Jeffrey Kaye, MDLayton Professor of Neurology & Biomedical EngineeringOregon Center for Aging & TechnologyNIA - Layton Aging & Alzheimer's Disease Centerkaye@ohsu.edu

A Vision for the Future of Aging & Technology

New Yorker, Oct. 1, 2007

Technology in Health Research and Practice

• Spectacular progress has been made in applying technology to the basic biology of disease creating an embarrassment of riches of potential treatments.

• In contrast, clinical assessment ‘technology’ has not appreciably changed since 1747.

“The Message” -• Pervasive computing technologies can radically

change the way we conduct clinical research and provide care.

• This will lead to major advances in detecting prodromal change, managing manifest disease and in transforming the effectiveness of clinical research.

A fundamental limitation of current assessment... detecting meaningful change

Cardinal features of change - slow decline punctuated with acute, unpredictable events - are challenging to assess with current tools and methods.

Self Report InaccuracyAre you sure?: Lapses in Self-Reported Activities Among Healthy Older Adults Reporting Online. Wild et al. Journal of Applied Gerontology (2015)

• 26% No Match Between Sensors & Report• 49% Partial Agreement• 25% Full Match

Area Firings Time

“What were you doing during the past 2 hours?” n=95; Mean age 84 yrs

Early detection

Why detecting meaningful change is hard ... And how to improve detection of change

Baseline 3 years 6 years

Mea

sure

Symptoms Reported

Functional range

Change

Is this the disease onset?

Changing the Clinical Paradigm

• New Observations & Discovery• Maximally Effective Clinical Research• Better Outcomes for Patients & Families

• Brief• Episodic• Clinic-based• Subjective• Obtrusive• Inconvenient

Pervasive Computing Wireless Technologies “Big Data Analytics”

• Real-time• Continuous• Home-based• Objective• Unobtrusive• Ambient

SecureInternet

ComputerActivity

Phone Activity

MedTracker

Pervasive Computing Platforms for Assessment: Community-wide ‘Life Lab’

Activity, Sleep, Mobility Time & Location

Doors Opening/Closing

Balance, Body CompositionHeart Rate, Temperature, C02

Kaye et al. Journals of Gerontology: Psychological Sciences, 2011

Device/Sensor “X”

MotionDetectors

Contact/DoorSwitches

PhoneSensors

Load Cells /Bed Sensors

LocationTracking

MedicationTracker

Computer

Raw Sensor Data

Sleep

Phone Use

Weight

MedicationEvents

DeparturesArrivals

GaitVelocity

ComputerInteractions

WeightScale

Mobility

LocationEstimation

Sleep Hygiene

Socialization

MedicationAdherence

Depression

PhysicalImpairments

Direct Assessment Inference

Memory

Attention

Information Level Fusion

Sensor Level Fusion

Functional Status

Change Detection

Data flow for inference engine assessing function

Kitchen Bath Bedroom Living room Computer Session

What can you see?Total Activity: Life Space & EventAnalysisSpiral plot: The plot is a 24 hour clock representing here 8 weeks of continuous data. At the top of the clock is midnight; at the bottom is noon. Each concentric blue circle outward represents 2 weeks of time. The colors of the dots represent firings of sensors by location

Norovirus Epidemic: All ill patients identified by decreased room transition events without self report

-34%-34%

-24%-24%

-40%-40%

Campbell, 2011

What can you see?

Healthy Diagnosed with Parkinson’s Disease

Treatment with Sinemet

SEPT-OCT 2012 SEPT-OCT 2013FEB-MAR 2011

What can you see?

June 2011 June 2012June 2010

CDR = 0; MMSE = 28 CDR = 0.5; MMSE = 27 CDR = 0.5; MMSE = 28

xx

Walks: From 2 to 7000 per year

Photo: NYT, 2009

Gait Mat vs Sensor Line

r = .99

Hayes, 2009; Hagler, 2010; Kaye, 2012

Differentiation of early MCI: Total Activity & Walking

Hayes et al. Alzheimer's & Dementia, 2008; 4(6): 395-405.

MCI

NL

Hayes et al. Alzheimers Dement, 2008

MCI cases 9Xmore likely in Slow Group

Trajectories of walking speed over time

Dodge, et al. Neurology, 2012

Activity patterns associated with mild cognitive impairment

Differentiation of early MCI: Night-time Behavior & Sleep

Hayes, et al. Alzheimer Dis Assoc Disord. 2014

Normal

NA-MCI

A-MCI

Medication Adherence over Time

EFFECT OF HOLIDAYS

Weekly adherence to twice-daily dosing using the MedTracker for 1285 days (3.5 years). Blue line (top): total adherence to 2 pills per day; red line (bottom): adherence to the required time regimen of one pill at 7am and one pill at 7pm.

ORCATECH MedTracker

Hayes et al., Proceedings : Engineering in Medicine and Biology Soc, 2006; Leen, et al., Technology and Aging, 2007 ; Hayes et al. .Journal of Aging Health, 2009; Hayes et al. Telemedicine Jounal and E-Health, 2009

Every Day Cognition: Medication adherence as a measure of cognitive function

• Adherence assessed continuously x 5 wks with MedTracker taking a

• Mean Age - 83 yrs• Based on ADAScog: Lower

Cognition Group vs Higher Cognition Group

Hayes et al., Proceedings : Engineering in Medicine and Biology Soc, 2006; Leen, et al., Technology and Aging, 2007 ; Hayes et al. .Journal of Aging Health, 2009; Hayes et al. Telemedicine Jounal and E-Health, 2009

0

10

20

30

40

50

60

70

80

90

100

Lower Cognition Higher Cognition

% A

dher

ent

Median time within 12.0 mins of goal

Median time within 53.4 mins of goal

Significantly Worse Adherence in Lower Cognition Group

Every Day Cognition: Computer use changes over time in MCI (without formal cognitive tests)

• At Baseline: Mean 1.5 hours on computer/per day

• Over time:– Less use days per

month – Less use time

when in session– More variable in

use pattern over time0 4 8 12 16 20 24 28 32

14

16

18

20

Months of Continuous Monitoring

Me

an

Da

ys

on

Co

mp

ute

r

Intact MCI

Kaye, et al. Alzheimers Dement. 2014; Silbert et al. submitted, 2015

Putting it all together: High Dimensional Data Fusion Model of Clinical Assessment

Context:Weather, CCI,

living in a retirement

community, etc.

Behavioral - Activity Data: Computer use,

time out of home, etc.

Weekly Self-Report:

Mood, Falls, ER visits, Visitors, etc…

Annual Clinical Assessment:

Cognition, physical function,

biomarkers, etc.

Demographics:Age, education, socioeconomic

status, etc.

Controls:Number of rooms in

home, etc.

Model CareTransition

Outcome

63,745,978 observations...

Austin et al. 2014 GSA

Predicting Care Transitions: Sensitivity Analysis

• Likelihood of a person transitioning within next six months – ROC AUC under curve= 0.974

20Austin et al. 2014 GSA

Home Assessment Technologies are also Treatment Technologies: RCT to Increase Social Interaction in MCI Using Home-based Technologies

• MCI or Normal randomized to video chat or control group

• 6 week of daily 30 min video chats• 89% of all possible sessions completed;

Exceptional adherence – no drop-out

Dodge et al. Alzheimer's & Dementia: Translational Research & Clinical Interventions, 2015

• Intervention group improved on executive/fluency measure.• MCI participants spoke 2985 words on average while intact spoke

2423 words during sessions. • Discriminated MCI from intact subjects better than the traditional

cognitive tests (Animal Fluency and Delayed List Recall).

Clinical Practice Implications: ‘Teledementia’- Direct to home visits and assessments ...

http://psych.nyu.edu/freemanlab/research.htm

Alzheimer’s Disease Cooperative Study Home Based Assessment Study (ORCATECH Kiosk System used in HBA Study)

Harnessing the power of pervasive computing systems: transform the conduct of clinical trials

The Bounty of Biotechnology

The Opportunity of Pervasive Computing

http://www.phrma.org/sites/default/files/Alzheimer%27s%202013.pdf

Transforming Clinical Trials with High Frequency, Objective, Continuous Data: “Big Data” for Each Subject

Dodge, 2014, AAIC

500 measured walking speeds per month...My slow walking speed ≠ Your slow walking speed

Conventional Method

Continuous Measures

LM Delayed Recall*

Computer Use**

Walking Speed**

SAMPLE SIZE TO SHOW50% EFFECT

688 10 94

SAMPLE SIZE TO SHOW 40% EFFECT

1076 16 148

SAMPLE SIZE TO SHOW 30% EFFECT

1912 26 262

SAMPLE SIZE TO SHOW 20% EFFECT

4300 58 588

MCI Prevention Trial – Sample Size Estimates

• More precise estimates of the trajectory of change; allows for intra-individual predictions.

• Reduces required sample size and/or time to identify meaningful change.

• Reduces exposure to harm (fewer needed/ fewer exposed)

• Provides the opportunity to substantially improve efficiency and inform go/no-go decisions of trials.

Acknowledgements

"The smallest act of kindness is worth more than the grandest intention."

- Oscar Wilde

25

Profound Thanks to My Amazing Colleagues and the Research Volunteers

Many Academic Centers - Collaborators

26

Funders

27

Companies

28

Thank You!

kaye@ohsu.edu www.orcatech.org

20061956