Prashanth Shyam Kumar
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Prashanth Shyam Kumar has a total of 36 co-authors. Here are the top co-authors by number of shared publications:
Vijay K. Varadan
The Pennsylvania State Univ. (United States)
21 shared publicationsPratyush Rai
Nanowear Inc., Brooklyn, USA
14 shared publicationsSechang Oh
University of Arkansas
13 shared publicationsMouli Ramasamy
The Pennsylvania State University
10 shared publicationsHyeokjun Kwon
Univ. of Arkansas (United States)
8 shared publicationsGyanesh N. Mathur
Univ. of Arkansas (United States) and Global Institute of Nanotechnology (United States)
4 shared publications
Latest Publications
- 1 January 2024
- Published by Springer Nature
- p. 333-349
Identification of Tear-Based Protein Biomarkers: Its Application
- 1 January 2024
- Published by Springer Nature
- p. 333-349
Identification of Tear-Based Protein Biomarkers: Its Application
- 1 January 2024
- Published by Springer Nature
- p. 351-368
Engineering a Signal Transduction Mechanism for Protein-Based Biosensors
- 1 January 2024
- Published by Springer Nature
- p. 351-368
Engineering a Signal Transduction Mechanism for Protein-Based Biosensors
- Open Access
A Comparison of Personalized and Generalized LSTM Neural Networks for Deriving VCG from 12-Lead ECG
Vectorcardiography (VCG) is a valuable diagnostic tool that complements the standard 12-lead ECG by offering additional spatiotemporal information to clinicians. However, due to the need for additional measurement hardware and too many electrodes in a clinical scenario if performed along with a standard 12-lead, there is a need to find methods to derive the VCG from the ECG. We have evaluated the use of Long Short-term Memory (LSTM) neural networks to learn the transformation from 12-lead ECG to VCG that is applicable across subjects and for each subject. We refer to these networks as generalized and personalized, respectively. We calculated the Root Mean Square Error (RMSE), R2, and Pearson correlation coefficient to compare waveforms of derived and actual VCG. We also extracted and compared diagnostic parameters from VCG, namely the QRS-loop magnitude, T-loop magnitude, and QRS-T spatial angle, from actual and derived VCGs using the Pearson correlation coefficient and Bland Altman limits of agreement. The personalized models performed better than generalized models in waveform comparisons and in the error of extracted diagnostic parameters from VCG waveforms. The use of personalized transformations for the derivation of VCG from standard 12-lead has the potential to improve and augment the diagnostic yield and accuracy of a standard 12-lead interpretation.
Open AccessA Comparison of Personalized and Generalized LSTM Neural Networks for Deriving VCG from 12-Lead ECG
Vectorcardiography (VCG) is a valuable diagnostic tool that complements the standard 12-lead ECG by offering additional spatiotemporal information to clinicians. However, due to the need for additional measurement hardware and too many electrodes in a clinical scenario if performed along with a standard 12-lead, there is a need to find methods to derive the VCG from the ECG. We have evaluated the use of Long Short-term Memory (LSTM) neural networks to learn the transformation from 12-lead ECG to VCG that is applicable across subjects and for each subject. We refer to these networks as generalized and personalized, respectively. We calculated the Root Mean Square Error (RMSE), R2, and Pearson correlation coefficient to compare waveforms of derived and actual VCG. We also extracted and compared diagnostic parameters from VCG, namely the QRS-loop magnitude, T-loop magnitude, and QRS-T spatial angle, from actual and derived VCGs using the Pearson correlation coefficient and Bland Altman limits of agreement. The personalized models performed better than generalized models in waveform comparisons and in the error of extracted diagnostic parameters from VCG waveforms. The use of personalized transformations for the derivation of VCG from standard 12-lead has the potential to improve and augment the diagnostic yield and accuracy of a standard 12-lead interpretation.
- Open Access
Personalized LSTM Models for ECG Lead Transformations Led to Fewer Diagnostic Errors Than Generalized Models: Deriving 12-Lead ECG from Lead II, V2, and V6
Background and Objective: The prevalence of chronic cardiovascular diseases (CVDs) has risen globally, nearly doubling from 1990 to 2019. ECG is a simple, non-invasive measurement that can help identify CVDs at an early and treatable stage. A multi-lead ECG, up to 15 leads in a wearable form factor, is desirable. We seek to derive multiple ECG leads from a select subset of leads so that the number of electrodes can be reduced in line with a patient-friendly wearable device. We further compare personalized derivations to generalized derivations. Methods: Long-Short Term Memory (LSTM) networks using Lead II, V2, and V6 as input are trained to obtain generalized models using Bayesian Optimization for hyperparameter tuning for all patients and personalized models for each patient by applying transfer learning to the generalized models. We compare quantitatively using error metrics Root Mean Square Error (RMSE), R2, and Pearson correlation (ρ). We compare qualitatively by matching ECG interpretations of board-certified cardiologists. Results: ECG interpretations from personalized models, when corrected for an intra-observer variance, were identical to the original ECGs, whereas generalized models led to errors. Mean performance values for generalized and personalized models were (RMSE-74.31 µV, R2-72.05, ρ-0.88) and (RMSE-26.27 µV, R2-96.38, ρ-0.98), respectively. Conclusions: Diagnostic accuracy based on derived ECG is the most critical validation of ECG derivation methods. Personalized transformation should be sought to derive ECGs. Performing a personalized calibration step to wearable ECG systems and LSTM networks could yield ambulatory 15-lead ECGs with accuracy comparable to clinical ECGs.
Open AccessPersonalized LSTM Models for ECG Lead Transformations Led to Fewer Diagnostic Errors Than Generalized Models: Deriving 12-Lead ECG from Lead II, V2, and V6
Background and Objective: The prevalence of chronic cardiovascular diseases (CVDs) has risen globally, nearly doubling from 1990 to 2019. ECG is a simple, non-invasive measurement that can help identify CVDs at an early and treatable stage. A multi-lead ECG, up to 15 leads in a wearable form factor, is desirable. We seek to derive multiple ECG leads from a select subset of leads so that the number of electrodes can be reduced in line with a patient-friendly wearable device. We further compare personalized derivations to generalized derivations. Methods: Long-Short Term Memory (LSTM) networks using Lead II, V2, and V6 as input are trained to obtain generalized models using Bayesian Optimization for hyperparameter tuning for all patients and personalized models for each patient by applying transfer learning to the generalized models. We compare quantitatively using error metrics Root Mean Square Error (RMSE), R2, and Pearson correlation (ρ). We compare qualitatively by matching ECG interpretations of board-certified cardiologists. Results: ECG interpretations from personalized models, when corrected for an intra-observer variance, were identical to the original ECGs, whereas generalized models led to errors. Mean performance values for generalized and personalized models were (RMSE-74.31 µV, R2-72.05, ρ-0.88) and (RMSE-26.27 µV, R2-96.38, ρ-0.98), respectively. Conclusions: Diagnostic accuracy based on derived ECG is the most critical validation of ECG derivation methods. Personalized transformation should be sought to derive ECGs. Performing a personalized calibration step to wearable ECG systems and LSTM networks could yield ambulatory 15-lead ECGs with accuracy comparable to clinical ECGs.
- Open Access
- 25 August 2022
- Published by MDPI AG in Electronics
- Vol. 11 (17) , 2655
Evaluation of Signal Quality from a Wearable Phonocardiogram (PCG) Device and Personalized Calibration
Currently, the only clinically utilized Phonocardiogram (PCG) is an electronic stethoscope used in a hospital or clinical environment. The availability of continuously recorded PCGs can provide a new avenue of research into chronic disease management at home. Researchers have proposed such wearable PCG devices. However, limitations exist in evaluating such devices as PCG recording devices in home-like environments. Here, we evaluate a wearable PCG system in a belt-type form factor with an embedded force sensor, accelerometer, and a single lead ECG to study the feasibility of acquiring diagnostic-grade PCGs while the wearer performs daily activities. We describe qualitative and quantitative exploratory analysis methods for cross-subject comparison of PCG signal quality, wearer comfort, and the impact of activities using Signal-to-Noise (SNR) comparisons and cross-spectral coherence between activity and PCG. The analysis of the data suggests that a common user-chosen method of donning a wearable PCG is not applicable across subjects for obtaining optimal PCG recording quality. We propose a method to calibrate wearable PCG devices using an embedded force sensor and by following a protocol involving feedback from the embedded force sensor to determine the optimal method of wearing the device. Following a similar path to precision medicine using genomic data and the extrapolation of risk, wearable devices with healthcare applications should be developed with the ability to be adapted and calibrated to each individual. In the immediate future this may involve calibration procedures such as those followed in this work, using controlled measurements performed with each patient to tune a device for them.
- 25 August 2022
- Published by MDPI AG in Electronics
- Vol. 11 (17) , 2655
Open AccessEvaluation of Signal Quality from a Wearable Phonocardiogram (PCG) Device and Personalized Calibration
Currently, the only clinically utilized Phonocardiogram (PCG) is an electronic stethoscope used in a hospital or clinical environment. The availability of continuously recorded PCGs can provide a new avenue of research into chronic disease management at home. Researchers have proposed such wearable PCG devices. However, limitations exist in evaluating such devices as PCG recording devices in home-like environments. Here, we evaluate a wearable PCG system in a belt-type form factor with an embedded force sensor, accelerometer, and a single lead ECG to study the feasibility of acquiring diagnostic-grade PCGs while the wearer performs daily activities. We describe qualitative and quantitative exploratory analysis methods for cross-subject comparison of PCG signal quality, wearer comfort, and the impact of activities using Signal-to-Noise (SNR) comparisons and cross-spectral coherence between activity and PCG. The analysis of the data suggests that a common user-chosen method of donning a wearable PCG is not applicable across subjects for obtaining optimal PCG recording quality. We propose a method to calibrate wearable PCG devices using an embedded force sensor and by following a protocol involving feedback from the embedded force sensor to determine the optimal method of wearing the device. Following a similar path to precision medicine using genomic data and the extrapolation of risk, wearable devices with healthcare applications should be developed with the ability to be adapted and calibrated to each individual. In the immediate future this may involve calibration procedures such as those followed in this work, using controlled measurements performed with each patient to tune a device for them.
- Open Access
- 29 July 2022
- Published by Springer Nature in Scientific Reports
- Vol. 12 (1) , 1-11
Multiparametric cloth-based wearable, SimpleSense, estimates blood pressure
Targeted maintenance of blood pressure for hypertensive patients requires accurate monitoring of blood pressure at home. Use of multiparametric vital signs ECG, heart sounds, and thoracic impedance for blood pressure estimation at home has not been reported previously. In an observational multi-site study, 120 subjects (female (N = 61, 52%)) between 18 and 83 years of age were recruited with the following stratification (Normal (20%), prehypertensive (37%), stage 1(26%), and stage 2 (18%). From these subjects, 1686 measurements of blood pressure from a sphygmomanometer were associated with simultaneously acquired signals from the SimpleSense device. An ensemble of tree-based models was trained with inputs as metrics derived from the multiparametric and patient demographics data. A test Mean Absolute Difference (MAD) of ± 6.38 mm of Hg and ± 5.10 mm of Hg were obtained for systolic and diastolic blood pressures (SBP; DBP), respectively. Comparatively, the MAD for wrist-worn blood pressure cuff OMRON BP6350 (GUDID—10073796266353) was ± 8.92 mm of Hg and ± 6.86 mm of Hg, respectively. Machine learning models trained to use multiparametric data can monitor SBP and DBP without the need for calibration, and with accuracy levels comparable to at-home cuff-based blood pressure monitors.
- 29 July 2022
- Published by Springer Nature in Scientific Reports
- Vol. 12 (1) , 1-11
Open AccessMultiparametric cloth-based wearable, SimpleSense, estimates blood pressure
Targeted maintenance of blood pressure for hypertensive patients requires accurate monitoring of blood pressure at home. Use of multiparametric vital signs ECG, heart sounds, and thoracic impedance for blood pressure estimation at home has not been reported previously. In an observational multi-site study, 120 subjects (female (N = 61, 52%)) between 18 and 83 years of age were recruited with the following stratification (Normal (20%), prehypertensive (37%), stage 1(26%), and stage 2 (18%). From these subjects, 1686 measurements of blood pressure from a sphygmomanometer were associated with simultaneously acquired signals from the SimpleSense device. An ensemble of tree-based models was trained with inputs as metrics derived from the multiparametric and patient demographics data. A test Mean Absolute Difference (MAD) of ± 6.38 mm of Hg and ± 5.10 mm of Hg were obtained for systolic and diastolic blood pressures (SBP; DBP), respectively. Comparatively, the MAD for wrist-worn blood pressure cuff OMRON BP6350 (GUDID—10073796266353) was ± 8.92 mm of Hg and ± 6.86 mm of Hg, respectively. Machine learning models trained to use multiparametric data can monitor SBP and DBP without the need for calibration, and with accuracy levels comparable to at-home cuff-based blood pressure monitors.
- 24 April 2017
- Published by SPIE-Intl Soc Optical Eng
- Vol. 10167, 1016703-1016703-8
Wearable nanosensor systems and their applications in healthcare
- 24 April 2017
- Published by SPIE-Intl Soc Optical Eng
- Vol. 10167, 1016703-1016703-8
Wearable nanosensor systems and their applications in healthcare
- 24 April 2017
- Published by SPIE-Intl Soc Optical Eng
- Vol. 10167, 101671
Nanomechanics of carbon nanotubes
This review focusses on introducing the mechanics in carbon nanotubes (CNT), and the major applications of CNT and its composites in biomedicine. It emphasizes the nanomechanics of these materials by reviewing the widely followed experimental methods, theoretical models, simulations, classification, segregation and applications the aforementioned materials. First, several mechanical properties contributing to the classification of the CNT, for various biomedicine applications, are discussed in detail to provide a cursory glance at the uses of CNT. The mechanics of CNT discussed in this paper include: elasticity, stress, tension, compression, nano-scale mechanics. In addition to these basic properties, a brief introduction about nanoscale composites is given. Second, a brief review on some of the major applications of CNT in biomedicine including drug delivery, therapeutics, diagnostics and regenerative medicine is given. © (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
- 24 April 2017
- Published by SPIE-Intl Soc Optical Eng
- Vol. 10167, 101671
Nanomechanics of carbon nanotubes
This review focusses on introducing the mechanics in carbon nanotubes (CNT), and the major applications of CNT and its composites in biomedicine. It emphasizes the nanomechanics of these materials by reviewing the widely followed experimental methods, theoretical models, simulations, classification, segregation and applications the aforementioned materials. First, several mechanical properties contributing to the classification of the CNT, for various biomedicine applications, are discussed in detail to provide a cursory glance at the uses of CNT. The mechanics of CNT discussed in this paper include: elasticity, stress, tension, compression, nano-scale mechanics. In addition to these basic properties, a brief introduction about nanoscale composites is given. Second, a brief review on some of the major applications of CNT in biomedicine including drug delivery, therapeutics, diagnostics and regenerative medicine is given. © (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
- 24 April 2017
- Published by SPIE-Intl Soc Optical Eng
- Vol. 10167, 1016715-1016715-9
Magnetic nanotubes for drug delivery
- 24 April 2017
- Published by SPIE-Intl Soc Optical Eng
- Vol. 10167, 1016715-1016715-9
Magnetic nanotubes for drug delivery
- 24 April 2017
- Published by SPIE-Intl Soc Optical Eng
- Vol. 10167, 1016705-1016705-7
Left lateral decubitus position on patients with atrial fibrillation and congestive heart failure
- 24 April 2017
- Published by SPIE-Intl Soc Optical Eng
- Vol. 10167, 1016705-1016705-7
Left lateral decubitus position on patients with atrial fibrillation and congestive heart failure