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
PyTorch implementation for our NeurIPS 2021 Spotlight paper "Long Short-Term Transformer for Online Action Detection".

Long Short-Term Transformer for Online Action Detection Introduction This is a PyTorch implementation for our NeurIPS 2021 Spotlight paper "Long Short

77 Dec 16, 2022
Leaderboard, taxonomy, and curated list of few-shot object detection papers.

Leaderboard, taxonomy, and curated list of few-shot object detection papers.

Gabriel Huang 70 Jan 07, 2023
A rule-based log analyzer & filter

Flog 一个根据规则集来处理文本日志的工具。 前言 在日常开发过程中,由于缺乏必要的日志规范,导致很多人乱打一通,一个日志文件夹解压缩后往往有几十万行。 日志泛滥会导致信息密度骤减,给排查问题带来了不小的麻烦。 以前都是用grep之类的工具先挑选出有用的,再逐条进行排查,费时费力。在忍无可忍之后决

上山打老虎 9 Jun 23, 2022
A clean and extensible PyTorch implementation of Masked Autoencoders Are Scalable Vision Learners

A clean and extensible PyTorch implementation of Masked Autoencoders Are Scalable Vision Learners A PyTorch re-implementation of Mask Autoencoder trai

Tianyu Hua 23 Dec 13, 2022
The lightweight PyTorch wrapper for high-performance AI research. Scale your models, not the boilerplate.

The lightweight PyTorch wrapper for high-performance AI research. Scale your models, not the boilerplate. Website • Key Features • How To Use • Docs •

Pytorch Lightning 21.1k Dec 29, 2022
This repository contains the source codes for the paper AtlasNet V2 - Learning Elementary Structures.

AtlasNet V2 - Learning Elementary Structures This work was build upon Thibault Groueix's AtlasNet and 3D-CODED projects. (you might want to have a loo

Théo Deprelle 123 Nov 11, 2022
For auto aligning, cropping, and scaling HR and LR images for training image based neural networks

ImgAlign For auto aligning, cropping, and scaling HR and LR images for training image based neural networks Usage Make sure OpenCV is installed, 'pip

15 Dec 04, 2022
Revisiting, benchmarking, and refining Heterogeneous Graph Neural Networks.

Heterogeneous Graph Benchmark Revisiting, benchmarking, and refining Heterogeneous Graph Neural Networks. Roadmap We organize our repo by task, and on

THUDM 176 Dec 17, 2022
An automated facial recognition based attendance system (desktop application)

Facial_Recognition_based_Attendance_System An automated facial recognition based attendance system (desktop application) Made using Python, Tkinter an

1 Jun 21, 2022
[ArXiv 2021] Data-Efficient Instance Generation from Instance Discrimination

InsGen - Data-Efficient Instance Generation from Instance Discrimination Data-Efficient Instance Generation from Instance Discrimination Ceyuan Yang,

GenForce: May Generative Force Be with You 93 Dec 25, 2022
Convert ONNX model graph to Keras model format.

Convert ONNX model graph to Keras model format.

Grigory Malivenko 175 Dec 28, 2022
[CVPR 2022] Thin-Plate Spline Motion Model for Image Animation.

[CVPR2022] Thin-Plate Spline Motion Model for Image Animation Source code of the CVPR'2022 paper "Thin-Plate Spline Motion Model for Image Animation"

yoyo-nb 1.4k Dec 30, 2022
Code to accompany our paper "Continual Learning Through Synaptic Intelligence" ICML 2017

Continual Learning Through Synaptic Intelligence This repository contains code to reproduce the key findings of our path integral approach to prevent

Ganguli Lab 82 Nov 03, 2022
StableSims is an open-source project aimed at simulating MakerDAO's Dai stablecoin system

StableSims is an open-source project aimed at simulating MakerDAO's Dai stablecoin system, initially used for researching optimal incentive parameters for Liquidations 2.0.

Blockchain at Berkeley 52 Nov 21, 2022
Faster Convex Lipschitz Regression

Faster Convex Lipschitz Regression This reepository provides a python implementation of our Faster Convex Lipschitz Regression algorithm with GPU and

Ali Siahkamari 0 Nov 19, 2021
An Efficient Implementation of Analytic Mesh Algorithm for 3D Iso-surface Extraction from Neural Networks

AnalyticMesh Analytic Marching is an exact meshing solution from neural networks. Compared to standard methods, it completely avoids geometric and top

Karbo 45 Dec 21, 2022
Neural Tangent Generalization Attacks (NTGA)

Neural Tangent Generalization Attacks (NTGA) ICML 2021 Video | Paper | Quickstart | Results | Unlearnable Datasets | Competitions | Citation Overview

Chia-Hung Yuan 34 Nov 25, 2022
Tandem Mass Spectrum Prediction with Graph Transformers

MassFormer This is the original implementation of MassFormer, a graph transformer for small molecule MS/MS prediction. Check out the preprint on arxiv

Röst Lab 13 Oct 27, 2022
Code for the ICME 2021 paper "Exploring Driving-Aware Salient Object Detection via Knowledge Transfer"

TSOD Code for the ICME 2021 paper "Exploring Driving-Aware Salient Object Detection via Knowledge Transfer" Usage For training, open train_test, run p

Jinming Su 2 Dec 23, 2021
3D cascade RCNN for object detection on point cloud

3D Cascade RCNN This is the implementation of 3D Cascade RCNN: High Quality Object Detection in Point Clouds. We designed a 3D object detection model

Qi Cai 22 Dec 02, 2022