Prior research implicates cerebrovascular disease in the development of age-related cognitive decline and dementia, but the underlying vascular mechanisms are not well understood [1]. An improved understanding of the nature of normal cerebrovascular aging is needed to help establish the role that vascular dysfunction might play in cognitive decline and dementia.

Transcranial Doppler (TCD) ultrasound enables measurement of beat-to-beat blood flow velocity of major cerebral arteries and is commonly utilized for assessing the regulatory parameters of the cerebral circulation, including neurovascular coupling (NVC), cerebrovascular reactivity (responses to hyper- and hypocapnia) and the pressure-flow response (as a measure of cerebral autoregulation) [2] (See Table 1).

Reduced middle cerebral artery velocity (MCAv) has been consistently reported in older adults [3, 4]. However, data concerning the regulatory parameters of the cerebral circulation are less consistent, with some studies reporting reduced neurovascular coupling [5] and cerebrovascular reactivity [5–7], while others have found no effect of age on cerebrovascular function [8–13]. Further, some studies have reported enhanced cerebrovascular responses with healthy aging [14, 15].

To date, the regulatory factors of cerebrovascular function have commonly been studied in isolation, which may contribute to the variance reported in the literature and our limited understanding of aging on cerebrovascular function [2]. Indeed, the aging process is heterogeneous and complex with the likelihood that cerebrovascular parameters will be differentially affected depending on the individual. A related issue is that few studies have examined the differential effects of aging on cerebrovascular reactivity to elevated and reduced P_ETCO_2, which may offer important insights into the effect of aging on vasodilation and vasoconstriction, respectively. Indeed, prior work has shown age-related changes in reactivity under hypercapnic conditions [4, 5]. A recent study by Galvin, Celi [14] measured hypercapnic and hypocapnic responses separately, and described greater hypocapnic responses in healthy older adults with and without coronary artery disease. Combined, these findings suggest that both responses warrant investigation in understanding the effects of aging of cerebrovascular reactivity to CO₂.

Therefore, to effectively distinguish between young and old adults and in order to fully understand the nature of cerebrovascular aging, a multicomponent measure of cerebrovascular function (which captures all potential changes) is needed. Such knowledge is vital since a full understanding of the nature of cerebrovascular aging is an important step towards understanding the vascular bases of age-related cognitive decline and dementia, and can ultimately inform the development of intervention and prevention programs tailored to these aging populations. Therefore, the purpose of this study was to provide a more complete investigation of the independent parameters of cerebrovascular function, by examining both their collective and independent contribution in a sample of healthy young adults aged 18–30 years compared with older adults without cognitive impairments aged 60–75 years.

Participants were instructed to abstain from caffeinated food and beverages, nicotine and alcohol 12 hours prior to their assessment. In addition, they were asked to avoid vigorous exercise on the day. Room temperature was controlled at approximately 23 degrees Celsius. Height (cm) and weight (kg) measurements were recorded. Blood pressure of the brachial artery was measured manually on 2 occasions.

Participants underwent a 2-hour assessment of their cerebrovascular function. Tasks were separated by 5-minute blocks to allow recovery and prevent cross-over effects (Fig 1).

Participants were instrumented for the continuous assessment of MCAv, heart rate, blood pressure and partial pressure of arterial carbon dioxide (P_ETCO_2). Three electrocardiogram (ECG) electrodes were attached to the torso using a lead-II configuration for the assessment of heart rate. Blood pressure was continuously monitored at the index finger of the left hand via plethysmography, with a sling holding the hand at heart level (Finapress, Amsterdam, the Netherlands). MCAv was measured using transcranial Doppler ultrasonography (TCD, Multigon, Neurovision, Elmsford, N.Y., USA), where a 2MHz probe was secured over the transtemporal window above the zygomatic arch [as per standardised techniques, 2] with a padded headframe. Insonation depth began at 50mm and was adjusted as necessary to achieve an optimal signal. MCAv was assessed on left side, except in 1 participant where the right side was used to obtain an optimal signal. Expired CO₂ concentration was monitored throughout using a fitted facemask and was used to calculate the partial pressure of end-tidal CO₂ (P_ETCO₂) (Respironics, AD Instruments, Sydney, Australia). All data were continuously sampled at 1KHz and synchronized using a data acquisition system for offline analysis (Powerlab, ADInstruments, Sydney, Australia).

Groups did not differ significantly based on BMI or physical activity levels and diastolic and systolic BP was significantly higher in the old (see Table 2). Gosling’s Pulsatility Index (PI) at rest indicated no difference between the young (M = .90, SD = .09) and old group (M = .93, SD = .14) in vascular resistance, p = .280.

When combined, the cerebrovascular parameters distinguished the old from the young, accounting for 60% of the variance (Wilk’s lambda .397, F(5,52) = 15.78, p < .001, η²_p = .603, power = 1.00). The significant MANOVA was followed-up by between-subject contrasts to determine which factors independently discriminated between groups. These revealed that resting MCAv and pressure-flow responses were significantly reduced in the old, exhibiting large magnitude effects: η²_p = .353 and .378, respectively. In addition, responses to hypocapnia were significantly elevated in the old relative to the young. This was a medium to large effect, η²_p = .159. No significant differences in NVCi or hypercapnic responses were observed (η²_p = .008 and .00) (see Table 3).

To confirm that medication use (i.e., BP lowering, lipid regulating and antiplatelet (aspirin)) did not moderate effects, a second MANOVA was performed excluding such cases. This did not affect the results (Wilk’s lambda .408, F(5,41) = 11.90, p < .001, η²_p = .592, power = 1.00), such that differences in MCA (p < .001), hypocapnic responses (p = .026) and pressure-flow responses (p < .001) remained statistically significant.

The results of this study indicate that a multicomponent assessment of cerebrovascular parameters discriminated between the young and old group. This finding is novel and meaningfully significant. Given that the aging process is heterogeneous with a high degree of inter-individual variability, a measure of cerebrovascular function that encapsulates the range of variance within a population is essential to examine the nature of cerebrovascular aging.

Prior research has reported a reduction in CBF with increasing age [3, 4], but studies investigating regulatory parameters of cerebrovascular function have yielded inconsistent results. In contrast to other studies investigating autoregulatory pressure-flow responses using TCD [10, 12], we found greater reductions in MCAv in response to decreases in MAP (hypotension) in the old compared with the young. This is particularly noteworthy since aging is already associated with reductions in CBF. Indeed, poor CBF regulation under hypotensive conditions may lead to cerebral hypoperfusion, ischemic injury and ultimately changes in cognitive function [20, 21]. In regard to NVC, recent studies have shown that NVC is unaffected in older adults [9, 22]. Our data corroborate findings from these studies, strengthening the notion that the neurovascular coupling is preserved in healthy aging.

Interestingly, we identified differential effects of aging on cerebrovascular reactivity to CO_2, such that hypercapnic responses were unaffected, but hypocapnic responses were significantly elevated in the old group. This data is consistent with Galvin, Celi [14] reporting no effect of aging on hypercapnia, but elevated hypocapnic responses in a small sample of older adults with and without coronary artery disease. Notably, no differences were found between the groups, suggesting that such changes may be attributable to aging.

Notably, it was the test of vasoconstriction, and not those of vasodilation (i.e., NVC and responses to hypercapnia) that differentiated the old from the young. Although the underlying mechanisms remain unclear, alterations in vascular tone may account for the present findings [14]. For instance, given that resting MCAv was reduced, predilatory compensatory mechanisms may have led to the elevated hypocapnic response observed in the old group [14, 23]. Indeed, such patterns warrant further investigation, but do highlight the importance of assessing all regulatory components concurrently. The use of this approach is a major strength of this study.

In conclusion, the results of this study suggest that aging is associated with reductions in MCAv, may increase cerebrovascular reactivity under hypocapnic conditions and weaken the brain’s capacity to combat reductions in pressure. Importantly, the results suggest that a multicomponent assessment of cerebrovascular parameters can distinguish older adults from healthy young adults. Since aging is heterogeneous and complex, this multicomponent measure of cerebrovascular function (which encapsulates the wide spectrum of change in this population), may be invaluable in terms of differentiating between normal and pathological aging, as well as providing insights into potential mechanisms at play in the case of age-related and neurodegenerative disease.