Skin mottling score assesses peripheral tissue hypoperfusion in critically ill patients following cardiac surgery.

BACKGROUND: Skin mottling is a common manifestation of peripheral tissue hypoperfusion, and its severity can be described using the skin mottling score (SMS). This study aims to evaluate the value of the SMS in detecting peripheral tissue hypoperfusion in critically ill patients following cardiac surgery. METHODS: Critically ill patients following cardiac surgery with risk factors for tissue hypoperfusion were enrolled (n = 373). Among these overall patients, we further defined a hypotension population (n = 178) and a shock population (n = 51). Hemodynamic and perfusion parameters were recorded. The primary outcome was peripheral hypoperfusion, defined as significant prolonged capillary refill time (CRT, > 3.0 s). The characteristics and hospital mortality of patients with and without skin mottling were compared. The area under receiver operating characteristic curves (AUROC) were used to assess the accuracy of SMS in detecting peripheral hypoperfusion. Besides, the relationships between SMS and conventional hemodynamic and perfusion parameters were investigated, and the factors most associated with the presence of skin mottling were identified. RESULTS: Of the 373-case overall population, 13 (3.5%) patients exhibited skin mottling, with SMS ranging from 1 to 5 (5, 1, 2, 2, and 3 cases, respectively). Patients with mottling had lower mean arterial pressure, higher vasopressor dose, less urine output (UO), higher CRT, lactate levels and hospital mortality (84.6% vs. 12.2%, p < 0.001). The occurrences of skin mottling were higher in hypotension population and shock population, reaching 5.6% and 15.7%, respectively. The AUROC for SMS to identify peripheral hypoperfusion was 0.64, 0.68, and 0.81 in the overall, hypotension, and shock populations, respectively. The optimal SMS threshold was 1, which corresponded to specificities of 98, 97 and 91 and sensitivities of 29, 38 and 67 in the three populations (overall, hypotension and shock). The correlation of UO, lactate, CRT and vasopressor dose with SMS was significant, among them, UO and CRT were identified as two major factors associated with the presence of skin mottling. CONCLUSION: In critically ill patients following cardiac surgery, SMS is a very specific yet less sensitive parameter for detecting peripheral tissue hypoperfusion.

Predictive value of estimated plasma volume for postoperative hypotension in percutaneous intramyocardial septal radiofrequency ablation treating for hypertrophic obstructive cardiomyopathy.

BACKGROUND: Estimated plasma volume status (ePVS) estimated by the Duarte formula is associated with clinical outcomes in patients with heart failure. It remains unclear the predictive value of the ePVS to the postoperative hypotension (POH) in percutaneous intramyocardial septal radiofrequency ablation (PIMSRA) treating hypertrophic obstructive cardiomyopathy (HOCM). METHODS: Data of HOCM patients who underwent PIMSRA were retrospectively collected. Preoperative ePVS was calculated using the Duarte formulas which derived from hemoglobin and hematocrit ratios. Clinical variables including physical assessment, biological and echocardiographic parameters were recorded. Patients were labeled with or without POH according to the medical record in the hospital. Univariable and multivariable logistic regression were performed to evaluate the association between ePVS and POH. Using different thresholds derived from quartiles and the best cutoff value of the receiver operating characteristic curve, the diagnostic performance of ePVS was quantified. RESULTS: Among the 405 patients included in this study, 53 (13.1%) patients were observed with symptomatic POH. Median (IQR) of ePVS in overall patients was 3.77 (3.27~4.40) mL/g and in patients with POH were higher than those without POH. The ePVS was associated with POH, with the odds ratio of 1.669 (95% CI 1.299 ~ 2.144) per mL/g. After adjusted by potential confounders, ePVS remained independently associated with POH, with the approximate odds ratio in different models. CONCLUSION: The preoperative ePVS derived from the Duarte formulas was independently associated with postoperative hypotension in HOCM patients who underwent PIMSRA and showed prognostic value to the risk stratification of postoperative management. TRIAL REGISTRATION: NCT06003478 (22/08/2023).

Teamwork matters: The association between nontechnical skills and cardiac arrest in trauma patients presenting with hypotension.

BACKGROUND: The impact of trauma team dynamics on outcomes in injured patients is not completely understood. We sought to evaluate the association between trauma team function, as measured by a modified Trauma Non-Technical Skills assessment, and cardiac arrest in hypotensive trauma patients. We hypothesized that better team function is associated with a decreased probability of developing cardiac arrest. METHODS: Trauma video review was used to collect data from resuscitations of adult hypotensive trauma patients at 19 centers. Hypotension at emergency department presentation was defined as an initial systolic blood pressure <90 mm Hg or an initial systolic blood pressure ≥90 mm Hg followed by a systolic blood pressure <90 mm Hg within the first 5 minutes. Team dynamics were scored using a modified Trauma Non-Technical Skills assessment composed of 5 domains with combined scores ranging from 5 (best) to 15 (worst). Scores were compared between cardiac arrest/noncardiac arrest cases in the trauma bay. Logistic regression was used to evaluate the independent association between the Trauma Non-Technical Skills assessment and cardiac arrest. RESULTS: A total of 430 patients were included (median age 43 years [interquartile range: 29-61]; 71.8% male; 36% penetrating mechanism; median Injury Severity Score 20 [10-33]; 11% experienced cardiac arrest in trauma bay). The median total Trauma Non-Technical Skills assessment score was 7 (6-9), higher in patients who experienced cardiac arrest in the trauma bay (9 [6-10] vs 7 [6-9]; P = .016). This association persisted after controlling for age, sex, mechanism, injury severity, initial systolic blood pressure, and initial Glasgow Coma Scale score (adjusted odds ratio: 1.28; 95% confidence interval:1.11-1.48; P < .001), indicating a ∼3% higher predicted probability of cardiac arrest per Trauma Non-Technical Skills point. CONCLUSION: Better team function is independently associated with a decreased probability of cardiac arrest in trauma patients presenting with hypotension. This suggests that trauma team training may improve outcomes in peri-arrest patients.

External validation of the prediction model of intradialytic hypotension: a multicenter prospective cohort study.

OBJECTIVE: Intradialytic hypotension (IDH) is a common and serious complication in patients with Maintenance Hemodialysis (MHD). The purpose of this study is to externally verify three IDH risk prediction models recently developed by Ma et al. and recalibrate, update and present the optimal model to improve the accuracy and applicability of the model in clinical environment. METHODS: A multicenter prospective cohort study of patients from 11 hemodialysis centers in Sichuan Province, China, was conducted using convenience sampling from March 2022 to July 2022, with a follow-up period of 1 month. Model performance was assessed by: (1) Discrimination: Evaluated through the computation of the Area Under Curve (AUC) and its corresponding 95% confidence intervals. (2) Calibration: scrutinized through visual inspection of the calibration plot and utilization of the Brier score. (3) The incremental value of risk prediction and the utility of updating the model were gauged using NRI (Net Reclassification Improvement) and IDI (Integrated Discrimination Improvement). Decision Curve Analysis (DCA) was employed to evaluate the clinical benefit of updating the model. RESULTS: The final cohort comprised 2235 individuals undergoing maintenance hemodialysis, exhibiting a 14.6% occurrence rate of IDH. The externally validated Area Under the Curve (AUC) values for the three original prediction models were 0.746 (95% CI: 0.718 to 0.775), 0.709 (95% CI: 0.679 to 0.739), and 0.735 (95% CI: 0.706 to 0.764) respectively. Conversely, the AUC value for the recalibrated and updated columnar plot model reached 0.817 (95% CI: 0.791 to 0.842), accompanied by a Brier score of 0.081. Furthermore, Decision Curve Analysis (DCA) exhibited a net benefit within the threshold probability range of 15.2% to 87.1%. CONCLUSION: Externally validated, recalibrated, updated, and presented IDH prediction models may serve as a valuable instrument for evaluating IDH risk in clinical practice. Furthermore, they hold the potential to guide clinical providers in discerning individuals at risk and facilitating judicious clinical intervention decisions.

Intraoperative Blood Pressure Management and Its Effects on Postoperative Delirium After Cardiac Surgery: A Single-Center Retrospective Cohort Study.

OBJECTIVES: There is accumulating evidence that blood pressure management might be associated with end-organ dysfunction after cardiac surgery. This study aimed to investigate the impact of intraoperative hypotension (IOH) on adverse neurologic outcomes and mortality. DESIGN: A single-center retrospective cohort study. SETTING: The Heart and Diabetes Centre Bad Oeynhausen NRW, Ruhr-University Bochum. PARTICIPANTS: This retrospective cohort study included 31,315 adult patients who underwent elective cardiac surgery at the authors' institution between January 2009 and December 2018. INTERVENTIONS: All cardiac surgery procedures except assist device implantation, organ transplantation, and emergency surgery. MEASUREMENTS AND MAIN RESULTS: Adverse neurologic outcomes were defined as postoperative delirium and stroke. IOH was defined as mean arterial pressure below 60 mmHg for >2 minutes. The frequency of IOH episodes and the cumulative IOH duration were recorded. The association between IOH and adverse neurologic outcomes was examined with unadjusted statistical analysis and multiple logistic regression analysis. Eight hundred forty-nine (2.9%) patients developed postoperative stroke, and 2,401 (7.7%) patients developed postoperative delirium. The frequency of IOH episodes was independently associated with postoperative delirium in the multiple logistic regression analysis (odds ratio 1.02, 95% CI 1.003-1.03, p < 0.001), whereas there was no association between it and stroke. CONCLUSION: This large retrospective monocentric cohort study revealed that increased episodes of IOH were associated with the risk of developing postoperative delirium after cardiac surgery. This might have important clinical implications with respect to careful and precise hemodynamic monitoring and proactive treatment, especially in patients with increased risk for postoperative delirium.

Effect of phenylephrine rescue injection on hypotension after spinal anaesthesia for caesarean delivery when guided by both heart rate and SBP during an early warning window: A randomised controlled trial.

BACKGROUND: Spinal anaesthesia is now the most common technique for caesarean delivery. However, because of the intermittent nature of noninvasive blood pressure (NIBP) measurements, maternal blood pressure may become hypotensive between the measurements. There is thus an inbuilt delay before the anaesthesiologist can intervene to counteract the hypotension. Based on the principle that changes in blood pressure can induce compensatory changes in the heart rate (HR), combining the NIBP with real-time HR, we designed two warning windows to predict hypotension and hypertension. OBJECTIVE: To evaluate whether phenylephrine administration guided by these warning windows would help maintain haemodynamic stability. SETTING: A teaching hospital. DESIGN: A randomised controlled trial. PATIENTS: One hundred and ten pregnant women scheduled for elective caesarean delivery were enrolled, from which, after exclusions, 86 were eligible for the study. INTERVENTIONS: All eligible patients received a continuous intravenous infusion of phenylephrine as soon as spinal anaesthesia was initiated. Thereafter, patients were randomly assigned to two groups. In the test group (Win-Group): rescue phenylephrine administration was triggered by an early warning window of HR above 100 beats per minute (bpm) and SBP 90 to 110 mmHg; pausing the infusion phenylephrine was triggered by a HR lower than 60 bpm and SBP greater than 90 mmHg. In the control group, phenylephrine was guided by BP only when it appeared on the monitor: SBP less than 90 mmHg was the trigger for administering rescue phenylephrine; SBP greater than 110 mmHg was the trigger for pausing the phenylephrine infusion. MAIN OUTCOME MEASURES: The primary outcome was incidence of hypotension. Secondary outcomes were the incidence of hypertension and other adverse haemodynamic events. RESULTS: The incidence of hypotension was significantly lower in the Win-Group than in the BP-Group (27.8 vs. 66.7%, P  = 0.001). The minimum SBP was significantly higher in Win-Group than in BP-Group (93.9 ±â€Š9.49 vs. 86.7 ±â€Š11.16 mmHg, P   =  0.004). There was no significant difference in the incidence of hypertension between groups. CONCLUSION: After spinal anaesthesia for caesarean delivery, when phenylephrine infusion is guided by HR along with BP from a warning window it effectively reduces the incidence of hypotension without any significant effect on incidence of hypertension. TRIAL REGISTRATION: Chictr.org.cn; Identifier: ChiCTR 2100041812.

Prevalence of postprandial hypotension in older adults: a systematic review and meta-analysis.

BACKGROUND: Older adults with postprandial hypotension (PPH) increase susceptibility to falls, syncope, stroke, acute cardiovascular diseases and even death. However, the prevalence of this condition varies significantly across studies. We aimed to determine the prevalence of PPH in older adults. METHODS: Web of Science, PubMed, Cochrane Library, Embase and CINAHL were searched from their inception until February 2023. Search terms included 'postprandial period', 'hypotension' and 'postprandial hypotension'. Eligible studies were assessed using the Joanna Briggs Institute tool. Meta-analyses were performed among similar selected studies. RESULTS: Thirteen eligible studies were included, and data from 3,021 participants were pooled. The meta-analysis revealed a PPH prevalence of 40.5% [95% confidence interval (CI): 0.290-0.519] in older adults, and this was prevalent in the community (32.8%, 95% CI: 0.078-0.647, n = 1,594), long-term healthcare facility (39.4%, 95% CI: 0.254-0.610, n = 1,062) and geriatrics department of hospitals (49.3%, 95% CI: 0.357-0.630, n = 365). The pooled results showed significant heterogeneity (I2 > 90%), partially related to the different ages, sex, pre-prandial systolic blood pressure levels of participants, or the different criteria and methodology used to diagnose PPH. CONCLUSIONS: PPH is a prevalent condition in older adults. Further research is needed to confirm this result, and priority should be given to establishing international consensus on PPH diagnostic criteria and designing its diagnostic procedure.

Preoperative Renin-Angiotensin System Antagonists Intake and Blood Pressure Responses During Ambulatory Surgical Procedures: A Prospective Cohort Study.

BACKGROUND: There is limited evidence to inform the association between the intake of angiotensin-converting enzyme inhibitors (ACEIs)/angiotensin II receptor blockers (ARBs) and intraoperative blood pressure (BP) changes in an ambulatory surgery population. METHODS: Adult patients who underwent ambulatory surgery and were discharged on the same day or within 24 hours of their procedure were enrolled in this prospective cohort study. The primary outcome of the study was early intraoperative hypotension (first 15 minutes of induction). Secondary outcomes included any hypotension, BP variability, and recovery. Hypotension was defined as a decrease in systolic BP of >30% from baseline for ≥5 minutes or a mean BP of <55 mm Hg. Four exposure groups were compared (no antihypertensives, ACEI/ARB intake <10 hours before surgery, ACEI/ARB intake ≥10 hours before surgery, and other antihypertensives). RESULTS: Of the 537 participants, early hypotension was observed in 25% (n = 134), and any hypotension in 41.5% (n = 223). Early hypotension occurred in 30% (29 of 98) and 41% (17 of 41) with the intake of ACEI/ARBs <10 and ≥10 hours before surgery, respectively, compared to 30% (9 of 30) with other antihypertensives and 21% (79 of 368) with no antihypertensives ( P = .02). Those on antihypertensives also experienced any hypotension more frequently than those who were not on antihypertensives ( P < .001). After adjusting for age and baseline BP in a regression analysis, antihypertensive exposure groups were observed to be associated only with any intraoperative hypotension ( P = .012). In the ACEI/ARB subset, there was no evidence of an association between time since the last ACEI/ARB dose, and hypotension or minimum mean or systolic BP. Compared to normal baseline BP, BP ≥ 140/90 mm Hg increased the odds of early and any hypotension (odds ratio [OR], 3.9; 95% confidence interval [CI], 2.1-7.1 and OR, 7.7; 95% CI, 3.7-14.9, respectively; P < .001). Intraoperative variability in systolic and diastolic BP demonstrated significant differences with age, baseline BP, and antihypertensive exposure group ( P < .001). CONCLUSIONS: Early and any hypotension occurred more frequently in those on antihypertensives than those not on antihypertensives. Unadjusted associations between antihypertensive exposure and intraoperative hypotension were largely explained by baseline hypertension rather than the timing of ACEI/ARBs or type of antihypertensive exposure. Patients with hypertension and on treatment experience more intraoperative BP variability and should be monitored appropriately.

Adverse Events of Peripherally Administered Norepinephrine During Surgery: A Prospective Multicenter Study.

BACKGROUND: Perioperative treatment of hypotension by intravenous administration of norepinephrine in a peripheral vein can lead to adverse events, for example, tissue necrosis. However, the incidence and severity of adverse events during perioperative administration are unknown. METHODS: This was a prospective observational study conducted at 3 Swedish hospitals from 2019 to 2022. A total of 1004 patients undergoing surgery, who met the criteria for perioperative peripheral norepinephrine administration, were included. The infusion site was inspected regularly. If swelling or paleness of skin was detected, the infusion site was changed to a different peripheral line. Systolic blood pressure and pulse frequency were monitored during the infusion time and defined as adverse events at >220 mm Hg and <40 beats•min -1 . In case of adverse events, patients were observed for up to 48 hours. The primary outcome was prevalence of extravasation, defined as swelling around the infusion site. Secondary outcomes were all types of adverse events and associations between predefined clinical variables and risk of adverse events. RESULTS: We observed 2.3% (95% confidence interval [CI], 1.4%-3.2%) extravasation of infusion and 0.9% (95% CI, 0.4%-1.7%) bradycardia. No cases of tissue necrosis or severe hypertension were detected. All adverse events had dissipated spontaneously within 48 hours. Proximal catheter placement was associated with more adverse events. CONCLUSIONS: Extravasation of peripherally administrated norepinephrine in the perioperative period occurred at similar rates as in previous studies in critically ill patients. In our setting, where we regularly inspected the infusion site and shifted site in case of swelling or paleness of skin, we observed no case of severe adverse events. Given that severe adverse events were absent, the potential benefit of this preventive approach requires confirmation in a larger population.

EARLY BLOOD LACTATE AS A BIOMARKER FOR CARDIOVASCULAR COLLAPSE IN EXPERIMENTAL SEPSIS.

ABSTRACT: Cecal ligation and puncture (CLP) is the gold standard model for studying septic shock, which is characterized by hypotension and hyporeactivity to vasoconstrictors. However, approximately 30% of CLP animals do not exhibit cardiovascular changes, requiring more replicates because of the high variability of the model. Therefore, biomarkers enabling the early prediction of cardiovascular collapse in sepsis would greatly benefit sepsis nonclinical studies, refining experimental models and improving clinical translation. Thus, this study aimed to test whether the early increase in lactate levels could predict hypotension and hyporesponsiveness to vasoconstrictors in a rat model of sepsis. Male and female Wistar rats were subjected to CLP or sham procedure. Tail blood lactate was measured 6, 12, and 24 h after surgery. Then, inflammatory, biochemical, and hemodynamic parameters were evaluated. Rats subjected to CLP developed hypotension, hyporesponsiveness to vasoconstrictors, an intense inflammatory process, and increased plasma markers of organ dysfunction. By using receiver operating characteristics curve analysis, we have established that a lactate value of 2.45 mmol/L can accurately discriminate between a rat exhibiting a normal vasoconstrictive response and a vasoplegic rat with 84% accuracy (area under the curve: 0.84; confidence interval [CI]: 0.67-1.00). The sensitivity, which is the ability to identify a diseased rat (true positive), was 75% (CI: 41-95), and the true negative rate was 81% (CI: 57-93). Therefore, early measurement of lactate levels in sepsis could serve as a valuable biomarker for distinguishing vasoplegic rats from those exhibiting normal vasoconstrictive responses.

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.

Haemodynamic assessment and management of hypotension in the preterm.

The management of low blood flow states in premature neonates is fraught with many challenges. We remain over-reliant on regimented stepwise protocols that use mean blood pressure as a threshold for intervention to guide treatment, without giving due consideration to the underlying pathophysiology. The current available evidence does not reflect the need to concentrate on the unique pathophysiology of the preterm infant and thus leads to widespread misuse of vasoactive agents that often do not provide the desired clinical effect. Therefore, understanding the underlying pathophysiological underpinnings of haemodynamic compromise may better guide choice of agent and assess physiological response to the selected intervention.

Droxidopa or Atomoxetine for Refractory Hypotension in Critically Ill Cardiothoracic Surgery Patients.

OBJECTIVE: To evaluate the effects of droxidopa or atomoxetine on intravenous (IV) vasoactive agent discontinuation in cardiothoracic intensive care unit (ICU) patients with hypotension refractory to midodrine. DESIGN: Single-center, retrospective cohort study. SETTING: Tertiary- and quaternary-care university teaching hospital. PARTICIPANTS: Included patients who received at least 4 consecutive doses of droxidopa or atomoxetine and remained on concurrent midodrine. Patients were excluded if they received study medication before admission, had clinical deterioration after study medication initiation requiring additional vasoactives/escalation of IV vasoactive dosage for at least 12 hours, had a diagnosis of hepatorenal syndrome, were prisoners, or were pregnant. INTERVENTIONS: Droxidopa, atomoxetine, or both. MEASUREMENTS AND MAIN RESULTS: The primary endpoint was time to discontinuation of IV vasoactive agents after initiation of study medication, analyzed using a Kaplan-Meier estimate with the Wilcoxon method, censoring death within 24 hours of the last dose of study medication. No adjustment for repetitive analyses was made, as the analysis was hypothesis-generating. Of the 72 charts reviewed, 45 patients met inclusion criteria (18 atomoxetine, 17 droxidopa, and 10 both). There were no differences in median time to discontinuation of IV vasoactive agents (21.9 days v 8.0 days v 13.9 days, respectively; p = 0.259) or ICU or hospital length of stay between groups. A higher percentage of patients who survived to hospital discharge received both study medications or droxidopa alone (90% v 76.5%) than atomoxetine alone (44.4%, p = 0.028). CONCLUSIONS: Droxidopa and atomoxetine are oral vasoactive agents with potential mechanisms to facilitate IV vasopressor weaning for patients in the ICU with hypotension refractory to midodrine, but further prospective research is needed.

The real-world safety of sacubitril / valsartan among older adults (≥75): A pharmacovigilance study from the FDA data.

BACKGROUND: Heart failure is a major cause of morbidity and mortality among older adults. Sacubitril-Valsartan (Sac/Val) has been shown to improve patients' outcomes; however, its safety profile among older adults has not been adequately examined. We therefore aimed to examine its safety profile among this population. METHODS: We conducted a retrospective pharmacovigilance study utilizing the FDA's database of safety reports (FAERS). We employed disproportionality analysis comparing Sac/Val to angiotensin receptor blockers (ARBs). We aim to evaluate the reporting of pre-defined adverse events associated with Sac/Val (hypotension, acute kidney injury (AKI), hyperkalemia and angioedema) in two age groups: adults (< 75 years) and older adults (≥ 75). For each subgroup, we calculated reporting odds ratio (ROR) and compared them by calculating P for interaction. RESULTS: The FAERS database encompassed 18,432 unique reports of Sac/Val. Of them, 12,630 (68.5%) subjects were adults (< 75 years), and 5802 (31.5%) were older adults (≥ 75 years), with a median age (IQR) of 68 (59-77). When compared to ARBs, Sac/Val was associated with higher reporting of hypotension, lower reporting of acute kidney injury (AKI) and hyperkalemia, and similar reporting of angioedema. Notably, we did not observe a significant interaction between the age subgroups and the risk estimates (AKI: Pinteraction = 0.72, hyperkalemia: Pinteraction = 0.94, hypotension: Pinteraction = 0.31, and angioedema: Pinteraction = 0.61). CONCLUSIONS: In this postmarking study, none of the prespecified adverse events was reported more frequently in older adults. These findings provide reassurance for safety use of Sac/Val in older adults.

American society of anesthesiologists physical status classification significantly affects the performances of machine learning models in intraoperative hypotension inference.

STUDY OBJECTIVE: To explore how American Society of Anesthesiologists (ASA) physical status classification affects different machine learning models in hypotension prediction and whether the prediction uncertainty could be quantified. DESIGN: Observational Studies SETTING: UofL health hospital PATIENTS: This study involved 562 hysterectomy surgeries performed on patients (≥ 18 years) between June 2020 and July 2021. INTERVENTIONS: None MEASUREMENTS: Preoperative and intraoperative data is collected. Three parametric machine learning models, including Bayesian generalized linear model (BGLM), Bayesian neural network (BNN), a newly proposed BNN with multivariate mixed responses (BNNMR), and one nonparametric model, Gaussian Process (GP), were explored to predict patients' diastolic and systolic blood pressures (continuous responses) and patients' hypotensive event (binary response) for the next five minutes. Data was separated into American Society of Anesthesiologists (ASA) physical status class 1- 4 before being read in by four machine learning models. Statistical analysis and models' constructions are performed in Python. Sensitivity, specificity, and the confidence/credible intervals were used to evaluate the prediction performance of each model for each ASA physical status class. MAIN RESULTS: ASA physical status classes require distinct models to accurately predict intraoperative blood pressures and hypotensive events. Overall, high sensitivity (above 0.85) and low uncertainty can be achieved by all models for ASA class 4 patients. In contrast, models trained without controlling ASA classes yielded lower sensitivity (below 0.5) and larger uncertainty. Particularly, in terms of predicting binary hypotensive event, for ASA physical status class 1, BNNMR yields the highest sensitivity of 1. For classes 2 and 3, BNN has the highest sensitivity of 0.429 and 0.415, respectively. For class 4, BNNMR and GP are tied with the highest sensitivity of 0.857. On the other hand, the sensitivity is just 0.031, 0.429, 0.165 and 0.305 for BNNMR, BNN, GBLM and GP models respectively, when training data is not divided by ASA physical status classes. In terms of predicting systolic blood pressure, the GP regression yields the lowest root mean squared errors (RMSE) of 2.072, 7.539, 9.214 and 0.295 for ASA physical status classes 1, 2, 3 and 4, respectively, but a RMSE of 126.894 if model is trained without controlling the ASA physical status class. The RMSEs for other models are far higher. RMSEs are 2.175, 13.861, 17.560 and 22.426 for classes 1, 2, 3 and 4 respectively for the BGLM. In terms of predicting diastolic blood pressure, the GP regression yields the lowest RMSEs of 2.152, 6.573, 5.371 and 0.831 for ASA physical status classes 1, 2, 3 and 4, respectively; RMSE of 8.084 if model is trained without controlling the ASA physical status class. The RMSEs for other models are far higher. Finally, in terms of the width of the 95% confidence interval of the mean prediction for systolic and diastolic blood pressures, GP regression gives narrower confidence interval with much smaller margin of error across all four ASA physical status classes. CONCLUSIONS: Different ASA physical status classes present different data distributions, and thus calls for distinct machine learning models to improve prediction accuracy and reduce predictive uncertainty. Uncertainty quantification enabled by Bayesian inference provides valuable information for clinicians as an additional metric to evaluate performance of machine learning models for medical decision making.