On Monetizing Personal Wearable Devices Data: A Blockchain-based Marketplace for Data Crowdsourcing and Federated Machine Learning in Healthcare

Source:
By:Mohamed Emish, Hari Kishore Chaparala, Zeyad Kelani, Sean D. Young

DOI: https://doi.org/10.30564/aia.v4i2.5316

Abstract: Machine learning advancements in healthcare have made data collected through smartphones and wearable devices a vital source of public health and medical insights. While wearable device data helps to monitor, detect, and predict diseases and health conditions, some data owners hesitate to share such sensitive data with companies or researchers due to privacy concerns. Moreover, wearable devices have been recently available as commercial products; thus large, diverse, and representative datasets are not available to most researchers. In this article, we propose an open marketplace where wearable device users securely monetize their wearable device records by sharing data with consumers (e.g., researchers) to make wearable device data more available to healthcare researchers. To secure the data transactions in a privacy-preserving manner, we use a decentralized approach using Blockchain and Non-Fungible Tokens (NFTs). To ensure data originality and integrity with secure validation, our marketplace uses Trusted Execution Environments (TEE) in wearable devices to verify the correctness of health data. The marketplace also allows researchers to train models using Federated Learning with a TEE-backed secure aggregation of data users may not be willing to share. To ensure user participation, we model incentive mechanisms for the Federated Learning-based and anonymized data-sharing approaches using NFTs. We also propose using payment channels and batching to reduce smart contact gas fees and optimize user profits. If widely adopted, we believe that TEE and Blockchain-based incentives will promote the ethical use of machine learning with validated wearable device data in healthcare and improve user participation due to incentives. References:

[1] Dimitrov, D.V., 2016. Medical internet of things and big data in healthcare. Healthcare Informatics Re- search. 22(3), 156.DOI: https://doi.org/10.4258/hir.2016.22.3.156 [2] Elshafeey, A., Mhaimeed, O., Al Ani, J., et al., 2021. Wearable devices and machine learning algorithms for cardiovascular health assessment. Machine Learning in Cardiovascular Medicine. 10(1), 353- 370.DOI: https://doi.org/10.1016/b978-0-12-820273-9.00015-4 [3] Cilliers, L., 2019. Wearable devices in healthcare: Privacy and information security issues. Health In- formation Management Journal. 49(2-3), 150-156.DOI: https://doi.org/10.1177/1833358319851684 [4] Raposo, V.L., 2021. Big brother knows that you are infected: Wearable devices to track potential COVID-19 infections. Law, Innovation and Technol- ogy. 13(2), 422-438.DOI: https://doi.org/10.1080/17579961.2021.1977214 [5] Kostkova, P., Brewer, H., de Lusignan, S., et al., 2016. Who owns the data? Open data for healthcare. Frontiers in Public Health. 17(4), 7. Available from: https://pubmed.ncbi.nlm.nih.gov/26925395/. [6] Seh, A.H., Zarour, M., Alenezi, M., et al., 2020. Healthcare data breaches: Insights and implications. Healthcare. 8(2), 133.DOI: https://doi.org/10.3390/healthcare8020133 [7 Pozzar, R., Hammer, M.J., Underhill-Blazey, M., et al., 2020. Threats of bots and other bad actors to data quality following research participant recruitment through social media: Cross-sectional questionnaire. Journal of Medical Internet Research. 22(10).DOI: https://doi.org/10.2196/23021 [8] Sadowski, J., 2019. When data is capital: Datafica- tion, accumulation, and extraction. Big Data & Soci- ety. 6(1), 205395171882054.DOI: https://doi.org/10.1177/2053951718820549 [9] Huhn, S., Matzke, I., Koch, M., et al., 2022. Using wearable devices to generate real-world, individu- al-level data in rural, low-resource contexts in Burki- na Faso, Africa: A case study. Frontiers in Public Health. 10, 972177.DOI: https://doi.org/10.3389/fpubh.2022.972177 [10] Hayano, J., Yamamoto, H., Nonaka, I., et al., 2020. Quantitative detection of sleep apnea with wearable watch device. Plos One. 15(11), e0237279.DOI: https://doi.org/10.1101/2020.07.24.219261 [11] Sundararajan, K., Georgievska, S., te Lindert, B.H., et al., 2021. Sleep classification from wrist-worn accelerometer data using random forests. Scientific Reports. 11(1).DOI: https://doi.org/10.1038/s41598-020-79217-x [12] Wong, C.K., Ho, D.T., Tam, A.R., et al., 2020. Ar- tificial intelligence mobile health platform for early detection of COVID-19 in quarantine subjects using a wearable biosensor: Protocol for a randomised con- trolled trial. BMJ Open. 10(7).DOI: https://doi.org/10.1136/bmjopen-2020-038555 [13] Un, K.C., Wong, C.K., Lau, Y.M., et al., 2021. Obser- vational study on wearable biosensors and machine learning-based remote monitoring of COVID-19 pa- tients. Scientific Reports. 11(1).DOI: https://doi.org/10.1038/s41598-021-82771-7 [14] Laureanti, R., Bilucaglia, M., Zito, M., et al. (editors), 2020. Emotion assessment using machine learning and low-cost wearable devices. 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC); 2020 Jul 20- 24; Montreal, QC, Canada. USA:IEEE. p. 576-579.DOI: https://doi.org/10.1109/embc44109.2020.9175221 [15] Ayata, D., Yaslan, Y., Kamasak, M.E., 2020. Emotion recognition from multimodal physiological signals for emotion aware healthcare systems. Journal of Medical and Biological Engineering. 40(2), 149-157.DOI: https://doi.org/10.1007/s40846-019-00505-7 [16] Regalia, G., Onorati, F., Lai, M., et al., 2019. Multi- modal wrist-worn devices for seizure detection and advancing research: Focus on the empatica wrist- bands. Epilepsy Research. 153, 79-82.DOI: https://doi.org/10.1016/j.eplepsyres.2019.02.007 [17] Onorati, F., Regalia, G., Caborni, C., et al., 2021. Prospective study of a multimodal convulsive seizure detection wearable system on pediatric and adult patients in the epilepsy monitoring unit. Frontiers in Neurology. 12, 724904.DOI: https://doi.org/10.3389/fneur.2021.724904 [18] Onorati, F., Regalia, G., Caborni, C., et al., 2017. Multicenter clinical assessment of improved wear- able multimodal convulsive seizure detectors. Epi- lepsia. 58(11), 1870-1879.DOI: https://doi.org/10.1111/epi.13899 [19] Laureanti, R., Bilucaglia, M., Zito, M., et al. (editors), 2020. Emotion assessment using machine learning and low-cost wearable devices. 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC); 2020 Jul 20- 24; Montreal, QC, Canada. USA:IEEE. p. 576-579.DOI: https://doi.org/10.1109/embc44109.2020.9175221 [20] Al Zoubi, O., Awad, M., Kasabov, N.K., 2018. Any- time multipurpose emotion recognition from EEG data using a liquid state machine based framework. Artificial Intelligence in Medicine. 86, 1-8.DOI: https://doi.org/10.1016/j.artmed.2018.01.001 [21] Potluri, S., Chandran, A.B., Diedrich, C. (editors), et al., 2019. Machine learning based human gait seg- mentation with wearable sensor platform. 2019 41st [22] Annual International Conference of the IEEE Engi- neering in Medicine and Biology Society (EMBC); 2019 Jul 23-27; Berlin, Germany. USA:IEEE. p. 588-594.DOI: https://doi.org/10.1109/embc.2019.8857509 [23] Zhang, H., Guo, Y., Zanotto, D., 2020. Accurate ambulatory gait analysis in walking and running using machine learning models. IEEE Transactions on Neural Systems and Rehabilitation Engineering. 28(1), 191-202.DOI: https://doi.org/10.1109/tnsre.2019.2958679 [24] Moore, S.R., Kranzinger, C., Fritz, J., et al., 2020. Foot strike angle prediction and pattern classification using LOADSOLTM wearable sensors: A compari- son of machine learning techniques. Sensors. 20(23), 6737.DOI: https://doi.org/10.3390/s20236737 [25] Hannun, A.Y., Rajpurkar, P., Haghpanahi, M., et al., 2019. Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network. Nature Medicine. 25(1), 65- 69.DOI: https://doi.org/10.1038/s41591-018-0268-3 [26] Kwon, S., Hong, J., Choi, E.K., et al., 2020. Detec- tion of atrial fibrillation using a ring-type wearable device (CardioTracker) and deep learning analysis of photoplethysmography signals: Prospective observational proof-of-concept study. Journal of Medical Internet Research. 22(5).DOI: https://doi.org/10.2196/16443 [27] Mei, Z., Gu, X., Chen, H., et al., 2018. Automatic atrial fibrillation detection based on heart rate vari- ability and spectral features. IEEE Access. 6, 53566- 53575.DOI: https://doi.org/10.1109/access.2018.2871220 [28] Miao, F., Wen, B., Hu, Z., et al., 2020. Continuous blood pressure measurement from one-channel elec- trocardiogram signal using deep learning techniques. Artificial Intelligence in Medicine. 108, 101919.DOI: https://doi.org/10.1016/j.artmed.2020.101919 [29] Lown, M., Brown, M., Brown, C., et al., 2020. Ma- chine learning detection of atrial fibrillation using wearable technology. Plos One. 15(1).DOI: https://doi.org/10.1371/journal.pone.0227401 [30] Liu, Y., Fang, B., Zhao, Y., et al. (editors), 2021. Ensemble learning for atrial fibrillation screening from a single lead ECG wave of wearable devices. 2021 IEEE 3rd International Conference on Frontiers Technology of Information and Computer (ICFTIC); 2021 Nov12-14; Greenville, SC, USA. USA: IEEE. p. 590-594.DOI: https://doi.org/10.1109/icftic54370.2021.9647218 [31] Colman, A., Chowdhury, M.J., Baruwal, C.M. (edi- tors), 2019. Towards a trusted marketplace for wear- able data. 2019 IEEE 5th International Conference on Collaboration and Internet Computing (CIC); 2019 Dec 12-14; Los Angeles, CA, USA. USA: IEEE. p. 314-321.DOI: https://doi.org/10.1109/cic48465.2019.00044 [32] Hynes, N., Dao, D., Yan, D., et al., 2018. A demon- stration of sterling. Proceedings of the VLDB En- dowment. 11(12), 2086-2089.DOI: https://doi.org/10.14778/3229863.3236266 [33] Garrido, G.M., Sedlmeir, J., Uludağ, Ö., et al., 2022. Revealing the landscape of privacy-enhancing tech- nologies in the context of data markets for the IOT: A systematic literature review. Journal of Network and Computer Applications. 207, 103465.DOI: https://doi.org/10.1016/j.jnca.2022.103465 [34] Song, Q., Cao, G., Sun, K., et al. (editors), 2021. Try before you buy: Privacy-preserving data evaluation on cloud-based machine learning data marketplace. ACSAC’21: Annual Computer Security Applica- tions Conference; 2021 Dec 6-10; New York: Virtual Event, USA. ACM. p.13.DOI: https://dl.acm.org/doi/10.1145/3485832.3485921 [35] Tang, H., Qiao, Y., Yang, F., et al., 2022. DMOBAs: A data marketplace on blockchain with arbitration using side-contracts mechanism. Computer Commu- nications. 193, 10-22.DOI: https://doi.org/10.1016/j.comcom.2022.06.029 [36] Zhang, C., Xu, Y., Hu, Y., et al., 2022. A block- chain-based multi-cloud storage data auditing scheme to locate faults. IEEE Transactions on Cloud Computing. 10(4), 2252-2263.DOI: https://doi.org/10.1109/tcc.2021.3057771 [37] Makhdoom, I., Zhou, I., Abolhasan, M., et al., 2019. Privysharing: A blockchain-based Framework for In- tegrity and Privacy-preserving Data Sharing in Smart Cities. Computers & Security. 88, 101653.DOI: https://doi.org/10.1016/j.cose.2019.101653 [38] Li, T., Wang, H., He, D., et al., 2022. Block Chain Based Privacy-preserving and Rewarding Private Data Sharing for IOT. IEEE Internet of Things Jour- nal. 9(16), 15138-15149.DOI: https://doi.org/10.1109/jiot.2022.3147925 [39] Zhao, Y., Zhao, J., Jiang, L., et al., 2021. Priva- cy-preserving Blockchain-based Federated Learning for IOT Devices [Internet] [Retrieved 2022 Dec 7]. Available from: https://arxiv.org/abs/1906.10893. [39] Facts & Factors, 2022. Insights on Global Wear- able Technology Market Size & Share to Surpass USD 380.5 Billion by 2028, Exhibit a Cagr of 18.5% Industry Analysis, Trends, Value, Growth, Opportunities, Segmentation, Outlook & Fore- cast Report by Facts & Factors [Internet]. Globe- Newswire News Room [Retrieved 2022 Dec 7]. Available from: https://www.globenewswire.com/news-release/2022/04/13/2421597/0/en/Insightson-GlobalWearableTechnology-Market-SizeShare-to-Surpass-USD380-5-Billion-by-2028-Exhibit-a-CAGR-of-18-5-IndustryAnalysis-TrendsValueGrowth-OpportunitiesSegmentatio.html. [40] Entriken, W., Shirley, D., Evans, J., et al., 2018. EIP- 721: Non-Fungible Token Standard. Ethereum Im- provement Proposals [Internet] [Retrieved 2022 Dec 7]. Available from: https://eips.ethereum.org/EIPS/eip-721. [41] LTE Cat-m a Cellular Standard for IOT—ARM Ar- chitecture Family [Internet] [Retrieved 2022 Dec 8]. Available from: https://community.arm.com/cfsfile/key/telligent-evolution-components-attach-ments/01-2142-0000-00-00-68-74/LTE-Cat 2D00 M-2D00-A-Cellular-Standard-forIoT.pdf. [42] Intel Software Guard Extensions [Internet] [Retrieved 2022 Dec 7]. Available from: https://www.intel.com/content/www/us/en/developer/tools/softwareguardextensions/overview.html. [43] Microsoft Pluton Security Processor [Internet]. AMD Pro Security [Retrieved 2022 Dec 8]. Available from: https://www.amd.com/en/technologies/prosecurity. [44] System-Wide Security for IoT Devices [Internet]. Trustzone for Cortex-M-ARM® [Retrieved 2022 Dec 7]. Available from: https://www.arm.com/technologies/trustzonefor-cortex-m. [45] Oliveira, D., Gomes, T., Pinto, S., 2012. UTANGO: An Open-source Tee for IOT Devices [Internet]. arX- iv [Retrieved 2022 Dec 8]. Available from: https://arxiv.org/pdf/2102.03625.pdf. [46] Your Home for NFT Media [Internet]. Pinata [Retrieved 2022 Dec 7]. Available from: https://www.pinata.cloud/. [47] Konečný, J., McMahan, H.B., Yu, F.X., et al., 2017. Federated Learning: Strategies for Improving Com- munication Efficiency [Internet]. arXiv.org [Re- trieved 2022 Dec 7]. Available from: https://arxiv.org/abs/1610.05492. [48] McMahan, H.B., Moore, E., Ramage, D., et al., 2017. Communication-efficient Learning of Deep Net- works from Decentralized Data [Internet]. arXiv.org [Retrieved 2022 Dec 7]. Available from: https://arxiv. org/abs/1602.05629. [49] Fang, H., Qian, Q., 2021. Privacy Preserving Ma- chine Learning with Homomorphic Encryption and Federated Learning [Internet]. MDPI [Retrieved 2022 Dec 7]. Available from: https://www.mdpi.com/19995903/13/4/94. [50] Polygon Wallet—Bring the World to Ethereum [Internet] [Retrieved 2022 Dec 7]. Available from: https://polygon.technology/. [51] Lightning Network [Internet] [Retrieved 2022 Dec 7]. Available from: https://lightning.network/. [52] Can I List an Item Without Paying to “Mint” It? [Internet] Opensea [Retrieved 2022 December 8] Available from: https://support.opensea.io/hc/en-us/ articles/1500003076601-Can-I-list-an-item-without- paying-to-mint-it-. [53] Powering Decentralized Crypto Commerce [Internet]. Wyvern Protocol [Retrieved 2022 Dec 7]. Available from: https://wyvernprotocol.com/. [54] Explore, Collect, and Sell NFTs [Internet]. OpenSea, the Largest NFT Marketplace [Retrieved 2022 Dec 7]. Available from: https://opensea.io/. [55] Wilkinson, M.D., Dumontier, M., Aalbersberg, I.J.J., et al., 2016. The fair guiding principles for scientific data management and stewardship. Scientific Data. 3(1).DOI: https://doi.org/10.1038/sdata.2016.18