Brain Waves and Machine Learning Join Forces to Tell Alzheimer’s and FTD Apart

Distinguishing Alzheimer’s disease from frontotemporal dementia early in the course of illness is one of the most stubborn challenges in neurology, and a new study suggests that the answer may be hiding in the brain’s electrical static. Researchers at Aydın Adnan Menderes University in Turkey have built a machine learning framework that fuses electroencephalography signals with routine clinical information to separate the two dementias with striking accuracy. Writing in the journal Neural Computing and Applications, Ahmet Çağdaş Seçkin and Fatih Soygazi report that their best model, a gradient-boosted decision tree ensemble known as XGBoost, reached 89.8 percent classification accuracy with an area under the receiver operating characteristic curve of 0.971, a level of discrimination that approaches the performance of far more invasive and expensive diagnostic modalities.

The clinical stakes of this distinction could hardly be higher. Alzheimer’s disease and frontotemporal dementia can look deceptively similar in the clinic, particularly in the earliest stages when symptoms are subtle and brain scans may still appear unremarkable. Yet the two conditions strike different neural circuits, progress along different trajectories, and respond to entirely different care strategies. Alzheimer’s disease typically begins in the medial temporal lobes and hippocampal networks, eroding memory before spreading outward, while frontotemporal dementia attacks the frontal and anterior temporal lobes, producing early changes in personality, behavior, and language. Misdiagnosis at this fork in the road can delay appropriate treatment, mislead families about what to expect, and complicate enrollment into clinical trials that increasingly depend on identifying the right patients at the right time.

Current gold-standard diagnostics rely on positron emission tomography imaging, cerebrospinal fluid analysis, and, more recently, plasma biomarkers, all of which carry substantial cost, limited availability, or patient burden. Electroencephalography, by contrast, is cheap, painless, widely available in hospitals around the world, and capable of capturing the brain’s oscillatory dynamics with millisecond resolution. The idea that dementia leaves fingerprints in these rhythms is not new; decades of research have documented slowing of background activity and disrupted functional connectivity in affected brains. What has been missing is a rigorous, interpretable way to translate those signals into a reliable differential diagnosis, and that is precisely the gap the Turkish team set out to close.

The study drew on a publicly available dataset of routine scalp EEG recordings from patients with Alzheimer’s disease, patients with frontotemporal dementia, and healthy individuals, a collection originally curated and described by Miltiadous and colleagues. Rather than feeding raw waveforms into a deep neural network, the researchers took a feature-engineering approach, extracting a rich library of measurements from each recording. These included time-domain statistics that describe the amplitude and distribution of the voltage signal, as well as frequency-domain features that quantify how the brain’s power is distributed across the canonical EEG bands, from the slow delta and theta rhythms to the faster alpha and beta oscillations. Such features encode well-established neurophysiological phenomena, including the posterior alpha slowing characteristic of Alzheimer’s pathology and the frontal-predominant changes associated with frontotemporal degeneration.

Crucially, the team did not rely on brain data alone. They combined the EEG-derived features with demographic and cognitive information, creating a genuinely multimodal input space that mirrors how a clinician actually reasons, weighing test results alongside age, sex, and cognitive scores. To prevent this expanded feature set from overwhelming their relatively small sample, the researchers applied the Fast Correlation-Based Filter, a feature selection method introduced by Yu and Liu that prunes redundant and weakly informative variables by evaluating correlations between features and their relationship to the class label. The result was a compact, information-dense feature vector that preserved the most diagnostic signals while discarding noise, a critical step when the number of measurements threatens to exceed the number of subjects.

With the feature space curated, the authors benchmarked an arsenal of classical machine learning models: XGBoost, Random Forest, AdaBoost, artificial neural networks, and Gradient Boosting. Each was evaluated under leave-one-out cross-validation, a demanding scheme in which the model is trained on all but one subject and then asked to classify the held-out individual, repeated across every participant. In small-sample biomedical research, this procedure is widely regarded as the most honest way to estimate generalization performance, though it is computationally expensive and leaves no room for the model to hide from difficult cases. XGBoost emerged as the clear winner, an outcome consistent with the algorithm’s track record on structured tabular data, where its regularized boosting framework excels at capturing nonlinear interactions among heterogeneous features without requiring massive datasets.

What elevates the study beyond a leaderboard exercise is its commitment to explainability. Black-box predictions have long been a barrier to clinical adoption, and regulators and physicians alike are increasingly unwilling to act on outputs they cannot interrogate. Seçkin and Soygazi addressed this by applying SHAP, or SHapley Additive exPlanations, a technique rooted in cooperative game theory that assigns each feature a consistent, individualized contribution to every prediction. Rather than asking simply whether the model was right, the SHAP analysis reveals which specific measurements pushed each classification toward Alzheimer’s disease or frontotemporal dementia, and by how much. This transforms the model from an oracle into a collaborator, allowing neurologists to inspect the evidence behind a diagnosis and judge whether it aligns with the clinical picture.

The interpretability layer also serves a scientific purpose. By aggregating SHAP values across the cohort, researchers can identify which neurophysiological and clinical variables carry the greatest discriminative weight, generating hypotheses about the underlying pathophysiology. If, for example, particular spectral features from frontal electrode sites dominate the separation between the two dementias, that pattern itself becomes a biomarker candidate worth validating in prospective studies. The approach situates the work within a rapidly growing literature on explainable artificial intelligence in dementia research, including recent scoping reviews of xAI in dementia detection and prior explainable deep learning frameworks for EEG-based diagnosis, while distinguishing itself through its explicit multimodal design and its head-to-head comparison of interpretable tree ensembles.

The authors are careful to frame the results as promising rather than definitive. The dataset, while valuable, is modest in size, and the leave-one-out design, though rigorous, cannot substitute for external validation on independent cohorts recruited in different clinical settings with different equipment and preprocessing pipelines. Routine EEG recordings also carry artifacts and variability that a research-grade dataset may not fully capture. The authors note that no new data were collected for the study, meaning that ethical approval was not required, and they declare no conflicts of interest. The underlying dataset remains available to other researchers upon reasonable request, an openness that should accelerate replication efforts.

Even with those caveats, the implications are compelling. A diagnostic aid built on a machine that already exists in most neurology departments, requiring no contrast agents, no lumbar punctures, and no radioactive tracers, could dramatically widen access to early differential diagnosis, particularly in regions where advanced imaging is scarce. Combined with the transparency afforded by SHAP analysis, such a tool could earn the trust of clinicians rather than merely impressing them with accuracy statistics. The next steps, external validation, prospective testing, and integration into clinical workflows, are demanding, but the study demonstrates that the humble EEG, married to carefully engineered features and explainable machine learning, can do more than record brain activity. It can help answer one of dementia medicine’s most consequential questions with nearly ninety percent confidence, and it can show its work while doing so.

Subject of Research: Explainable multimodal machine learning using EEG and clinical data for early differential diagnosis of Alzheimer's disease and frontotemporal dementia

Article Title: Explainable multimodal learning for early differential diagnosis oF Alzheimer’S disease and frontotemporal dementia

Article References: Seçkin, A. Ç., & Soygazi, F. (2026). Explainable multimodal learning for early differential diagnosis oF Alzheimer’S disease and frontotemporal dementia. Neural Computing and Applications, 38(17), Article 715. https://doi.org/10.1007/s00521-026-12444-x

Image Credits: AI Generated

DOI: 10.1007/s00521-026-12444-x

Keywords: Alzheimer's disease, frontotemporal dementia, EEG, machine learning, explainable AI, XGBoost, SHAP, feature selection, dementia diagnosis, neurodegenerative diseases, clinical decision support, biomarkers