Asif Rahman

Senior Scientist
Machine Learning in Healthcare

My interests are at the interface of digital health, time series analysis, and machine learning. I currently work on applications of machine learning in healthcare at Philips Research with a special interest in decision analysis for clarifying uncertain and dynamic decision problems in critical care. Previously, I obtained my PhD in neural engineering and was a data scientist at Stitch Fix.

Recent Publications

Phenotyping with Prior Knowledge using Patient Similarity (video)
A Wide and Deep Transformer Neural Network for 12-Lead ECG Classification
A Multi-Task Imputation and Classification Neural Architecture for Early Prediction of Sepsis from Multivariate Clinical Time Series
Densely connected convolutional networks for detection of atrial fibrillation from short single-lead ECG recordings
Analyzing single-lead short ECG recordings using dense convolutional neural networks and feature-based post-processing to detect atrial fibrillation
An ensemble boosting model for predicting transfer to the pediatric intensive care unit
Patient Similarity Using Population Statistics and Multiple Kernel Learning
Ensemble of feature-based and deep learning-based classifiers for detection of abnormal heart sounds


Offline Off-Policy Reinforcement Learning with Contextual Bandits
Quantifying Associations Using Odds-Ratios and Risk Curves
Transform Grouped Pandas DataFrame to Numpy Array
AWS Lambda Web Scraper
Deploy static website with rsync
Svelte Webpack Boilerplate
Arrhythmia classification with stationary first order Markov process
Nowcasting: Maintaining real time estimates of infrequently observed time series
State space models and the Kalman filter
Pandoc static site generator
Data science at the command line
Punchcard visualization using D3.js
Data Mining PubMed


Method for transforming patient data into images for infection prediction
Learning and applying contextual similarities between entities
Person identification systems and methods
Discretized embeddings of physiological waveforms
Detecting atrial fibrillation using short single-lead ecg recordings
Using a neural network
Classifier ensemble for detection of abnormal heart sounds
Voltage limited neurostimulation