IP Library › Granted Patent US 12,383,206
Granted Patent B2
US 12,383,206 · App. 17/923,958 · Granted Aug 12, 2025

System and method for testing for SARS-COV-2/COVID-19 based on wearable medical sensors and neural networks

Inventors: Shayan Hassantabar (Ewing, NJ); Niraj K. Jha (Princeton, NJ)
Assignee: THE TRUSTEES OF PRINCETON UNIVERSITY
A61B5/7267A61B5/0205A61B5/0533G16H10/20G16H50/80
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,383,206
App. No.
17/923,958
Granted
Aug 12, 2025
Kind
B2
Abstract

According to various embodiments, a machine-learning based system for coronavirus detection is disclosed. The system includes one or more processors configured to interact with a plurality of wearable medical sensors (WMSs). The processors are configured to receive physiological data from the WMSs and questionnaire data from a user interface. The processors are further configured to train at least one neural network based on raw physiological data and questionnaire data augmented with synthetic data and subjected to a grow-and-prune paradigm to generate at least one coronavirus inference model. The processors are also configured to output a coronavirus-based decision by inputting the received physiological data and questionnaire data into the generated coronavirus inference model.

Claims (58)

1. A machine-learning based system for coronavirus detection, comprising one or more processors configured to interact with a plurality of wearable medical sensors (WMSs), the processors configured to:

receive physiological data from the WMSs and questionnaire data from a user interface;

train at least one neural network based on raw physiological data and questionnaire data augmented with synthetic data and subjected to a grow-and-prune paradigm to generate at least one coronavirus inference model; and

output a coronavirus-based decision by inputting the received physiological data and questionnaire data into the generated coronavirus inference model,

wherein the grow-and-prune paradigm comprises the neural network growing at least one of connections and neurons based on gradient information and pruning away at least one of connections and neurons based on magnitude information, and

wherein the growing at least one of connections and neurons based on gradient information comprises adding connection or neuron when its gradient magnitude is greater than a predefined percentile of gradient magnitudes based on a growth ratio.

2. The system of claim 1 , wherein the physiological data comprises at least one of Galvanic skin response and inter-beat interval.

3. The system of claim 2 , wherein inter-beat interval indicates at least one of heart rate, skin temperature, oxygen saturation, and blood pressure.

4. The system of claim 1 , wherein questionnaire data comprises yes/no answers for at least one of immunocompromised, chronic lung disease, cough, shortness of breath, chills, fever, muscle pain, headache, sore throat, smell-taste loss, and diarrhea.

5. The system of claim 1 , wherein the pruning away at least one of connections and neurons based on magnitude information comprises removing a connection or neuron when its magnitude is less than a predefined percentile of magnitudes based on a pruning ratio.

6. The system of claim 1 , wherein the grow-and-prune paradigm is iterative.

7. The system of claim 1 , wherein outputting a coronavirus-based decision comprises data preprocessing, synthetic data generation and neural network pre-training, grow-and-prune synthesis, and output generation.

8. The system of claim 7 , wherein data preprocessing comprises data normalization and data alignment.

9. The system of claim 7 , wherein synthetic data generation comprises using at least one of multi-variate normal distribution, Gaussian mixture model, and kernel density estimation.

10. The system of claim 7 , wherein synthetic data generation comprises building a knowledge base based on the raw physiological data and questionnaire data.

11. A machine-learning based method for coronavirus detection, based on one or more processors configured to interact with a plurality of wearable medical sensors (WMSs), the method comprising:

receiving physiological data from the WMSs and questionnaire data from a user interface;

training at least one neural network based on raw physiological data and questionnaire data augmented with synthetic data and subjected to a grow-and-prune paradigm to generate at least one coronavirus inference model; and

outputting a coronavirus-based decision by inputting the received physiological data and questionnaire data into the generated coronavirus inference model,

wherein the grow-and-prune paradigm comprises the neural network growing at least one of connections and neurons based on gradient information and pruning away at least one of connections and neurons based on magnitude information, and

wherein the growing at least one of connections and neurons based on gradient information comprises adding connection or neuron when its gradient magnitude is greater than a predefined percentile of gradient magnitudes based on a growth ratio.

12. The method of claim 11 , wherein the physiological data comprises at least one of Galvanic skin response and inter-beat interval.

13. The method of claim 12 , wherein inter-beat interval indicates at least one of heart rate, skin temperature, oxygen saturation, and blood pressure.

14. The method of claim 11 , wherein questionnaire data comprises yes/no answers for at least one of immunocompromised, chronic lung disease, cough, shortness of breath, chills, fever, muscle pain, headache, sore throat, smell-taste loss, and diarrhea.

15. The method of claim 11 , wherein the pruning away at least one of connections and neurons based on magnitude information comprises removing a connection or neuron when its magnitude is less than a predefined percentile of magnitudes based on a pruning ratio.

16. The method of claim 11 , wherein the grow-and-prune paradigm is iterative.

17. The method of claim 11 , wherein outputting a coronavirus-based decision comprises data preprocessing, synthetic data generation and neural network pre-training, grow-and-prune synthesis, and output generation.

18. The method of claim 17 , wherein data preprocessing comprises data normalization and data alignment.

19. The method of claim 17 , wherein synthetic data generation comprises using at least one of multi-variate normal distribution, Gaussian mixture model, and kernel density estimation.

20. The method of claim 17 , wherein synthetic data generation comprises building a knowledge base based on the raw physiological data and questionnaire data.

21. A non-transitory computer-readable medium having stored thereon a computer program for execution by a processor configured to perform a machine-learning based method for coronavirus detection, the method comprising:

receiving physiological data from the WMSs and questionnaire data from a user interface;

training at least one neural network based on raw physiological data and questionnaire data augmented with synthetic data and subjected to a grow-and-prune paradigm to generate at least one coronavirus inference model; and

outputting a coronavirus-based decision by inputting the received physiological data and questionnaire data into the generated coronavirus inference model,

wherein the grow-and-prune paradigm comprises the neural network growing at least one of connections and neurons based on gradient information and pruning away at least one of connections and neurons based on magnitude information, and

wherein the growing at least one of connections and neurons based on gradient information comprises adding connection or neuron when its gradient magnitude is greater than a predefined percentile of gradient magnitudes based on a growth ratio.

22. The non-transitory computer-readable medium of claim 21 , wherein the physiological data comprises at least one of Galvanic skin response and inter-beat interval.

23. The non-transitory computer-readable medium of claim 22 , wherein inter-beat interval indicates at least one of heart rate, skin temperature, oxygen saturation, and blood pressure.

24. The non-transitory computer-readable medium of claim 21 , wherein questionnaire data comprises yes/no answers for at least one of immunocompromised, chronic lung disease, cough, shortness of breath, chills, fever, muscle pain, headache, sore throat, smell-taste loss, and diarrhea.

25. The non-transitory computer-readable medium of claim 21 , wherein the pruning away at least one of connections and neurons based on magnitude information comprises removing a connection or neuron when its magnitude is less than a predefined percentile of magnitudes based on a pruning ratio.

26. The non-transitory computer-readable medium of claim 21 , wherein the grow-and-prune paradigm is iterative.

27. The non-transitory computer-readable medium of claim 21 , wherein outputting a coronavirus-based decision comprises data preprocessing, synthetic data generation and neural network pre-training, grow-and-prune synthesis, and output generation.

28. The non-transitory computer-readable medium of claim 27 , wherein data preprocessing comprises data normalization and data alignment.

29. The non-transitory computer-readable medium of claim 27 , wherein synthetic data generation comprises using at least one of multi-variate normal distribution, Gaussian mixture model, and kernel density estimation.

30. The non-transitory computer-readable medium of claim 27 , wherein synthetic data generation comprises building a knowledge base based on the raw physiological data and questionnaire data.

31. A machine-learning based system for coronavirus detection, comprising one or more processors configured to interact with a plurality of wearable medical sensors (WMSs), the processors configured to:

receive physiological data from the WMSs and questionnaire data from a user interface;

train at least one neural network based on raw physiological data and questionnaire data augmented with synthetic data to generate at least one coronavirus inference model; and

output a coronavirus-based decision by inputting the received physiological data and questionnaire data into the generated coronavirus inference model,

wherein the grow-and-prune paradigm comprises the neural network growing at least one of connections and neurons based on gradient information and pruning away at least one of connections and neurons based on magnitude information, and

wherein the growing at least one of connections and neurons based on gradient information comprises adding connection or neuron when its gradient magnitude is greater than a predefined percentile of gradient magnitudes based on a growth ratio.

32. The system of claim 31 , wherein the physiological data comprises at least one of Galvanic skin response and inter-beat interval.

33. The system of claim 32 , wherein inter-beat interval indicates at least one of heart rate, skin temperature, oxygen saturation, and blood pressure.

34. The system of claim 31 , wherein questionnaire data comprises yes/no answers for at least one of immunocompromised, chronic lung disease, cough, shortness of breath, chills, fever, muscle pain, headache, sore throat, smell-taste loss, and diarrhea.

35. The system of claim 31 , wherein outputting a coronavirus-based decision comprises data preprocessing, synthetic data generation and neural network pre-training, and output generation.

36. The system of claim 35 , wherein data preprocessing comprises data normalization and data alignment.

37. The system of claim 35 , wherein synthetic data generation comprises using at least one of multi-variate normal distribution, Gaussian mixture model, and kernel density estimation.

38. The system of claim 35 , wherein synthetic data generation comprises building a knowledge base based on the raw physiological data and questionnaire data.

Assignments (2)
CONFIRMATORY LICENSE Recorded Jan 31, 2025
From: PRINCETON UNIVERSITY
To: NATIONAL SCIENCE FOUNDATION
Reel/Frame 070075/0938 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 16, 2023
From: HASSANTABAR, SHAYAN; JHA, NIRAJ
To: THE TRUSTEES OF PRINCETON
Reel/Frame 063003/0607 →
Continuity (3)
Provisional Application 63022997 · May 11, 2020
Provisional Application 63053912 · Jul 20, 2020
Related Publication 20230181120A1 · Jun 15, 2023
References Cited (49)
US 20140247151A1 · Proud et al. · 2014 [cited by applicant]
US 20180353085A1 · Olivero · 2018 [cited by applicant]
Thomas, Journal of Biomedical Informatics, Apr. 2021, pp. 1-22. [cited by examiner]
Pratama, Neurocomputing, 2017, pp. 4-27. [cited by examiner]
Dail, ArXiv, 2018, pp. 1-13. [cited by examiner]
International Search Report and Written Opinion for corresponding PCT Application No. PCT/US2021/028088, dated Jul. 16, 2021. [cited by applicant]
Landi, “Boston startup using AI, remote monitoring to fight coronavirus”, fiercehealthcare.com, [online] [retrieved on Jun. 16, 2021 (Jun. 16, 2021)) Retrieved from the Internet < URL: https://www.fiercehealthcare.com/t… [cited by applicant]
Yin et al., “DiabDeep: Pervasive Diabetes Diagnosis based on Wearable Medical Sensors and Efficient NeuralNetworks”, Cornell University Library/Computer Science/Computer Vision and Pattern Recognition, (online) (retriev… [cited by applicant]
Hassantabar et al., “SCANN: Synthesis of compact and accurate neural networks”, arXiv preprint arXiv.1904.09090, 2019. [cited by applicant]
Dai et al., “NeST: A neural network synthesis tool based on a grow-and-prune paradigm”, IEEE Trans. Computers, vol. 68, No. 10, pp. 1487-1497, Oct. 2019. [cited by applicant]
Hassantabar, Shayan et al., “TUTOR: Training Neural Networks Using Decision Rules as Model Priors,” arXiv:2010.05429, Oct. 2020. [cited by applicant]
Hassantabar, Shayan et al., “SCANN: Synthesis of compact and accurate neural networks,” arXiv: 1904.09090, Apr. 2019. [cited by applicant]
Dai, Xiaoliang et al., “NeST: A neural network synthesis tool based on a grow-and-prune paradigm”, IEEE Trans. Computers, vol. 68, No. 10, pp. 1487-1497, Oct. 2019. [cited by applicant]
Dheda, Keertan et al., “Diagnosis of COVID-19: Considerations, Controversies and Challenges in South Africa,” Wits Journal of Clinical Medicine, vol. 2, No. SI, pp. 3-10, 2020. [cited by applicant]
Bullock, Joseph et al., “Mapping the landscape of artificial intelligence applications against COVID-19,” Journal of Artificial Intelligence Research, vol. 69, pp. 807-845, Nov. 2020. [cited by applicant]
Farooq, Muhammad and Hafeez, Abdul, “COVID-ResNet: A Deep Learning Framework for Screening of COVID19 from Radiographs,” arXiv:2003.14395, 2020. [cited by applicant]
Wang, Linda et al., “COVID-Net: A tailored deep convolutional neural network design for detection of COVID-19 cases from chest radiography images,” Scientific Reports, vol. 10, No. 19549, 2020. [cited by applicant]
Giovagnoni, A. and Agostini, A., “Diagnosi radiologica e prevenzione della diffusione di COVID-19 nei dipartmenti di radiologia,” SIRM, 2020, online: https://www.sirm.org/wp-content/uploads/2020/03/SIRM-Covid-19.pdf. [cited by applicant]
Zhang, Jianpeng et al., “COVID-19 Screening on Chest X-ray Images Using Deep Learning based Anomaly Detection,” arXiv:2003.12338v1, Mar. 27, 2020. [cited by applicant]
Narin, Ali et al., “Automatic detection of coronavirus disease (COVID-19) using X-ray images and deep convolutional neural networks,” Pattern Analysis and Applications, vol. 24, pp. 1207-1220, May 9, 2021. [cited by applicant]
Abbas, Asmaa et al., “Classification of COVID-19 in chest X-ray images using DeTraC deep convolutional neural network,” Applied Intelligence, vol. 51, pp. 854-864, Sep. 5, 2020. [cited by applicant]
Hall, Lawrence O. et al., “Finding COVID-19 from Chest X-rays using Deep Learning on a Small Dataset,” arXiv:2004.02060, 2020. [cited by applicant]
Sethy, Prabira Kumar and Behera, Santi Kumari, “Detection of coronavirus disease (COVID-19) based on Deep Features,” Preprints, vol. 2020030300, 2020. [cited by applicant]
Li, Lin et al., “Artificial Intelligence Distinguishes COVID-19 from Community Acquired Pneumonia on Chest CT,” Radiology, p. 200905, 2020. [cited by applicant]
Gozes, Ophir et al., “Rapid AI development cycle for the coronavirus (COVID-19) pandemic: Initial results for automated detection & patient monitoring using deep learning CT image analysis,” arXiv:2003.05037, 2020. [cited by applicant]
Apostolopoulos, Ioannis D. and Mpesiana, Tzani A., “COVID-19: Automatic detection from X-ray images utilizing transfer learning with convolutional neural networks,” Physical and Engineering Sciences in Medicine, vol. 43… [cited by applicant]
Wang, Shuo et al., “A fully automatic deep learning system for COVID-19 diagnostic and prognostic analysis,” European Respiratory Journal, vol. 56, No. 2000775, 2020. [cited by applicant]
Afshar, Parnian et al., “COVID-CAPS: A capsule network-based framework for identification of COVID-19 cases from X-ray images,” Pattern Recognition Letters, vol. 138, pp. 638-643, Sep. 16, 2020. [cited by applicant]
Kalkreuth, Roman and Kaufmann, Paul, “COVID-19: A Survey on Public Medical Imaging Data Resources,” arXiv:2004.04569v2, May 9, 2020. [cited by applicant]
Cohen, Joseph Paul et al., “COVID-19 Image Data Collection,” arXiv:2003.11597v1, Mar. 25, 2020. [cited by applicant]
Lin, MD, Liaoyi et al., “CT Manifestations of Coronavirus Disease (COVID-19) Pneumonia and Influenza Virus Pneumonia: A Comparative Study,” AJR, vol. 216, pp. 71-79, Jul. 9, 2020. [cited by applicant]
Imran, Ali et al., “AI4COVID-19: AI enabled preliminary diagnosis for COVID-19 from cough samples via an app,” Informatics in Medicine Unlocked, vol. 20, No. 100378, Jun. 26, 2020. [cited by applicant]
Sandler, Mark et al., “MobileNetV2: Inverted Residuals and Linear Bottlenecks,” arXiv:1801.04381v4, Mar. 21, 2019. [cited by applicant]
Ma, Ningning et al., “ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design,” arXiv: 1807.11164v1, Jul. 30, 2018. [cited by applicant]
Wu, Bichen et al., “Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions,” arXiv:1711.08141v2, Dec. 3, 2017. [cited by applicant]
Dai, Xiaoliang et al., “ChamNet: Towards Efficient Network Design through Platform-Aware Model Adaptation,” arXiv: 1812.08934v1, Dec. 21, 2018. [cited by applicant]
Hassantabar, Shayan et al., “Steerage: Synthesis of Neural Networks Using Architecture Search and Grown-and-Prune Methods,” arXiv: 1912.05831v1, Dec. 12, 2019. [cited by applicant]
Han, Song et al., “Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding,” arXiv: 1510.00149v5, Feb. 15, 2016. [cited by applicant]
Han, Song et al., “ESE: Efficient Speech Recognition Engine with Sparse LSTM on FPGA,” arXiv: 1612.00694v2, Feb. 20, 2017. [cited by applicant]
Dai, Xiaoliang et al., “Grow and Prune Compact, Fast, and Accurate LSTMs,” arXiv: 1805.11797v2, May 31, 2018. [cited by applicant]
Zhu, Chenzhuo et al., “Trained Ternary Quantization,” arXiv: 1612.01064v3, Feb. 23, 2017. [cited by applicant]
Krizhevsky, Alex et al., “ImageNet Classification with Deep Convolutional Neural Networks,” Proceedings of Advances in Neural Information Processing Systems, pp. 1097-1105, 2012. [cited by applicant]
Grossberg, Stephen, “Nonlinear Neural Networks: Principles, Mechanisms, and Architectures,” Neural Networks, vol. 1, pp. 17-61, 1988. [cited by applicant]
World Health Organization and Others, “Coronavirus disease 2019 (COVID-19): Situation report—72,” Apr. 1, 2020, online: https://apps.who.int/iris/bitstream/handle/10665/331685/nCoVsitrep01Apr2020-eng.pdf. [cited by applicant]
Mahase, Elisabeth, “Coronavirus: covid-19 has killed more people than SARS and MERS combined, despite lower case fatality rate,” The British Medical Journal, vol. 368, Feb. 18, 2020. [cited by applicant]
Nicola, Maria et al., “The socio-economic implications of the coronavirus pandemic (COVID-19): A review,” International Journal of Surgery, vol. 78, pp. 185-193, 2020. [cited by applicant]
Butt, Charmaine et al., “Deep learning system to screen coronavirus disease 2019 pneumonia,” Applied Intelligence, Apr. 22, 2020. [cited by applicant]
Yin, Hongxu and Jha, Niraj K., “A Health Decision Support System for Disease Diagnosis Based on Wearable Medical Sensors and Machine Learning Ensembles,” IEEE Transactions on Multi-Scale Computing Systems, vol. 3, No. 4… [cited by applicant]
Wang, Lucy Lu et al., “CORD-19: The COVID-19 Open Research Dataset,” arXiv:2004.10706v4, Jul. 10, 2020. [cited by applicant]