Pulse ID: The Case for Robustness of ECG as a Biometric Identifier

Chandrashekhar, Vishnu; Singh, Prerna; Paralkar, Mihir; Tonguz, O.K.

doi:10.1109/mlsp49062.2020.9231814

Cited by 8 publications

(6 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The promulgation of a Unique patient identifier legislation was blocked by congress in the US ( 33 ). Similarly, Electrocardiogram (ECG) signals have been used to encode unique signatures to identify an individual patient uniquely ( 34 ). Other biometrics like finger print in Nigeria ( 35 ) and Iris biometric identification in Kenya ( 36 ), Biometric patient identification and management ( 37 ).…”

Section: Resultsmentioning

confidence: 99%

Scaling up a decentralized offline patient ID generation and matching algorithm to accelerate universal health coverage: Insights from a literature review and health facility survey in Nigeria

Chukwu

Ekong

Garg

2022

Front. Digit. Health

View full text Add to dashboard Cite

BackgroundQuality of health service delivery data remains sub-optimal in many Low and middle-income countries (LMICs) despite over a decade of progress in digitization and Health Management Information Systems (HMIS) improvements. Identifying everyone residing in a country utilizing universal civil registration and/or national unique identification number systems especially for vulnerable patients seeking care within the care continuum is an essential part of pursuing universal health coverage (UHC). Many different strategies or candidate digital technologies exist for uniquely identifying and tracking patients within a health system, and the different strategies also have their advantages and trade-offs. The recent approval of Decentralized identifier (DID) core specification by World Wide Web Consortium (W3C) heralds the search for consensus on standard interoperable DID methods.ObjectiveThis paper aims to: (1) assess how candidate Patient Identification Systems fit the digital Patient ID desirable attributes framework in literature; and (2) use insights from Nigeria to propose the scale-up of an offline, interoperable decentralized Patient ID generation and a matching model for addressing network reliability challenges of centralized electronic registries in LMICs.MethodsWe combined: (i) systematic review of the literature to identify the characteristics of leading candidates for Patient ID systems, with (ii) review of policies and (iii) quantitative survey of 14 general hospitals in Nigeria's Federal Capital Territory to understand the model(s) of patient ID strategies currently implemented by public hospitals.ResultsEvidence from the literature review and quantitative survey showed that no current Patient ID strategy in Nigeria simultaneously meets the six attributes of uniqueness, unchanging, uncontroversial, inexpensive, ubiquitous, and uncomplicated required for ensuring the reliability of unique patient identification systems and of the HMIS more generally.ConclusionsThe findings are used to propose a model of algorithms for universal-offline Patient ID generation and matching models that is cost effective and can be easily scaled-up throughout Nigeria. The prototype has promise for generating and validating a universally unique Patient ID given a set of patient characteristics without a central rigid authority. The model can also help to fast-track the implementation of a Master Patient Index (MPI) and interoperability of existing digital health platforms in LMICs.

show abstract

Section: Resultsmentioning

confidence: 99%

Scaling up a decentralized offline patient ID generation and matching algorithm to accelerate universal health coverage: Insights from a literature review and health facility survey in Nigeria

Chukwu

Ekong

Garg

2022

Front. Digit. Health

View full text Add to dashboard Cite

show abstract

“…For instance, many contemporary ECG signal recognition algorithms were developed using public ECG datasets. Furthermore, most of these ECG datasets are collected in clinical settings using medical-grade sensors in a controlled environment [31]. Therefore, it is inappropriate for wearable gadgets [32].…”

Section: Related Workmentioning

confidence: 99%

“…Therefore, it is inappropriate for wearable gadgets [32]. In addition, wearable systems using time variability for ECG biometric detection have only been the focus of a small number of studies in [28,31,33,34]. Besides, only work in [33,34] have developed a wearable ECG biometric model incorporating smart textile shirts in their study.…”

Section: Related Workmentioning

confidence: 99%

ECG in Real World Scenario: Time Variability in Biometric Using Wearable Smart Textile Shirts

Muhammad Muizz Mohd Nawawi,

Khairul Azami Sidek,

Amelia Wong Azman

2024

ARASET

View full text Add to dashboard Cite

Biomedical signals, such as an electrocardiogram (ECG), have been included in wearable platforms for biometric reasons due to the rapid expansion of apps and technology capable of gathering this physiological data. Most studies using ECG biometrics are conducted in clinical settings, which is impractical for wearable ECG-based biometric applications. Therefore, this study aims to determine the reliability of ECG signals obtained from the commercially available Hexoskin Proshirt and HeartIn Fit shirt, which may be worn for biometric verification in real-world scenarios. ECG data from 22 participants were collected over a span period of more than 30 days. The raw ECG signal is first pre-processed in the time domain using noise-removal Butterworth filters, and then a successful QRS segmented feature extraction method is used. Not to mention, 300 datasets were used to test the recommended recognition method using a Quadratic Support Vector Machine (QSVM). In comparison, around 854 datasets were prepared for training and validation of the classifier. The findings showed that the proposed method provided a considerable accuracy above 99.63 % with a FAR of 0.14 %, an FRR of 2.86 %, and a TPR of 97.14 %. Thus, the study supports using ECG biometrics for verification in real-world settings by employing a smart textile shirt with varying temporal variability.

show abstract

“…Many proposals can also be found that use Machine Learning (ML) or DL algorithms to perform user identification and classification. Some of the most promising algorithms tested for user identification could be some of the ML algorithms such as Support Vectors Machine (SVM) [72,102,103], a Random Forest [104,105] or Logistic Regression [106,107], other deep learning algorithms as a k-Nearest Neighbour (k-NN) [108,109,110] or any Neural Network (NN) [93,111,112,113,114].…”

Section: The Process Of Ekg Identificationmentioning

confidence: 99%

ELEKTRA: ELEKTRokardiomatrix application to biometric identification with convolutional neural networks

Fuster-Barceló

Peris-López²,

Cámara³

2022

Neurocomputing

View full text Add to dashboard Cite

Pulse ID: The Case for Robustness of ECG as a Biometric Identifier

Cited by 8 publications

References 7 publications

Scaling up a decentralized offline patient ID generation and matching algorithm to accelerate universal health coverage: Insights from a literature review and health facility survey in Nigeria

Scaling up a decentralized offline patient ID generation and matching algorithm to accelerate universal health coverage: Insights from a literature review and health facility survey in Nigeria

ECG in Real World Scenario: Time Variability in Biometric Using Wearable Smart Textile Shirts

ELEKTRA: ELEKTRokardiomatrix application to biometric identification with convolutional neural networks

Contact Info

Product

Resources

About