Case Studies

Read about success stories.

Honeybrains Biotech

Honeybrains Biotech is a U.S.-based life science company (founded 2020) focused on treating anxiety-related disorders such as Panic Disorder and PTSD – both debilitating conditions affecting millions worldwide.

 

Summary

The company is conducting a Phase 2 Clinical Trial of their novel HB-1 compound aimed at treatment of PTSD. The company is looking to address a challenge that has become increasingly common in the neuropsychiatric drug development space: proving clinical efficacy in the face of biological heterogeneity.

In recent years, numerous psychiatric drugs have failed in clinical trials—not necessarily because the compounds lack therapeutic potential, but because they are evaluated across broad, heterogeneous patient populations. This “one-size-fits-all” approach overlooks crucial biological and phenotypic differences that influence how individual patients respond to a given treatment. As a result, many promising therapies appear ineffective at the population level, even though they may be highly effective for specific subgroups.

To overcome these challenges, Honeybrains Biotech selected Brainify.AI to provide a comprehensive ‘white glove’ biomarker discovery service. As part of this engagement, Brainify.AI will collect EEG data and apply its EEG Foundational Model to identify the drug’s responder sub-population, thereby improving HB-1’s observed clinical effectiveness.

 

Strategy

Brainify.AI was engaged to address this challenge with a tailored biomarker solution leveraging EEG Foundational Model. Brainify.AI has come up with a strategy to enable biomarker discovery and implementation:

1. EEG Protocol Development:

Design protocols including scales, ERP (event-related potential) tasks, and standardized procedures for biomarker discovery

2. EEG Protocol Implementation:

Install, verify, and test EEG/ERP hardware and software to ensure readiness for data collection 

3. EEG Data Collection

Conduct day-to-day EEG acquisition at clinical sites by trained Brainify.AI technicians

4. Biomarker/CDx Research

Leverage Brainify.AI’s EEG Foundational Model, trained on 150,000+ subjects, for biomarker discovery and validation

5. Post-Approval CDx Deployment

Implement the biomarker on Brainify.AI’s neurotech platform for clinical practice use

 

Impact

This approach powered by the EEG Foundational Model offers several key advantages for Honeybrains Biotech:

1. Large-scale Training Data: Brainify.AI’s EEG Foundational Model is trained on an extensive dataset (over 150,000 subjects), enabling it to recognize complex, generalized patterns associated with neuropsychiatric disorders.

2. Adaptability: The EEG Foundational Model serves as a versatile basis from which specific biomarkers for various psychiatric conditions and treatments can be derived. This flexibility accelerates the development and validation of treatment-specific biomarkers, significantly reducing time and costs.

3. Enhanced Prediction Accuracy: Such a model allows for precise prediction of treatment and placebo responses, greatly increasing the likelihood of clinical trial success and the efficiency of biomarker discovery and validation processes.

Electroencephalography (EEG) is considered an excellent choice for biomarker research for several reasons:

1. Objective Biomarkers: EEG provides objective neurophysiological biomarkers that can measure brain activity directly, offering insights into the neurological effects of treatments and placebo responses.

2. Non-invasive and Scalable: EEG procedures are non-invasive, relatively low-cost, and practical for widespread implementation across clinical trial sites, thus being scalable and accessible for diverse patient populations. 

Expected Outcomes

The expected outcomes of adopting Brainify.AI’s EEG biomarker approach for Honeybrains Biotech include:

  • Enhanced Clinical Trial Success: By incorporating EEG-based biomarkers, particularly for placebo response prediction, Honeybrains Biotech can significantly improve trial outcomes, ensuring clearer differentiation of HB-1’s efficacy versus placebo
  • Increased Market Penetration: With validated EEG biomarkers serving as companion diagnostics (CDx), HB-1 could potentially be elevated from fourth- or fifth-line treatments to second- or third-line options, substantially expanding market reach and revenue potential.
  • Cost Efficiency: Adopting Brainify.AI’s platform would substantially reduce overall clinical trial costs by minimizing required sample sizes and enhancing statistical power without compromising trial quality.
  • Regulatory Advantage: The EEG biomarkers (once validated) facilitate regulatory approval processes by clearly demonstrating treatment efficacy, thus streamlining FDA interactions and approvals for HB-1 and associated companion diagnostics.

Overall, adopting Brainify.AI’s full-stack neurotech platform (integrated hardware, software, AI and CDx) presents a strategic advantage for Honeybrains Biotech by addressing critical clinical and commercial challenges in psychiatric drug development.

Back to top

Predicting age from resting-state scalp EEG signals with deep convolutional neural networks on TD-brain dataset

The current study aimed to create a new deep learning solution for brain age prediction using raw resting-state scalp EEG. The architecture and training method of the proposed deep convolutional neural networks (DCNN) improve state-of-the-art metrics in the age prediction task using raw resting-state EEG data by 13%. Given that brain age prediction might be a potential biomarker of numerous brain diseases, inexpensive and precise EEG-based estimation of brain age will be in demand for clinical practice.

Published in Frontiers on December 6th, 2022

Prediction of brain sex from EEG: using large-scale heterogeneous dataset for developing a highly accurate and interpretable ML model

This study presents a comprehensive examination of sex-related differences in resting-state electroencephalogram (EEG) data, leveraging two different types of machine learning models to predict an individual's sex. The best-performing model achieved an accuracy of 85% and a ROC AUC of 89%, surpassing all prior benchmarks set using EEG data and rivalling the top-tier results derived from fMRI studies.

Published in Neuroimage in January 2024

Optimization of the Deep Neural Networks for Seizure Detection

The goal of the present study was to optimize model selection and data preparation procedures for seizure detection in patients with epilepsy on wearable EEG data for the "ICASSP Signal Processing Grand Challenge’. We tested more than 100 deep convolutional neural networks (DCNN) architectures and hyperparameter combinations to achieve the most accurate, robust, and generalizable performance in seizure detection tasks. The best models included the spectral transformation of raw EEG data for the DCNN model input, using correct cross-validation procedures, tuning data sampling for class imbalance problems, and data augmentation procedures. 

Published in IEEE Xplore on May 5th, 2023

Data Leakage Problem in Large Multi-site EEG Datasets

In the current study, we show that data leakage is an important problem in the existing large-scale EEG datasets. Using the DCNN model we demonstrate such non-physiological information of EEG as the recording location can be predicted with 99% accuracy. Our results show that crucial for advances in neuroscience large-scale EEG projects studies urgently require tools to harmonize data and eliminate the data leakage problem.

Presented at the International Symposium on Biomedical Imaging (ISBI - 2023) organized by IEEE in Colombia

“Brain sex” prediction from EEG data using
tree-based algorithms

Current research on sex-related electrical
signatures of the brain shows that some of these features are more common in females and others are more common in males. Overall, sex-related brain variance is better described as a continuous rather than a binary variable. Moreover, fMRI studies have found the mosaic “male” and “female” zones (Joel et al., 2015), and the distribution of such zones can be unique for a person. The “brain sex” phenotype may act as a
biomarker to mark certain mental health disorders (Phillips et al., 2019).

Published at the Max Planck Institute for Human Cognitive and Brain Sciences