SlideShare a Scribd company logo
1 of 31
Download to read offline
IEEE 35th International Symposium on Computer
Based Medical Systems (CBMS 2022)
Policy-Based Diabetes Detection using Formal Runtime
Verification Monitors
Abhinandan Panda 1
, Srinivas Pinisetty1
, Partha Roop 2
1
Indian Institute of Technology, Bhubaneswar, India
2
University of Auckland, Auckland, New Zealand
December 5, 2022
Outline
1 Introduction
2 ECG
3 Proposed monitoring system
4 Policies Mining
5 RV Monitor
6 Experimental results & Comparison
7 Conclusion & Future Works
8 References
Introduction
ECG
Proposed monitoring
system
Policies Mining
RV Monitor
Experimental results
& Comparison
Conclusion & Future
Works
References
References
Introduction: Diabetes
• A metabolic disorder
• Lack of control or balance in blood glucose (BG)
• Type 1 diabetes (deficiency of insulin) / Type 2 diabetes (excess of
insulin)
• Hyperglycemia (very high blood glucose levels) / hypoglycemia (very
low blood glucose levels) events (normal blood glucose level 140
mg/dL).
CBMS 2022 Abhinandan Panda December 5, 2022 1/28
Introduction
ECG
Proposed monitoring
system
Policies Mining
RV Monitor
Experimental results
& Comparison
Conclusion & Future
Works
References
References
Health Complications in Diabetes
Figure: Health complications in diabetes [1]
CBMS 2022 Abhinandan Panda December 5, 2022 2/28
Introduction
ECG
Proposed monitoring
system
Policies Mining
RV Monitor
Experimental results
& Comparison
Conclusion & Future
Works
References
References
Global Diabetic Growth
Figure: Global diabetic growth [1]
CBMS 2022 Abhinandan Panda December 5, 2022 3/28
Introduction
ECG
Proposed monitoring
system
Policies Mining
RV Monitor
Experimental results
& Comparison
Conclusion & Future
Works
References
References
Invasive Blood Glucose Monitoring
Figure: Invasive blood glucose monitoring [1]
CBMS 2022 Abhinandan Panda December 5, 2022 4/28
Introduction
ECG
Proposed monitoring
system
Policies Mining
RV Monitor
Experimental results
& Comparison
Conclusion & Future
Works
References
References
Need of non-invasive continuous monitoring of diabetes
• Severe health complications [2].
• Around 9.3% of people are affected by diabetes globally [3] .
• Tedious initial screening process
• About 45.8% of diabetes cases with cardiac complications are untreated
[4].
• Continuous diabetes monitoring technique should be adopted [5]
CBMS 2022 Abhinandan Panda December 5, 2022 5/28
Introduction
ECG
Proposed monitoring
system
Policies Mining
RV Monitor
Experimental results
& Comparison
Conclusion & Future
Works
References
References
Non-invasive approach: monitoring physiological signal ECG
Time
Amplitude
S
R
Q
P
Q
R
S
QRS interval
P
PR interval
P-wave
interval
QT interval
RT interval
TpTe interval
Te
RR interval
Tp
Tp
Figure: A typical ECG Signal
CBMS 2022 Abhinandan Panda December 5, 2022 6/28
Introduction
ECG
Proposed monitoring
system
Policies Mining
RV Monitor
Experimental results
& Comparison
Conclusion & Future
Works
References
References
ECG in diabetes
Figure: ECG in diabetes [6]
CBMS 2022 Abhinandan Panda December 5, 2022 7/28
Introduction
ECG
Proposed monitoring
system
Policies Mining
RV Monitor
Experimental results
& Comparison
Conclusion & Future
Works
References
References
ECG and Diabetes: Analysis
hypoglycemia (low blood glucose level) results in prolongation of QT
interval [christensen2010].
Hypoglycemia (low blood glucose level) associated with increased heart
rate (HR) [heger1996].
Hyperglycemia (high blood glucose level) related with reduced heart rate
variability (HRV) [singh2000].
Corrected QT dispersion and PR interval have a significant change in
hyperglycemia condition [marfella2000].
According to [nguyen2012], ECG parameters such as corrected QT
interval, PR interval, corrected RT interval, corrected TpTe interval and
heart rate (HR) can be used for identification of hypoglycemia and
hyperglycemia detection.
CBMS 2022 Abhinandan Panda December 5, 2022 8/28
Introduction
ECG
Proposed monitoring
system
Policies Mining
RV Monitor
Experimental results
& Comparison
Conclusion & Future
Works
References
References
Related Works
Authors Methods Accuracy
Acharya et al. [7] Nonlinear 86.0
Jian et al. [8] Higher order spectrum 79.93
Acharya et al. [9] Discrete wavelet transform 92.02
Pachori et al. [10] Empirical mode decomposition 95.63
Swapna et al. [11] Deep learning (CNN-LSTM) 95.1
CBMS 2022 Abhinandan Panda December 5, 2022 9/28
Introduction
ECG
Proposed monitoring
system
Policies Mining
RV Monitor
Experimental results
& Comparison
Conclusion & Future
Works
References
References
Motivation
Deep learning-based models such as CNN, RNN, LSTM, BI-LSTM,
GRU, etc. provide a good prediction accuracy, however, these models are
"black-box".
Monitor should not only be able to classify the input signals (ECG, PPG)
accurately to access the condition of a patient but also the cause of the
outcome should be explainable.
To understand further the effect of physiological signal features on
the outcome.
There is an urge for explainable monitoring models in healthcare
[reyes2020, gastounioti2020].
We propose a formal method-based framework that is correct by
construction.
We develop a formal runtime monitoring (RV) framework based on
ECG sensing for diabetes monitoring.
CBMS 2022 Abhinandan Panda December 5, 2022 10/28
Introduction
ECG
Proposed monitoring
system
Policies Mining
RV Monitor
Experimental results
& Comparison
Conclusion & Future
Works
References
References
Runtime Verification : Overview
Figure: Overview of the monitor based verification process
CBMS 2022 Abhinandan Panda December 5, 2022 11/28
Introduction
ECG
Proposed monitoring
system
Policies Mining
RV Monitor
Experimental results
& Comparison
Conclusion & Future
Works
References
References
RV Monitor
Definition
Consider a given property φ ⊆ tw(Σ) defining the property to monitor
that is defined as TA Aφ. Function Mφ : tw(Σ) → D is a verification
monitor for φ, where D = {T, F, CT, CF} and is defined as follows, with
σ ∈ tw(Σ) denoting the current observation (a finite timed word over the
alphabet Σ):
Mφ(σ) =







T if ∀σ′
∈ tw(Σ) : σ · σ′
∈ φ
F if ∀σ′
∈ tw(Σ) : σ · σ′
̸∈ φ
CT if σ ∈ φ ∧ ∃σ′
∈ tw(Σ) : σ · σ′
̸∈ φ
CF if σ ̸∈ φ ∧ ∃σ′
∈ tw(Σ) : σ · σ′
∈ φ
Correct by construction
Satisfy impartiality and anticipation constraints (Bauer et al.[12]).
CBMS 2022 Abhinandan Panda December 5, 2022 12/28
Introduction
ECG
Proposed monitoring
system
Policies Mining
RV Monitor
Experimental results
& Comparison
Conclusion & Future
Works
References
References
Proposed Monitoring Approach
Raw ECG
ECG
intervals ECG
Policy
inference
ECG
Processing
Module
Data
Mining
Model
ECG
Dataset
(Diabetic,
Healthy)
Class label
(diabetes/healthy)
Figure: Policy learning framework
ECG
events True / False
(Diabetes
detection)
Inferred ECG Policies
ECG signal
ECG
Sensor
ECG
Processing
Module
RV monitor
Figure: Proposed monitoring framework
CBMS 2022 Abhinandan Panda December 5, 2022 13/28
Introduction
ECG
Proposed monitoring
system
Policies Mining
RV Monitor
Experimental results
& Comparison
Conclusion & Future
Works
References
References
ECG and Diabetes Dataset
Dataset
We consider DICARDIA database [ledezma2014] of 65 subjects with:
i) 51 diabetic subjects with cardiac complications of age 57.00 ± 10.00
years
ii) 3 diabetic subjects without cardiac complications of age 49.00 ±
12.00 years
iii) 11 healthy subjects as a control group of age 50.00 ± 6.00 years.
iv) Approximately 30 min. long records.
Signal Processing
The ECG_Processing module is implemented in Python toolkit
Neurokit2 [Makowski2021].
Apply a high pass Butterworth filter and a low pass filter to remove
baseline drift and high-frequency noise from the ECG signal.
The R-peaks in ECG are extracted using the Pan-Tompkins
algorithm [13].
Wavelet analysis to detect the P-peaks, Q-peaks, R-peaks, T-peaks and
T-ends of the ECG.
CBMS 2022 Abhinandan Panda December 5, 2022 14/28
Introduction
ECG
Proposed monitoring
system
Policies Mining
RV Monitor
Experimental results
& Comparison
Conclusion & Future
Works
References
References
ECG Feature extraction
Figure: Processed ECG
CBMS 2022 Abhinandan Panda December 5, 2022 15/28
Introduction
ECG
Proposed monitoring
system
Policies Mining
RV Monitor
Experimental results
& Comparison
Conclusion & Future
Works
References
References
Policies Mining : Decision tree
Features
ECG intervals: PR, RR, QT, TpTe and RT
Class: Healhty (H), Diabetic (diabetic, diabetic with cardiac
complications)
CBMS 2022 Abhinandan Panda December 5, 2022 16/28
Introduction
ECG
Proposed monitoring
system
Policies Mining
RV Monitor
Experimental results
& Comparison
Conclusion & Future
Works
References
References
ECG Policies
• φECG1: If RR > 619 ms and PR > 127 ms and QT > 361 ms, then it is
diabetes.
• φECG2: If RR > 619 ms and PR <= 127 ms, then it indicates diabetes.
• φECG3: When RR > 528 ms and RR <= 619 ms and RT > 297.5 ms,
diabetes is present.
• φECG4: When RR > 619 ms and PR > 127 ms and PR <= 140 ms and
QT <= 361 ms, it is diabetes.
• φECG5: If RR > 401 ms and RR <= 408 ms and RT <= 297.5 ms,
then it indicates diabetes.
CBMS 2022 Abhinandan Panda December 5, 2022 17/28
Introduction
ECG
Proposed monitoring
system
Policies Mining
RV Monitor
Experimental results
& Comparison
Conclusion & Future
Works
References
References
Sub-policies
Each ECG policy is a combination of multiple sub-policies. For example,
to monitor policy φECG1, we monitor the intersection of the following
sub-policies.
• PECG11: The RR interval of ECG should be less than or equal to 619 ms.
• PECG12: The PR interval of ECG should be less than or equal to 127 ms.
• PECG13: The QT interval of ECG should be less than or equal to 361 ms.
CBMS 2022 Abhinandan Panda December 5, 2022 18/28
Introduction
ECG
Proposed monitoring
system
Policies Mining
RV Monitor
Experimental results
& Comparison
Conclusion & Future
Works
References
References
ECG policy as Timed Automata
l0 l1 l2
Σ  R
R, x := 0
ΣR
R,
x > 619
R, x ≤ 619
Σ
(a) Timed automata representing policy
PECG11
l0 l1 l2
Σ  P
P, x := 0
ΣR
R,
x > 127
R, x ≤ 127
Σ
(b) Timed automata representing policy
PECG12
l0 l1 l2
Σ  Q
Q, x := 0
ΣTe
T e,
x > 361
T e, x ≤ 361
Σ
(c) Timed automata representing policy
PECG13
Figure: Timed automata representing ECG policies PECG11, PECG12 and PECG13
CBMS 2022 Abhinandan Panda December 5, 2022 19/28
Introduction
ECG
Proposed monitoring
system
Policies Mining
RV Monitor
Experimental results
& Comparison
Conclusion & Future
Works
References
References
RV Monitor
Definition
Consider a given property φ ⊆ tw(Σ) defining the property to monitor
that is defined as TA Aφ. Function Mφ : tw(Σ) → D is a verification
monitor for φ, where D = {T, F, CT, CF} and is defined as follows, with
σ ∈ tw(Σ) denoting the current observation (a finite timed word over the
alphabet Σ):
Mφ(σ) =







T if ∀σ′
∈ tw(Σ) : σ · σ′
∈ φ
F if ∀σ′
∈ tw(Σ) : σ · σ′
̸∈ φ
CT if σ ∈ φ ∧ ∃σ′
∈ tw(Σ) : σ · σ′
̸∈ φ
CF if σ ̸∈ φ ∧ ∃σ′
∈ tw(Σ) : σ · σ′
∈ φ
Synthesis of RV monitor from policies formalized as timed automata
following the approaches mentioned in [pinisetty2017, pinisetty2018,
Bauer:2011].
CBMS 2022 Abhinandan Panda December 5, 2022 20/28
Introduction
ECG
Proposed monitoring
system
Policies Mining
RV Monitor
Experimental results
& Comparison
Conclusion & Future
Works
References
References
Example: Input-output Behavior of a RV Monitor
ECG trace : [σ = (P, 30) · (Q, 150) · (R, 155) · (Te, 500) · (R, 800)]
Table: RV monitor’s behaviour for the policy φECG1
σ MφECG1(σ)
(P, 30) CT
(P, 30) · (Q, 150) CT
(P, 30) · (Q, 150) · (R, 155) CT
(P, 30) · (Q, 150) · (R, 155) · (Te, 500) CT
(P, 30) · (Q, 150) · (R, 155) · (Te, 500) · (R, 800) CF
CBMS 2022 Abhinandan Panda December 5, 2022 21/28
Introduction
ECG
Proposed monitoring
system
Policies Mining
RV Monitor
Experimental results
& Comparison
Conclusion & Future
Works
References
References
Sample excetion of ECG trace on RV monitor
CBMS 2022 Abhinandan Panda December 5, 2022 22/28
Introduction
ECG
Proposed monitoring
system
Policies Mining
RV Monitor
Experimental results
& Comparison
Conclusion & Future
Works
References
References
Experimental Results
Accuracy(%) =
TP + TN
TP + TN + FP + FN
× 100
Sensitivity(%) =
TP
TP + FN
× 100
Specificity(%) =
TN
TN + FP
× 100
Accuracy Sensitivity Specificity
RV framework 88.07% 89.36% 86.36%
Table: RV framework Performance
Table: Comparison with other works
Authors Methods Accuracy
Acharya et al. [7] Nonlinear 86.0
Jian et al. [8] Higher order spectrum 79.93
Acharya et al. [9] Discrete wavelet transform 92.02
Pachori et al. [10] Empirical mode decomposition 95.63
Swapna et al. [11] Deep learning (CNN-LSTM) 95.1
Our RV framework Policy based 88.07
CBMS 2022 Abhinandan Panda December 5, 2022 23/28
Introduction
ECG
Proposed monitoring
system
Policies Mining
RV Monitor
Experimental results
& Comparison
Conclusion & Future
Works
References
References
RV Monitor on Wearable Device
Figure: RV monitor on wearable device [14]
CBMS 2022 Abhinandan Panda December 5, 2022 24/28
Introduction
ECG
Proposed monitoring
system
Policies Mining
RV Monitor
Experimental results
& Comparison
Conclusion & Future
Works
References
References
Conclusion & Future Works
Conclusion
Explainable health monitoring
Correct by construction model
Future work
Testing with other datasets
Analysing other ECG features
Implementation on wearable device
CBMS 2022 Abhinandan Panda December 5, 2022 25/28
Introduction
ECG
Proposed monitoring
system
Policies Mining
RV Monitor
Experimental results
& Comparison
Conclusion & Future
Works
References
References
References I
[1] Prateek Jain, Amit M Joshi, and Saraju Mohanty. “Everything you
wanted to know about noninvasive glucose measurement and
control”. In: arXiv preprint arXiv:2101.08996 (2021).
[2] American Diabetes Association. “Diagnosis and classification of
diabetes mellitus”. In: Diabetes care 37.Supplement_1 (2014),
S81–S90.
[3] Pouya Saeedi et al. “Global and regional diabetes prevalence
estimates for 2019 and projections for 2030 and 2045: Results from
the International Diabetes Federation Diabetes Atlas”. In: Diabetes
research and clinical practice 157 (2019), p. 107843.
[4] Jessica Beagley et al. “Global estimates of undiagnosed diabetes in
adults”. In: Diabetes research and clinical practice 103.2 (2014),
pp. 150–160.
[5] Melanie J Davies et al. “Management of hyperglycemia in type 2
diabetes, 2018. A consensus report by the American Diabetes
Association (ADA) and the European Association for the Study of
Diabetes (EASD)”. In: Diabetes care 41.12 (2018), pp. 2669–2701.
CBMS 2022 Abhinandan Panda December 5, 2022 26/28
Introduction
ECG
Proposed monitoring
system
Policies Mining
RV Monitor
Experimental results
& Comparison
Conclusion & Future
Works
References
References
References II
[6] Jukka Lipponen et al. “Dynamic estimation of cardiac
repolarization characteristics during hypoglycemia in healthy and
diabetic subjects”. In: Physiological measurement 32 (June 2011),
pp. 649–60. doi: 10.1088/0967-3334/32/6/003.
[7] U Rajendra Acharya et al. “An integrated diabetic index using heart
rate variability signal features for diagnosis of diabetes”. In:
Computer methods in biomechanics and biomedical engineering
16.2 (2013), pp. 222–234.
[8] Lee Wei Jian and Teik-Cheng Lim. “Automated detection of
diabetes by means of higher order spectral features obtained from
heart rate signals”. In: Journal of medical imaging and health
informatics 3.3 (2013), pp. 440–447.
[9] U Rajendra Acharya et al. “Computer-aided diagnosis of diabetic
subjects by heart rate variability signals using discrete wavelet
transform method”. In: Knowledge-based systems 81 (2015),
pp. 56–64.
CBMS 2022 Abhinandan Panda December 5, 2022 27/28
Introduction
ECG
Proposed monitoring
system
Policies Mining
RV Monitor
Experimental results
& Comparison
Conclusion & Future
Works
References
References
References III
[10] Ram Bilas Pachori et al. “An improved online paradigm for
screening of diabetic patients using RR-interval signals”. In: Journal
of Mechanics in Medicine and Biology 16.01 (2016), p. 1640003.
[11] Goutham Swapna, Soman Kp, and Ravi Vinayakumar. “Automated
detection of diabetes using CNN and CNN-LSTM network and
heart rate signals”. In: Procedia computer science 132 (2018),
pp. 1253–1262.
[12] Andreas Bauer, Martin Leucker, and Christian Schallhart. “Runtime
Verification for LTL and TLTL”. In: ACM Trans. Softw. Eng.
Methodol. 20.4 (Sept. 2011), 14:1–14:64. issn: 1049-331X.
[13] Jiapu Pan and Willis J Tompkins. “A real-time QRS detection
algorithm”. In: IEEE transactions on biomedical engineering 3
(1985), pp. 230–236.
[14] Srinivas Pinisetty et al. “Runtime enforcement of cyber-physical
systems”. In: ACM Transactions on Embedded Computing Systems
(TECS) 16.5s (2017), pp. 1–25.
CBMS 2022 Abhinandan Panda December 5, 2022 28/28
Thank you!

More Related Content

Similar to CBMS_Presentation (5).pdf

Definition and staging criteria of acute kidney injury in adults up todate
Definition and staging criteria of acute kidney injury in adults up todateDefinition and staging criteria of acute kidney injury in adults up todate
Definition and staging criteria of acute kidney injury in adults up todateCamilaEscobar83
 
Diabetes prediction based on discrete and continuous mean amplitude of glycem...
Diabetes prediction based on discrete and continuous mean amplitude of glycem...Diabetes prediction based on discrete and continuous mean amplitude of glycem...
Diabetes prediction based on discrete and continuous mean amplitude of glycem...journalBEEI
 
KDIGO-AKI-Guideline_Cass-2014.pdf
KDIGO-AKI-Guideline_Cass-2014.pdfKDIGO-AKI-Guideline_Cass-2014.pdf
KDIGO-AKI-Guideline_Cass-2014.pdfSebastianTjuwatja1
 
IRJET - Survey on Chronic Kidney Disease Prediction System with Feature Selec...
IRJET - Survey on Chronic Kidney Disease Prediction System with Feature Selec...IRJET - Survey on Chronic Kidney Disease Prediction System with Feature Selec...
IRJET - Survey on Chronic Kidney Disease Prediction System with Feature Selec...IRJET Journal
 
RSS 2009 - Investigating the impact of the QOF on quality of primary care
RSS 2009 - Investigating the impact of the QOF on quality of primary careRSS 2009 - Investigating the impact of the QOF on quality of primary care
RSS 2009 - Investigating the impact of the QOF on quality of primary careEvangelos Kontopantelis
 
Ppt For Esteck Complex For New Broucher Diagnosis
Ppt For Esteck Complex For New Broucher DiagnosisPpt For Esteck Complex For New Broucher Diagnosis
Ppt For Esteck Complex For New Broucher Diagnosisinov8solutions
 
Prognosis of Diabetes by Performing Data Mining of HbA1c
 Prognosis of Diabetes by Performing Data Mining of HbA1c Prognosis of Diabetes by Performing Data Mining of HbA1c
Prognosis of Diabetes by Performing Data Mining of HbA1cIJCSIS Research Publications
 
Meaningful (meta)data at scale: removing barriers to precision medicine research
Meaningful (meta)data at scale: removing barriers to precision medicine researchMeaningful (meta)data at scale: removing barriers to precision medicine research
Meaningful (meta)data at scale: removing barriers to precision medicine researchNolan Nichols
 
Tuning of digital PID controller for blood glucose level of diabetic patient
Tuning of digital PID controller for blood glucose level of diabetic patientTuning of digital PID controller for blood glucose level of diabetic patient
Tuning of digital PID controller for blood glucose level of diabetic patientIRJET Journal
 
Internal 2013 - General practice clinical systems
Internal 2013 - General practice clinical systemsInternal 2013 - General practice clinical systems
Internal 2013 - General practice clinical systemsEvangelos Kontopantelis
 
uptodate on acute kidney injury
uptodate on acute kidney injuryuptodate on acute kidney injury
uptodate on acute kidney injurySherif Mohammed
 
Can the tqt study be replaced b darpo london june 2013 (2)
Can the tqt study be replaced b darpo london june 2013 (2)Can the tqt study be replaced b darpo london june 2013 (2)
Can the tqt study be replaced b darpo london june 2013 (2)Sasha Latypova
 
Early Stage Diabetic Disease Prediction and Risk Minimization using Machine L...
Early Stage Diabetic Disease Prediction and Risk Minimization using Machine L...Early Stage Diabetic Disease Prediction and Risk Minimization using Machine L...
Early Stage Diabetic Disease Prediction and Risk Minimization using Machine L...IRJET Journal
 
Interpretation of CGM .pptx
Interpretation of CGM .pptxInterpretation of CGM .pptx
Interpretation of CGM .pptxDr BHARAT SABOO
 
Stich Qol Mark
Stich Qol MarkStich Qol Mark
Stich Qol Markhospital
 
CONTROL OF BLOOD GLUCOSE IN DIABETIC PATIENTS
CONTROL OF BLOOD GLUCOSE IN DIABETIC PATIENTSCONTROL OF BLOOD GLUCOSE IN DIABETIC PATIENTS
CONTROL OF BLOOD GLUCOSE IN DIABETIC PATIENTSVictoria Onifade
 
Forecasting Diabetes Mellitus at an Initial Stage using Machine Learning Methods
Forecasting Diabetes Mellitus at an Initial Stage using Machine Learning MethodsForecasting Diabetes Mellitus at an Initial Stage using Machine Learning Methods
Forecasting Diabetes Mellitus at an Initial Stage using Machine Learning MethodsIRJET Journal
 
freipresleyecqmsnurse16
freipresleyecqmsnurse16freipresleyecqmsnurse16
freipresleyecqmsnurse16Bill Presley
 
CCO_ENDO_CGM2022_Downloadable.pptx
CCO_ENDO_CGM2022_Downloadable.pptxCCO_ENDO_CGM2022_Downloadable.pptx
CCO_ENDO_CGM2022_Downloadable.pptxakramabdalla1
 
IMM_683_kSORT_ISPOR_Poster_rebrand2015_v2
IMM_683_kSORT_ISPOR_Poster_rebrand2015_v2IMM_683_kSORT_ISPOR_Poster_rebrand2015_v2
IMM_683_kSORT_ISPOR_Poster_rebrand2015_v2Kevin Jaglinski
 

Similar to CBMS_Presentation (5).pdf (20)

Definition and staging criteria of acute kidney injury in adults up todate
Definition and staging criteria of acute kidney injury in adults up todateDefinition and staging criteria of acute kidney injury in adults up todate
Definition and staging criteria of acute kidney injury in adults up todate
 
Diabetes prediction based on discrete and continuous mean amplitude of glycem...
Diabetes prediction based on discrete and continuous mean amplitude of glycem...Diabetes prediction based on discrete and continuous mean amplitude of glycem...
Diabetes prediction based on discrete and continuous mean amplitude of glycem...
 
KDIGO-AKI-Guideline_Cass-2014.pdf
KDIGO-AKI-Guideline_Cass-2014.pdfKDIGO-AKI-Guideline_Cass-2014.pdf
KDIGO-AKI-Guideline_Cass-2014.pdf
 
IRJET - Survey on Chronic Kidney Disease Prediction System with Feature Selec...
IRJET - Survey on Chronic Kidney Disease Prediction System with Feature Selec...IRJET - Survey on Chronic Kidney Disease Prediction System with Feature Selec...
IRJET - Survey on Chronic Kidney Disease Prediction System with Feature Selec...
 
RSS 2009 - Investigating the impact of the QOF on quality of primary care
RSS 2009 - Investigating the impact of the QOF on quality of primary careRSS 2009 - Investigating the impact of the QOF on quality of primary care
RSS 2009 - Investigating the impact of the QOF on quality of primary care
 
Ppt For Esteck Complex For New Broucher Diagnosis
Ppt For Esteck Complex For New Broucher DiagnosisPpt For Esteck Complex For New Broucher Diagnosis
Ppt For Esteck Complex For New Broucher Diagnosis
 
Prognosis of Diabetes by Performing Data Mining of HbA1c
 Prognosis of Diabetes by Performing Data Mining of HbA1c Prognosis of Diabetes by Performing Data Mining of HbA1c
Prognosis of Diabetes by Performing Data Mining of HbA1c
 
Meaningful (meta)data at scale: removing barriers to precision medicine research
Meaningful (meta)data at scale: removing barriers to precision medicine researchMeaningful (meta)data at scale: removing barriers to precision medicine research
Meaningful (meta)data at scale: removing barriers to precision medicine research
 
Tuning of digital PID controller for blood glucose level of diabetic patient
Tuning of digital PID controller for blood glucose level of diabetic patientTuning of digital PID controller for blood glucose level of diabetic patient
Tuning of digital PID controller for blood glucose level of diabetic patient
 
Internal 2013 - General practice clinical systems
Internal 2013 - General practice clinical systemsInternal 2013 - General practice clinical systems
Internal 2013 - General practice clinical systems
 
uptodate on acute kidney injury
uptodate on acute kidney injuryuptodate on acute kidney injury
uptodate on acute kidney injury
 
Can the tqt study be replaced b darpo london june 2013 (2)
Can the tqt study be replaced b darpo london june 2013 (2)Can the tqt study be replaced b darpo london june 2013 (2)
Can the tqt study be replaced b darpo london june 2013 (2)
 
Early Stage Diabetic Disease Prediction and Risk Minimization using Machine L...
Early Stage Diabetic Disease Prediction and Risk Minimization using Machine L...Early Stage Diabetic Disease Prediction and Risk Minimization using Machine L...
Early Stage Diabetic Disease Prediction and Risk Minimization using Machine L...
 
Interpretation of CGM .pptx
Interpretation of CGM .pptxInterpretation of CGM .pptx
Interpretation of CGM .pptx
 
Stich Qol Mark
Stich Qol MarkStich Qol Mark
Stich Qol Mark
 
CONTROL OF BLOOD GLUCOSE IN DIABETIC PATIENTS
CONTROL OF BLOOD GLUCOSE IN DIABETIC PATIENTSCONTROL OF BLOOD GLUCOSE IN DIABETIC PATIENTS
CONTROL OF BLOOD GLUCOSE IN DIABETIC PATIENTS
 
Forecasting Diabetes Mellitus at an Initial Stage using Machine Learning Methods
Forecasting Diabetes Mellitus at an Initial Stage using Machine Learning MethodsForecasting Diabetes Mellitus at an Initial Stage using Machine Learning Methods
Forecasting Diabetes Mellitus at an Initial Stage using Machine Learning Methods
 
freipresleyecqmsnurse16
freipresleyecqmsnurse16freipresleyecqmsnurse16
freipresleyecqmsnurse16
 
CCO_ENDO_CGM2022_Downloadable.pptx
CCO_ENDO_CGM2022_Downloadable.pptxCCO_ENDO_CGM2022_Downloadable.pptx
CCO_ENDO_CGM2022_Downloadable.pptx
 
IMM_683_kSORT_ISPOR_Poster_rebrand2015_v2
IMM_683_kSORT_ISPOR_Poster_rebrand2015_v2IMM_683_kSORT_ISPOR_Poster_rebrand2015_v2
IMM_683_kSORT_ISPOR_Poster_rebrand2015_v2
 

Recently uploaded

Call Girls Bangalore Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Bangalore Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Bangalore Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Bangalore Just Call 9907093804 Top Class Call Girl Service AvailableDipal Arora
 
Top Rated Bangalore Call Girls Mg Road ⟟ 9332606886 ⟟ Call Me For Genuine Se...
Top Rated Bangalore Call Girls Mg Road ⟟  9332606886 ⟟ Call Me For Genuine Se...Top Rated Bangalore Call Girls Mg Road ⟟  9332606886 ⟟ Call Me For Genuine Se...
Top Rated Bangalore Call Girls Mg Road ⟟ 9332606886 ⟟ Call Me For Genuine Se...narwatsonia7
 
Call Girls Siliguri Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Siliguri Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Siliguri Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Siliguri Just Call 9907093804 Top Class Call Girl Service AvailableDipal Arora
 
Manyata Tech Park ( Call Girls ) Bangalore ✔ 6297143586 ✔ Hot Model With Sexy...
Manyata Tech Park ( Call Girls ) Bangalore ✔ 6297143586 ✔ Hot Model With Sexy...Manyata Tech Park ( Call Girls ) Bangalore ✔ 6297143586 ✔ Hot Model With Sexy...
Manyata Tech Park ( Call Girls ) Bangalore ✔ 6297143586 ✔ Hot Model With Sexy...vidya singh
 
VIP Call Girls Indore Kirti 💚😋 9256729539 🚀 Indore Escorts
VIP Call Girls Indore Kirti 💚😋  9256729539 🚀 Indore EscortsVIP Call Girls Indore Kirti 💚😋  9256729539 🚀 Indore Escorts
VIP Call Girls Indore Kirti 💚😋 9256729539 🚀 Indore Escortsaditipandeya
 
Call Girls Dehradun Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Dehradun Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Dehradun Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Dehradun Just Call 9907093804 Top Class Call Girl Service AvailableDipal Arora
 
Call Girls Gwalior Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Gwalior Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Gwalior Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Gwalior Just Call 9907093804 Top Class Call Girl Service AvailableDipal Arora
 
Night 7k to 12k Navi Mumbai Call Girl Photo 👉 BOOK NOW 9833363713 👈 ♀️ night ...
Night 7k to 12k Navi Mumbai Call Girl Photo 👉 BOOK NOW 9833363713 👈 ♀️ night ...Night 7k to 12k Navi Mumbai Call Girl Photo 👉 BOOK NOW 9833363713 👈 ♀️ night ...
Night 7k to 12k Navi Mumbai Call Girl Photo 👉 BOOK NOW 9833363713 👈 ♀️ night ...aartirawatdelhi
 
Bangalore Call Girls Nelamangala Number 7001035870 Meetin With Bangalore Esc...
Bangalore Call Girls Nelamangala Number 7001035870  Meetin With Bangalore Esc...Bangalore Call Girls Nelamangala Number 7001035870  Meetin With Bangalore Esc...
Bangalore Call Girls Nelamangala Number 7001035870 Meetin With Bangalore Esc...narwatsonia7
 
Top Rated Bangalore Call Girls Ramamurthy Nagar ⟟ 8250192130 ⟟ Call Me For Ge...
Top Rated Bangalore Call Girls Ramamurthy Nagar ⟟ 8250192130 ⟟ Call Me For Ge...Top Rated Bangalore Call Girls Ramamurthy Nagar ⟟ 8250192130 ⟟ Call Me For Ge...
Top Rated Bangalore Call Girls Ramamurthy Nagar ⟟ 8250192130 ⟟ Call Me For Ge...narwatsonia7
 
Call Girls Nagpur Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Nagpur Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Nagpur Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Nagpur Just Call 9907093804 Top Class Call Girl Service AvailableDipal Arora
 
VIP Hyderabad Call Girls Bahadurpally 7877925207 ₹5000 To 25K With AC Room 💚😋
VIP Hyderabad Call Girls Bahadurpally 7877925207 ₹5000 To 25K With AC Room 💚😋VIP Hyderabad Call Girls Bahadurpally 7877925207 ₹5000 To 25K With AC Room 💚😋
VIP Hyderabad Call Girls Bahadurpally 7877925207 ₹5000 To 25K With AC Room 💚😋TANUJA PANDEY
 
Top Rated Hyderabad Call Girls Erragadda ⟟ 6297143586 ⟟ Call Me For Genuine ...
Top Rated  Hyderabad Call Girls Erragadda ⟟ 6297143586 ⟟ Call Me For Genuine ...Top Rated  Hyderabad Call Girls Erragadda ⟟ 6297143586 ⟟ Call Me For Genuine ...
Top Rated Hyderabad Call Girls Erragadda ⟟ 6297143586 ⟟ Call Me For Genuine ...chandars293
 
Call Girls Coimbatore Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Coimbatore Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Coimbatore Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Coimbatore Just Call 9907093804 Top Class Call Girl Service AvailableDipal Arora
 
Call Girls Tirupati Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Tirupati Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Tirupati Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Tirupati Just Call 9907093804 Top Class Call Girl Service AvailableDipal Arora
 
The Most Attractive Hyderabad Call Girls Kothapet 𖠋 6297143586 𖠋 Will You Mis...
The Most Attractive Hyderabad Call Girls Kothapet 𖠋 6297143586 𖠋 Will You Mis...The Most Attractive Hyderabad Call Girls Kothapet 𖠋 6297143586 𖠋 Will You Mis...
The Most Attractive Hyderabad Call Girls Kothapet 𖠋 6297143586 𖠋 Will You Mis...chandars293
 
Call Girls Ooty Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Ooty Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Ooty Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Ooty Just Call 9907093804 Top Class Call Girl Service AvailableDipal Arora
 
Premium Call Girls Cottonpet Whatsapp 7001035870 Independent Escort Service
Premium Call Girls Cottonpet Whatsapp 7001035870 Independent Escort ServicePremium Call Girls Cottonpet Whatsapp 7001035870 Independent Escort Service
Premium Call Girls Cottonpet Whatsapp 7001035870 Independent Escort Servicevidya singh
 
Call Girls Faridabad Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Faridabad Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Faridabad Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Faridabad Just Call 9907093804 Top Class Call Girl Service AvailableDipal Arora
 
Call Girls Kochi Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Kochi Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Kochi Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Kochi Just Call 9907093804 Top Class Call Girl Service AvailableDipal Arora
 

Recently uploaded (20)

Call Girls Bangalore Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Bangalore Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Bangalore Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Bangalore Just Call 9907093804 Top Class Call Girl Service Available
 
Top Rated Bangalore Call Girls Mg Road ⟟ 9332606886 ⟟ Call Me For Genuine Se...
Top Rated Bangalore Call Girls Mg Road ⟟  9332606886 ⟟ Call Me For Genuine Se...Top Rated Bangalore Call Girls Mg Road ⟟  9332606886 ⟟ Call Me For Genuine Se...
Top Rated Bangalore Call Girls Mg Road ⟟ 9332606886 ⟟ Call Me For Genuine Se...
 
Call Girls Siliguri Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Siliguri Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Siliguri Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Siliguri Just Call 9907093804 Top Class Call Girl Service Available
 
Manyata Tech Park ( Call Girls ) Bangalore ✔ 6297143586 ✔ Hot Model With Sexy...
Manyata Tech Park ( Call Girls ) Bangalore ✔ 6297143586 ✔ Hot Model With Sexy...Manyata Tech Park ( Call Girls ) Bangalore ✔ 6297143586 ✔ Hot Model With Sexy...
Manyata Tech Park ( Call Girls ) Bangalore ✔ 6297143586 ✔ Hot Model With Sexy...
 
VIP Call Girls Indore Kirti 💚😋 9256729539 🚀 Indore Escorts
VIP Call Girls Indore Kirti 💚😋  9256729539 🚀 Indore EscortsVIP Call Girls Indore Kirti 💚😋  9256729539 🚀 Indore Escorts
VIP Call Girls Indore Kirti 💚😋 9256729539 🚀 Indore Escorts
 
Call Girls Dehradun Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Dehradun Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Dehradun Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Dehradun Just Call 9907093804 Top Class Call Girl Service Available
 
Call Girls Gwalior Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Gwalior Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Gwalior Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Gwalior Just Call 9907093804 Top Class Call Girl Service Available
 
Night 7k to 12k Navi Mumbai Call Girl Photo 👉 BOOK NOW 9833363713 👈 ♀️ night ...
Night 7k to 12k Navi Mumbai Call Girl Photo 👉 BOOK NOW 9833363713 👈 ♀️ night ...Night 7k to 12k Navi Mumbai Call Girl Photo 👉 BOOK NOW 9833363713 👈 ♀️ night ...
Night 7k to 12k Navi Mumbai Call Girl Photo 👉 BOOK NOW 9833363713 👈 ♀️ night ...
 
Bangalore Call Girls Nelamangala Number 7001035870 Meetin With Bangalore Esc...
Bangalore Call Girls Nelamangala Number 7001035870  Meetin With Bangalore Esc...Bangalore Call Girls Nelamangala Number 7001035870  Meetin With Bangalore Esc...
Bangalore Call Girls Nelamangala Number 7001035870 Meetin With Bangalore Esc...
 
Top Rated Bangalore Call Girls Ramamurthy Nagar ⟟ 8250192130 ⟟ Call Me For Ge...
Top Rated Bangalore Call Girls Ramamurthy Nagar ⟟ 8250192130 ⟟ Call Me For Ge...Top Rated Bangalore Call Girls Ramamurthy Nagar ⟟ 8250192130 ⟟ Call Me For Ge...
Top Rated Bangalore Call Girls Ramamurthy Nagar ⟟ 8250192130 ⟟ Call Me For Ge...
 
Call Girls Nagpur Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Nagpur Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Nagpur Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Nagpur Just Call 9907093804 Top Class Call Girl Service Available
 
VIP Hyderabad Call Girls Bahadurpally 7877925207 ₹5000 To 25K With AC Room 💚😋
VIP Hyderabad Call Girls Bahadurpally 7877925207 ₹5000 To 25K With AC Room 💚😋VIP Hyderabad Call Girls Bahadurpally 7877925207 ₹5000 To 25K With AC Room 💚😋
VIP Hyderabad Call Girls Bahadurpally 7877925207 ₹5000 To 25K With AC Room 💚😋
 
Top Rated Hyderabad Call Girls Erragadda ⟟ 6297143586 ⟟ Call Me For Genuine ...
Top Rated  Hyderabad Call Girls Erragadda ⟟ 6297143586 ⟟ Call Me For Genuine ...Top Rated  Hyderabad Call Girls Erragadda ⟟ 6297143586 ⟟ Call Me For Genuine ...
Top Rated Hyderabad Call Girls Erragadda ⟟ 6297143586 ⟟ Call Me For Genuine ...
 
Call Girls Coimbatore Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Coimbatore Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Coimbatore Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Coimbatore Just Call 9907093804 Top Class Call Girl Service Available
 
Call Girls Tirupati Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Tirupati Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Tirupati Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Tirupati Just Call 9907093804 Top Class Call Girl Service Available
 
The Most Attractive Hyderabad Call Girls Kothapet 𖠋 6297143586 𖠋 Will You Mis...
The Most Attractive Hyderabad Call Girls Kothapet 𖠋 6297143586 𖠋 Will You Mis...The Most Attractive Hyderabad Call Girls Kothapet 𖠋 6297143586 𖠋 Will You Mis...
The Most Attractive Hyderabad Call Girls Kothapet 𖠋 6297143586 𖠋 Will You Mis...
 
Call Girls Ooty Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Ooty Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Ooty Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Ooty Just Call 9907093804 Top Class Call Girl Service Available
 
Premium Call Girls Cottonpet Whatsapp 7001035870 Independent Escort Service
Premium Call Girls Cottonpet Whatsapp 7001035870 Independent Escort ServicePremium Call Girls Cottonpet Whatsapp 7001035870 Independent Escort Service
Premium Call Girls Cottonpet Whatsapp 7001035870 Independent Escort Service
 
Call Girls Faridabad Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Faridabad Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Faridabad Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Faridabad Just Call 9907093804 Top Class Call Girl Service Available
 
Call Girls Kochi Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Kochi Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Kochi Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Kochi Just Call 9907093804 Top Class Call Girl Service Available
 

CBMS_Presentation (5).pdf

  • 1. IEEE 35th International Symposium on Computer Based Medical Systems (CBMS 2022) Policy-Based Diabetes Detection using Formal Runtime Verification Monitors Abhinandan Panda 1 , Srinivas Pinisetty1 , Partha Roop 2 1 Indian Institute of Technology, Bhubaneswar, India 2 University of Auckland, Auckland, New Zealand December 5, 2022
  • 2. Outline 1 Introduction 2 ECG 3 Proposed monitoring system 4 Policies Mining 5 RV Monitor 6 Experimental results & Comparison 7 Conclusion & Future Works 8 References
  • 3. Introduction ECG Proposed monitoring system Policies Mining RV Monitor Experimental results & Comparison Conclusion & Future Works References References Introduction: Diabetes • A metabolic disorder • Lack of control or balance in blood glucose (BG) • Type 1 diabetes (deficiency of insulin) / Type 2 diabetes (excess of insulin) • Hyperglycemia (very high blood glucose levels) / hypoglycemia (very low blood glucose levels) events (normal blood glucose level 140 mg/dL). CBMS 2022 Abhinandan Panda December 5, 2022 1/28
  • 4. Introduction ECG Proposed monitoring system Policies Mining RV Monitor Experimental results & Comparison Conclusion & Future Works References References Health Complications in Diabetes Figure: Health complications in diabetes [1] CBMS 2022 Abhinandan Panda December 5, 2022 2/28
  • 5. Introduction ECG Proposed monitoring system Policies Mining RV Monitor Experimental results & Comparison Conclusion & Future Works References References Global Diabetic Growth Figure: Global diabetic growth [1] CBMS 2022 Abhinandan Panda December 5, 2022 3/28
  • 6. Introduction ECG Proposed monitoring system Policies Mining RV Monitor Experimental results & Comparison Conclusion & Future Works References References Invasive Blood Glucose Monitoring Figure: Invasive blood glucose monitoring [1] CBMS 2022 Abhinandan Panda December 5, 2022 4/28
  • 7. Introduction ECG Proposed monitoring system Policies Mining RV Monitor Experimental results & Comparison Conclusion & Future Works References References Need of non-invasive continuous monitoring of diabetes • Severe health complications [2]. • Around 9.3% of people are affected by diabetes globally [3] . • Tedious initial screening process • About 45.8% of diabetes cases with cardiac complications are untreated [4]. • Continuous diabetes monitoring technique should be adopted [5] CBMS 2022 Abhinandan Panda December 5, 2022 5/28
  • 8. Introduction ECG Proposed monitoring system Policies Mining RV Monitor Experimental results & Comparison Conclusion & Future Works References References Non-invasive approach: monitoring physiological signal ECG Time Amplitude S R Q P Q R S QRS interval P PR interval P-wave interval QT interval RT interval TpTe interval Te RR interval Tp Tp Figure: A typical ECG Signal CBMS 2022 Abhinandan Panda December 5, 2022 6/28
  • 9. Introduction ECG Proposed monitoring system Policies Mining RV Monitor Experimental results & Comparison Conclusion & Future Works References References ECG in diabetes Figure: ECG in diabetes [6] CBMS 2022 Abhinandan Panda December 5, 2022 7/28
  • 10. Introduction ECG Proposed monitoring system Policies Mining RV Monitor Experimental results & Comparison Conclusion & Future Works References References ECG and Diabetes: Analysis hypoglycemia (low blood glucose level) results in prolongation of QT interval [christensen2010]. Hypoglycemia (low blood glucose level) associated with increased heart rate (HR) [heger1996]. Hyperglycemia (high blood glucose level) related with reduced heart rate variability (HRV) [singh2000]. Corrected QT dispersion and PR interval have a significant change in hyperglycemia condition [marfella2000]. According to [nguyen2012], ECG parameters such as corrected QT interval, PR interval, corrected RT interval, corrected TpTe interval and heart rate (HR) can be used for identification of hypoglycemia and hyperglycemia detection. CBMS 2022 Abhinandan Panda December 5, 2022 8/28
  • 11. Introduction ECG Proposed monitoring system Policies Mining RV Monitor Experimental results & Comparison Conclusion & Future Works References References Related Works Authors Methods Accuracy Acharya et al. [7] Nonlinear 86.0 Jian et al. [8] Higher order spectrum 79.93 Acharya et al. [9] Discrete wavelet transform 92.02 Pachori et al. [10] Empirical mode decomposition 95.63 Swapna et al. [11] Deep learning (CNN-LSTM) 95.1 CBMS 2022 Abhinandan Panda December 5, 2022 9/28
  • 12. Introduction ECG Proposed monitoring system Policies Mining RV Monitor Experimental results & Comparison Conclusion & Future Works References References Motivation Deep learning-based models such as CNN, RNN, LSTM, BI-LSTM, GRU, etc. provide a good prediction accuracy, however, these models are "black-box". Monitor should not only be able to classify the input signals (ECG, PPG) accurately to access the condition of a patient but also the cause of the outcome should be explainable. To understand further the effect of physiological signal features on the outcome. There is an urge for explainable monitoring models in healthcare [reyes2020, gastounioti2020]. We propose a formal method-based framework that is correct by construction. We develop a formal runtime monitoring (RV) framework based on ECG sensing for diabetes monitoring. CBMS 2022 Abhinandan Panda December 5, 2022 10/28
  • 13. Introduction ECG Proposed monitoring system Policies Mining RV Monitor Experimental results & Comparison Conclusion & Future Works References References Runtime Verification : Overview Figure: Overview of the monitor based verification process CBMS 2022 Abhinandan Panda December 5, 2022 11/28
  • 14. Introduction ECG Proposed monitoring system Policies Mining RV Monitor Experimental results & Comparison Conclusion & Future Works References References RV Monitor Definition Consider a given property φ ⊆ tw(Σ) defining the property to monitor that is defined as TA Aφ. Function Mφ : tw(Σ) → D is a verification monitor for φ, where D = {T, F, CT, CF} and is defined as follows, with σ ∈ tw(Σ) denoting the current observation (a finite timed word over the alphabet Σ): Mφ(σ) =        T if ∀σ′ ∈ tw(Σ) : σ · σ′ ∈ φ F if ∀σ′ ∈ tw(Σ) : σ · σ′ ̸∈ φ CT if σ ∈ φ ∧ ∃σ′ ∈ tw(Σ) : σ · σ′ ̸∈ φ CF if σ ̸∈ φ ∧ ∃σ′ ∈ tw(Σ) : σ · σ′ ∈ φ Correct by construction Satisfy impartiality and anticipation constraints (Bauer et al.[12]). CBMS 2022 Abhinandan Panda December 5, 2022 12/28
  • 15. Introduction ECG Proposed monitoring system Policies Mining RV Monitor Experimental results & Comparison Conclusion & Future Works References References Proposed Monitoring Approach Raw ECG ECG intervals ECG Policy inference ECG Processing Module Data Mining Model ECG Dataset (Diabetic, Healthy) Class label (diabetes/healthy) Figure: Policy learning framework ECG events True / False (Diabetes detection) Inferred ECG Policies ECG signal ECG Sensor ECG Processing Module RV monitor Figure: Proposed monitoring framework CBMS 2022 Abhinandan Panda December 5, 2022 13/28
  • 16. Introduction ECG Proposed monitoring system Policies Mining RV Monitor Experimental results & Comparison Conclusion & Future Works References References ECG and Diabetes Dataset Dataset We consider DICARDIA database [ledezma2014] of 65 subjects with: i) 51 diabetic subjects with cardiac complications of age 57.00 ± 10.00 years ii) 3 diabetic subjects without cardiac complications of age 49.00 ± 12.00 years iii) 11 healthy subjects as a control group of age 50.00 ± 6.00 years. iv) Approximately 30 min. long records. Signal Processing The ECG_Processing module is implemented in Python toolkit Neurokit2 [Makowski2021]. Apply a high pass Butterworth filter and a low pass filter to remove baseline drift and high-frequency noise from the ECG signal. The R-peaks in ECG are extracted using the Pan-Tompkins algorithm [13]. Wavelet analysis to detect the P-peaks, Q-peaks, R-peaks, T-peaks and T-ends of the ECG. CBMS 2022 Abhinandan Panda December 5, 2022 14/28
  • 17. Introduction ECG Proposed monitoring system Policies Mining RV Monitor Experimental results & Comparison Conclusion & Future Works References References ECG Feature extraction Figure: Processed ECG CBMS 2022 Abhinandan Panda December 5, 2022 15/28
  • 18. Introduction ECG Proposed monitoring system Policies Mining RV Monitor Experimental results & Comparison Conclusion & Future Works References References Policies Mining : Decision tree Features ECG intervals: PR, RR, QT, TpTe and RT Class: Healhty (H), Diabetic (diabetic, diabetic with cardiac complications) CBMS 2022 Abhinandan Panda December 5, 2022 16/28
  • 19. Introduction ECG Proposed monitoring system Policies Mining RV Monitor Experimental results & Comparison Conclusion & Future Works References References ECG Policies • φECG1: If RR > 619 ms and PR > 127 ms and QT > 361 ms, then it is diabetes. • φECG2: If RR > 619 ms and PR <= 127 ms, then it indicates diabetes. • φECG3: When RR > 528 ms and RR <= 619 ms and RT > 297.5 ms, diabetes is present. • φECG4: When RR > 619 ms and PR > 127 ms and PR <= 140 ms and QT <= 361 ms, it is diabetes. • φECG5: If RR > 401 ms and RR <= 408 ms and RT <= 297.5 ms, then it indicates diabetes. CBMS 2022 Abhinandan Panda December 5, 2022 17/28
  • 20. Introduction ECG Proposed monitoring system Policies Mining RV Monitor Experimental results & Comparison Conclusion & Future Works References References Sub-policies Each ECG policy is a combination of multiple sub-policies. For example, to monitor policy φECG1, we monitor the intersection of the following sub-policies. • PECG11: The RR interval of ECG should be less than or equal to 619 ms. • PECG12: The PR interval of ECG should be less than or equal to 127 ms. • PECG13: The QT interval of ECG should be less than or equal to 361 ms. CBMS 2022 Abhinandan Panda December 5, 2022 18/28
  • 21. Introduction ECG Proposed monitoring system Policies Mining RV Monitor Experimental results & Comparison Conclusion & Future Works References References ECG policy as Timed Automata l0 l1 l2 Σ R R, x := 0 ΣR R, x > 619 R, x ≤ 619 Σ (a) Timed automata representing policy PECG11 l0 l1 l2 Σ P P, x := 0 ΣR R, x > 127 R, x ≤ 127 Σ (b) Timed automata representing policy PECG12 l0 l1 l2 Σ Q Q, x := 0 ΣTe T e, x > 361 T e, x ≤ 361 Σ (c) Timed automata representing policy PECG13 Figure: Timed automata representing ECG policies PECG11, PECG12 and PECG13 CBMS 2022 Abhinandan Panda December 5, 2022 19/28
  • 22. Introduction ECG Proposed monitoring system Policies Mining RV Monitor Experimental results & Comparison Conclusion & Future Works References References RV Monitor Definition Consider a given property φ ⊆ tw(Σ) defining the property to monitor that is defined as TA Aφ. Function Mφ : tw(Σ) → D is a verification monitor for φ, where D = {T, F, CT, CF} and is defined as follows, with σ ∈ tw(Σ) denoting the current observation (a finite timed word over the alphabet Σ): Mφ(σ) =        T if ∀σ′ ∈ tw(Σ) : σ · σ′ ∈ φ F if ∀σ′ ∈ tw(Σ) : σ · σ′ ̸∈ φ CT if σ ∈ φ ∧ ∃σ′ ∈ tw(Σ) : σ · σ′ ̸∈ φ CF if σ ̸∈ φ ∧ ∃σ′ ∈ tw(Σ) : σ · σ′ ∈ φ Synthesis of RV monitor from policies formalized as timed automata following the approaches mentioned in [pinisetty2017, pinisetty2018, Bauer:2011]. CBMS 2022 Abhinandan Panda December 5, 2022 20/28
  • 23. Introduction ECG Proposed monitoring system Policies Mining RV Monitor Experimental results & Comparison Conclusion & Future Works References References Example: Input-output Behavior of a RV Monitor ECG trace : [σ = (P, 30) · (Q, 150) · (R, 155) · (Te, 500) · (R, 800)] Table: RV monitor’s behaviour for the policy φECG1 σ MφECG1(σ) (P, 30) CT (P, 30) · (Q, 150) CT (P, 30) · (Q, 150) · (R, 155) CT (P, 30) · (Q, 150) · (R, 155) · (Te, 500) CT (P, 30) · (Q, 150) · (R, 155) · (Te, 500) · (R, 800) CF CBMS 2022 Abhinandan Panda December 5, 2022 21/28
  • 24. Introduction ECG Proposed monitoring system Policies Mining RV Monitor Experimental results & Comparison Conclusion & Future Works References References Sample excetion of ECG trace on RV monitor CBMS 2022 Abhinandan Panda December 5, 2022 22/28
  • 25. Introduction ECG Proposed monitoring system Policies Mining RV Monitor Experimental results & Comparison Conclusion & Future Works References References Experimental Results Accuracy(%) = TP + TN TP + TN + FP + FN × 100 Sensitivity(%) = TP TP + FN × 100 Specificity(%) = TN TN + FP × 100 Accuracy Sensitivity Specificity RV framework 88.07% 89.36% 86.36% Table: RV framework Performance Table: Comparison with other works Authors Methods Accuracy Acharya et al. [7] Nonlinear 86.0 Jian et al. [8] Higher order spectrum 79.93 Acharya et al. [9] Discrete wavelet transform 92.02 Pachori et al. [10] Empirical mode decomposition 95.63 Swapna et al. [11] Deep learning (CNN-LSTM) 95.1 Our RV framework Policy based 88.07 CBMS 2022 Abhinandan Panda December 5, 2022 23/28
  • 26. Introduction ECG Proposed monitoring system Policies Mining RV Monitor Experimental results & Comparison Conclusion & Future Works References References RV Monitor on Wearable Device Figure: RV monitor on wearable device [14] CBMS 2022 Abhinandan Panda December 5, 2022 24/28
  • 27. Introduction ECG Proposed monitoring system Policies Mining RV Monitor Experimental results & Comparison Conclusion & Future Works References References Conclusion & Future Works Conclusion Explainable health monitoring Correct by construction model Future work Testing with other datasets Analysing other ECG features Implementation on wearable device CBMS 2022 Abhinandan Panda December 5, 2022 25/28
  • 28. Introduction ECG Proposed monitoring system Policies Mining RV Monitor Experimental results & Comparison Conclusion & Future Works References References References I [1] Prateek Jain, Amit M Joshi, and Saraju Mohanty. “Everything you wanted to know about noninvasive glucose measurement and control”. In: arXiv preprint arXiv:2101.08996 (2021). [2] American Diabetes Association. “Diagnosis and classification of diabetes mellitus”. In: Diabetes care 37.Supplement_1 (2014), S81–S90. [3] Pouya Saeedi et al. “Global and regional diabetes prevalence estimates for 2019 and projections for 2030 and 2045: Results from the International Diabetes Federation Diabetes Atlas”. In: Diabetes research and clinical practice 157 (2019), p. 107843. [4] Jessica Beagley et al. “Global estimates of undiagnosed diabetes in adults”. In: Diabetes research and clinical practice 103.2 (2014), pp. 150–160. [5] Melanie J Davies et al. “Management of hyperglycemia in type 2 diabetes, 2018. A consensus report by the American Diabetes Association (ADA) and the European Association for the Study of Diabetes (EASD)”. In: Diabetes care 41.12 (2018), pp. 2669–2701. CBMS 2022 Abhinandan Panda December 5, 2022 26/28
  • 29. Introduction ECG Proposed monitoring system Policies Mining RV Monitor Experimental results & Comparison Conclusion & Future Works References References References II [6] Jukka Lipponen et al. “Dynamic estimation of cardiac repolarization characteristics during hypoglycemia in healthy and diabetic subjects”. In: Physiological measurement 32 (June 2011), pp. 649–60. doi: 10.1088/0967-3334/32/6/003. [7] U Rajendra Acharya et al. “An integrated diabetic index using heart rate variability signal features for diagnosis of diabetes”. In: Computer methods in biomechanics and biomedical engineering 16.2 (2013), pp. 222–234. [8] Lee Wei Jian and Teik-Cheng Lim. “Automated detection of diabetes by means of higher order spectral features obtained from heart rate signals”. In: Journal of medical imaging and health informatics 3.3 (2013), pp. 440–447. [9] U Rajendra Acharya et al. “Computer-aided diagnosis of diabetic subjects by heart rate variability signals using discrete wavelet transform method”. In: Knowledge-based systems 81 (2015), pp. 56–64. CBMS 2022 Abhinandan Panda December 5, 2022 27/28
  • 30. Introduction ECG Proposed monitoring system Policies Mining RV Monitor Experimental results & Comparison Conclusion & Future Works References References References III [10] Ram Bilas Pachori et al. “An improved online paradigm for screening of diabetic patients using RR-interval signals”. In: Journal of Mechanics in Medicine and Biology 16.01 (2016), p. 1640003. [11] Goutham Swapna, Soman Kp, and Ravi Vinayakumar. “Automated detection of diabetes using CNN and CNN-LSTM network and heart rate signals”. In: Procedia computer science 132 (2018), pp. 1253–1262. [12] Andreas Bauer, Martin Leucker, and Christian Schallhart. “Runtime Verification for LTL and TLTL”. In: ACM Trans. Softw. Eng. Methodol. 20.4 (Sept. 2011), 14:1–14:64. issn: 1049-331X. [13] Jiapu Pan and Willis J Tompkins. “A real-time QRS detection algorithm”. In: IEEE transactions on biomedical engineering 3 (1985), pp. 230–236. [14] Srinivas Pinisetty et al. “Runtime enforcement of cyber-physical systems”. In: ACM Transactions on Embedded Computing Systems (TECS) 16.5s (2017), pp. 1–25. CBMS 2022 Abhinandan Panda December 5, 2022 28/28