosphere™ platform was employed, integrating advanced parameters (e.g., HPI, Ea-dyn, dP/dt) and tailored interventions to minimize intraoperative hypotension. The primary endpoint was cumulative intraoperative hypotension time < 10% of surgical time, with secondary endpoints including incidence of hypotensive events, time-weighted averages of MAP < 65 mmHg (TWA65) and < 50 mmHg (TWA50), and postoperative complications.

RESULTS

We enrolled 53 patients submitted to open abdominal aortic repair. The primary endpoint (time in hypotension < 10%) was successfully reached: 5 [1-10] %. The targeted time-weighted average (< 0.40 mmHg) both for MAP < 65 mmHg (TWA65) and MAP < 50 mmHg (severe hypotension; TWA50) were reached: TWA65 = 0.26 [0.04-0.65] mmHg and TWA50 = 0.00 [0.00-0.01].

CONCLUSIONS

Our hemodynamic management algorithm based on the HPI and other parameters of the Hemosphere™ platform was able to limit the incidence and severity of intraoperative hypotension during open abdominal aortic repair.

TRIAL REGISTRATION

NCT05478564.

The hypotension prediction index in major abdominal surgery - A prospective randomised clinical trial protocol

Background

Patients undergoing major abdominal surgery are at increased risk of developing perioperative hypotension, which is associated with increased mortality and morbidity. Despite using advanced technologies such as evaluating arterial pressure derived cardiac output, anaesthetic management to maintain hemodynamic stability is still reactive when the clinical decision is made after hypotension has developed. Previous perioperative goal-directed studies have not proven the benefits of this approach with high certainty. A new, approved technology called the Hypotension Prediction Index (HPI) aims to prevent hypotension occurrence by allowing the precise hemodynamic monitoring of patients under general anaesthesia, significantly reducing intraoperative hypotension events. This prospective randomised clinical trial aims to compare the rate of perioperative hypotension in patients undergoing major abdominal surgery according to their type of hemodynamic monitoring.

Methods

and Analysis: Patients meeting the inclusion criteria will be randomly assigned to receive hemodynamic assessment with arterial pressure cardiac output (APCO) monitoring (group A) or hemodynamic monitoring with the HPI software (group B). The primary outcome is a time-weighted average (TWA) mean arterial pressure (MAP) of <65 mmHg: TWA MAP = (depth of hypotension [in mmHg] below a MAP of 65 mmHg × time [in minutes] spent below a MAP of 65 mmHg)/total duration of the operation (in minutes). Its secondary outcomes include perioperative hemodynamic management and the rate of postoperative complications.

Ethics and dissemination

This trial was approved by the Ethics Committee of the Poznan University of Medical Sciences (KB-559/220; date: 01/07/2022). Its results will be submitted for publication in a peer-reviewed journal.

Trial registration number

NCT06247384.

Deep learning model to identify and validate hypotension endotypes in surgical and critically ill patients

BACKGROUND

Hypotension is associated with organ injury and death in surgical and critically ill patients. In clinical practice, treating hypotension remains challenging because it can be caused by various underlying haemodynamic alterations. We aimed to identify and independently validate endotypes of hypotension in big datasets of surgical and critically ill patients using unsupervised deep learning.

METHODS

We developed an unsupervised deep learning algorithm, specifically a deep learning autoencoder model combined with a Gaussian mixture model, to identify endotypes of hypotension based on stroke volume index, heart rate, systemic vascular resistance index, and stroke volume variation observed during episodes of hypotension. The algorithm was developed with data from 871 surgical patients who had 6962 hypotensive events and validated in two independent datasets, one including 1000 surgical patients who had 7904 hypotensive events and another including 1000 critically ill patients who had 53 821 hypotensive events. We defined hypotension as a mean arterial pressure <65 mm Hg for at least 1 min.

RESULTS

In the development dataset, we identified four hypotension endotypes. Based on their physiological and clinical characteristics, we labelled them as: vasodilation, hypovolaemia, myocardial depression, and bradycardia. The same four hypotension endotypes were identified in the two independent validation datasets of surgical and critically ill patients.

CONCLUSIONS

Unsupervised deep learning identified four endotypes of hypotension in surgical and critically ill patients: vasodilation, hypovolaemia, myocardial depression, and bradycardia. The algorithm provides the probability of each endotype for each hypotensive data point. Identifying hypotensive endotypes could guide clinicians to causal treatments for hypotension.

Forecasting intraoperative hypotension during hepatobiliary surgery

Prediction and avoidance of intraoperative hypotension (IOH) can lead to less postoperative morbidity. Machine learning (ML) is increasingly being applied to predict IOH. We hypothesize that incorporating demographic and physiological features in an ML model will improve the performance of IOH prediction. In addition, we added a "dial" feature to alter prediction performance. An ML prediction model was built based on a multivariate random forest (RF) trained algorithm using 13 physiologic time series and patient demographic data (age, sex, and BMI) for adult patients undergoing hepatobiliary surgery. A novel implementation was developed with an adjustable, multi-model voting (MMV) approach to improve performance in the challenging context of a dynamic, sliding window for which the propensity of data is normal (negative for IOH). The study cohort included 85% of subjects exhibiting at least one IOH event. Males constituted 70% of the cohort, median age was 55.8 years, and median BMI was 27.7. The multivariate model yielded average AUC = 0.97 in the static context of a single prediction made up to 8 min before a possible IOH event, and it outperformed a univariate model based on MAP-only (average AUC = 0.83). The MMV model demonstrated AUC = 0.96, PPV = 0.89, and NPV = 0.98 within the challenging context of a dynamic sliding window across 40 min prior to a possible IOH event. We present a novel ML model to predict IOH with a distinctive "dial" on sensitivity and specificity to predict first IOH episode during liver resection surgeries.

Effect of a Machine Learning-Derived Early Warning Tool With Treatment Protocol on Hypotension During Cardiac Surgery and ICU Stay: The Hypotension Prediction 2 (HYPE-2) Randomized Clinical Trial

OBJECTIVES

Cardiac surgery is associated with perioperative complications, some of which might be attributable to hypotension. The Hypotension Prediction Index (HPI), a machine-learning-derived early warning tool for hypotension, has only been evaluated in noncardiac surgery. We investigated whether using HPI with diagnostic guidance reduced hypotension during cardiac surgery and in the ICU.

DESIGN

Randomized clinical trial conducted between May 2021 and February 2023.

SETTING

Single-center study conducted in an academic hospital in the Netherlands.

PATIENTS

Adults undergoing elective on-pump coronary artery bypass grafting, with or without single heart valve surgery, were enrolled if a mean arterial pressure (MAP) greater than or equal to 65 mm Hg was targeted during the surgical off-pump phases and ICU stay. After eligibility assessment, 142 of 162 patients approached gave informed consent for participation.

INTERVENTIONS

Patients randomized 1:1 received either diagnostic guidance in addition to standard care if HPI reached greater than or equal to 75 ( n = 72) or standard care alone ( n = 70).

MEASUREMENTS AND MAIN RESULTS

The primary outcome was the severity of hypotension, measured as time-weighted average (TWA) of MAP less than 65 mm Hg. Secondary outcomes encompassed hypertension severity and intervention disparities. Of 142 patients randomized, 130 were included in the primary analysis. The HPI group showed 63% reduction in median TWA of hypotension compared with the standard care group, with a median of differences of -0.40 mm Hg (95% CI, -0.65 to -0.27; p < 0.001). In the HPI group, patients spent a median 28 minutes (95% CI, 17-44 min) less in hypotension, with a measurement duration of 322 minutes in the HPI group and 333 minutes in the standard care group. No significant differences were observed in hypertension severity, treatment choice, or fluid, vasopressors, and inotrope amounts.

CONCLUSIONS

Using HPI combined with diagnostic guidance on top of standard care significantly decreased hypotension severity in elective cardiac surgery patients compared with standard care.

A comparison between invasive and noninvasive measurement of the Hypotension Prediction Index: A post hoc analysis of a prospective cohort study

BACKGROUND

Clinical trials and validation studies demonstrate promising hypotension prediction capability by the Hypotension Prediction Index (HPI). Most studies that evaluate HPI derive it from invasive blood pressure readings, but a direct comparison with the noninvasive alternative remains undetermined. Such a comparison could provide valuable insights for clinicians in deciding between invasive and noninvasive monitoring strategies.

OBJECTIVES

Evaluating predictive differences between HPI when obtained through noninvasive versus invasive blood pressure monitoring.

DESIGN

Post hoc analysis of a prospective observational study conducted between 2018 and 2020.

SETTING

Single-centre study conducted in an academic hospital in the Netherlands.

PATIENTS

Adult noncardiac surgery patients scheduled for over 2 h long elective procedures. After obtaining informed consent, 91 out of the 105 patients had sufficient data for analysis.

MAIN OUTCOME MEASURES

The primary outcome was the difference in area under the receiver-operating characteristics (ROC) curve (AUC) obtained for HPI predictions between the two datasets. Additionally, difference in time-to-event estimations were calculated.

RESULTS

AUC (95% confidence interval (CI)) results revealed a nonsignificant difference between invasive and noninvasive HPI, with areas of 94.2% (90.5 to 96.8) and 95.3% (90.4 to 98.2), respectively with an estimated difference of 1.1 (-3.9 to 6.1)%; P  = 0.673. However, noninvasive HPI demonstrated significantly longer time-to-event estimations for higher HPI values.

CONCLUSION

Noninvasive HPI is reliably accessible to clinicians during noncardiac surgery, showing comparable accuracy in HPI probabilities and the potential for additional response time.

TRIAL REGISTRATION

Clinicaltrials.gov (NCT03795831) https://clinicaltrials.gov/study/NCT03795831.

Evaluation of hypotension prediction index software in patients undergoing orthotopic liver transplantation: retrospective observational study

BACKGROUND

Extreme hemodynamic changes, especially intraoperative hypotension (IOH), are common and often prolonged during Liver Transplant (LT) surgery and during initial hours of recovery. Hypotension Prediction Index (HPI) software is one of the tools which can help in proactive hemodynamic management. The accuracy of the advanced hemodynamic parameters such as Cardiac Output (CO) and Systemic Vascular Resistance (SVR) obtained from HPI software and prediction performance of the HPI in LT surgery remains unknown.

METHODS

This was a retrospective observational study conducted in a tertiary academic center with a large liver transplant program. We enrolled 23 adult LT patients who received both Pulmonary Artery Catheter (PAC) and HPI software monitoring. Primarily, we evaluated agreement between PAC and HPI software measured CO and SVR. A priori, we defined a relative difference of less than 20% between measurements as an adequate agreement for a pair of measurements and estimated the Lin's Concordance Correlation Coefficient and Bland-Altman Limits of Agreement (LOA). Clinically acceptable LOA was defined as ± 1 L.min-1 for CO and ± 200 dynes s.cm-5 for SVR. Secondary outcome was the ability of the HPI to predict future hypotension, defined as Mean Arterial Pressure (MAP) less than 65 mmHg lasting at least one minute. We estimated sensitivity, positive predictive value, and time from alert to hypotensive events for HPI software.

RESULTS

Overall, 125 pairs of CO and 122 pairs of SVR records were obtained from 23 patients. Based on our predefined criteria, only 42% (95% CI 30%, 55%) of CO records and 53% (95% CI 28%, 72%) of SVR records from HPI software were considered to agree with those from PAC. Across all patients, there were a total of 1860 HPI alerts (HPI ≥ 85) and 642 hypotensive events (MAP < 65 mmHg). Out of the 642 hypotensive events, 618 events were predicted by HPI alert with sensitivity of 0.96 (95% CI: 0.95). Many times, the HPI value remained above alert level and was followed by multiple hypotensive events. Thus, to evaluate PPV and time to hypotension metric, we considered only the first HPI alert followed by a hypotensive event ("true alerts"). The "true alert" was the first alert when there were several alerts before a hypotension. There were 614 "true alerts" and the PPV for HPI was 0.33 (95% CI 0.31, 0.35). The median time from HPI alert to hypotension was 3.3 [Q1, Q3: 1, 9.3] mins.

CONCLUSION

There was poor agreement between the pulmonary artery catheter and HPI software calculated advanced hemodynamic parameters (CO and SVR), in the patients undergoing LT surgery. HPI software had high sensitivity but poor specificity for hypotension prediction, resulting in a high burden of false alarms.

Intraoperative Hypotension Is an Important Modifiable Risk Factor for Major Complications in Spinal Fusion Surgery

STUDY DESIGN

Retrospective observational cohort.

OBJECTIVES

This study explores the impact of Intraoperative hypotension (IOH) on postoperative complications for major thoracolumbar spine fusion procedures.

SUMMARY OF BACKGROUND DATA

IOH with mean arterial pressure (MAP) <65 mm Hg is associated with postoperative acute kidney injury (AKI) in general surgery. In spinal deformity surgery, IOH is a contributing factor to MEP changes and spinal cord dysfunction with deformity correction.

METHODS

A total of 539 thoracolumbar fusion cases, more than six surgical levels and >3 hours duration, were identified. Anesthetic/surgical data included OR time, fluid volume, blood loss, blood product replacement and use of vasopressors. Arterial-line based MAP data was collected at 1-minute intervals. Cummulative duration of MAP <65 mm Hg was recorded. IOH within the first hour of surgery vs. the entire case was determined. Post-op course and complications including SSI, GI complications, pulmonary complications, MI, DVT, PE, AKI, and encephalopathy were noted. Cumulative complications were grouped as none, one to two complications, or more than three complications.

RESULTS

There was a significant association between occurrence of complications and duration of IOH within the first hour of surgery (8.2 vs . 5.6 min, P <0.001) and across the entire procedure (28.1 vs . 19.3 min, P =0.008). This association persisted for individual major complications including SSI, acute respiratory failure, PE, ileus requiring NGT, and postoperative cognitive dysfunction. Comparison of patients with zero versus one to two versus three or more complications demonstrated that patients with three or more complications had a longer duration of IOH in the first hour of the surgery and that patients who had no complications received less vasopressor than patients who had one to two or three or more complications.

CONCLUSION

This study identifies duration of IOH during the first hour of surgery as a previously unrecognized modifiable risk associated with major complications for multilevel lumbar fusion surgery.

LEVEL OF EVIDENCE

III.

Decreased cardio-respiratory information transfer is associated with deterioration and a poor prognosis in critically ill patients with sepsis

Assessing illness severity in the intensive care unit (ICU) is crucial for early prediction of deterioration and prognosis. Traditional prognostic scores often treat organ systems separately, overlooking the body's interconnected nature. Network physiology offers a new approach to understanding these complex interactions. This study used the concept of transfer entropy (TE) to measure information flow between heart rate (HR), respiratory rate (RR), and capillary oxygen saturation ([Formula: see text]) in critically ill patients with sepsis, hypothesizing that TE between these signals would correlate with disease outcome. The retrospective cohort study utilized the Medical Information Mart for Intensive Care III Clinical Database, including patients who met Sepsis-3 criteria on admission and had 30 min of continuous HR, RR, and [Formula: see text] data. TE between the signals was calculated to create physiological network maps. Cox regression assessed the relationship between cardiorespiratory network indices and both deterioration [Sequential Organ Failure Assessment (SOFA) score increase of ≥2 points at 48 h] and 30-day mortality. Among 164 patients, higher information flow from [Formula: see text] to HR [TE ([Formula: see text] → HR)] and reciprocal flow between HR and RR [TE (RR → HR) and TE (HR → RR)] were linked to reduced mortality, independent of age, mechanical ventilation, SOFA score, and comorbidity. Reductions in TE (HR → RR), TE (RR → HR), TE ([Formula: see text] → RR), and TE ([Formula: see text] → HR) were associated with an increased risk of 48-h deterioration. After adjustment for potential confounders, only TE (HR → RR) and TE (RR → HR) remained statistically significant. The study confirmed that physiological network mapping using routine signals in patients with sepsis could indicate illness severity and that higher TE values were generally associated with improved outcomes.NEW & NOTEWORTHY This study adopts an integrative approach through physiological network analysis to investigate sepsis, with the goal of identifying differences in information transfer between physiological signals in sepsis survivors versus nonsurvivors. We found that greater information flow between heart rate, respiratory rate, and capillary oxygen saturation was associated with reduced mortality, independent of age, disease severity, and comorbidities. In addition, reduced information transfer was linked to an increased risk of 48-h deterioration in patients with sepsis.

The Hemodynamic Management and Postoperative Outcomes After Cytoreductive Surgery and Hyperthermic Intraperitoneal Chemotherapy: A Prospective Observational Study

Background: Cytoreductive surgery with hyperthermic intraperitoneal chemotherapy (CRS-HIPEC) has become standard treatment for peritoneal cancers and metastases, significantly enhancing survival rates. This study evaluated the relationship between tumor burden, hemodynamic management, and postoperative outcomes after CRS-HIPEC. Methodology: This study included 203 patients undergoing CRS-HIPEC. The study was registered with ClinicalTrials.gov (NCT02754115). Routine and advanced hemodynamic monitoring was performed. Data on fluid and blood transfusions, coagulation management, body temperature, blood gases, Peritoneal Carcinomatosis Index (PCI), and chemotherapeutic agents used were collected. Postoperatively, complications using the Clavien-Dindo classification were employed. Primary outcomes assessed PCI's impact on hemodynamic parameters and fluid management, with secondary outcomes including postoperative complications, mortality, and length of ICU and hospital stays. Results: Patients with PCI > 20 experienced significantly longer surgeries (796.2 ± 158.3 min) as compared with patients with PCI 0-10 (551 ± 127 min) and patients with PCI between 11 and 20 (661.78 ± 137.7 min) (p ≤ 0.01). Patients with PCI > 20 received higher fluid requirements (mean: 5497.7 ± 2401.9 mL) as compared with PCI 0-10 (2631.2 ± 1459.9 mL) and PCI 10-20 (3964.65 ± 2044.6 mL) (p ≤ 0.01). Patients with PCI > 20 also had a prolonged ICU stays (median: 4 days) as compared with PCI 0-20 (median: 3 days). However, these differences were not significant in patients with PCI between 10 and 20. Significant differences in CI and SVI were observed among PCI groups during and after HIPEC. Significant differences were also observed among PCI groups for postoperative complications. Although 30-day survival rates varied clinically, they did not reach statistical significance. Conclusion: A higher PCI score was significantly associated with increased duration of surgery, fluid requirements, the need for invasive hemodynamic monitoring, postoperative complications, and longer ICU stays. Tailoring perioperative strategies based on PCI scores has the potential to optimize these outcomes. Trial Registration: ClinicalTrials.gov identifier: NCT02754115.

Overview of Wearable Healthcare Devices for Clinical Decision Support in the Prehospital Setting

Prehospital medical care is a major challenge for both civilian and military situations as resources are limited, yet critical triage and treatment decisions must be rapidly made. Prehospital medicine is further complicated during mass casualty situations or remote applications that require more extensive medical treatments to be monitored. It is anticipated on the future battlefield where air superiority will be contested that prolonged field care will extend to as much 72 h in a prehospital environment. Traditional medical monitoring is not practical in these situations and, as such, wearable sensor technology may help support prehospital medicine. However, sensors alone are not sufficient in the prehospital setting where limited personnel without specialized medical training must make critical decisions based on physiological signals. Machine learning-based clinical decision support systems can instead be utilized to interpret these signals for diagnosing injuries, making triage decisions, or driving treatments. Here, we summarize the challenges of the prehospital medical setting and review wearable sensor technology suitability for this environment, including their use with medical decision support triage or treatment guidance options. Further, we discuss recommendations for wearable healthcare device development and medical decision support technology to better support the prehospital medical setting. With further design improvement and integration with decision support tools, wearable healthcare devices have the potential to simplify and improve medical care in the challenging prehospital environment.

Beyond the debut: unpacking six years of Hypotension Prediction Index software in intraoperative hypotension prevention - a systematic review and meta-analysis

PURPOSE

Intraoperative hypotension (IOH) during general anesthesia is associated with higher morbidity and mortality, although randomized trials have not established a causal relation. Historically, our approach to IOH has been reactive. The Hypotension Prediction Index (HPI) is a machine learning software that predicts hypotension minutes in advance. This systematic review and meta-analysis explores whether using HPI alongside a personalized treatment protocol decreases intraoperative hypotension.

METHODS

A systematic search was performed in Pubmed and Scopus to retrieve articles published from January 2018 to February 2024 regarding the impact of the HPI software on reducing IOH in adult patients undergoing non-cardio/thoracic surgery. Excluded were case series, case reports, meta-analyses, systematic reviews, and studies using non-invasive arterial waveform analysis. The risk of bias was assessed by the Cochrane risk-of-bias tool (RoB 2) and the Risk Of Bias In Non-randomised Studies (ROBINS-I). A meta-analysis was undertaken solely for outcomes where sufficient data were available from the included studies.

RESULTS

9 RCTs and 5 cohort studies were retrieved. The overall median differences between the HPI-guided and the control groups were - 0.21 (95% CI:-0.33, -0.09) - p < 0.001 for the Time-Weighted Average (TWA) of Mean Arterial Pressure (MAP) < 65mmHg, -3.71 (95% CI= -6.67, -0.74)-p = 0.014 for the incidence of hypotensive episodes per patient, and - 10.11 (95% CI= -15.82, -4.40)-p = 0.001 for the duration of hypotension. Notably a large amount of heterogeneity was detected among the studies.

CONCLUSIONS

While the combination of HPI software with personalized treatment protocols may prevent intraoperative hypotension (IOH), the large heterogeneity among the studies and the lack of reliable data on its clinical significance necessitate further investigation.

Prediction of intraoperative hypotension using deep learning models based on non-invasive monitoring devices

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.

[Intraoperative hypotension in children-Measurement and treatment]

Intraoperative hypotension is a common perioperative complication in pediatric anesthesia. Oscillometric blood pressure measurement is therefore an essential part of standard perioperative monitoring in pediatric anesthesia. The optimum measurement site is the upper arm. Attention must be paid to the correct cuff size. Blood pressure should be measured before induction. In children undergoing major surgery or in critically ill children, invasive blood pressure measurement is still the gold standard. Continuous noninvasive measurement methods could be an alternative in the future.Threshold values to define hypotension remain unknown, even in awake children. There are also little data on hypotension thresholds in the perioperative setting. The most reliable measurement parameter for estimating hypotension is the mean arterial pressure. The threshold values for intraoperative hypotension are 40 mm Hg in newborns, 45 mm Hg in infants, 50 mm Hg in young children and 65 mm Hg in adolescents. Treatment should be initiated at a deviation of 10% and intensified at a deviation of 20%.Bolus administration of isotonic balanced crystalloid solutions, vasopressors and/or catecholamines are used as treatment options. Consistent and rapid intervention in the event of hypotension appears to be crucial. So far there is no evidence as to whether this leads to an improvement in outcome parameters.

Intraoperative Hypotension Prediction: Current Methods, Controversies, and Research Outlook

Intraoperative hypotension prediction has been increasingly emphasized due to its potential clinical value in reducing organ injury and the broad availability of large-scale patient datasets and powerful machine learning tools. Hypotension prediction methods can mitigate low blood pressure exposure time. However, they have yet to be convincingly demonstrated to improve objective outcomes; furthermore, they have recently become controversial. This review presents the current state of intraoperative hypotension prediction and makes recommendations on future research. We begin by overviewing the current hypotension prediction methods, which generally rely on the prevailing mean arterial pressure as one of the important input variables and typically show good sensitivity and specificity but low positive predictive value in forecasting near-term acute hypotensive events. We make specific suggestions on improving the definition of acute hypotensive events and evaluating hypotension prediction methods, along with general proposals on extending the methods to predict reduced blood flow and treatment effects. We present a start of a risk-benefit analysis of hypotension prediction methods in clinical practice. We conclude by coalescing this analysis with the current evidence to offer an outlook on prediction methods for intraoperative hypotension. A shift in research toward tailoring hypotension prediction methods to individual patients and pursuing methods to predict appropriate treatment in response to hypotension appear most promising to improve outcomes.

Development and external validation of temporal fusion transformer models for continuous intraoperative blood pressure forecasting

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.

Hypotension Prediction Index Is Equally Effective in Predicting Intraoperative Hypotension during Noncardiac Surgery Compared to a Mean Arterial Pressure Threshold: A Prospective Observational Study

BACKGROUND

The Hypotension Prediction Index is designed to predict intraoperative hypotension in a timely manner and is based on arterial waveform analysis using machine learning. It has recently been suggested that this algorithm is highly correlated with the mean arterial pressure itself. Therefore, the aim of this study was to compare the index with mean arterial pressure-based prediction methods, and it is hypothesized that their ability to predict hypotension is comparable.

METHODS

In this observational study, the Hypotension Prediction Index was used in addition to routine intraoperative monitoring during moderate- to high-risk elective noncardiac surgery. The agreement in time between the default Hypotension Prediction Index alarm (greater than 85) and different concurrent mean arterial pressure thresholds was evaluated. Additionally, the predictive performance of the index and different mean arterial pressure-based methods were assessed within 5, 10, and 15 min before hypotension occurred.

RESULTS

A total of 100 patients were included. A mean arterial pressure threshold of 73 mmHg agreed 97% of the time with the default index alarm, whereas a mean arterial pressure threshold of 72 mmHg had the most comparable predictive performance. The areas under the receiver operating characteristic curve of the Hypotension Prediction Index (0.89 [0.88 to 0.89]) and concurrent mean arterial pressure (0.88 [0.88 to 0.89]) were almost identical for predicting hypotension within 5 min, outperforming both linearly extrapolated mean arterial pressure (0.85 [0.84 to 0.85]) and delta mean arterial pressure (0.66 [0.65 to 0.67]). The positive predictive value was 31.9 (31.3 to 32.6)% for the default index alarm and 32.9 (32.2 to 33.6)% for a mean arterial pressure threshold of 72 mmHg.

CONCLUSIONS

In clinical practice, the Hypotension Prediction Index alarms are highly similar to those derived from mean arterial pressure, which implies that the machine learning algorithm could be substituted by an alarm based on a mean arterial pressure threshold set at 72 or 73 mmHg. Further research on intraoperative hypotension prediction should therefore include comparison with mean arterial pressure-based alarms and related effects on patient outcome.

EDITOR’S PERSPECTIVE

Comparison of Differences in Cohort (Forward) and Case Control (Backward) Methodologic Approaches for Validation of the Hypotension Prediction Index

BACKGROUND

The Hypotension Prediction Index (the index) software is a machine learning algorithm that detects physiologic changes that may lead to hypotension. The original validation used a case control (backward) analysis that has been suggested to be biased. This study therefore conducted a cohort (forward) analysis and compared this to the original validation technique.

METHODS

A retrospective analysis of data from previously reported studies was conducted. All data were analyzed identically with two different methodologies, and receiver operating characteristic curves were constructed. Both backward and forward analyses were performed to examine differences in area under the receiver operating characteristic curves for the Hypotension Prediction Index and other hemodynamic variables to predict a mean arterial pressure (MAP) less than 65 mmHg for at least 1 min 5, 10, and 15 min in advance.

RESULTS

The analysis included 2,022 patients, yielding 4,152,124 measurements taken at 20-s intervals. The area under the curve for the index predicting hypotension analyzed by backward and forward methodologies respectively was 0.957 (95% CI, 0.947 to 0.964) versus 0.923 (95% CI, 0.912 to 0.933) 5 min in advance, 0.933 (95% CI, 0.924 to 0.942) versus 0.923 (95% CI, 0.911 to 0.933) 10 min in advance, and 0.929 (95% CI, 0.918 to 0.938) versus 0.926 (95% CI, 0.914 to 0.937) 15 min in advance. No variable other than MAP had an area under the curve greater than 0.7. The areas under the curve using forward analysis for MAP predicting hypotension 5, 10, and 15 min in advance were 0.932 (95% CI, 0.920 to 0.940), 0.929 (95% CI, 0.918 to 0.938), and 0.932 (95% CI, 0.921 to 0.940), respectively. The R2 for the variation in the index due to MAP was 0.77.

CONCLUSIONS

Using an updated methodology, the study found that the utility of the Hypotension Prediction Index to predict future hypotensive events is high, with an area under the receiver operating characteristics curve similar to that of the original validation method.

EDITOR’S PERSPECTIVE

Predictive ability of hypotension prediction index and machine learning methods in intraoperative hypotension: a systematic review and meta-analysis

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.

A retrospective study of the effects of a vasopressor bolus on systolic slope (dP/dt) and dynamic arterial elastance (Eadyn)

BACKGROUND

To enhance the utility of functional hemodynamic monitoring, the variables systolic slope (dP/dt) and dynamic arterial elastance (Eadyn) are calculated by the Hypotension Prediction Index (HPI) Acumen® Software. This study was designed to characterize the effects of phenylephrine and ephedrine on dP/dt and Eadyn.

METHODS

This was a retrospective, non-randomized analysis of data collected during two clinical studies. All patients required intra-operative controlled mechanical ventilation and had an indwelling radial artery catheter connected to an Acumen IQ sensor. Raw arterial pressure waveform data was downloaded from the patient monitor and all hemodynamic measurements were calculated off-line. The anesthetic record was reviewed for bolus administrations of either phenylephrine or ephedrine. Cardiovascular variables prior to drug administration were compared to those following vasopressor administrations. The primary outcome was the difference for dP/dt and Eadyn at baseline compared with the average after the bolus administration. All data sets demonstrated non-normal distributions so statistical analysis of paired and unpaired data followed the Wilcoxon matched pairs signed-rank test or Mann-Whitney U test, respectively.

RESULTS

201 doses of phenylephrine and 100 doses of ephedrine were analyzed. All data sets are reported as median [95% CI]. Mean arterial pressure (MAP) increased from 62 [54,68] to 78 [76,80] mmHg following phenylephrine and from 59 [55,62] to 80 [77,83] mmHg following ephedrine. Stroke volume and cardiac output both increased. Stroke volume variation and pulse pressure variation decreased. Both drugs produced significant increases in dP/dt, from 571 [531, 645] to 767 [733, 811] mmHg/sec for phenylephrine and from 537 [509, 596] to 848 [779, 930] mmHg/sec for ephedrine. No significant changes in Eadyn were observed.

CONCLUSION

Bolus administration of phenylephrine or ephedrine increases dP/dt but does not change Eadyn. dP/dt demonstrates potential for predicting the inotropic response to phenylephrine or ephedrine, providing guidance for the most efficacious vasopressor when treating hypotension.

TRIAL REGISTRATION

Data was collected from two protocols. The first was deemed to not require written, informed consent by the Institutional Review Board (IRB). The second was IRB-approved (Effect of Diastolic Dysfunction on Dynamic Cardiac Monitors) and registered on ClinicalTrials.gov (NCT04177225).

Development and validation of a predictive model for PACU hypotension in elderly patients undergoing sedated gastrointestinal endoscopy

BACKGROUND

Hypotension, characterized by abnormally low blood pressure, is a frequently observed adverse event in sedated gastrointestinal endoscopy procedures. Although the examination time is typically short, hypotension during and after gastroscopy procedures is frequently overlooked or remains undetected. This study aimed to construct a risk nomogram for post-anesthesia care unit (PACU) hypotension in elderly patients undergoing sedated gastrointestinal endoscopy.

METHODS

This study involved 2919 elderly patients who underwent sedated gastrointestinal endoscopy. A preoperative questionnaire was used to collect data on patient characteristics; intraoperative medication use and adverse events were also recorded. The primary objective of the study was to evaluate the risk of PACU hypotension in these patients. To achieve this, the least absolute shrinkage and selection operator (LASSO) regression analysis method was used to optimize variable selection, involving cyclic coordinate descent with tenfold cross-validation. Subsequently, multivariable logistic regression analysis was applied to build a predictive model using the selected predictors from the LASSO regression. A nomogram was visually developed based on these variables. To validate the model, a calibration plot, receiver operating characteristic (ROC) curve, and decision curve analysis (DCA) were used. Additionally, external validation was conducted to further assess the model's performance.

RESULTS

The LASSO regression analysis identified predictors associated with an increased risk of adverse events during surgery: age, duration of preoperative water abstinence, intraoperative mean arterial pressure (MAP) <65 mmHg, decreased systolic blood pressure (SBP), and use of norepinephrine (NE). The constructed model based on these predictors demonstrated moderate predictive ability, with an area under the ROC curve of 0.710 in the training set and 0.778 in the validation set. The DCA indicated that the nomogram had clinical applicability when the risk threshold ranged between 20 and 82%, which was subsequently confirmed in the external validation with a range of 18-92%.

CONCLUSION

Incorporating factors such as age, duration of preoperative water abstinence, intraoperative MAP <65 mmHg, decreased SBP, and use of NE in the risk nomogram increased its usefulness for predicting PACU hypotension risk in elderly patient undergoing sedated gastrointestinal endoscopy.

Early Autocalibrated Arterial Waveform Analysis for the Management of Burn Shock-A Cohort Study

Adequate fluid therapy is crucial for resuscitation after major burns. To adapt this to individual patient demands, standard is adjustment of volume to laboratory parameters and values of enhanced hemodynamic monitoring. To implement calibrated parameters, patients must have reached the intensive care unit (ICU). The aim of this study was, to evaluate the use of an auto-calibrated enhanced hemodynamic monitoring device to improve fluid management before admission to ICU. We used PulsioflexProAqt® (Getinge) during initial treatment and burn shock resuscitation. Analysis was performed regarding time of measurement, volume management, organ dysfunction, and mortality. We conducted a monocentre, prospective cohort study of 20 severely burned patients, >20% total body surface area (TBSA), receiving monitoring immediately after admission. We compared to 57 patients, matched in terms of TBSA, age, sex, and existence of inhalation injury out of a retrospective control group, who received standard care. Hemodynamic measurement with autocalibrated monitoring started significantly earlier: 3.75(2.67-6.0) hours (h) after trauma in the study group versus 13.6(8.1-17.5) h in the control group (P < .001). Study group received less fluid after 6 h: 1.7(1.2-2.2) versus 2.3(1.6-2.8) ml/TBSA%/kg, P = .043 and 12 h: 3.0(2.5-4.0) versus 4.2(3.1-5.0) ml/TBSA%/kg, P = .047. Dosage of norepinephrine was higher after 18 h in the study group: 0.20(0.12-0.3) versus 0.08(0.02-0.18) µg/kg/min, P = .014. The study group showed no adult respiratory distress syndrome versus 21% in the control group, P = .031. There was no difference in other organ failures, organ replacement therapy, and mortality. The use of auto-calibrated enhanced hemodynamic monitoring is a fast and feasible way to guide early fluid therapy after burn trauma. It reduces the time to reach information about patient's volume capacity. Management of fluid application changed to a more restrictive fluid use in the early period of burn shock and led to a reduction of pulmonary complications.

Hypotension prediction index for prevention of intraoperative hypotension in patients undergoing general anesthesia: a randomized controlled trial

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.

LDSG-Net: an efficient lightweight convolutional neural network for acute hypotensive episode prediction during ICU hospitalization

Objective. Acute hypotension episode (AHE) is one of the most critical complications in intensive care unit (ICU). A timely and precise AHE prediction system can provide clinicians with sufficient time to respond with proper therapeutic measures, playing a crucial role in saving patients' lives. Recent studies have focused on utilizing more complex models to improve predictive performance. However, these models are not suitable for clinical application due to limited computing resources for bedside monitors.Approach. To address this challenge, we propose an efficient lightweight dilated shuffle group network. It effectively incorporates shuffling operations into grouped convolutions on the channel and dilated convolutions on the temporal dimension, enhancing global and local feature extraction while reducing computational load.Main results. Our benchmarking experiments on the MIMIC-III and VitalDB datasets, comprising 6036 samples from 1304 patients and 2958 samples from 1047 patients, respectively, demonstrate that our model outperforms other state-of-the-art lightweight CNNs in terms of balancing parameters and computational complexity. Additionally, we discovered that the utilization of multiple physiological signals significantly improves the performance of AHE prediction. External validation on the MIMIC-IV dataset confirmed our findings, with prediction accuracy for AHE 5 min prior reaching 93.04% and 92.04% on the MIMIC-III and VitalDB datasets, respectively, and 89.47% in external verification.Significance. Our study demonstrates the potential of lightweight CNN architectures in clinical applications, providing a promising solution for real-time AHE prediction under resource constraints in ICU settings, thereby marking a significant step forward in improving patient care.

Effect of using hypotension prediction index versus conventional goal-directed haemodynamic management to reduce intraoperative hypotension in non-cardiac surgery: A randomised controlled trial

STUDY OBJECTIVE

It remains unclear whether it is the hypotension prediction index itself or goal-directed haemodynamic therapy that mitigates intraoperative hypotension.

DESIGN

A single centre randomised controlled trial.

SETTING

Sapporo Medical University Hospital.

PATIENTS

A total of 64 adults patients undergoing major non-cardiac surgery under general anaesthesia.

INTERVENTIONS

Patients were randomly assigned to either group receiving conventional goal-directed therapy (FloTrac group) or combination of the hypotension prediction index and conventional goal-directed therapy (HPI group). To investigate the independent utility of the index, the peak rates of arterial pressure and dynamic arterial elastance were not included in the treatment algorithm for the HPI group.

MEASUREMENTS

The primary outcome was the time-weighted average of the areas under the threshold. Secondary outcomes were area under the threshold, the number of hypotension events, total duration of hypotension events, mean mean arterial pressure during the hypotension period, number of hypotension events with mean arterial pressure < 50 mmHg, amounts of fluids, blood products, blood loss, and urine output, frequency and amount of vasoactive agents, concentration of haemoglobin during the monitoring period, and 30-day mortality.

MAIN RESULTS

The time-weighted average of the area below the threshold was lower in the HPI group than in the control group; 0.19 mmHg (interquartile range, 0.06-0.80 mmHg) vs. 0.66 mmHg (0.28-1.67 mmHg), with a median difference of -0.41 mmHg (95% confidence interval, -0.69 to -0.10 mmHg), p = 0.005. Norepinephrine was administered to 12 (40%) and 5 (17%) patients in the HPI and FloTrac groups, respectively (p = 0.045). No significant differences were observed in the volumes of fluid and blood products between the study groups.

CONCLUSIONS

The current randomised controlled trial results suggest that using the hypotension prediction index independently lowered the cumulative amount of intraoperative hypotension during major non-cardiac surgery.

Effect of subclavian vein diameter combined with perioperative fluid therapy on preventing post-induction hypotension in patients with ASA status I or II

BACKGROUND

Perioperative hypotension is frequently observed following the initiation of general anesthesia administration, often associated with adverse outcomes. This study assessed the effect of subclavian vein (SCV) diameter combined with perioperative fluid therapy on preventing post-induction hypotension (PIH) in patients with lower ASA status.

METHODS

This two-part study included patients aged 18 to 65 years, classified as ASA physical status I or II, and scheduled for elective surgery. The first part (Part I) included 146 adult patients, where maximum SCV diameter (dSCVmax), minimum SCV diameter (dSCVmin), SCV collapsibility index (SCVCI) and SCV variability (SCVvariability) assessed using ultrasound. PIH was determined by reduction in mean arterial pressure (MAP) exceeding 30% from baseline measurement or any instance of MAP < falling below 65 mmHg for ≥ a duration of at least 1 min during the period from induction to 10 min after intubation. Receiver Operating Characteristic (ROC) curve analysis was employed to determine the predictive values of subclavian vein diameter and other relevant parameters. The second part comprised 124 adult patients, where patients with SCV diameter above the optimal cutoff value, as determined in Part I study, received 6 ml/kg of colloid solution within 20 min before induction. The study evaluated the impact of subclavian vein diameter combined with perioperative fluid therapy by comparing the observed incidence of PIH after induction of anesthesia.

RESULTS

The areas under the curves (with 95% confidence intervals) for SCVCI and SCVvariability were both 0.819 (0.744-0.893). The optimal cutoff values were determined to be 45.4% and 14.7% (with sensitivity of 76.1% and specificity of 86.7%), respectively. Logistic regression analysis, after adjusting for confounding factors, demonstrated that both SCVCI and SCVvariability were significant predictors of PIH. A threshold of 45.4% for SCVCI was chosen as the grouping criterion. The incidence of PIH in patients receiving fluid therapy was significantly lower in the SCVCI ≥ 45.4% group compared to the SCVCI < 45.4% group.

CONCLUSIONS

Both SCVCI and SCVvariability are noninvasive parameters capable of predicting PIH, and their combination with perioperative fluid therapy can reduce the incidence of PIH.

Impact of clinicians' behavior, an educational intervention with mandated blood pressure and the hypotension prediction index software on intraoperative hypotension: a mixed methods study

PURPOSE

Intraoperative hypotension (IOH) is associated with adverse outcomes. We therefore explored beliefs regarding IOH and barriers to its treatment. Secondarily, we assessed if an educational intervention and mandated mean arterial pressure (MAP), or the implementation of the Hypotension Prediction Index-software (HPI) were associated with a reduction in IOH.

METHODS

Structured interviews (n = 27) and questionnaires (n = 84) were conducted to explore clinicians' beliefs and barriers to IOH treatment, in addition to usefulness of HPI questionnaires (n = 14). 150 elective major surgical patients who required invasive blood pressure monitoring were included in three cohorts to assess incidence and time-weighted average (TWA) of hypotension (MAP < 65 mmHg). Cohort one received standard care (baseline), the clinicians of cohort two had a training on hypotension and a mandated MAP > 65 mmHg, and patients of the third cohort received protocolized care using the HPI.

RESULTS

Clinicians felt challenged to manage IOH in some patients, yet they reported sufficient knowledge and skills. HPI-software was considered useful and beneficial. No difference was found in incidence of IOH between cohorts. TWA was comparable between baseline and education cohort (0.15 mmHg [0.05-0.41] vs. 0.11 mmHg [0.02-0.37]), but was significantly lower in the HPI cohort (0.04 mmHg [0.00 to 0.11], p < 0.05 compared to both).

CONCLUSIONS

Clinicians believed they had sufficient knowledge and skills, which could explain why no difference was found after the educational intervention. In the HPI cohort, IOH was significantly reduced compared to baseline, therefore HPI-software may help prevent IOH.

TRIAL REGISTRATION

ISRCTN 17,085,700 on May 9th, 2019.

AcumenTM hypotension prediction index guidance for prevention and treatment of hypotension in noncardiac surgery: a prospective, single-arm, multicenter trial

BACKGROUND

Intraoperative hypotension is common during noncardiac surgery and is associated with postoperative myocardial infarction, acute kidney injury, stroke, and severe infection. The Hypotension Prediction Index software is an algorithm based on arterial waveform analysis that alerts clinicians of the patient's likelihood of experiencing a future hypotensive event, defined as mean arterial pressure < 65 mmHg for at least 1 min.

METHODS

Two analyses included (1) a prospective, single-arm trial, with continuous blood pressure measurements from study monitors, compared to a historical comparison cohort. (2) A post hoc analysis of a subset of trial participants versus a propensity score-weighted contemporaneous comparison group, using external data from the Multicenter Perioperative Outcomes Group (MPOG). The trial included 485 subjects in 11 sites; 406 were in the final effectiveness analysis. The post hoc analysis included 457 trial participants and 15,796 comparison patients. Patients were eligible if aged 18 years or older, American Society of Anesthesiologists (ASA) physical status 3 or 4, and scheduled for moderate- to high-risk noncardiac surgery expected to last at least 3 h.

MEASUREMENTS

minutes of mean arterial pressure (MAP) below 65 mmHg and area under MAP < 65 mmHg.

RESULTS

Analysis 1: Trial subjects (n = 406) experienced a mean of 9 ± 13 min of MAP below 65 mmHg, compared with the MPOG historical control mean of 25 ± 41 min, a 65% reduction (p < 0.001). Subjects with at least one episode of hypotension (n = 293) had a mean of 12 ± 14 min of MAP below 65 mmHg compared with the MPOG historical control mean of 28 ± 43 min, a 58% reduction (p< 0.001). Analysis 2: In the post hoc inverse probability treatment weighting model, patients in the trial demonstrated a 35% reduction in minutes of hypotension compared to a contemporaneous comparison group [exponentiated coefficient: - 0.35 (95%CI - 0.43, - 0.27); p < 0.001].

CONCLUSIONS

The use of prediction software for blood pressure management was associated with a clinically meaningful reduction in the duration of intraoperative hypotension. Further studies must investigate whether predictive algorithms to prevent hypotension can reduce adverse outcomes.

TRIAL REGISTRATION

Clinical trial number: NCT03805217. Registry URL: https://clinicaltrials.gov/ct2/show/NCT03805217 . Principal investigator: Xiaodong Bao, MD, PhD. Date of registration: January 15, 2019.

Effect of machine learning-guided haemodynamic optimization on postoperative free flap perfusion in reconstructive maxillofacial surgery: A study protocol

AIMS

Intraoperative hypotension and liberal fluid haemodynamic therapy are associated with postoperative medical and surgical complications in maxillofacial free flap surgery. The novel haemodynamic parameter hypotension prediction index (HPI) has shown good performance in predicting hypotension by analysing arterial pressure waveform in various types of surgery. HPI-based haemodynamic protocols were able to reduce the duration and depth of hypotension. We will try to determine whether haemodynamic therapy based on HPI can improve postoperative flap perfusion and tissue oxygenation by improving intraoperative mean arterial pressure and reducing fluid infusion.

METHODS

We present here a study protocol for a single centre, randomized, controlled trial (n = 42) in maxillofacial patients undergoing free flap surgery. Patients will be randomized into an intervention or a control group. In the intervention, group haemodynamic optimization will be guided by machine learning algorithm and functional haemodynamic parameters presented by the HemoSphere platform (Edwards Lifesciences, Irvine, CA, USA), most importantly, HPI. Tissue oxygen saturation of the free flap will be monitored noninvasively by near-infrared spectroscopy during the first 24 h postoperatively. The primary outcome will be the average value of tissue oxygen saturation in the first 24 h postoperatively.

Validation of Preload Assessment Technologies at Altitude in a Porcine Model of Hemorrhage

INTRODUCTION

Dynamic preload assessment measures including pulse pressure variation (PPV), stroke volume variation (SVV), pleth variability index (PVI), and hypotension prediction index (HPI) have been utilized clinically to guide fluid management decisions in critically ill patients. These values aid in the balance of correcting hypotension while avoiding over-resuscitation leading to respiratory failure and increased mortality. However, these measures have not been previously validated at altitude or in those with temporary abdominal closure (TAC).

METHODS

Forty-eight female swine (39 ± 2 kg) were separated into eight groups (n = 6) including all combinations of flight versus ground, hemorrhage versus no hemorrhage, and TAC versus no TAC. Flight animals underwent simulated aeromedical evacuation via an altitude chamber at 8000 ft. Hemorrhagic shock was induced via stepwise hemorrhage removing 10% blood volume in 15-min increments to a total blood loss of 40% or a mean arterial pressure of 35 mmHg. Animals were then stepwise transfused with citrated shed blood with 10% volume every 15 min back to full blood volume. PPV, SVV, PVI, and HPI were monitored every 15 min throughout the simulated aeromedical evacuation or ground control. Blood samples were collected and analyzed for serum levels of serum IL-1β, IL-6, IL-8, and TNF-α.

RESULTS

Hemorrhage groups demonstrated significant increases in PPV, SVV, PVI, and HPI at each step compared to nonhemorrhage groups. Flight increased PPV (P = 0.004) and SVV (P = 0.003) in hemorrhaged animals. TAC at ground level increased PPV (P < 0.0001), SVV (P = 0.0003), and PVI (P < 0.0001). When TAC was present during flight, PPV (P = 0.004), SVV (P = 0.003), and PVI (P < 0.0001) values were decreased suggesting a dependent effect between altitude and TAC. There were no significant differences in serum IL-1β, IL-6, IL-8, or TNF-α concentration between injury groups.

CONCLUSIONS

Based on our study, PPV and SVV are increased during flight and in the presence of TAC. Pleth variability index is slightly increased with TAC at ground level. Hypotension prediction index demonstrated no significant changes regardless of altitude or TAC status, however this measure was less reliable once the resuscitation phase was initiated. Pleth variability index may be the most useful predictor of preload during aeromedical evacuation as it is a noninvasive modality.

Hypotension prediction index for the prevention of hypotension during surgery and critical care: A narrative review

Surgeons and anesthesia clinicians commonly face a hemodynamic disturbance known as intraoperative hypotension (IOH), which has been linked to more severe postoperative outcomes and increases mortality rates. Increased occurrence of IOH has been positively associated with mortality and incidence of myocardial infarction, stroke, and organ dysfunction hypertension. Hence, early detection and recognition of IOH is meaningful for perioperative management. Currently, when hypotension occurs, clinicians use vasopressor or fluid therapy to intervene as IOH develops but interventions should be taken before hypotension occurs; therefore, the Hypotension Prediction Index (HPI) method can be used to help clinicians further react to the IOH process. This literature review evaluates the HPI method, which can reliably predict hypotension several minutes before a hypotensive event and is beneficial for patients' outcomes.

The Incidence of Perioperative Hypotension in Patients Undergoing Major Abdominal Surgery with the Use of Arterial Waveform Analysis and the Hypotension Prediction Index Hemodynamic Monitoring-A Retrospective Analysis

Intraoperative hypotension (IH) is common in patients receiving general anesthesia and can lead to serious complications such as kidney failure, myocardial injury and increased mortality. The Hypotension Prediction Index (HPI) algorithm is a machine learning system that analyzes the arterial pressure waveform and alerts the clinician of an impending hypotension event. The purpose of the study was to compare the frequency of perioperative hypotension in patients undergoing major abdominal surgery with different types of hemodynamic monitoring. The study included 61 patients who were monitored with the arterial pressure-based cardiac output (APCO) technology (FloTrac group) and 62 patients with the Hypotension Prediction Index algorithm (HPI group). Our primary outcome was the time-weighted average (TWA) of hypotension below < 65 mmHg. The median TWA of hypotension in the FloTrac group was 0.31 mmHg versus 0.09 mmHg in the HPI group (p = 0.000009). In the FloTrac group, the average time of hypotension was 27.9 min vs. 8.1 min in the HPI group (p = 0.000023). By applying the HPI algorithm in addition to an arterial waveform analysis alone, we were able to significantly decrease the frequency and duration of perioperative hypotension events in patients who underwent major abdominal surgery.

CON: The hypotension prediction index is not a validated predictor of hypotension

The Hypotension Prediction Index (HPI) algorithm is a commercial prediction algorithm developed to predict hypotension, a mean arterial pressure (MAP) below 65 mmHg. Although HPI has been investigated in several studies, recent concerns of have been raised regarding HPI's predictive abilities, which may have been overstated. A selection bias may have forced the HPI algorithm to learn almost exclusively from MAP. This CON position paper describes the selection bias further and summarises the scientific status of HPI's predictive abilities, including the meaning of a recent erratum retracting the primary conclusion of a published HPI validation study. We argue that the HPI algorithm needs re-validation or complete re-development to achieve a clinically relevant 'added value' in comparison with the predictive performance of a simple and costless MAP alarm threshold in the range of 70 to 75 mmHg.

[Big data and artificial intelligence in anesthesia : Reality or fiction?]

Big data and artificial intelligence are buzzwords that everyone is talking about and yet always provide a touch of science fiction to the scenery. What is the status of these topics in anesthesia? Are the first robots already rolling through the corridors while doctors are getting bored as all the work has been done? Spoiler alert! We are still far away from achieving this. Initially, paper charts and analogue notes stand in the way of comprehensive digitization. Source systems need to be merged and data standardized, harmonized and validated. Therefore, the friendly android that is rolling towards us, waving and holding a freshly brewed cup of coffee in our thoughts will have to wait; however, a glimpse of the future is already evident in some clinics and the first promising developments are already showing what could be the standard tomorrow. Learning algorithms calculate the length of stay individually for each patient in the intensive care unit (ICU), reducing negative consequences such as readmission and mortality. The field of ultrasound technology for regional anesthesia and closed-loop anesthesia systems is also demonstrating the benefits of artificial intelligence (AI)-assisted technologies in practice. The efforts are diverse and ambitious but they repeatedly collide with privacy challenges and significant capital expenditure, which weigh heavily on an already financially strained healthcare system; however, anyone who listens carefully to the medical staff knows that robots are not what they would expect and the buzzwords big data and artificial intelligence might be less science fiction than initially assumed.

Personalized Predictive Hemodynamic Management for Gynecologic Oncologic Surgery: Feasibility of Cost-Benefit Derivatives of Digital Medical Devices

BACKGROUND

Intraoperative hypotension is associated with increased perioperative complications, hospital length of stay (LOS) and healthcare expenditure in gynecologic surgery. We tested the hypothesis that the adoption of a machine learning-based warning algorithm (hypotension prediction index-HPI) might yield an economic advantage, with a reduction in adverse outcomes that outweighs the costs for its implementation as a medical device.

METHODS

A retrospective-matched cohort cost-benefit Italian study in gynecologic surgery was conducted. Sixty-six female patients treated with standard goal-directed therapy (GDT) were matched in a 2:1 ratio with thirty-three patients treated with HPI based on ASA status, diagnosis, procedure, surgical duration and age.

RESULTS

The most relevant contributor to medical costs was operating room occupation (46%), followed by hospital stay (30%) and medical devices (15%). Patients in the HPI group had EURO 300 greater outlay for medical devices without major differences in total costs (GDT 5425 (3505, 8127), HPI 5227 (4201, 7023) p = 0.697). A pre-specified subgroup analysis of 50% of patients undergoing laparotomic surgery showed similar medical device costs and total costs, with a non-significant saving of EUR 1000 in the HPI group (GDT 8005 (5961, 9679), HPI 7023 (5227, 11,438), p = 0.945). The hospital LOS and intensive care unit stay were similar in the cohorts and subgroups.

CONCLUSIONS

Implementation of HPI is associated with a scenario of cost neutrality, with possible economic advantage in high-risk settings.

Comparison of propofol vs. remimazolam on emergence profiles after general anesthesia: A randomized clinical trial

STUDY OBJECTIVE

The emergence profiles in patients undergoing total intravenous anesthesia with either propofol or remimazolam with flumazenil reversal were compared.

DESIGN

A prospective, double-blind, randomized trial.

SETTING

An operating room and a post-anesthesia care unit (PACU).

PATIENTS

Adult patients (n = 100) having American Society of Anesthesiologists (ASA) physical status of I-III undergoing general anesthesia were enrolled and randomly assigned to the propofol or the remimazolam group.

INTERVENTIONS

The propofol group received target-controlled infusion of propofol, and the remimazolam group received continuous infusion of remimazolam. Continuous infusion of remifentanil was used in both groups. For emergence, flumazenil was used in increments of 0.2 mg in the remimazolam group.

MEASUREMENTS

The primary outcome was the time required for the patient to obey verbal commands. The secondary outcomes included the time to bispectral index (BIS) over 80, the time to laryngeal mask airway (LMA) removal, the Richmond Agitation-Sedation Scale (RASS) scores in the PACU, and adverse events throughout the study period.

MAIN RESULTS

The time taken to obey verbal commands was significantly longer in the propofol group than the remimazolam group (14 [9, 19]) vs. 5 [3, 7]) minutes, P < 0.001; median difference -9, 95% confidence interval -11 to -6). The times to BIS over 80 and to LMA removal were also significantly longer in the propofol group. In addition, the RASS score upon arrival to the PACU differed significantly between the two groups (P = 0.006). Re-sedation in the PACU was observed in 11 (22%) of the patients in the remimazolam group.

CONCLUSIONS

Remimazolam-based total intravenous anesthesia with flumazenil reversal may be effective in reducing emergence time, but a significant incidence of re-sedation was observed in the PACU. Further studies are needed to determine adequate dose and timing of routine flumazenil use and minimize the risk of re-sedation.

Machine Learning of Physiologic Waveforms and Electronic Health Record Data: A Large Perioperative Data Set of High-Fidelity Physiologic Waveforms

Perioperative morbidity and mortality are significantly associated with both static and dynamic perioperative factors. The studies investigating static perioperative factors have been reported; however, there are a limited number of previous studies and data sets analyzing dynamic perioperative factors, including physiologic waveforms, despite its clinical importance. To fill the gap, the authors introduce a novel large size perioperative data set: Machine Learning Of physiologic waveforms and electronic health Record Data (MLORD) data set. They also provide a concise tutorial on machine learning to illustrate predictive models trained on complex and diverse structures in the MLORD data set.

The role of compression in large scale data transfer and storage of typical biomedical signals at hospitals

In modern hospitals, monitoring patients' vital signs and other biomedical signals is standard practice. With the advent of data-driven healthcare, Internet of medical things, wearable technologies, and machine learning, we expect this to accelerate and to be used in new and promising ways, including early warning systems and precision diagnostics. Hence, we see an ever-increasing need for retrieving, storing, and managing the large amount of biomedical signal data generated. The popularity of standards, such as HL7 FHIR for interoperability and data transfer, have also resulted in their use as a data storage model, which is inefficient. This article raises concern about the inefficiency of using FHIR for storage of biomedical signals and instead highlights the possibility of a sustainable storage based on data compression. Most reported efforts have focused on ECG signals; however, many other typical biomedical signals are understudied. In this article, we are considering arterial blood pressure, photoplethysmography, and respiration. We focus on simple lossless compression with low implementation complexity, low compression delay, and good compression ratios suitable for wide adoption. Our results show that it is easy to obtain a compression ratio of 2.7:1 for arterial blood pressure, 2.9:1 for photoplethysmography, and 4.1:1 for respiration.

Prediction of episode of hemodynamic instability using an electrocardiogram based analytic: a retrospective cohort study

BACKGROUND

Predicting the onset of hemodynamic instability before it occurs remains a sought-after goal in acute and critical care medicine. Technologies that allow for this may assist clinicians in preventing episodes of hemodynamic instability (EHI). We tested a novel noninvasive technology, the Analytic for Hemodynamic Instability-Predictive Indicator (AHI-PI), which analyzes a single lead of electrocardiogram (ECG) and extracts heart rate variability and morphologic waveform features to predict an EHI prior to its occurrence.

METHODS

Retrospective cohort study at a quaternary care academic health system using data from hospitalized adult patients between August 2019 and April 2020 undergoing continuous ECG monitoring with intermittent noninvasive blood pressure (NIBP) or with continuous intraarterial pressure (IAP) monitoring.

RESULTS

AHI-PI's low and high-risk indications were compared with the presence of EHI in the future as indicated by vital signs (heart rate > 100 beats/min with a systolic blood pressure < 90 mmHg or a mean arterial blood pressure of < 70 mmHg). 4,633 patients were analyzed (3,961 undergoing NIBP monitoring, 672 with continuous IAP monitoring). 692 patients had an EHI (380 undergoing NIBP, 312 undergoing IAP). For IAP patients, the sensitivity and specificity of AHI-PI to predict EHI was 89.7% and 78.3% with a positive and negative predictive value of 33.7% and 98.4% respectively. For NIBP patients, AHI-PI had a sensitivity and specificity of 86.3% and 80.5% with a positive and negative predictive value of 11.7% and 99.5% respectively. Both groups performed with an AUC of 0.87. AHI-PI predicted EHI in both groups with a median lead time of 1.1 h (average lead time of 3.7 h for IAP group, 2.9 h for NIBP group).

CONCLUSIONS

AHI-PI predicted EHIs with high sensitivity and specificity and within clinically significant time windows that may allow for intervention. Performance was similar in patients undergoing NIBP and IAP monitoring.

Hypotension Prediction Index and Incidence of Perioperative Hypotension: A Single-Center Propensity-Score-Matched Analysis

(1) Background: Intraoperative hypotension is common and is associated with increased morbidity and mortality. The Hypotension Prediction Index (HPI) is an advancement of arterial waveform analysis and allows preventive treatments. We used a propensity-score-matched study design to test whether application of the HPI reduces hypotensive events in non-cardiac surgery patients; (2) Methods: 769 patients were selected for propensity score matching. After matching, both HPI and non-HPI groups together comprised n = 136 patients. A goal-directed treatment protocol was applied in both groups. The primary endpoint was the incidence and duration of hypotensive events defined as MAP < 65 mmHg, evaluated by the time-weighted average (TWA) of hypotension. (3) Results: The median TWA of hypotension below 65 mmHg in the matched cohort was 0.180 mmHg (IQR 0.060, 0.410) in the non-HPI group vs. 0.070 mmHg (IQR 0.020, 0.240) in the HPI group (p < 0.001). TWA was higher in patients with ASA classification III/IV (0.170 mmHg; IQR 0.035, 0.365) than in patients with ASA status II (0.100; IQR 0.020, 0.250; p = 0.02). Stratification by intervention group showed no differences in the HPI group while TWA values in the non-HPI group were more than twice as high in patients with ASA status III/IV (p = 0.01); (4) Conclusions: HPI reduces intraoperative hypotension in a matched cohort seen for TWA below 65 mmHg and relative time in hypotension. In addition, non-HPI patients with ASA status III/IV showed a higher TWA compared with HPI-patients, indicating an advantageous effect of using HPI in patients at higher risk.

Blood Pressure Goals in Critically Ill Patients

Blood pressure goals in the intensive care unit (ICU) have been extensively investigated in large datasets and have been associated with various harm thresholds at or greater than a mean pressure of 65 mm Hg. While it is difficult to perform interventional randomized trials of blood pressure in the ICU, important evidence does not support defense of a higher pressure, except in retrospective database analyses. Perfusion pressure may be a more important target than mean pressure, even more so in the vulnerable patient population. In the cardiac ICU, blood pressure targets are tailored to specific cardiac pathophysiology and patient characteristics. Generally, the goal is to maintain adequate blood pressure within a certain range to support cardiac function and to ensure end organ perfusion. Individualized targets demand the use of both invasive and noninvasive monitoring modalities and frequent titration of medications and/or mechanical circulatory support where necessary. In this review, we aim to identify appropriate blood pressure targets in the ICU, recognizing special patient populations and outlining the risk factors and predictors of end organ failure.