More details on our work here: https://www.researchgate.net/project/Bloomlife-improving-prenatal-health-through-longitudinal-physiological-monitoring-at-large-scale
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
Talk at the International Conference on Biomedical and Health Informatics (BHI 2017)
1. Variable-length accelerometer features and
electromyography to improve accuracy of fetal kicks
detection during pregnancy using a single wearable
device
BHI, 2017 bloomlife.com
Marco Altini, Elisa Rossetti, Michiel Rooijakkers, Julien Penders, Dorien Lanssens, Lars Grieten and
Wilfried Gyselaers
2. 2|
FETAL MOVEMENT
BHI, 2017 bloomlife.com
Monitoring fetal movement during pregnancy is the most
practical and widespread method to assess fetal
wellbeing, one of the most important and complex tasks of
modern obstetrics.!
!
As birth outcomes are strongly linked to the development of
fetal conditions during pregnancy, several techniques have
been developed to monitor fetal movement up to date!
3. 3|
CURRENT CLINICAL PRACTICE
BHI, 2017 bloomlife.com
Ultrasound: relies on high frequency sound!
waves being used to generate an image of the fetus and!
can be used only for a limited amount of time due to!
safety concerns. Require hospital stays or trained personnel.!
!
Continuous cardiotocography: require cumbersome
infrastructure and hospital visits, also involving trained
personnel to set up the device and process the produced
information.!
4. 4|
CURRENT CLINICAL PRACTICE
BHI, 2017 bloomlife.com
Ultrasound: relies on high frequency sound!
waves being used to generate an image of the fetus and!
can be used only for a limited amount of time due to!
safety concerns. Require hospital stays or trained personnel.!
!
Continuous cardiotocography: require cumbersome
infrastructure and hospital visits, also involving trained
personnel to set up the device and process the produced
information.!
-> Only sporadic checks in the hospital environment
5. 5|
NEW PASSIVE SOLUTIONS
BHI, 2017 bloomlife.com
Accelerometers: Most studies to date involved one single
accelerometer placed on the abdomen and reported rather
low sensitivity and specificity.!
!
Other researchers added a reference accelerometer
with the rationale that by monitoring maternal movement!
artifacts using an accelerometer placed outside of the
abdominal area, fetal movement should be separable from!
maternal movement and therefore detected more accurately. !
6. 6|
NEW PASSIVE SOLUTIONS: REFERENCE
ACCELEROMETER
BHI, 2017 bloomlife.com
0
100
0 5 10 15
Timestamp (minutes)
Motioninte
0
50
100
150
200
0 5 10 15
Timestamp (minutes)
Motionintensitysensor3
0
10
20
30
40
50
0 5 10 15
Timestamp (minutes)
Motionintensitysensor6
Reference accelerometer on the back
Fetal movements do not
appear on the reference
accelerometer, while
maternal movements
typically do!
8. 8|
SINGLE SENSOR
BHI, 2017 bloomlife.com
Performance: consistently lower with respect to multiple
sensors and reference accelerometers outside of the
abdomen area. Higher false positives (harder to
discriminate between maternal movements / artifacts and
fetal movements)!
!
!
How do we reduce false positives?
9. 9|
VARIABLE-LENGTH ACCELEROMETER
FEATURES AND PHYSIOLOGICAL DATA
BHI, 2017 bloomlife.com
The proposed techniques aim at reducing false positives by!
providing more contextual information related to maternal!
movement while still using a single wearable device to cope!
with the absence of a reference accelerometer or a more!
obtrusive system.!
!
To account for different dynamics in maternal and fetal
movement, we computed features over two time windows of 0.5
and 4 seconds. The rationale is that short fetal movements
should be averaged out over longer time windows but captured
over short ones, while maternal movements should appear over
windows of both durations.!
10. 0.0
0.1
0.2
0.3
0 5 10 15
Timestamp (minutes)
Motionintensity
label
nothing
kick
Single sensor, short time window
0.0
0.1
0.2
0 5 10 15
Timestamp (minutes)
Motionintensity
Single sensor, long time window
10|
VARIABLE-LENGTH ACCELEROMETER
FEATURES AND PHYSIOLOGICAL DATA
BHI, 2017 bloomlife.com
11. 0.0
0.1
0.2
0.3
0 5 10 15
Timestamp (minutes)
Motionintensity
label
nothing
kick
Single sensor, short time window
0.0
0.1
0.2
0 5 10 15
Timestamp (minutes)
Motionintensity
Single sensor, long time window
11|
VARIABLE-LENGTH ACCELEROMETER
FEATURES AND PHYSIOLOGICAL DATA
BHI, 2017 bloomlife.com
Maternal movements
appear on both traces!
12. 0.0
0.1
0.2
0.3
0 5 10 15
Timestamp (minutes)
Motionintensity
label
nothing
kick
Single sensor, short time window
0.0
0.1
0.2
0 5 10 15
Timestamp (minutes)
Motionintensity
Single sensor, long time window
12|
VARIABLE-LENGTH ACCELEROMETER
FEATURES AND PHYSIOLOGICAL DATA
BHI, 2017 bloomlife.com
Fetal movements
appear on the short
window trace only!
13. 0.0
0.1
0 5 10 15
Timestamp (minutes)
Motionint
0.0
0.1
0.2
0 5 10 15
Timestamp (minutes)
Motionintensity
Single sensor, long time window
0
100
200
300
0 5 10 15
Timestamp (minutes)
EHGintensity
Single sensor, EHG data
0.0
0.1
0.2
0.3
0 5 10 15
Timestamp (minutes)
Motionintensity
label
nothing
kick
Single sensor, short time window
0.0
0.1
0.2
0 5 10 15
Timestamp (minutes)
Motionintensity
Single sensor, long time window
13|
VARIABLE-LENGTH ACCELEROMETER
FEATURES AND PHYSIOLOGICAL DATA
BHI, 2017 bloomlife.com
Maternal movements
are more likely to trigger
EMG activity!
14. 14|
STUDY DESIGN
BHI, 2017 bloomlife.com
Twenty-two recordings of about 60 minutes duration were
collected from 22 pregnant women at different gestational ages
during pregnancy, all from week 30 onwards. !
!
Fetal movements ranged between 0 for inactive babies to 315
for hiccups cases. !
!
Measurements were performed using two devices. A research
version of the Bloomlife wearable device, configured to acquire
two channels EMG at 4096 Hz and triaxial accelerometer data at
128 Hz and the TMSi system including 6 accelerometers, five
placed on the abdomen and one on the back.!
15. 15|
FEATURES, CLASSIFIER AND CLASS-IMBALANCE
BHI, 2017 bloomlife.com
Features: low-complexity time domain features (mean, standard!
deviation, interquartile range, correlation between axis, sum,!
min, max and magnitude).!
!
Classification: Random forests. We set the number of features to
select at each iteration to the square root of the total number of
features.!
!
Class imbalance: small number of kicks with respect to the total
available data. The optimal ratio between reference class (kicks)
and majority class (non-kicks) was determined by cross-
validating and optimizing for F-score. Our optimal balance
included all data from the minority class and one fifth of the
majority class data !
16. 16|
COMPARISONS AND CROSS-VALIDATION
BHI, 2017 bloomlife.com
We compared four feature sets associated to the two systems
used in this study in order to highlight the impact of the novel
methods proposed to improve accuracy of a single wearable
device:!
1. TMSi (6 accelerometer system) and variable-length features.!
2. Bloomlife (single wearable sensor) and features computed
over a short time window only Bloomlife and features
computed over both short and long time windows. !
3. Bloomlife and features computed over both short and long
time windows plus EMG features. !
All models were derived and validated using leave one!
participant out cross-validation!
19. 19|
RESULTS: SENSITIVITY
BHI, 2017 bloomlife.com
0
25
50
75
Multi SL Single S Single SLSingle SLE
Model
Percentage(%)
Sensitivity
Sensitivity does not change
much by introducing variable-
length and EMG features as the
aim of these features is to
reduce false positives. !
20. 20|
RESULTS: SENSITIVITY
BHI, 2017 bloomlife.com
Sensitivity does not change
much by introducing variable-
length and EMG features as the
aim of these features is to
reduce false positives. !
0
25
50
75
Multi SL Single S Single SLSingle SLE
Model
Percentage(%)
Sensitivity
21. 21|
RESULTS: POSITIVE PREDICTIVE VALUE
BHI, 2017 bloomlife.com
0
25
50
75
Multi SL Single S Single SLSingle SLE
Model
Percentage(%)
Sensitivity
0
25
50
75
Multi SL Single S Single SLSingle SLE
Model
Percentage(%)
PPV
22. 22|
RESULTS: POSITIVE PREDICTIVE VALUE
BHI, 2017 bloomlife.com
On the other hand, PPV was 0.75 for
the 6 sensors system and increased
between 0.65 to 0.75 when
including variable-length and EMG
features
0
25
50
75
Multi SL Single S Single SLSingle SLE
Model
Percentage(%)
Sensitivity
0
25
50
75
Multi SL Single S Single SLSingle SLE
Model
Percentage(%)
PPV
23. 23|
RESULTS: POSITIVE PREDICTIVE VALUE
BHI, 2017 bloomlife.com
On the other hand, PPV was 0.75 for
the 6 sensors system and increased
between 0.65 to 0.75 when
including variable-length and EMG
features
0
25
50
75
Multi SL Single S Single SLSingle SLE
Model
Percentage(%)
Sensitivity
0
25
50
75
Multi SL Single S Single SLSingle SLE
Model
Percentage(%)
PPV
24. 24|
RESULTS: POSITIVE PREDICTIVE VALUE
BHI, 2017 bloomlife.com
On the other hand, PPV was 0.75 for
the 6 sensors system and increased
between 0.65 to 0.75 when
including variable-length and EMG
features
0
25
50
75
Multi SL Single S Single SLSingle SLE
Model
Percentage(%)
Sensitivity
0
25
50
75
Multi SL Single S Single SLSingle SLE
Model
Percentage(%)
PPV
25. 25|
RESULTS: TOTAL NUMBER OF KICKS PER
RECORDING
BHI, 2017 bloomlife.com
●
●●●●●● ●
●
●
●
●●
●●
●
●
●
●
●
●
0
100
0 100 200 300
Detected kicks
Actual
●
●●●●●●●
●
●
●
●
●●
●●
●
●
●
●
●
●
0
100
200
300
0 100 200 300
Detected kicks
Actualkicks
Actual vs Detected kicks, Single S
●
●●●●●●●
●
●
●
●●
●
●
●
●
●
●
●
●
0
100
0 100 200 300
Detected kicks
Actual
●
●● ●●●●●
●
●
●
●
●●
●
●
●
●
●
●
●
●
0
100
200
300
0 100 200 300
Detected kicks
Actualkicks
Actual vs Detected kicks, Single SLE
26. 26|
RESULTS: TOTAL NUMBER OF KICKS PER
RECORDING
BHI, 2017 bloomlife.com
●
●●●●●● ●
●
●
●
●●
●●
●
●
●
●
●
●
0
100
0 100 200 300
Detected kicks
Actual
●
●●●●●●●
●
●
●
●
●●
●●
●
●
●
●
●
●
0
100
200
300
0 100 200 300
Detected kicks
Actualkicks
Actual vs Detected kicks, Single S
●
●●●●●●●
●
●
●
●●
●
●
●
●
●
●
●
●
0
100
0 100 200 300
Detected kicks
Actual
●
●● ●●●●●
●
●
●
●
●●
●
●
●
●
●
●
●
●
0
100
200
300
0 100 200 300
Detected kicks
Actualkicks
Actual vs Detected kicks, Single SLE
27. 27|
RESULTS: TOTAL NUMBER OF KICKS PER
RECORDING
BHI, 2017 bloomlife.com
●
●●●●●● ●
●
●
●
●●
●●
●
●
●
●
●
●
0
100
0 100 200 300
Detected kicks
Actual
●
●●●●●●●
●
●
●
●
●●
●●
●
●
●
●
●
●
0
100
200
300
0 100 200 300
Detected kicks
Actualkicks
Actual vs Detected kicks, Single S
●
●●●●●●●
●
●
●
●●
●
●
●
●
●
●
●
●
0
100
0 100 200 300
Detected kicks
Actual
●
●● ●●●●●
●
●
●
●
●●
●
●
●
●
●
●
●
●
0
100
200
300
0 100 200 300
Detected kicks
Actualkicks
Actual vs Detected kicks, Single SLE
28. 28|
RESULTS: TOTAL NUMBER OF KICKS PER
RECORDING
BHI, 2017 bloomlife.com
Less overdetections at the recording level as well
●
●●●●●● ●
●
●
●
●●
●●
●
●
●
●
●
●
0
100
0 100 200 300
Detected kicks
Actual
●
●●●●●●●
●
●
●
●
●●
●●
●
●
●
●
●
●
0
100
200
300
0 100 200 300
Detected kicks
Actualkicks
Actual vs Detected kicks, Single S
●
●●●●●●●
●
●
●
●●
●
●
●
●
●
●
●
●
0
100
0 100 200 300
Detected kicks
Actual
●
●● ●●●●●
●
●
●
●
●●
●
●
●
●
●
●
●
●
0
100
200
300
0 100 200 300
Detected kicks
Actualkicks
Actual vs Detected kicks, Single SLE
29. 29|
CONCLUSIONS
BHI, 2017 bloomlife.com
We proposed a method to improve the accuracy of fetal kicks
detection during pregnancy using a single wearable device
placed on the abdomen. !
!
Including variable-length accelerometer features, short fetal
movement is averaged out over longer time windows but
captured over short ones, while maternal movements of greater
intensity appear over windows of both durations. As a result, a
single wearable device can be used to better discriminate fetal
and maternal movement without the need for a reference
accelerometer (11% improvement in PPV).!