Health AI Clinical Data Science fNIRS + TSFRESH Melbourne Bionics Institute

Objective Tinnitus Detection from fNIRS

Led by Melbourne Bionics Institute, a machine learning workflow for objective tinnitus classification from fNIRS hbo/hbr signals, combining TSFRESH feature engineering, PCA compression, and repeated model evaluation.

Tinnitus project visual
fNIRSHBO and HBR
2 ModesResting and Trigger
2 ModalitiesAudio and Visual
TSFRESHFeature Extraction

Project Summary

Melbourne Bionics Institute led this project, which investigates whether fNIRS time-series signals can support objective identification of tinnitus cases versus controls. Data includes 32 channels (2 x 16 layout) with both hbo and hbr signals collected across resting and stimulus-triggered sessions.

The pipeline transforms channel-level time-series into rich feature vectors, reduces dimensionality, and benchmarks multiple classifiers over repeated stratified splits using clinical performance metrics.

My Role

I developed and implemented the machine learning modeling workflow with a focus on TSFRESH-based feature engineering for physiological time-series within the Melbourne Bionics Institute-led research program. My contributions included:

  • Building data-to-feature pipelines for resting and trigger-mode experiments.
  • Designing PCA-based dimensionality reduction for high-dimensional TSFRESH outputs.
  • Training and evaluating SVM, Random Forest, and kNN models with repeated validation.
  • Producing channel-ranking analyses to identify high-value signal locations.
  • Developing a deployable end-to-end GUI that accepts fNIRS sensory records as input and returns ML-based diagnosis output with a severity score and confidence estimate.

Technical Workflow

1) Data Structuring

fNIRS sensor setup

Per-channel hbo/hbr signals are chunked and transformed into modeling tables for subject-level analyses in resting and trigger settings.

2) TSFRESH Features

TSFRESH logo

Automated extraction of comprehensive time-series descriptors is performed with TSFRESH to capture statistical and temporal signal characteristics.

3) Dimensionality Reduction

PCA dimensionality reduction illustration

PCA reduces dimensionality and stabilizes downstream model fitting across channels and trigger conditions.

4) Classification

fNIRS time-series and model data output

Repeated train/test evaluation compares SVM, Random Forest, and kNN, reporting AUC, sensitivity, specificity, and accuracy.

5) Channel and ROI Analysis

Channel and ROI analysis illustration

Channel-level and regional analyses (frontal, temporal, occipital) are used to interpret where discriminative signal patterns are strongest.

6) Clinical Translation


Clinical translation pipeline illustration



The framework demonstrates how neurophysiological time-series can be converted into reproducible machine learning evidence for clinical decision-support research.

Interested in this work? I can share additional technical details and references on request.