Bipolar disorder, affecting 1–2.5% of the French population, is characterized by alternating depressive and hyperthymic episodes, with Type I involving manic or hypomanic states and Type II only hypomanic. Diagnosis currently rests on clinical interviews and symptom reporting. Inès Tahir’s PhD research, embedded in the BipoNIRS clinical study led by Prof. Mircea Polosan (Université Grenoble Alpes, CHU Grenoble Alpes, FondaMental Expert Center) in collaboration with Israel’s Holon Institute of Technology, seeks to replace this subjectivity with objective biomarkers for more accurate and earlier diagnosis.

CEA‑Leti deployed a headset combining EEG (scalp electrodes capturing electrical activity) and fNIRS (optical sensors measuring oxygenated and deoxygenated hemoglobin via light scattering). A cohort of 25 healthy controls, 21 bipolar I patients, and 25 bipolar II patients performed a visual emotional task designed to probe emotion regulation, which is typically impaired and slower in bipolar individuals. To handle the modest sample size, Tahir built an AI classifier with explicit measures to curb overfitting and bias while preserving generalization.

The model identified relevant biomarkers and reliably discriminated between bipolar I, bipolar II, and healthy participants. Combining EEG and fNIRS significantly boosted classification performance compared to EEG alone. With whole‑head EEG, accuracy was high; more importantly, when the system was restricted to frontal electrodes and optodes—a region plagued by ocular artifacts in EEG—the multimodal approach compensated and maintained satisfactory discrimination. fNIRS signals offset the noise in frontal EEG, confirming the feasibility of a compact, forehead‑only device for routine clinical use.

These proof‑of‑concept results, published in Translational Psychiatry, point toward a portable tool that could assist psychiatrists in faster, more objective bipolar disorder diagnosis. The work was performed with CHU Grenoble Alpes and Université Grenoble Alpes.

​Bipolar disorder is a mental health condition that affects, according to the French National Authority for Health, at least 1 to 2.5% of the French population. It is characterized by marked mood changes, including depressive episodes and hyperthymic episodes, which are periods of elevated mood and increased energy. Bipolar disorder is mainly divided into two subtypes. Type I involves depressive and manic or hypomanic episodes, while type II involves depressive and hypomanic episodes.

Diagnosis of this disorder is generally based on a clinical assessment performed by a psychiatrist, using reported symptoms and observed clinical signs.

Inès Tahir's PhD thesis specifically aims to help physicians establish a diagnosis. Her work is part of a clinical study led by Professor Mircea Polosan — Professor at Université Grenoble Alpes, Head of the Psychiatry Department at Grenoble Alpes University Hospital, Head of a FondaMental Expert Center, and thesis director — within a broader collaborative project with the Holon Institute of Technology in Tel Aviv, Israel. Named BipoNIRS, this study aims to identify relevant biomarkers for the classification of bipolar disorder and its subtypes. In the longer term, the goal is to support earlier diagnosis.

Inès Tahir contributes to this objective by analyzing the collected data to identify biomarkers of bipolar disorder across the full set of acquired signals. She is also pursuing this work by proposing a frontal EEG-fNIRS configuration based on the most relevant biomarkers. This configuration could facilitate the development of a dedicated clinical device for routine use.

EEG consists of placing electrodes on the scalp to measure the brain's electrical activity. fNIRS, on the other hand, relies on optical sensors, known as optodes, to estimate concentrations of oxygenated and deoxygenated hemoglobin in the brain by analyzing how light is scattered and absorbed through tissue. These two complementary methods have been investigated by CEA-Leti.

The study conducted by Inès Tahir is based on a cohort of 25 healthy subjects, 21 patients with bipolar disorder type I, and 25 patients with bipolar disorder type II.

All participants wore a headset combining EEG and fNIRS. They completed a protocol involving a “visual emotional task", designed to explore the cognitive and emotional processing of different stimuli. This type of task generally requires more time in people with bipolar disorder, due to their difficulties in regulating emotions.

To process the EEG and fNIRS data, she developed an AI model capable of learning to classify the different subjects.

The algorithm was designed to account for the limited sample size, reduce overfitting and potential bias, and preserve good generalization ability.

The model was then tested on this sample. It successfully identified relevant biomarkers and distinguished individuals with bipolar disorder type I from those with type II and from healthy subjects. In particular, combining EEG and fNIRS signals significantly improved classification performance compared with EEG alone.

More specifically, in the configuration where EEG covered the whole head, accuracy reached:

The study also confirmed the complementarity of EEG and fNIRS. When the two modalities were combined, classification remained possible using only frontal electrodes and optodes. In this configuration, fNIRS compensates for the difficulty of using frontal EEG signals alone, which are often affected by ocular artifacts.

These results were obtained while maintaining satisfactory overall discrimination performance. They support the relevance of a compact, portable system compatible with clinical practice.

These initial results open up several promising perspectives.

Discover the publication:https://www.nature.com/articles/s41398-026-03858-1

This work was conducted in collaboration withCHU Grenoble Alpes and Université Grenoble Alpes.​