Asif Rahman

Senior Scientist
Machine Learning in Healthcare

My interests are at the interface of digital health and machine learning. I currently work on applications of machine learning in healthcare at Philips Research with a special interest in modelling biosignals, sequence similarity search, and incorporating prior knowledge into AI models. Previously, I obtained my PhD in neural engineering and was a data scientist at Stitch Fix. Author of Machine Learning for Digital Health

Research topics

My work at Philips centers on developing clinical analytics for patient monitors using machine learning to enable personalized care, empower care givers with AI-powered reasoning tools, and improve patient & operational outcomes.

  1. Risk prediction & phenotyping →
  2. Patient similarity & information retrieval →
  3. Interpretable machine learning →
  4. Biosignal processing →

1. Risk prediction & phenotyping

I build realtime clinical risk indicators that are deployed on patient monitors and central stations.

2. Patient similarity & information retrieval

Patient similarity aims to identify cohorts based on a set of characteristics (like demographics, vitals, labs, medical history, and treatments) to enable applications like case-based comparisons for clinical decision support and to compare treatments across similar cohorts.

3. Interpretable machine learning

A key requirement of clinical models is that they have to be explainable so that the nurse or clinician can understand the risk factors. The models should also be editable so we can identify when then algorithm makes an error and fix it before deployment.

4. Biosignal processing

I develop deep learning algorithms using temporal convolutional neural networks, recurrent neural networks, and transformers for physiological signals collected from wearable devices, including electrocardiograms (ECG), photoplethysmography (PPG), phonocardiograms (PCG, heart sounds), and arterial blood pressure (ABP). Many of these solutions have come in first place at the PhysioNet Challenges. See publications below.

Recent Publications

Year Title
2021 Early prediction of hemodynamic interventions in the intensive care unit using machine learning
2021 Interpretable Additive Recurrent Neural Networks For Multivariate Clinical Time Series
2021 Utilizing machine learning to improve clinical trial design for acute respiratory distress syndrome
2020 Phenotyping with Prior Knowledge using Patient Similarity
2020 A Wide and Deep Transformer Neural Network for 12-Lead ECG Classification
2019 A Multi-Task Imputation and Classification Neural Architecture for Early Prediction of Sepsis from Multivariate Clinical Time Series
2018 Densely connected convolutional networks for detection of atrial fibrillation from short single-lead ECG recordings
2018 Analyzing single-lead short ECG recordings using dense convolutional neural networks and feature-based post-processing to detect atrial fibrillation
2018 An ensemble boosting model for predicting transfer to the pediatric intensive care unit
2017 Patient Similarity Using Population Statistics and Multiple Kernel Learning
2016 Ensemble of feature-based and deep learning-based classifiers for detection of abnormal heart sounds

See all publications on Google Scholar

Patents

Year Title
2019 Method for transforming patient data into images for infection prediction
2018 Learning and applying contextual similarities between entities
2018 Person identification systems and methods
2018 Discretized embeddings of physiological waveforms
2018 Detecting atrial fibrillation using short single-lead ecg recordings
2017 Using a neural network
2017 Classifier ensemble for detection of abnormal heart sounds
2012 Voltage limited neurostimulation

Notes

Date Title
Mar 2022 Python project setup
Jan 2022 Cosine similarity 1D convolutions
Jan 2022 Group-by and count in Numpy
Jan 2022 Separable temporal convolutions
Oct 2021 Quantile binning with missing data
Sept 2021 Ensemble decision trees in Numba
Sept 2021 Feature engineering for time series data using Numba
Aug 2021 Select a random window of maximum duration in NumPy
Feb 2021 Causal inference learners
Jul 2020 Offline Off-Policy Reinforcement Learning with Contextual Bandits
Jul 2020 Univariate Risk Curves
Jun 2020 Transform Grouped Pandas DataFrame to Numpy Array
Jun 2020 AWS Lambda Web Scraper
Jun 2020 Deploy static website with rsync
May 2020 Svelte Webpack Boilerplate
Dec 2018 Arrhythmia classification with stationary first order Markov process
Dec 2018 Nowcasting: Maintaining real time estimates of infrequently observed time series
Feb 2016 State space models and the Kalman filter
May 2015 Pandoc static site generator
Dec 2014 Data science at the command line
Aug 2014 Punchcard visualization using D3.js
Mar 2014 Data Mining PubMed