The Influence of Carbon Dioxide on Cerebral Autoregulation During Sevoflurane-based Anesthesia in Patients With Type 2 Diabetes.

BACKGROUND: Cerebral autoregulation (CA) continuously adjusts cerebrovascular resistance to maintain cerebral blood flow (CBF) constant despite changes in blood pressure. Also, CBF is proportional to changes in arterial carbon dioxide (CO 2 ) (cerebrovascular CO 2 reactivity). Hypercapnia elicits cerebral vasodilation that attenuates CA efficacy, while hypocapnia produces cerebral vasoconstriction that enhances CA efficacy. In this study, we quantified the influence of sevoflurane anesthesia on CO 2 reactivity and the CA-CO 2 relationship. METHODS: We studied patients with type 2 diabetes mellitus (DM), prone to cerebrovascular disease, and compared them to control subjects. In 33 patients (19 DM, 14 control), end-tidal CO 2 , blood pressure, and CBF velocity were monitored awake and during sevoflurane-based anesthesia. CA, calculated with transfer function analysis assessing phase lead (degrees) between low-frequency oscillations in CBF velocity and mean arterial blood pressure, was quantified during hypocapnia, normocapnia, and hypercapnia. RESULTS: In both control and DM patients, awake CO 2 reactivity was smaller (2.8%/mm Hg CO 2 ) than during sevoflurane anesthesia (3.9%/mm Hg; P <0.005). Hyperventilation increased CA efficacy more (3 deg./mm Hg CO 2 ) in controls than in DM patients (1.8 deg./mm Hg CO 2 ; P <0.001) in both awake and sevoflurane-anesthetized states. CONCLUSIONS: The CA-CO 2 relationship is impaired in awake patients with type 2 DM. Sevoflurane-based anesthesia does not further impair this relationship. In patients with DM, hypocapnia induces cerebral vasoconstriction, but CA efficacy does not improve as observed in healthy subjects.

Transfer function analysis of dynamic cerebral autoregulation: A CARNet white paper 2022 update.

Cerebral autoregulation (CA) refers to the control of cerebral tissue blood flow (CBF) in response to changes in perfusion pressure. Due to the challenges of measuring intracranial pressure, CA is often described as the relationship between mean arterial pressure (MAP) and CBF. Dynamic CA (dCA) can be assessed using multiple techniques, with transfer function analysis (TFA) being the most common. A 2016 white paper by members of an international Cerebrovascular Research Network (CARNet) that is focused on CA strove to improve TFA standardization by way of introducing data acquisition, analysis, and reporting guidelines. Since then, additional evidence has allowed for the improvement and refinement of the original recommendations, as well as for the inclusion of new guidelines to reflect recent advances in the field. This second edition of the white paper contains more robust, evidence-based recommendations, which have been expanded to address current streams of inquiry, including optimizing MAP variability, acquiring CBF estimates from alternative methods, estimating alternative dCA metrics, and incorporating dCA quantification into clinical trials. Implementation of these new and revised recommendations is important to improve the reliability and reproducibility of dCA studies, and to facilitate inter-institutional collaboration and the comparison of results between studies.

Influence of breathing on variation in cardiac stroke volume at the onset of cycling.

PURPOSE: During cycling, the variation in cardiac stroke volume (SVV) is similar to that at rest. However, SVV may be influenced by ventilation at the start of cycling, e.g., by a Valsalva-like maneuver used to stabilize the body. This study evaluated the influence of ventilation on SV during initiation of cycling. METHODS: Ten healthy recreationally physical active males (mean ± SD: age 26 ± 3 years, height 184 ± 9 cm, weight 85 ± 9 kg) cycled on an ergometer for four 30 s intervals at submaximal workloads while synchronizing ventilatory and cardiovascular variables derived from gas exchange and arterial pulse contour analysis, respectively. RESULTS: At exercise onset, cardiac output increased by an instantaneous rise in heart rate and SV (P < 0.05). In contrast, blood pressure increased only after 15 s (P < 0.05), reflected in a decline in total peripheral resistance from exercise onset (P < 0.05). SVV was similar at rest (20 ± 6%) and during exercise (21 ± 5%) except for the first 5 s of exercise when a ~ 2.5-fold elevation (47 ± 6%; P < 0.05) was correlated to variation in respiratory frequency (= 0.71, P = 0.02) and tidal volume (R = 0.66, P = 0.04) but not to variation in heart rate or blood pressure. Stepwise multiple regression analysis indicated a respiratory frequency influence on SVV at the onset of ergometer cycling. CONCLUSION: The data provide evidence for a ventilatory influence on SVV at the onset of cycling exercise.

Systemic and cerebral circulatory adjustment within the first 60 s after active standing: An integrative physiological view.

Transient cardiovascular and cerebrovascular responses within the first minute of active standing provide the means to assess autonomic, cardiovascular and cerebrovascular regulation using a real-world everyday stimulus. Traditionally, these responses have been used to detect autonomic dysfunction, and to identify the hemodynamic correlates of patient symptoms and attributable causes of (pre)syncope and falls. This review addresses the physiology of systemic and cerebrovascular adjustment within the first 60 s after active standing. Mechanical factors induced by standing up cause a temporal mismatch between cardiac output and vascular conductance which leads to an initial blood pressure drops with a nadir around 10 s. The arterial baroreflex counteracts these initial blood pressure drops, but needs 2-3 s to be initiated with a maximal effect occurring at 10 s after standing while, in parallel, cerebral autoregulation buffers these changes within 10 s to maintain adequate cerebral perfusion. Interestingly, both the magnitude of the initial drop and these compensatory mechanisms are thought to be quite well-preserved in healthy aging. It is hoped that the present review serves as a reference for future pathophysiological investigations and epidemiological studies. Further experimental research is needed to unravel the causal mechanisms underlying the emergence of symptoms and relationship with aging and adverse outcomes in variants of orthostatic hypotension.

Central Hypovolemia Detection During Environmental Stress-A Role for Artificial Intelligence?

The first step to exercise is preceded by the required assumption of the upright body position, which itself involves physical activity. The gravitational displacement of blood from the chest to the lower parts of the body elicits a fall in central blood volume (CBV), which corresponds to the fraction of thoracic blood volume directly available to the left ventricle. The reduction in CBV and stroke volume (SV) in response to postural stress, post-exercise, or to blood loss results in reduced left ventricular filling, which may manifest as orthostatic intolerance. When termination of exercise removes the leg muscle pump function, CBV is no longer maintained. The resulting imbalance between a reduced cardiac output (CO) and a still enhanced peripheral vascular conductance may provoke post-exercise hypotension (PEH). Instruments that quantify CBV are not readily available and to express which magnitude of the CBV in a healthy subject should remains difficult. In the physiological laboratory, the CBV can be modified by making use of postural stressors, such as lower body "negative" or sub-atmospheric pressure (LBNP) or passive head-up tilt (HUT), while quantifying relevant biomedical parameters of blood flow and oxygenation. Several approaches, such as wearable sensors and advanced machine-learning techniques, have been followed in an attempt to improve methodologies for better prediction of outcomes and to guide treatment in civil patients and on the battlefield. In the recent decade, efforts have been made to develop algorithms and apply artificial intelligence (AI) in the field of hemodynamic monitoring. Advances in quantifying and monitoring CBV during environmental stress from exercise to hemorrhage and understanding the analogy between postural stress and central hypovolemia during anesthesia offer great relevance for healthy subjects and clinical populations.

Cerebral Blood Flow in Patients with Severe Aortic Valve Stenosis Undergoing Transcatheter Aortic Valve Implantation.

BACKGROUND: Transcatheter aortic valve implantation (TAVI) is a minimally invasive, life-saving treatment for patients with severe aortic valve stenosis that improves quality of life. We examined cardiac output and cerebral blood flow in patients undergoing TAVI to test the hypothesis that improved cardiac output after TAVI is associated with an increase in cerebral blood flow. DESIGN: Prospective cohort study. SETTING: European high-volume tertiary multidisciplinary cardiac care. PARTICIPANTS: Thirty-one patients (78.3 ± 4.6 years; 61% female) with severe symptomatic aortic valve stenosis. MEASUREMENTS: Noninvasive prospective assessment of cardiac output (L/min) by inert gas rebreathing and cerebral blood flow of the total gray matter (mL/100 g per min) using arterial spin labeling magnetic resonance imaging in resting state less than 24 hours before TAVI and at 3-month follow-up. Cerebral blood flow change was defined as the difference relative to baseline. RESULTS: On average, cardiac output in patients with severe aortic valve stenosis increased from 4.0 ± 1.1 to 5.4 ± 2.4 L/min after TAVI (P = .003). The increase in cerebral blood flow after TAVI strongly varied between patients (7% ± 24%; P = .41) and related to the increase in cardiac output, with an 8.2% (standard error = 2.3%; P = .003) increase in cerebral blood flow per every additional liter of cardiac output following the TAVI procedure. CONCLUSION: Following TAVI, there was an association of increase in cardiac output with increase in cerebral blood flow. These findings encourage future larger studies to determine the influence of TAVI on cerebral blood flow and cognitive function.

Novel Methods for Quantification of Vasodepression and Cardioinhibition During Tilt-Induced Vasovagal Syncope.

RATIONALE: Assessing the relative contributions of cardioinhibition and vasodepression to the blood pressure (BP) decrease in tilt-induced vasovagal syncope requires methods that reflect BP physiology accurately. OBJECTIVE: To assess the relative contributions of cardioinhibition and vasodepression to tilt-induced vasovagal syncope using novel methods. METHODS AND RESULTS: We studied the parameters determining BP, that is, stroke volume (SV), heart rate (HR), and total peripheral resistance (TPR), in 163 patients with tilt-induced vasovagal syncope documented by continuous ECG and video EEG monitoring. We defined the beginning of cardioinhibition as the start of an HR decrease (HR) before syncope and used logarithms of SV, HR, and TPR ratios to quantify the multiplicative relation BP=SV·HR·TPR. We defined 3 stages before syncope and 2 after it based on direction changes of these parameters. The earliest BP decrease occurred 9 minutes before syncope. Cardioinhibition was observed in 91% of patients at a median time of 58 seconds before syncope. At that time, SV had a strong negative effect on BP, TPR a lesser negative effect, while HR had increased (all P<0.001). At the onset of cardioinhibition, the median HR was at 98 bpm higher than baseline. Cardioinhibition thus initially only represented a reduction of the corrective HR increase but was nonetheless accompanied by an immediate acceleration of the ongoing BP decrease. At syncope, SV and HR contributed similarly to the BP decrease (P<0.001), while TPR did not affect BP. CONCLUSIONS: The novel methods allowed the relative effects of SV, HR, and TPR on BP to be assessed separately, although all act together. The 2 major factors lowering BP in tilt-induced vasovagal syncope were reduced SV and cardioinhibition. We suggest that the term vasodepression in reflex syncope should not be limited to reduced arterial vasoconstriction, reflected in TPR, but should also encompass venous pooling, reflected in SV.

Cerebral vs. Cardiovascular Responses to Exercise in Type 2 Diabetic Patients.

The human brain is constantly active and even small limitations to cerebral blood flow (CBF) may be critical for preserving oxygen and substrate supply, e.g., during exercise and hypoxia. Exhaustive exercise evokes a competition for the supply of oxygenated blood between the brain and the working muscles, and inability to increase cardiac output sufficiently during exercise may jeopardize cerebral perfusion of relevance for diabetic patients. The challenge in diabetes care is to optimize metabolic control to slow progression of vascular disease, but likely because of a limited ability to increase cardiac output, these patients perceive aerobic exercise to be more strenuous than healthy subjects and that limits the possibility to apply physical activity as a preventive lifestyle intervention. In this review, we consider the effects of functional activation by exercise on the brain and how it contributes to understanding the control of CBF with the limited exercise tolerance experienced by type 2 diabetic patients. Whether a decline in cerebral oxygenation and thereby reduced neural drive to working muscles plays a role for "central" fatigue during exhaustive exercise is addressed in relation to brain's attenuated vascular response to exercise in type 2 diabetic subjects.

Neurovascular coupling and cerebral autoregulation in atrial fibrillation.

The risk of cognitive decline and stroke is increased by atrial fibrillation (AF). We sought to determine whether neurovascular coupling and cerebral autoregulation are blunted in people with AF in comparison with age-matched, patients with hypertension and healthy controls. Neurovascular coupling was assessed using five cycles of visual stimulation for 30 s followed by 30 s with both eyes-closed. Cerebral autoregulation was examined using a sit-stand test, and a repeated squat-to-stand (0.1 Hz) manoeuvre with transfer function analysis of mean arterial pressure (MAP; input) and middle cerebral artery mean blood flow velocity (MCA Vm; output) relationships at 0.1 Hz. Visual stimulation increased posterior cerebral artery conductance, but the magnitude of the response was blunted in patients with AF (18 [8] %; mean [SD]) and hypertension (17 [8] %), in comparison with healthy controls (26 [9] %) (P < 0.05). In contrast, transmission of MAP to MCA Vm was greater in AF patients compared to hypertension and healthy controls, indicating diminished cerebral autoregulation. We have shown for the first time that AF patients have impaired neurovascular coupling responses to visual stimulation and diminished cerebral autoregulation. Such deficits in cerebrovascular regulation may contribute to the increased risk of cerebral dysfunction in people with AF.

Aortic valve calcification volumes and chronic brain infarctions in patients undergoing transcatheter aortic valve implantation.

Chronic silent brain infarctions, detected as new white matter hyperintensities on magnetic resonance imaging (MRI) following transcatheter aortic valve implantation (TAVI), are associated with long-term cognitive deterioration. This is the first study to investigate to which extent the calcification volume of the native aortic valve (AV) measured with cardiac computed tomography angiography (CTA) predicts the increase in chronic white matter hyperintensity volume after TAVI. A total of 36 patients (79 ± 5 years, median EuroSCORE II 1.9%, Q1-Q3 1.5-3.4%) with severe AV stenosis underwent fluid attenuation inversion recovery (FLAIR) MRI < 24 h prior to TAVI and at 3 months follow-up for assessment of cerebral white matter hyperintensity volume (mL). Calcification volumes (mm3) of the AV, aortic arch, landing zone and left ventricle were measured on the CTA pre-TAVI. The largest calcification volumes were found in the AV (median 692 mm3) and aortic arch (median 633 mm3), with a large variation between patients (Q1-Q3 482-1297 mm3 and 213-1727 mm3, respectively). The white matter hyperintensity volume increased in 72% of the patients. In these patients the median volume increase was of 1.1 mL (Q1-Q3 0.3-4.6 mL), corresponding with a 27% increase from baseline (Q1-Q3 7-104%). The calcification volume in the AV predicted the increase of white matter hyperintensity volume (Δ%), with a 35% increase of white matter hyperintensity volume, per 100 mm3 of AV calcification volume (SE 8.5, p < 0.001). The calcification volumes in the aortic arch, landing zone and left ventricle were not associated with the increase in white matter hyperintensity volume. In 72% of the patients new chronic white matter hyperintensities developed 3 months after TAVI, with a median increase of 27%. A higher calcification volume in the AV was associated with a larger increase in the white matter hyperintensity volume. These findings show the potential for automated AV calcium screening as an imaging biomarker to predict chronic silent brain infarctions.

Slow sinusoidal tilt movements demonstrate the contribution to orthostatic tolerance of cerebrospinal fluid movement to and from the spinal dural space.

Standing up elicits a host of cardiovascular changes which all affect the cerebral circulation. Lowered mean arterial blood pressure (ABP) at brain level, change in the cerebral venous outflow path, lowered end-tidal PCO2 (PET CO2 ), and intracranial pressure (ICP) modify cerebral blood flow (CBF). The question we undertook to answer is whether gravity-induced blood pressure (BP) changes are compensated in CBF with the same dynamics as are spontaneous or induced ABP changes in a stable position. Twenty-two healthy subjects (18/4 m/f, 40 ± 8 years) were subjected to 30° and 70° head-up tilt (HUT) and sinusoidal tilts (SinTilt, 0°â†¨60° around 30° at 2.5-10 tilts/min). Additionally, at those three tilt levels, they performed paced breathing at 6-15 breaths/min to induce larger than spontaneous cardiovascular oscillations. We measured continuous finger BP and cerebral blood flow velocity (CBFv) in the middle cerebral artery by transcranial Doppler to compute transfer functions (TFs) from ABP- to CBFv oscillations. SinTilt induces the largest ABP oscillations at brain level with CBFv gains strikingly lower than for paced breathing or spontaneous variations. This would imply better autoregulation for dynamic gravitational changes. We demonstrate in a mathematical model that this difference is explained by ICP changes due to movement of cerebrospinal fluid (CSF) into and out of the spinal dural sack. Dynamic cerebrovascular autoregulation seems insensitive to how BP oscillations originate if the effect of ICP is factored in. CSF-movement in-and-out of the spinal dural space contributes importantly to orthostatic tolerance by its effect on cerebral perfusion pressure.

Impaired nocturnal blood pressure dipping in patients with type 2 diabetes mellitus.

Hypertension is a common comorbidity of type 2 diabetes mellitus (T2DM). Both conditions are associated with an increased cardiovascular risk, which is reduced by tight blood pressure (BP) and glycemic control. However, nondipping BP status continues to be an enduring cardiovascular risk factor in T2DM. Cardiovascular autonomic neuropathy and endothelial dysfunction have been proposed as potential mechanisms. This study tested the hypothesis that microvascular disease rather than cardiovascular autonomic neuropathy interferes with the physiological nocturnal BP reduction. Cardiovascular autonomic function and baroreflex sensitivity were determined in 22 type 2 diabetic patients with (DM+) and 23 diabetic patients without (DM-) manifest microvascular disease. BP dipping status was assessed from 24-hour ambulatory BP measurements. Sixteen nondiabetic subjects served as controls (CTRL). Cardiovascular autonomic function was normal in all subjects. Baroreflex sensitivity was lower in DM- compared with CTRL (7.7 ± 3.3 vs. 12.3 ± 8.3 ms·mm Hg-1; P < 0.05) and was further reduced in DM + (4.6 ± 2.0 ms·mm Hg-1; P < 0.01 vs. DM- and CTRL). The nocturnal decline in systolic and diastolic BP was blunted in DM- (12% and 14% vs. 17% and 19% in CTRL; P < 0.05) and even more so in DM+ (8% and 11%; P < 0.05 vs. DM- and P < 0.001 vs. CTRL). A nocturnal reduction in pulse pressure was observed in CTRL and DM- but not in DM+ (P < 0.05 vs. DM- and P < 0.01 vs. CTRL). In T2DM, progression of microvascular disease interferes with the normal nocturnal BP decline and coincides with a persistently increased pulse pressure and reduced baroreflex sensitivity, contributing to their increased cardiovascular risk.

Detecting central hypovolemia in simulated hypovolemic shock by automated feature extraction with principal component analysis.

Assessment of the volume status by blood pressure (BP) monitoring is difficult, since baroreflex control of BP makes it insensitive to blood loss up to about one liter. We hypothesized that a machine learning model recognizes the progression of central hypovolemia toward presyncope by extracting information of the noninvasive blood pressure waveform parametrized through principal component analysis. This was tested in healthy volunteers exposed to simulated hemorrhage by lower body negative pressure (LBNP). Fifty-six healthy volunteers were subjected to progressive central hypovolemia. A support vector machine was trained on the blood pressure waveform. Three classes of progressive stages of hypovolemia were defined. The model was optimized for the number of principal components and regularization parameter for penalizing misclassification (cost): C. Model performance was expressed as accuracy, mean squared error (MSE), and kappa statistic (inter-rater agreement). Forty-six subjects developed presyncope of which 41 showed an increase in model classification severity from baseline to presyncope. In five of the remaining nine subjects (1 was excluded) it stagnated. Classification of samples during baseline and end-stage LBNP had the highest accuracy (95% and 50%, respectively). Baseline and first stage of LBNP demonstrated the lowest MSE (0.01 respectively 0.32). Model MSE and accuracy did not improve for C values exceeding 0.01. Adding more than five principal components did not further improve accuracy or MSE. Increment in kappa halted after 10 principal components had been added. Automated feature extraction of the blood pressure waveform allows modeling of progressive hypovolemia with a support vector machine. The model distinguishes classes between baseline and presyncope.

Modeling Arterial Pulse Pressure From Heart Rate During Sympathetic Activation by Progressive Central Hypovolemia.

Heart rate (HR) has an impact on the central blood pressure (BP) wave shape and is related to pulse wave velocity and therefore to timing and duration of systole and diastole. This study tested the hypothesis that in healthy subjects both in rest and during sympathetic stimulation the relation between HR and pulse pressure (PP) is described by a linear effect model. Forty-four healthy volunteers were subjected to sympathetic stimulation by continuous lower body negative pressure (LBNP) until the onset of pre-syncopal symptoms. Changes in PP and HR were tracked non-invasively and modeled by linear mixed effect (LME) models. The dataset was split into two groups: the first was used for creating a model and the second for its evaluation. Models were created on the data obtained during LBNP. Model performance was expressed as absolute median error (1st; 3rd quantiles) and bias with limits of agreement (LOA) between modeled and measured PP. From rest to sympathetic stimulation, mean BP was maintained while HR increased (~30%) and PP decreased gradually (~20%). During baseline, PP could be modeled with an absolute error of 6 (4; 10) mm Hg and geometric mean ratio of the bias was 0.97 (LOA: 0.8-1.1). During LBNP, absolute median model error was 5 (4; 8) mmHg with geometric mean ratio 1.02 (LOA: 0.8-1.3). In conclusion, both during rest and during sustained sympathetic outflow induced by progressive central hypovolemia, a LME model of HR provides for an estimate of PP in healthy young adults.

Design of the ExCersion-VCI study: The effect of aerobic exercise on cerebral perfusion in patients with vascular cognitive impairment.

There is evidence for a beneficial effect of aerobic exercise on cognition, but underlying mechanisms are unclear. In this study, we test the hypothesis that aerobic exercise increases cerebral blood flow (CBF) in patients with vascular cognitive impairment (VCI). This study is a multicenter single-blind randomized controlled trial among 80 patients with VCI. Most important inclusion criteria are a diagnosis of VCI with Mini-Mental State Examination ≥22 and Clinical Dementia Rating ≤0.5. Participants are randomized into an aerobic exercise group or a control group. The aerobic exercise program aims to improve cardiorespiratory fitness and takes 14 weeks, with a frequency of three times a week. Participants are provided with a bicycle ergometer at home. The control group receives two information meetings. Primary outcome measure is change in CBF. We expect this study to provide insight into the potential mechanism by which aerobic exercise improves hemodynamic status.

Aging modifies the effect of cardiac output on middle cerebral artery blood flow velocity.

An association between cerebral blood flow (CBF) and cardiac output (CO) has been established in young healthy subjects. As of yet it is unclear how this association evolves over the life span. To that purpose, we continuously recorded mean arterial pressure (MAP; finger plethysmography), CO (pulse contour; CO-trek), mean blood flow velocity in the middle cerebral artery (MCAV; transcranial Doppler ultrasonography), and end-tidal CO2 partial pressure (PetCO2) in healthy young (19-27 years), middle-aged (51-61 years), and elderly subjects (70-79 years). Decreases and increases in CO were accomplished using lower body negative pressure and dynamic handgrip exercise, respectively. Aging in itself did not alter dynamic cerebral autoregulation or cerebrovascular CO2 reactivity. A linear relation between changes in CO and MCAVmean was observed in middle-aged (P < 0.01) and elderly (P = 0.04) subjects but not in young (P = 0.45) subjects, taking concurrent changes in MAP and PetCO2 into account. These data imply that with aging, brain perfusion becomes increasingly dependent on CO.

A machine-learning based analysis for the recognition of progressive central hypovolemia.

OBJECTIVE: Traditional patient monitoring during surgery includes heart rate (HR), blood pressure (BP) and peripheral oxygen saturation. However, their use as predictors for central hypovolemia is limited, which may lead to cerebral hypoperfusion. The aim of this study was to develop a monitoring model that can indicate a decrease in central blood volume (CBV) at an early stage. APPROACH: Twenty-eight healthy subjects (aged 18-50 years) were included. Lower body negative pressure (-50 mmHg) was applied to induce central hypovolemia until the onset of pre-syncope. Ten beat-to-beat and four discrete parameters were measured, normalized, and filtered with a 30 s moving window. Time to pre-syncope was scaled from 100%-0%. A total of 100 neural networks with 5, 10, 15, 20, or 25 neurons in their respective hidden layer were trained by 10, 20, 40, 80, 160, or 320 iterations to predict time to pre-syncope for each subject. The network with the lowest average slope of a fitted line over all subjects was chosen as optimal. MAIN RESULTS: The optimal generalized model consisted of 10 hidden neurons, trained using 80 iterations. The slope of the fitted line on the average prediction was -0.64 (SD 0.35). The model recognizes in 75% of the subjects the need for intervention at >200 s before pre-syncope. SIGNIFICANCE: We developed a neural network based on a set of physiological variables, which indicates a decrease in CBV even in the absence of HR and BP changes. This should allow timely intervention and prevent the development of symptomatic cerebral hypoperfusion.