Search Results for author: Majid Sarrafzadeh

Found 24 papers, 12 papers with code

A Self-supervised Framework for Improved Data-Driven Monitoring of Stress via Multi-modal Passive Sensing

no code implementations24 Mar 2023 Shayan Fazeli, Lionel Levine, Mehrab Beikzadeh, Baharan Mirzasoleiman, Bita Zadeh, Tara Peris, Majid Sarrafzadeh

Recent advances in remote health monitoring systems have significantly benefited patients and played a crucial role in improving their quality of life.

Auditing Algorithmic Fairness in Machine Learning for Health with Severity-Based LOGAN

no code implementations16 Nov 2022 Anaelia Ovalle, Sunipa Dev, Jieyu Zhao, Majid Sarrafzadeh, Kai-Wei Chang

Therefore, ML auditing tools must be (1) better aligned with ML4H auditing principles and (2) able to illuminate and characterize communities vulnerable to the most harm.

Bias Detection Clustering +1

Beyond Labels: Visual Representations for Bone Marrow Cell Morphology Recognition

1 code implementation19 May 2022 Shayan Fazeli, Alireza Samiei, Thomas D. Lee, Majid Sarrafzadeh

Analyzing and inspecting bone marrow cell cytomorphology is a critical but highly complex and time-consuming component of hematopathology diagnosis.

Contrastive Mixup: Self- and Semi-Supervised learning for Tabular Domain

1 code implementation27 Aug 2021 Sajad Darabi, Shayan Fazeli, Ali Pazoki, Sriram Sankararaman, Majid Sarrafzadeh

Recent literature in self-supervised has demonstrated significant progress in closing the gap between supervised and unsupervised methods in the image and text domains.

A Framework for Neural Topic Modeling of Text Corpora

1 code implementation19 Aug 2021 Shayan Fazeli, Majid Sarrafzadeh

Topic Modeling refers to the problem of discovering the main topics that have occurred in corpora of textual data, with solutions finding crucial applications in numerous fields.

Clustering

Unsupervised Acute Intracranial Hemorrhage Segmentation with Mixture Models

no code implementations12 May 2021 Kimmo Kärkkäinen, Shayan Fazeli, Majid Sarrafzadeh

We demonstrate the results of our algorithm on publicly-available datasets that contain all different hemorrhage types in various sizes and intensities, and our results are compared to earlier unsupervised and supervised algorithms.

Computed Tomography (CT)

COVID-19 and Big Data: Multi-faceted Analysis for Spatio-temporal Understanding of the Pandemic with Social Media Conversations

no code implementations22 Apr 2021 Shayan Fazeli, Davina Zamanzadeh, Anaelia Ovalle, Thu Nguyen, Gilbert Gee, Majid Sarrafzadeh

We provide a multi-faceted analysis of critical properties exhibited by these conversations on social media regarding the novel coronavirus pandemic.

Real-Time Decentralized knowledge Transfer at the Edge

1 code implementation11 Nov 2020 Orpaz Goldstein, Mohammad Kachuee, Derek Shiell, Majid Sarrafzadeh

Transferring knowledge in a selective decentralized approach enables models to retain their local insights, allowing for local flavors of a machine learning model.

Knowledge Distillation Transfer Learning

Transfer Learning for Activity Recognition in Mobile Health

1 code implementation12 Jul 2020 Yuchao Ma, Andrew T. Campbell, Diane J. Cook, John Lach, Shwetak N. Patel, Thomas Ploetz, Majid Sarrafzadeh, Donna Spruijt-Metz, Hassan Ghasemzadeh

While activity recognition from inertial sensors holds potential for mobile health, differences in sensing platforms and user movement patterns cause performance degradation.

Activity Recognition Transfer Learning

A Flexible and Intelligent Framework for Remote Health Monitoring Dashboards

1 code implementation9 Jun 2020 Shayan Fazeli, Majid Sarrafzadeh

Developing and maintaining monitoring panels is undoubtedly the main task in the remote patient monitoring (RPM) systems.

Hierarchical Target-Attentive Diagnosis Prediction in Heterogeneous Information Networks

no code implementations22 Dec 2019 Anahita Hosseini, Tyler Davis, Majid Sarrafzadeh

We introduce HTAD, a novel model for diagnosis prediction using Electronic Health Records (EHR) represented as Heterogeneous Information Networks.

feature selection Specificity

Group-Connected Multilayer Perceptron Networks

no code implementations20 Dec 2019 Mohammad Kachuee, Sajad Darabi, Shayan Fazeli, Majid Sarrafzadeh

GMLP is based on the idea of learning expressive feature combinations (groups) and exploiting them to reduce the network complexity by defining local group-wise operations.

Representation Learning

Cost-Sensitive Feature-Value Acquisition Using Feature Relevance

no code implementations17 Dec 2019 Kimmo Kärkkäinen, Mohammad Kachuee, Orpaz Goldstein, Majid Sarrafzadeh

The chosen features should increase the prediction accuracy for a low cost, but determining which features will do that is challenging.

Learning-To-Rank

Unsupervised Representation for EHR Signals and Codes as Patient Status Vector

no code implementations4 Oct 2019 Sajad Darabi, Mohammad Kachuee, Majid Sarrafzadeh

In this work, we present a two-step unsupervised representation learning scheme to summarize the multi-modal clinical time series consisting of signals and medical codes into a patient status vector.

Representation Learning Time Series +1

Target-Focused Feature Selection Using a Bayesian Approach

no code implementations15 Sep 2019 Orpaz Goldstein, Mohammad Kachuee, Kimmo Karkkainen, Majid Sarrafzadeh

In many real-world scenarios where data is high dimensional, test time acquisition of features is a non-trivial task due to costs associated with feature acquisition and evaluating feature value.

feature selection

TAPER: Time-Aware Patient EHR Representation

2 code implementations11 Aug 2019 Sajad Darabi, Mohammad Kachuee, Shayan Fazeli, Majid Sarrafzadeh

The data contained in these records are irregular and contain multiple modalities such as notes, and medical codes.

Language Modelling Representation Learning

Generative Imputation and Stochastic Prediction

2 code implementations22 May 2019 Mohammad Kachuee, Kimmo Karkkainen, Orpaz Goldstein, Sajad Darabi, Majid Sarrafzadeh

In order to make imputations, we train a simple and effective generator network to generate imputations that a discriminator network is tasked to distinguish.

Classification General Classification +2

Cost-Sensitive Diagnosis and Learning Leveraging Public Health Data

2 code implementations19 Feb 2019 Mohammad Kachuee, Kimmo Karkkainen, Orpaz Goldstein, Davina Zamanzadeh, Majid Sarrafzadeh

Furthermore, based on the suggested dataset, we provide a comparison of recent and state-of-the-art approaches to cost-sensitive feature acquisition and learning.

Unsupervised Prediction of Negative Health Events Ahead of Time

no code implementations31 Jan 2019 Anahita Hosseini, Majid Sarrafzadeh

The emergence of continuous health monitoring and the availability of an enormous amount of time series data has provided a great opportunity for the advancement of personal health tracking.

Anomaly Detection Clustering +3

Dynamic Feature Acquisition Using Denoising Autoencoders

1 code implementation3 Nov 2018 Mohammad Kachuee, Sajad Darabi, Babak Moatamed, Majid Sarrafzadeh

In real-world scenarios, different features have different acquisition costs at test-time which necessitates cost-aware methods to optimize the cost and performance trade-off.

Denoising Density Estimation +1

HeteroMed: Heterogeneous Information Network for Medical Diagnosis

no code implementations22 Apr 2018 Anahita Hosseini, Ting Chen, Wenjun Wu, Yizhou Sun, Majid Sarrafzadeh

To the best of our knowledge, this is the first study to use Heterogeneous Information Network for modeling clinical data and disease diagnosis.

Medical Diagnosis

Cannot find the paper you are looking for? You can Submit a new open access paper.