The final project for "Applying AI to Wearable Device Data" course from "AI for Healthcare" - Udacity.

Overview

Motion Compensated Pulse Rate Estimation

Overview

This project has 2 main parts.

  1. Develop a Pulse Rate Algorithm on the given training data. Then Test Your Algorithm and see that it has met the success criteria.
  2. Apply the Pulse Rate Algorithm on a Clinical Application and compute more clinically meaningful features and discover healthcare trends.

Part 1: Pulse Rate Algorithm

Introduction

A core feature that many users expect from their wearable devices is pulse rate estimation. Continuous pulse rate estimation can be informative for many aspects of a wearer's health. Pulse rate during exercise can be a measure of workout intensity and resting heart rate is sometimes used as an overall measure of cardiovascular fitness. In this project you will create a pulse rate estimation algorithm for a wrist-wearable device. Use the information in the Physiological Mechanics of Pulse Rate Estimation section below to inform the design of your algorithm. Make sure that your algorithm conforms to the given Algorithm Specifications in the following concept, Part 1: Overview & Instructions.

Background

Physiological Mechanics of Pulse Rate Estimation

Pulse rate is typically estimated by using the PPG sensor. When the ventricles contract, the capillaries in the wrist fill with blood. The (typically green) light emitted by the PPG sensor is absorbed by red blood cells in these capillaries and the photodetector will see the drop in reflected light. When the blood returns to the heart, fewer red blood cells in the wrist absorb the light and the photodetector sees an increase in reflected light. The period of this oscillating waveform is the pulse rate.

PPG Sensor on Blood Flow

However, the heart beating is not the only phenomenon that modulates the PPG signal. Blood in the wrist is fluid, and arm movement will cause the blood to move correspondingly. During exercise, like walking or running, we see another periodic signal in the PPG due to this arm motion. Our pulse rate estimator has to be careful not to confuse this periodic signal with the pulse rate.

We can use the accelerometer signal of our wearable device to help us keep track of which periodic signal is caused by motion. Because the accelerometer is only sensing arm motion, any periodic signal in the accelerometer is likely not due to the heart beating, and only due to the arm motion. If our pulse rate estimator is picking a frequency that's strong in the accelerometer, it may be making a mistake.

All estimators will have some amount of error. How much error is tolerable depends on the application. If we were using these pulse rate estimates to compute long term trends over months, then we may be more robust to higher error variance. However, if we wanted to give information back to the user about a specific workout or night of sleep, we would require a much lower error.

Algorithm Confidence and Availability

Many machine learning algorithms produce outputs that can be used to estimate their per-result error. For example, in logistic regression, you can use the predicted class probabilities to quantify trust in the classification. A classification where one class has a very high probability is probably more accurate than one where all classes have similar probabilities. Certainly, this method is not perfect and won't perfectly rank-order estimates based on error. But if accurate enough, it allows consumers of the algorithm more flexibility in how to use it. We call this estimation of the algorithm's error the confidence.

In pulse rate estimation, having a confidence value can be useful if a user wants just a handful of high-quality pulse rate estimate per night. They can use the confidence algorithm to select the 20 most confident estimates at night and ignore the rest of the outputs. Confidence estimates can also be used to set the point on the error curve that we want to operate at by sacrificing the number of estimates that are considered valid. There is a trade-off between availability and error. For example, if we want to operate at 10% availability, we look at our training dataset to determine the confidence threshold for which 10% of the estimates pass. Then if only if an estimate's confidence value is above that threshold, do we consider it valid. See the error vs. availability curve below.

This plot is created by computing the mean absolute error at all -- or at least 100 of -- the confidence thresholds in the dataset.

Building a confidence algorithm for pulse rate estimation is a little tricker than logistic regression because intuitively, there isn't some transformation of the algorithm output that can make a good confidence score. However, by understanding our algorithm behavior, we can come up with some general ideas that might create a good confidence algorithm. For example, if our algorithm is picking a strong frequency component that's not present in the accelerometer, we can be relatively confident in the estimate. Turn this idea into an algorithm by quantifying "strong frequency component".

Part 2: Clinical Application

Now that you have built your pulse rate algorithm and tested your algorithm to know it works, we can use it to compute more clinically meaningful features and discover healthcare trends.

Specifically, you will use 24 hours of heart rate data from 1500 samples to try to validate the well-known trend that average resting heart rate increases up until middle age and then decreases into old age. We'll also see if resting heart rates are higher for women than men. See the trend illustrated in this image:

Follow the steps in the notebook to reproduce this result!

Dataset (CAST)

The data from this project comes from the Cardiac Arrhythmia Suppression Trial (CAST), which was sponsored by the National Heart, Lung, and Blood Institute (NHLBI). CAST collected 24 hours of heart rate data from ECGs from people who have had a myocardial infarction (MI) within the past two years.[1] This data has been smoothed and resampled to more closely resemble PPG-derived pulse rate data from a wrist wearable.[2]

  1. CAST RR Interval Sub-Study Database Citation - Stein PK, Domitrovich PP, Kleiger RE, Schechtman KB, Rottman JN. Clinical and demographic determinants of heart rate variability in patients post-myocardial infarction: insights from the Cardiac Arrhythmia Suppression Trial (CAST). Clin Cardiol 23(3):187-94; 2000 (Mar)
  2. Physionet Citation - Goldberger AL, Amaral LAN, Glass L, Hausdorff JM, Ivanov PCh, Mark RG, Mietus JE, Moody GB, Peng C-K, Stanley HE. PhysioBank, PhysioToolkit, and PhysioNet: Components of a New Research Resource for Complex Physiologic Signals (2003). Circulation. 101(23):e215-e220.
Owner
Omar Laham
Bioinformatician and Healthcare AI Engineer
Omar Laham
TransFGU: A Top-down Approach to Fine-Grained Unsupervised Semantic Segmentation

TransFGU: A Top-down Approach to Fine-Grained Unsupervised Semantic Segmentation Zhaoyun Yin, Pichao Wang, Fan Wang, Xianzhe Xu, Hanling Zhang, Hao Li

DamoCV 25 Dec 16, 2022
A Data Annotation Tool for Semantic Segmentation, Object Detection and Lane Line Detection.(In Development Stage)

Data-Annotation-Tool How to Run this Tool? To run this software, follow the steps: git clone https://github.com/Autonomous-Car-Project/Data-Annotation

TiVRA AI 13 Aug 18, 2022
Learning Chinese Character style with conditional GAN

zi2zi: Master Chinese Calligraphy with Conditional Adversarial Networks Introduction Learning eastern asian language typefaces with GAN. zi2zi(字到字, me

Yuchen Tian 2.2k Jan 02, 2023
Arbitrary Distribution Modeling with Censorship in Real Time 59 2 60 3 Bidding Advertising for KDD'21

Arbitrary_Distribution_Modeling This repo implements the Neighborhood Likelihood Loss (NLL) and Arbitrary Distribution Modeling (ADM, with Interacting

7 Jan 03, 2023
Weakly Supervised 3D Object Detection from Point Cloud with Only Image Level Annotation

SCCKTIM Weakly Supervised 3D Object Detection from Point Cloud with Only Image-Level Annotation Our code will be available soon. The class knowledge t

1 Nov 12, 2021
The implementation for paper Joint t-SNE for Comparable Projections of Multiple High-Dimensional Datasets.

Joint t-sne This is the implementation for paper Joint t-SNE for Comparable Projections of Multiple High-Dimensional Datasets. abstract: We present Jo

IDEAS Lab 7 Dec 18, 2022
Implementation of PyTorch-based multi-task pre-trained models

mtdp Library containing implementation related to the research paper "Multi-task pre-training of deep neural networks for digital pathology" (Mormont

Romain Mormont 27 Oct 14, 2022
Home repository for the Regularized Greedy Forest (RGF) library. It includes original implementation from the paper and multithreaded one written in C++, along with various language-specific wrappers.

Regularized Greedy Forest Regularized Greedy Forest (RGF) is a tree ensemble machine learning method described in this paper. RGF can deliver better r

RGF-team 364 Dec 28, 2022
Learning infinite-resolution image processing with GAN and RL from unpaired image datasets, using a differentiable photo editing model.

Exposure: A White-Box Photo Post-Processing Framework ACM Transactions on Graphics (presented at SIGGRAPH 2018) Yuanming Hu1,2, Hao He1,2, Chenxi Xu1,

Yuanming Hu 719 Dec 29, 2022
Re-TACRED: Addressing Shortcomings of the TACRED Dataset

Re-TACRED Re-TACRED: Addressing Shortcomings of the TACRED Dataset

George Stoica 40 Dec 10, 2022
This is the source code for the experiments related to the paper Unsupervised Audio Source Separation Using Differentiable Parametric Source Models

Unsupervised Audio Source Separation Using Differentiable Parametric Source Models This is the source code for the experiments related to the paper Un

30 Oct 19, 2022
This is a Pytorch implementation of paper: DropEdge: Towards Deep Graph Convolutional Networks on Node Classification

DropEdge: Towards Deep Graph Convolutional Networks on Node Classification This is a Pytorch implementation of paper: DropEdge: Towards Deep Graph Con

401 Dec 16, 2022
Robustness via Cross-Domain Ensembles

Robustness via Cross-Domain Ensembles [ICCV 2021, Oral] This repository contains tools for training and evaluating: Pretrained models Demo code Traini

Visual Intelligence & Learning Lab, Swiss Federal Institute of Technology (EPFL) 27 Dec 23, 2022
A repository built on the Flow software package to explore cyber-security attacks on intelligent transportation systems.

A repository built on the Flow software package to explore cyber-security attacks on intelligent transportation systems.

George Gunter 4 Nov 14, 2022
Code for EMNLP 2021 paper Contrastive Out-of-Distribution Detection for Pretrained Transformers.

Contra-OOD Code for EMNLP 2021 paper Contrastive Out-of-Distribution Detection for Pretrained Transformers. Requirements PyTorch Transformers datasets

Wenxuan Zhou 27 Oct 28, 2022
You Only Sample (Almost) Once: Linear Cost Self-Attention Via Bernoulli Sampling

You Only Sample (Almost) Once: Linear Cost Self-Attention Via Bernoulli Sampling Transformer-based models are widely used in natural language processi

Zhanpeng Zeng 12 Jan 01, 2023
GeoMol: Torsional Geometric Generation of Molecular 3D Conformer Ensembles

GeoMol: Torsional Geometric Generation of Molecular 3D Conformer Ensembles This repository contains a method to generate 3D conformer ensembles direct

127 Dec 20, 2022
Code for ICCV 2021 paper: ARAPReg: An As-Rigid-As Possible Regularization Loss for Learning Deformable Shape Generators..

ARAPReg Code for ICCV 2021 paper: ARAPReg: An As-Rigid-As Possible Regularization Loss for Learning Deformable Shape Generators.. Installation The cod

Bo Sun 132 Nov 28, 2022
ML-Decoder: Scalable and Versatile Classification Head

ML-Decoder: Scalable and Versatile Classification Head Paper Official PyTorch Implementation Tal Ridnik, Gilad Sharir, Avi Ben-Cohen, Emanuel Ben-Baru

189 Jan 04, 2023