1-Year Mortality Prediction through Artificial Intelligence Using Hemodynamic Trace Analysis among Patients with ST Elevation Myocardial Infarction.

Background and Objectives: Patients presenting with ST Elevation Myocardial Infarction (STEMI) due to occlusive coronary arteries remain at a higher risk of excess morbidity and mortality despite being treated with primary percutaneous coronary intervention (PPCI). Identifying high-risk patients is prudent so that close monitoring and timely interventions can improve outcomes. Materials and Methods: A cohort of 605 STEMI patients [64.2 ± 13.2 years, 432 (71.41%) males] treated with PPCI were recruited. Their arterial pressure (AP) wave recorded throughout the PPCI procedure was analyzed to extract features to predict 1-year mortality. After denoising and extracting features, we developed two distinct feature selection strategies. The first strategy uses linear discriminant analysis (LDA), and the second employs principal component analysis (PCA), with each method selecting the top five features. Then, three machine learning algorithms were employed: LDA, K-nearest neighbor (KNN), and support vector machine (SVM). Results: The performance of these algorithms, measured by the area under the curve (AUC), ranged from 0.73 to 0.77, with accuracy, specificity, and sensitivity ranging between 68% and 73%. Moreover, we extended the analysis by incorporating demographics, risk factors, and catheterization information. This significantly improved the overall accuracy and specificity to more than 76% while maintaining the same level of sensitivity. This resulted in an AUC greater than 0.80 for most models. Conclusions: Machine learning algorithms analyzing hemodynamic traces in STEMI patients identify high-risk patients at risk of mortality.

iVR-fNIRS: studying brain functions in a fully immersive virtual environment.

Immersive virtual reality (iVR) employs head-mounted displays or cave-like environments to create a sensory-rich virtual experience that simulates the physical presence of a user in a digital space. The technology holds immense promise in neuroscience research and therapy. In particular, virtual reality (VR) technologies facilitate the development of diverse tasks and scenarios closely mirroring real-life situations to stimulate the brain within a controlled and secure setting. It also offers a cost-effective solution in providing a similar sense of interaction to users when conventional stimulation methods are limited or unfeasible. Although combining iVR with traditional brain imaging techniques may be difficult due to signal interference or instrumental issues, recent work has proposed the use of functional near infrared spectroscopy (fNIRS) in conjunction with iVR for versatile brain stimulation paradigms and flexible examination of brain responses. We present a comprehensive review of current research studies employing an iVR-fNIRS setup, covering device types, stimulation approaches, data analysis methods, and major scientific findings. The literature demonstrates a high potential for iVR-fNIRS to explore various types of cognitive, behavioral, and motor functions in a fully immersive VR (iVR) environment. Such studies should set a foundation for adaptive iVR programs for both training (e.g., in novel environments) and clinical therapeutics (e.g., pain, motor and sensory disorders and other psychiatric conditions).

Can Brain Volume-Driven Characteristic Features Predict the Response of Alzheimer's Patients to Repetitive Transcranial Magnetic Stimulation? A Pilot Study.

This study is a post-hoc examination of baseline MRI data from a clinical trial investigating the efficacy of repetitive transcranial magnetic stimulation (rTMS) as a treatment for patients with mild-moderate Alzheimer's disease (AD). Herein, we investigated whether the analysis of baseline MRI data could predict the response of patients to rTMS treatment. Whole-brain T1-weighted MRI scans of 75 participants collected at baseline were analyzed. The analyses were run on the gray matter (GM) and white matter (WM) of the left and right dorsolateral prefrontal cortex (DLPFC), as that was the rTMS application site. The primary outcome measure was the Alzheimer's disease assessment scale-cognitive subscale (ADAS-Cog). The response to treatment was determined based on ADAS-Cog scores and secondary outcome measures. The analysis of covariance showed that responders to active treatment had a significantly lower baseline GM volume in the right DLPFC and a higher GM asymmetry index in the DLPFC region compared to those in non-responders. Logistic regression with a repeated five-fold cross-validated analysis using the MRI-driven features of the initial 75 participants provided a mean accuracy of 0.69 and an area under the receiver operating characteristic curve of 0.74 for separating responders and non-responders. The results suggest that GM volume or asymmetry in the target area of active rTMS treatment (DLPFC region in this study) may be a weak predictor of rTMS treatment efficacy. These results need more data to draw more robust conclusions.

Repetitive transcranial magnetic stimulation as a treatment for Alzheimer's disease: A randomized placebo-controlled double-blind clinical trial.

We report results of a large multisite double-blind randomized trial investigating the short and long-term efficacy of repetitive transcranial magnetic stimulation (rTMS) applied to patients with Alzheimer's disease (AD) at mild to moderate stages, in doses of either 2 or 4 weeks of treatment (5 days/week), whilst compared with 4 weeks of sham rTMS. Randomization to treatment group was stratified based on age and severity. The objectives of this study were to: 1) investigate the efficacy of active rTMS versus sham, 2) investigate the effect of dose of treatment (2 or 4 weeks), and 3) investigate the length of benefits from treatment. The rTMS pulses (20 â€‹Hz, 30 pulses/train, 25 trains, 10-s intertrain interval) were applied serially to the left and right dorsolateral prefrontal cortex using neuro-navigation. We compared the primary outcome measure's (ADAS-Cog) score changes from pre- to post-treatment, with assessments at baseline and 4 more times up to 6 months post-treatment. Data of 135 patients were analyzed. The mean total ADAS-Cog score at baseline did not differ between the active and sham treatment groups, nor across the three study sites. The overall results show significant cognitive improvement after treatment up to two months post-treatment with either sham or active coils. The results show both short and long-term benefits of active rTMS treatment but also show similar benefits for sham coil treatment of mild/moderate AD. We discuss this finding in the context of the existing literature on rTMS therapy for AD, as well as evidence of the sham coil's potential to induce a low-level current in the brain. TRIAL REGISTRATION: https://clinicaltrials.gov/ct2/show/NCT02908815.

How accurate are coordinate systems being used for transcranial magnetic stimulation?

When applying transcranial magnetic stimulation (TMS) to the brain, it is desired to be as precise as possible to reach a target area in the brain. For that, neuronavigational system using individuals' MRI scans were developed to guide TMS pulses delivery. All neuronavigational systems need coordinates of the target area to guide the TMS coil. Talairach coordinate system, which uses the Talairach-Tournoux atlas, is the most common system used with TMS pulses. In this study we investigated how an average Talairach coordinate from 50 healthy individuals is close to the actual location of the hand area of the primary motor cortex to investigate if that elicit a motor response in the hand; thus, investigating the fitness and accuracy of the Talairach coordinate system. We performed this experiment on six individuals (ages 61-82). When applying TMS single pulses to hand area with the given Talairach coordinate system adjusted with the MRI of each participant, three participants had involuntary twitch and three participants had no consistent physical response, as corroborated by electromyography of the abductor pollicis brevis and first dorsal interosseous muscles at the resting motor threshold intensity. Subsequently, by trial-and-error, the hand area was successfully stimulated on those three non-responder participants. The largest deviation from the Talairach coordinates was found to be 19.5 mm, measured on the surface of the cranium, between the true hand area and the mean Talairach coordinate. This finding implies that using generalized coordinates might be misleading when choosing the optimal location for brain stimulation.

Gray and White Matter Voxel-Based Morphometry of Alzheimer's Disease With and Without Significant Cerebrovascular Pathologies.

Alzheimer's disease (AD) is the most common type of dementia, and AD individuals often present significant cerebrovascular disease (CVD) symptomology. AD with significant levels of CVD is frequently labeled mixed dementia (or sometimes AD-CVD), and the differentiation of these two neuropathologies (AD, AD-CVD) from each other is challenging, especially at early stages. In this study, we compared the gray matter (GM) and white matter (WM) volumes in AD (n = 83) and AD-CVD (n = 37) individuals compared with those of cognitively healthy controls (n = 85) using voxel-based morphometry (VBM) of their MRI scans. The control individuals, matched for age and sex with our two dementia groups, were taken from the ADNI. The VBM analysis showed widespread patterns of significantly lower GM and WM volume in both dementia groups compared to the control group (P < .05, family-wise error corrected). While comparing with AD-CVD, the AD group mainly demonstrated a trend of lower volumes in the GM of the left putamen and right hippocampus and WM of the right thalamus (uncorrected P < .005 with cluster threshold, K = 10). The AD-CVD group relative to AD tended to present lower GM and WM volumes, mainly in the cerebellar lobules and right brainstem regions, respectively (uncorrected P < .005 with cluster threshold, K = 10). Although finding a discriminatory feature in structural MRI data between AD and AD-CVD neuropathologies is challenging, these results provide preliminary evidence that demands further investigation in a larger sample size.

Obstructive sleep apnea detection during wakefulness: a comprehensive methodological review.

Obstructive sleep apnea (OSA) is a chronic condition affecting up to 1 billion people, globally. Despite this spread, OSA is still thought to be underdiagnosed. Lack of diagnosis is largely attributed to the high cost, resource-intensive, and time-consuming nature of existing diagnostic technologies during sleep. As individuals with OSA do not show many symptoms other than daytime sleepiness, predicting OSA while the individual is awake (wakefulness) is quite challenging. However, research especially in the last decade has shown promising results for quick and accurate methodologies to predict OSA during wakefulness. Furthermore, advances in machine learning algorithms offer new ways to analyze the measured data with more precision. With a widening research outlook, the present review compares methodologies for OSA screening during wakefulness, and recommendations are made for avenues of future research and study designs.

Evaluating the Diagnostic Value of Electrovestibulography (EVestG) in Alzheimer's Patients with Mixed Pathology: A Pilot Study.

Background and Objectives: Diagnosis of dementia subtypes caused by different brain pathophysiologies, particularly Alzheimer's disease (AD) from AD mixed with levels of cerebrovascular disease (CVD) symptomology (AD-CVD), is challenging due to overlapping symptoms. In this pilot study, the potential of Electrovestibulography (EVestG) for identifying AD, AD-CVD, and healthy control populations was investigated. Materials and Methods: A novel hierarchical multiclass diagnostic algorithm based on the outcomes of its lower levels of binary classifications was developed using data of 16 patients with AD, 13 with AD-CVD, and 24 healthy age-matched controls, and then evaluated on a blind testing dataset made up of a new population of 12 patients diagnosed with AD, 9 with AD-CVD, and 8 healthy controls. Multivariate analysis was run to test the between population differences while controlling for sex and age covariates. Results: The accuracies of the multiclass diagnostic algorithm were found to be 85.7% and 79.6% for the training and blind testing datasets, respectively. While a statistically significant difference was found between the populations after accounting for sex and age, no significant effect was found for sex or age covariates. The best characteristic EVestG features were extracted from the upright sitting and supine up/down stimulus responses. Conclusions: Two EVestG movements (stimuli) and their most informative features that are best selective of the above-populations' separations were identified, and a hierarchy diagnostic algorithm was developed for three-way classification. Given that the two stimuli predominantly stimulate the otholithic organs, physiological and experimental evidence supportive of the results are presented. Disruptions of inhibition associated with GABAergic activity might be responsible for the changes in the EVestG features.

Developing cognitive workload and performance evaluation models using functional brain network analysis.

Cognition, defined as the ability to learn, remember, sustain attention, make decisions, and solve problems, is essential in daily activities and in learning new skills. The purpose of this study was to develop cognitive workload and performance evaluation models using features that were extracted from Electroencephalogram (EEG) data through functional brain network and spectral analyses. The EEG data were recorded from 124 brain areas of 26 healthy participants conducting two cognitive tasks on a robot simulator. The functional brain network and Power Spectral Density features were extracted from EEG data using coherence and spectral analyses, respectively. Participants reported their perceived cognitive workload using the SURG-TLX questionnaire after each exercise, and the simulator generated actual performance scores. The extracted features, actual performance scores, and subjectively assessed cognitive workload values were used to develop linear models for evaluating performance and cognitive workload. Furthermore, the Pearson correlation was used to find the correlation between participants' age, performance, and cognitive workload. The findings demonstrated that combined EEG features retrieved from spectral analysis and functional brain networks can be used to evaluate cognitive workload and performance. The cognitive workload in conducting only Matchboard level 3, which is more challenging than Matchboard level 2, was correlated with age (0.54, p-value = 0.01). This finding may suggest playing more challenging computer games are more helpful in identifying changes in cognitive workload caused by aging. The findings could open the door for a new era of objective evaluation and monitoring of cognitive workload and performance.

Measuring anxiety disorder in bipolar disorder using EVestG: broad impact of medication groups.

Objectives: Anxiety disorder is present in approximately half of all bipolar disorder (BD) patients. There are neurologic bases for the comorbidity of balance (vestibular) disorders and anxiety. Our objective is to use electrovestibulography (EVestG), which is predominantly a measure of vestibular neural activity to not only quantitatively detect and measure comorbid anxiety disorder but also to quantitatively measure the impacts of anti-depressant, anti-psychotic, and mood stabilizer medication groups on anxiety measures in BD patients. Methods: In a population of 50 (24 with anxiety disorder) depressive phase BD patients, EVestG signals were measured. Participants were labeled depression-wise as anxious or non-anxious using standard questionnaires. Analyses were conducted on the whole dataset as well as on matched (age/gender/MADRS) and "modeled medication-free" subsets. Modulations of the low-frequency EVestG firing pattern data were measured. Findings: For BD, the main anxious minus non-anxious difference was the presence of an increase in spectral power proximal to 8-9 Hz, which was best attenuated by mood stabilizers. Novelty: This is the first study to use an oto-acoustic physiological measure to quantify anxiety disorder in BD wherein it appears to manifest as a peak proximal to 8-9 Hz which we hypothesize as likely linked to hippocampal theta.

Does Resting Motor Threshold correlate with severity of Alzheimer's disease?

Conflicting results have emerged from studies examining the potential of resting motor threshold (RMT) as a neurophysiological marker for Alzheimer's disease (AD) diagnosis and progression. In this study, we estimated the strength of the association between RMT measurements and severity of cognitive impairment in a relatively large sample (N=128) of clinical trial participants with mild (Clinical Dementia Rating - CDR=1) to moderate (CDR=2) AD. RMT for each participant was determined by applying single-pulse transcranial magnetic stimulation repeated at varying intensities over left and right sides of the primary motor cortex. RMT is the minimum intensity that evoked a visible contralateral involuntary finger twitch and RMT asymmetry is the absolute difference between the left and right RMT measurements. Cognitive impairment was measured with the Montreal Cognitive Assessment (MoCA) and the Alzheimer Disease Assessment Scale - Cognitive (ADAS-Cog) scores. Although the left and right RMT was lower in CDR 2 than in CDR 1 participants, neither RMT nor RMT asymmetry correlated significantly with cognitive test scores. In conclusion, our study in a large sample size does not support the idea that RMT is a sensitive marker of cognitive decline/severity in AD. Clinical Relevance- This study provides evidence that RMT may not be useful for AD progression monitoring.

Verification EVestG recordings are vestibuloacoustic signals.

Introduction: Neural dysfunction is associated with aberrant nerve firing; thus, electrodiagnosis has the potential for objective diagnosis and quantification of neural dysfunction. Electrical stimulation alters nerve firing and may also have treatment potential. This article outlines some findings related to electrodiagnosis and electrical stimulation of the ear. The quasi-synchronous firing of many vestibuloacoustic nerve fibers can produce an extracellular potential defined as a field potential (FP). Electrovestibulography (EVestG) is a method to record vestibuloacoustic signals and detect the associated FPs. A clear picture of the muscle-, EEG-, saccade-related, or other artefactual origins, and the physiologic basis of FPs recorded with EVestG, is evolving. EVestG was applied to demonstrate the effect of electrical stimulation on spontaneous FPs in the ear canal. Methods: Bilateral EVestG recordings were conducted on 14 guinea pigs before and after stimulation with 3-0.5 mA ipsilateral anodal electrical pulses before and after ablation via unilateral Scarpa's ganglionectomy to elucidate the origin of the EVestG recorded spontaneous FPs. Results: Anodal electrical stimulation suppresses the recorded activity. There was a significant reduction of the level of recorded signal observed following anodal stimulation on the ablated but not the intact side. Conclusion: Electrical stimulation of the external auditory canal reduces spontaneous electrical activity in the ear canal, some of which is due to central nervous system activity. The EVestG recorded FPs have a major vestibuloacoustic component.

Fluid-structure interaction modelling of the upper airway with and without obstructive sleep apnea: a review.

Obstructive sleep apnea (OSA) is a common respiratory disorder associated with the collapse of the upper airway during sleep. OSA may cause oxygen desaturation, arousals from sleep, and daytime sleepiness, in turn affecting quality of life. There is low success rate in existing OSA surgical treatments mainly due to heterogeneity of the OSA population and poor understanding of the mechanism of the upper airway collapse in each individual. However, advancements in computational simulation have led to some detailed structural modelling of the upper airway that may help to better understand its collapse mechanism in OSA. Alternative surgical treatment methods may be critically assessed with simulation prior to clinical adoption to provide personalized treatment insight for an OSA individual. This review summarizes the current literature related to the application of fluid structure interaction simulation for OSA analysis, with a focus on pharyngeal airway deformation mechanisms, airflow characteristics, and OSA surgical treatment efficacy; it also identifies the shortcomings of current models with suggestions for future studies. It is evident that the upper airway collapse mechanism, the anatomical factors affecting the location and timing of the collapse, and the association of the upper airway anatomical features with critical pressure (Pcrit) are still lacking. Moreover, numerical simulation has been shown to be a great tool in OSA surgical treatment efficacy. Future studies incorporating the practice of virtual surgery may further support clinical decision-making.

The Effect of Transcranial Alternating Current Stimulation With Cognitive Training on Executive Brain Function in Individuals With Dementia: Protocol for a Crossover Randomized Controlled Trial.

BACKGROUND: Although memory and cognitive declines are associated with normal brain aging, they may also be precursors to dementia. OBJECTIVE: We aim to offer a novel approach to prevent or slow the progress of neurodegenerative dementia, or plausibly, improve the cognitive functions of individuals with dementia. METHODS: We will recruit and enroll 75 participants (older than 50 years old with either mild cognitive impairment or probable early or moderate dementia) for this double-blind randomized controlled study to estimate the efficacy of active transcranial alternating current stimulation with cognitive treatment (in comparison with sham transcranial alternating current stimulation). This will be a crossover study; a cycle consists of sham or active treatment for a period of 4 weeks (5 days per week, in two 30-minute sessions with a half-hour break in between), and participants are randomized into 2 groups, with stratification by age, sex, and cognitive level (measured with the Montreal Cognitive Assessment). Outcomes will be assessed before and after each treatment cycle. The primary outcomes are changes in Wechsler Memory Scale Older Adult Battery and Alzheimer Disease Assessment Scale scores. Secondary outcomes are changes in performance on tests of frontal lobe functioning (verbal fluency), neuropsychiatric symptoms (Neuropsychiatric Inventory Questionnaire), mood changes (Montgomery-Åsberg Depression Rating Scale), and short-term recall (visual 1-back task). Exploratory outcome measures will also be assessed: static and dynamic vestibular response using electrovestibulography, neuronal changes using functional near-infrared spectroscopy, and change in spatial orientation using virtual reality navigation. RESULTS: As of February 10, 2022, the study is ongoing: 7 patients have been screened, and all were deemed eligible for and enrolled in the study; 4 participants have completed baseline assessments. CONCLUSIONS: We anticipate that transcranial alternating current stimulation will be a well-tolerated treatment, with no serious side effects and with considerable short- and long-term cognitive improvements. TRIAL REGISTRATION: Clinicaltrials.gov NCT05203523; https://clinicaltrials.gov/show/NCT05203523. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/37282.

Comparing Vestibular Responses to Linear and Angular Whole-Body Accelerations in Real and Immersive Environments.

The vestibular end organs differ in terms of anatomical and physiological characteristics. Sensory modalities' stimuli including visual stimuli and vestibular sensation can influence these organs differently. This paper explores differences between vestibular responses to axial tilts in physical and virtual environments. Four passive whole-body movements (linear: up-down, and angular: yaw, pitch, and roll) were applied to twenty-seven healthy participants once using a hydraulic chair (physical) and once visually using a head-mounted display (virtual). Electrovestibulography (EVestG) was used as the outcome measure to investigate the magnitude of vestibular-response-change in both ears for physical and virtual stimuli. Three features including average action potential (AP) area, AP amplitude, and mean detected firing rate change were used as indices of response. The results show that for both physical and virtual stimuli (1) generally the pitch and roll tilts produce the largest EVestG changes compared to other tilts (2) roll and pitch tilt responses are not significantly different from each other and (3) right side and left side roll tilts' responses are not significantly different. The findings indicate although visually- and physically-induced vestibular responses are different in terms of afferent activity, visual stimuli can still result in distinct responses when exposed to different axial tilts.

Sleep-wake states change the interictal localization of candidate epileptic source generators.

STUDY OBJECTIVES: To compare estimated epileptic source localizations from 5 sleep-wake states (SWS): wakefulness (W), rapid eye movement sleep (REM), and non-REM 1-3. METHODS: Electrical source localization (sLORETA) of interictal spikes from different SWS on surface EEG from the epilepsy monitoring unit at spike peak and take-off, with results mapped to individual brain models for 75% of patients. Concordance was defined as source localization voxels shared between 2 and 5 SWS, and discordance as those unique to 1 SWS against 1-4 other SWS. RESULTS: 563 spikes from 16 prospectively recruited focal epilepsy patients across 161 day-nights. SWS exerted significant differences at spike peak but not take-off. Source localization size did not vary between SWS. REM localizations were smaller in multifocal than unifocal patients (28.8% vs. 54.4%, p = .0091). All five SWS contributed about 45% of their localizations to converge onto 17.0 ± 15.5% voxels. Against any one other SWS, REM was least concordant (54.4% vs. 66.9%, p = .0006) and most discordant (39.3% vs. 29.6%, p = .0008). REM also yielded the most unique localizations (20.0% vs. 8.6%, p = .0059). CONCLUSIONS: REM was best suited to identify candidate epileptic sources. sLORETA proposes a model in which an "omni-concordant core" of source localizations shared by all five SWS is surrounded by a "penumbra" of source localizations shared by some but not all SWS. Uniquely, REM spares this core to "move" source voxels from the penumbra to unique cortex not localized by other SWS. This may reflect differential intra-spike propagation in REM, which may account for its reported superior localizing abilities.

An unbiased algorithm for objective separation of Alzheimer's, Alzheimer's mixed with cerebrovascular symptomology, and healthy controls from one another using electrovestibulography (EVestG).

Diagnosis of Alzheimer's disease (AD) from AD with cerebrovascular disease pathology (AD-CVD) is a rising challenge. Using electrovestibulography (EVestG) measured signals, we develop an automated feature extraction and selection algorithm for an unbiased identification of AD and AD-CVD from healthy controls as well as their separation from each other. EVestG signals of 24 healthy controls, 16 individuals with AD, and 13 with AD-CVD were analyzed within two separate groupings: One-versus-One and One-versus-All. A multistage feature selection process was conducted over the training dataset using linear support vector machine (SVM) classification with 10-fold cross-validation, k nearest neighbors/averaging imputation, and exhaustive search. The most frequently selected features that achieved highest classification performance were selected. 10-fold cross-validation was applied via a linear SVM classification on the entire dataset. Multivariate analysis was run to test the between population differences while controlling for the covariates. Classification accuracies of ≥ 80% and 78% were achieved for the One-versus-All classification approach and AD versus AD-CVD separation, respectively. The results also held true after controlling for the effect of covariates. AD/AD-CVD participants showed smaller/larger EVestG averaged field potential signals compared to healthy controls and AD-CVD/AD participants. These characteristics are in line with our previous study results.

Egocentric spatial orientation differences between Alzheimer's disease at early stages and mild cognitive impairment: a diagnostic aid.

Alzheimer's disease (AD) is a growing global crisis. Egocentric spatial orientation deteriorates with age and more significantly with AD. A simple and quick virtual reality (VR) localization and target finding technique is presented as a diagnostic aid to screen mild cognitive impairment (MCI) from AD. Spatial orientation data from 93 individuals (65 AD at a mild stage, 20 MCI, and 8 other dementia types) based on VR localization of a target on a landmark-less cubic 3-story building were analyzed. We hypothesize AD and MCI groups' performances are significantly different. AD and MCI spatial performances were statistically significantly (p < 0.001) different. These results plus the longitudinal tracking of three patients who developed AD over a period of 5 years suggest the proposed spatial tests may be used as a quick and simple clinical diagnostic aid to separate AD at early to mild stages from MCI.

Baseline Prediction of rTMS efficacy in Alzheimer patients.

Repetitive transcranial magnetic stimulation (rTMS) with extensive 2-6-week protocols are applied to improve cognition and/or slow the cognitive decline seen in Alzheimer's Disease (AD). To date, there are no means to predict the response of a patient to rTMS treatment at baseline. Electrovestibulography (EVestG) biomarkers can be used to predict, at baseline, the efficacy of rTMS when applied to AD individuals. In a population of 27 AD patients (8 with significant cerebrovascular symptomatology, labelled ADcvd) EVestG signals were measured before and after rTMS treatment, and then compared with 16 age-matched healthy controls. MoCA was measured at baseline, whilst ADAS-Cog was the primary outcome measure. AD severity and comorbid cerebrovascular disease were treated as covariates. Using ADAS-Cog total score change, 13/27 AD/ADcvd patients improved with rTMS and 14/27 showed no-improvement. Leave-one-out-cross-validated linear-discriminant-analysis using two EVestG features yielded a blind accuracy of 75% for separating the improved and non-improved populations. Three-way separation of improved/non-improved/control accuracy was 91.9% using MoCA (67% alone) and one EVestG feature (66% alone). AD severity affects the rTMS treatment efficacy. The effect of existing significant cerebrovascular symptomatology on the efficacy of rTMS treatment remains unresolved. Baseline EVestG features can be predictive of the efficacy of rTMS treatment.