Statistical Methods for Wearable Technology in CNS Trials Andrew - - PowerPoint PPT Presentation

▶
statistical methods for wearable technology in cns trials
SMART_READER_LITE
LIVE PREVIEW

Statistical Methods for Wearable Technology in CNS Trials Andrew - - PowerPoint PPT Presentation

May 17, 2023 357 likes •597 views

Statistical Methods for Wearable Technology in CNS Trials Andrew Potter, PhD Division of Biometrics 1, OB/OTS/CDER, FDA ISCTM 2018 Autumn Conference Oct. 15, 2018 Marina del Rey, CA www.fda.gov Disclaimer This presentation reflects the

slide-1
SLIDE 1

Statistical Methods for Wearable Technology in CNS Trials

Andrew Potter, PhD Division of Biometrics 1, OB/OTS/CDER, FDA ISCTM 2018 Autumn Conference – Oct. 15, 2018 Marina del Rey, CA

www.fda.gov

slide-2
SLIDE 2

2

Disclaimer

This presentation reflects the views of the author and should not be construed to represent FDA’s views or policies.

www.fda.gov

slide-3
SLIDE 3

3

Outline

  • Data
  • Statistical Methods

– Signal Processing – Feature Selection – Modeling of treatment effect evolution over time

  • Simulated case study in sleep medicine

www.fda.gov

slide-4
SLIDE 4

4

Movement Data from Acceleration Sensors

Gyllensten, IC, Physical Activity Recognition in Daily Life using a Triaxial Accelerometer, Master’s Thesis, 2010. 8 min 0 min

slide-5
SLIDE 5

5

Converting Acceleration Sensor Data to Health Outcomes

  • Dense information on a person’s movement while the device is

recording

– At least 100 measurements per day – Days to weeks of data

  • What are the important features of the signal?

– How does a feature relate to a disease state? – How do features change over time? – How to compare between people and groups? – How to define a drug effect?

  • How to identify features?

– Have subject tag events in real time on the device? – Can machine learning automate this task?

slide-6
SLIDE 6

6

An Important Feature: Circadian Variation in Sensor Data

  • Blood flow data from a ventricular assist device recorded every 15 min.
  • Circadian patterns present in multiple types of sensor data
slide-7
SLIDE 7

7

Total Sleep Time Derived from Acceleration Sensor

High device use Low device use Calendar Day

slide-8
SLIDE 8

8

Weekday to Weekend Variability In Total Sleep Time

Weekday mornings Weekend mornings

slide-9
SLIDE 9

9

Extracting Features – Fourier Transform

  • Focuses on periodic features in a

signal

– Represents the strength of a signal

  • ver a range of frequencies

– Signals with circadian variation have a peak at 1 cycle/day – Spectral representation of EEG

Circadian Cycle Feature

slide-10
SLIDE 10

10

Extracting Features – Smoothing Signal in Time

Source: Wang et al. Journal of Circadian Rhythms 2011, 9:11 http://www.jcircadianrhythms.com/content/9/1/11

slide-11
SLIDE 11

11

Feature Selection - LASSO

  • LASSO – least absolute shrinkage and selection operator
  • Extension of regression

– Automatically selects covariates – Subset of all covariates most predictive of outcome – Shrinks covariate coefficients towards zero - regularization

  • See ‘The Elements of Statistical Learning’ by Hastie, Tibshirani,

and Friedman for more details

slide-12
SLIDE 12

12

Feature Selection – Neural Networks

  • Automatic techniques that selects

a combination of features associated with a class membership

– Creates features from the data – Applications - Digital Phenotypes, detection of cancer in radiology images, classification of sleep states in polysomnography

  • Automated classification of PSG

and sleep events

Source: Nielsen, Neural Networks and Deep Learning, http://neuralnetworksanddeeplearning.com/chap6.html

slide-13
SLIDE 13

13

Feature Selection – Neural Networks

  • Multiple models using different feature of the

PSG

– Examples:

  • Supratak et al, DeepSleepNet: A Model for Automatic

Sleep Stage Scoring Based on Raw Single-Channel EEG, IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2017, 25 (11), pp. 1998-2008 https://ieeexplore.ieee.org/document/7961240/

  • Chambon et al, A Deep Learning Architecture for

Temporal Sleep Stage Classification Using Multivariate and Multimodal Time Series, IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2018, 26 (4), pp. 758-769 https://ieeexplore.ieee.org/document/8307462/

  • Olsen et al, Automatic, electrocardiographic-based

detection of autonomic arousals and their association with cortical arousals, leg movements, and respiratory events in sleep, Sleep, Volume 41, Issue 3, 1 March 2018, zsy006, https://doi.org/10.1093/sleep/zsy006

Source: Chambon et al. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2018, 26 (4), pp. 758-769 https://ieeexplore.ieee.org/document/8307462/

slide-14
SLIDE 14

14

Modeling Features – Functional Linear Models

  • Method for analyzing curves
  • Extends regression to curves
  • Multiple cases:

– Cross-sectional observation of a single curve per patient on a single

  • utcome measurement

– Longitudinal observations of the same curve on a single outcome measurement within a patient – Cross-sectional and longitudinal of multiple curves on the same patient

Source: Wang et al. Journal of Circadian Rhythms 2011, 9:11 http://www.jcircadianrhythms.com/content/9/1/11

AHI – Sleep Apnea Severity

slide-15
SLIDE 15

15

Case Study - Sleep

  • Wearable sensors introduce two statistical challenges
  • Analysis of the within day data recorded densely
  • Analysis of the longitudinal evolution of the daily sensor
  • Illustrate an approach to analyzing longitudinal evolution using total

sleep time (TST) as a summary measure of daily sensor data

  • Compare changes in TST between a new sleep medication to placebo over

four weeks

  • Focus on modeling the linear trend in TST in both groups
  • Use all observed data
  • Calculation of TST at specific time points conducted after statistical modeling
  • Framework extends to multiple sleep parameters and functional

models

slide-16
SLIDE 16

16

Case Study - Sleep

  • Simulated data:
  • 300 patients
  • 30 minute improvement in TST by day 15
  • Similar change in TST to several NDAs submitted to FDA
  • Measure treatment effect by:
  • Difference in TST at four weeks
  • Average TST trajectory in each group – focus on the linear trend
  • Use two statistical models
  • Linear mixed model with random slopes – strong assumption on covariance

between days

  • Generalized estimating equation (GEE) model – robust to misspecification of

covariance between days

slide-17
SLIDE 17

17

Simulated Clinical Trial – The Data

Example Subjects Subject Specific Change from Baseline in TST Triangles – Weekday Circles - Weekend

slide-18
SLIDE 18

18

Population Average Total Sleep Time Trajectories

slide-19
SLIDE 19

19

The Linear Mixed Model Results

Average TST Trajectories Estimate 95% Confidence Interval Intercept 312.937 302.183 323.690 Day 1.339 0.844 1.834 Treatment 7.333

  • 7.741

22.406 Tue

  • 1.522
  • 4.687

1.643 Wed 0.000

  • 3.175

3.174 Thurs

  • 0.267
  • 3.444

2.911 Fri

  • 0.740
  • 3.908

2.428 Sat 89.546 86.422 92.671 Sun 90.848 87.727 93.969 Treatment by Day 0.782 0.076 1.488 Week 4 Placebo Subtracted Treatment Effect 29.229 5.933 52.524

slide-20
SLIDE 20

20

The GEE Results

Average TST Trajectories Estimate 95% Confidence Interval Intercept 314.989 304.139 325.840 Day 1.189 0.629 1.748 Treatment 1.922

  • 12.964

16.807 Tue

  • 0.605
  • 3.576

2.366 Wed 0.397

  • 2.657

3.451 Thurs

  • 0.125
  • 3.124

2.873 Fri

  • 0.909
  • 3.835

2.017 Sat 89.420 86.623 92.217 Sun 90.874 88.044 93.704 Treatment by Day 0.781 0.009 1.552 Week 4 Placebo Subtracted Treatment Effect 23.776 0.519 47.030

slide-21
SLIDE 21

21

Final Thoughts

  • Rich new data source
  • Contains new information

about neurology and psychiatry diseases

  • Existing statistical method

provide starting point

  • Explore new methods to

show population and individual drug effects

slide-22
SLIDE 22