NEURO
science
x ML
x clinical ai
Contact

About

The human
behind the models.

I am a data scientist and ML researcher based in Vancouver, BC, currently in my MDS at UBC while contributing to three research labs across biomedical engineering, neuropathology, and addiction psychiatry.

My background spans electronics engineering, health informatics, and data science. That combination gives me the rigour to build robust ML pipelines and the domain knowledge to make them clinically meaningful.

Whether it is 6DOF VR sensor streams from Alzheimer's patients, post-mortem IHC brain slides, or large-scale health claims, I am drawn to data that sits at the edge of what medicine can currently see.

Outside the lab: hiking the North Shore mountains, lifting heavy things.

Neuroscience x ML Clinical AI MDS at UBC 2026 Vancouver, BC Open to roles
3Active Research LabsNC4, Hirsch-Reinshagen, ACD at UBC
3+Years in IndustryRonsare, KPMG India, In-Med
91.6%Best Model AccuracyRandom Forest on cardiac EMR at KPMG
🏆Best Oral PresentationPATHS Neuroscience Conference, UBC

Research

Active Research.

Three concurrent positions at UBC spanning cognitive neuroscience, neuropathology, and addiction psychiatry.

NC4 Lab — Neural Circuits for Computation, Cognition and ControlApr 2026 – Present

Cognitive Decline Detection via VR Spatial Navigation

Supervisor: Dr. Manu Madhav · UBC Biomedical Engineering

  • Building an ML pipeline on VR spatial navigation data to detect early markers of cognitive decline and Alzheimer's, working with 6DOF sensor streams (head orientation, avatar position, controller quaternions) from 45 participants.
  • XGBoost classifiers with handcrafted movement features (angular velocity, heading drift, rotation smoothness) alongside transformer-based sequence models for time-series classification.
  • Functional PCA and Dynamic Time Warping for feature extraction on variable-length multivariate time series.
XGBoostTransformerTime SeriesfPCADTWAlzheimer's6DOF VR
Hirsch-Reinshagen Lab — Neuropathology and CNS DisordersMar 2026 – Present

Computational IHC Analysis for CNS Disorders

Supervisor: Dr. Veronica Hirsch-Reinshagen · UBC Pathology / VGH

  • Computational image analysis of multiplexed IHC slides from post-mortem human brain tissue using QuPath for cell segmentation and stain colocalization.
  • ML pipelines for automated spatial profiling of protein markers across brain regions in neurodegeneration and traumatic spinal cord injury.
QuPathIHC AnalysisCell SegmentationNeurodegenerationSpinal Cord Injury
ACD Research Group — Addictions and Concurrent DisordersNov 2025 – Present

Opioid Overdose, ABI and Fentanyl Clustering

Supervisor: Dr. Michael Krausz · UBC Psychiatry

  • Co-authoring a paper on opioid overdose and acquired brain injury — systematic review, data extraction, and full manuscript writing.
  • Research on fentanyl overdose clustering and temporal patterns of overdose events across vulnerable populations.
  • Presented systematic review on stimulant co-use in opioid agonist therapy at the PATHS To A Cure Neuroscience Conference, UBC.
Systematic ReviewEpidemiologyOpioid ABIFentanyl Clustering
🏆 Best Oral Presentation — PATHS To A Cure Neuroscience Conference, UBC

Skills

Technical Stack.

Hover a cluster to illuminate its connections. Each node is a skill.

Languages
Python · R · SQL · C · Bash
ML and AI
XGBoost · LightGBM · Transformers · Time Series
Libraries
PyTorch · scikit-learn · pandas · OpenCV · tslearn
Clinical and Pathology
EHR/EMR · IHC · QuPath · Epidemiology
Tools and Cloud
Git · Docker · GCP · AWS · PostgreSQL

Projects

Personal Projects.

Independent builds, coursework, and capstone work — separate from lab research.

Capstone 2026 · MDS at UBC

INSPECT: Multimodal Pulmonary Embolism Prediction

Reproducing Stanford's INSPECT benchmark — a late-fusion pipeline combining CTPA deep learning (LRCN: ResNet encoder + GRU sequence model) with structured EHR data (LightGBM) to predict PE and 8 downstream clinical outcomes. Trained on GCP with GCS storage.

PyTorchLightGBMGCPCTPAEHR
GitHub ↗
Drug Discovery · Personal Project

Molecular Binding Affinity and Uncertainty

Predicts pChEMBL binding affinity against EGFR (cancer-relevant kinase) using 13k ChEMBL molecules. Compares Morgan fingerprint MLP vs Graph Attention Network (3-feature and 7-feature). MC Dropout uncertainty quantification on both models. Scaffold-split evaluation.

PyTorch GeometricGATMC DropoutOptuna
GitHub ↗
Personal Project · In Progress

BrainMRI-Net: Alzheimer's Classification

3-class MRI classification (Cognitively Normal, MCI, Alzheimer's) on the OASIS-1 dataset. CNN pipeline with Grad-CAM interpretability for radiologist-friendly visualisation. Subject-level splits to prevent data leakage.

PyTorchGrad-CAMOASIS-1CNNIn Progress
GitHub ↗

Journey

Education and Experience.

Jul 2018
BTech Electronics and Telecom (AI)
MIT Pune · India
Foundation in signal processing, circuits, and AI specialisation.
Oct 2020
Data Scientist
KPMG India · New Delhi
EMR/EHR analytics, heart disease prediction (91.6% accuracy), brain CT/MRI preprocessing pipelines.
Mar 2021
R&D Intern
In-Med Prognostics · Pune
Brain CT alignment pipeline for ~100 patients. Anatomical axis standardisation for downstream analysis.
Jun 2022
Data Scientist
Ronsare Research · Remote
3 years building healthcare claims ETL pipelines, ML preprocessing scripts, and data governance workflows.
Jan 2023
Advanced Diploma, Technology Management
RRC Polytech · Winnipeg
Technology management with focus on data-driven decision making.
Aug 2025
Master of Data Science
University of British Columbia
MDS program with concurrent RA positions across three UBC research labs.
2025 – 26
Research Assistant x 3
UBC · NC4, VGH, Psychiatry
VR cognitive decline, IHC neuropathology, opioid overdose epidemiology. Best Oral Presentation award.

Publications and Writing

Research and Writing.

Conference presentations, in-progress papers, and technical writing on Medium.

Paper — In Progress

Opioid Overdose and Acquired Brain Injury (ABI)

Co-authored under Dr. Michael Krausz (UBC Psychiatry). Systematic review, data extraction, and full manuscript writing on ABI prevalence in opioid-overdose populations.

In Review
Conference Presentation · UBC

Stimulant Co-Use in Opioid Agonist Therapy

Presented at the PATHS To A Cure Neuroscience Research Conference, UBC. 🏆 Best Oral Presentation.

2025–26
Technical Writing · Medium

Data Science, ML and Neuroscience Articles

Accessible, in-depth content on ML, clinical data science, and neuroscience for a technical audience.

Read ↗
Let's build something meaningful.
gurleenlakhman@gmail.com
LinkedIn ↗ GitHub ↗ Medium ↗