Original Data Vs High Performance Augmented Data for ANN Prediction of Glycemic Status in Diabetes Patients

Massaro, Alessandro and Magaletti, Nicola and Giardinelli, Vito O. M. and Cosoli, Gabriele and Leogrande, Angelo and Cannone, Francesco (2022): Original Data Vs High Performance Augmented Data for ANN Prediction of Glycemic Status in Diabetes Patients.

Abstract

In the following article a comparative analysis between Original Data (OD) and Augmented Data (AD) are carried out for the prediction of glycemic status in patients with diabetes. Specifically, the OD concerning the time series of the glycemic status of a patient are compared with AD. The AD are obtained by the randomised average with five different ranges, and are processed by a Machine Learning (ML) algorithm for prediction. The adopted ML algorithm is the Artificial Neural Network (ANN) Multilayer Perceptron (MLP). In order to optimise the prediction two different data partitioning scenarios selecting training datasets are analysed. The results show that the algorithm performances related to the use of AD through the randomisation of data in different ranges around the average value, are better than the OD data processing about the minimization of statistical errors in self learning models. The best achieved error decrease is of 75.4% if compared with ANN-MLP processing of the original dataset. Furthermore, in the paper is added a linked discussion about the economic and managerial impact of AD in the healthcare sector.

• Item Type: MPRA Paper
• Language: English
• Keywords: ANN-Artificial Neural Network, Augmented Data Generation, Telemedicine, EHealthcare, Model Optimization.
• Subjects: O - Economic Development, Innovation, Technological Change, and Growth > O3 - Innovation ; Research and Development ; Technological Change ; Intellectual Property Rights > O30 - General; O - Economic Development, Innovation, Technological Change, and Growth > O3 - Innovation ; Research and Development ; Technological Change ; Intellectual Property Rights > O31 - Innovation and Invention: Processes and Incentives; O - Economic Development, Innovation, Technological Change, and Growth > O3 - Innovation ; Research and Development ; Technological Change ; Intellectual Property Rights > O32 - Management of Technological Innovation and R&D; O - Economic Development, Innovation, Technological Change, and Growth > O3 - Innovation ; Research and Development ; Technological Change ; Intellectual Property Rights > O33 - Technological Change: Choices and Consequences ; Diffusion Processes; O - Economic Development, Innovation, Technological Change, and Growth > O3 - Innovation ; Research and Development ; Technological Change ; Intellectual Property Rights > O34 - Intellectual Property and Intellectual Capital

References

[1] M. Perkmann, R. Fini, J. M. Ross, A. Salter, C. Silvestri e V. Tartari, «Accounting for universities’ impact: Using augmented data to measure academic engagement and commercialization by academic scientists,» Research Evaluation, vol. 24, n. 4, pp. 380-39, 2015.

[2] R. Pierdicca, E. Frontoni, P. Zingaretti, A. Mancini, E. S. Malinverni, A. N. Tassetti e A. Galli, «Smart maintenance of riverbanks using a standard data layer and Augmented Reality,» Computers & Geosciences, vol. 95, pp. 67-74, 2016.

[3] X. Wang, Y. Wang, F. Tao e A. Liu, «New paradigm of data-driven smart customisation through digital twin,» Journal of manufacturing systems, vol. 58, pp. 270-280, 2021.

[4] L. Yi e M. W. Mak, «Adversarial data augmentation network for speech emotion0 recognition,» 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), n. IEEE, pp. 529-534, 2019.

[5] S. Y. Yu, A. V. Malawade, D. Muthirayan, P. P. Khargonekar e M. A. Al Faruque, «Scenegraph augmented data-driven risk assessment of autonomous vehicle decisions,» IEEE Transactions on Intelligent Transportation Systems, 2021.

[6] D. Kaushik, A. Setlur, E. Hovy e Z. C. Lipton, «Explaining the efficacy of counterfactually augmented data,» arXiv preprint arXiv:2010.02114., 2020.

[7] A. Massaro, A. Panarese, M. Gargaro, A. Colonna e A. Galiano, «A Case Study of Innovation in the Implementation of a DSS System for Intelligent Insurance Hub Services,» Comput. Sci. Inform. Technol, vol. 9, pp. 14-23, 2021.

[8] A. Massaro, A. Panarese, D. Giannone e A. Galiano, «Augmented Data and XGBoost Improvement for Sales Forecasting in the Large-Scale Retail Sector,» Applied Sciences, vol. 7793, n. 17, p. 11, 2021.

[9] A. Leogrande, N. Magaletti, G. Cosoli, V. Giardinelli e A. Massaro, «ICT Specialists in Europe.,» University Library of Munich Germany, 2022.

[10] I. Sen, M. Samory, F. Floeck, C. Wagner e I. Augenstein, «How Does Counterfactually Augmented Data Impact Models for Social Computing Constructs?,» arXiv preprint arXiv:2109.07022, 2021.

[11] S. Dargan, M. Kumar, M. R. Ayyagari e G. Kumar, «A survey of deep learning and its applications: a new paradigm to machine learning,» Archives of Computational Methods in Engineering, vol. 27, n. 4, pp. 1071-1092, 2020.

[12] S. Kayalvizhi e D. Thenmozhi, «Data set creation and empirical analysis for detecting signs of depression from social media postings,» arXiv preprint arXiv:2202.03047, 2022.

[13] A. Massaro, «Information Technology Infrastructures Supporting Industry 5.0 Facilities,» Electronics in Advanced Research Industries: Industry 4.0 to Industry 5.0 Advances, vol. IEEE, n. 10.1002/9781119716907.ch2., pp. 51-101, 2022.

[14] A. Massaro, V. Maritati, N. Savino e A. Galiano, «Neural Networks for Automated Smart Health Platforms oriented on Heart Predictive Diagnostic Big Data Systems,» AEIT International Annual Conference, n. 10.23919/AEIT.2018.8577362., pp. 1-5, 2018.

[15] A. Massaro, A. Galiano, D. Scarafile, A. Vacca, A. Frassanito, A. Melaccio e F. Attivissimo, «Telemedicine DSS-AI multi level platform for monoclonal gammopathy assistance,» IEEE International Symposium on Medical Measurements and Applications (MeMeA), pp. 1-5, 2020.

[16] A. Massaro, G. Ricci, S. Selicato, S. Raminelli e A. Galiano, «Decisional Support System with Artificial Intelligence oriented on Health Prediction using a Wearable Device and Big Data,» IEEE International Workshop on Metrology for Industry 4.0 & IoT, 2020.

[17] A. Massaro, V. Maritati, N. Savino, A. Galiano, D. Convertini, E. De Fonte e M. Di Muro, «A study of a health resources management platform integrating neural networks and DSS telemedicine for homecare assistance,» Information, vol. 7, n. 176, p. 9, 2018.

[18] S. Kouchaki, N. Pourshahrokhi, K. M. Kober, C. Miaskowski e P. Barnaghi, «A Hybrid Bayesian Model to Analyse Healthcare Data,» 35th Conference on Neural Information Processing Systems , 2021.

[19] U. R. Acharya, S. L. Oh, Y. Hagiwara, J. H. Tan, M. Adam, A. Gertych e R. San Tan, «A deep convolutional neural network model to classify heartbeats,» Computers in biology and medicine, vol. 89, pp. 389-396, 2017.

[20] J. Wei, A. Suriawinata, L. Vaickus, B. Ren, X. Liu, J. Wei e S. Hassanpour, «Generative image translation for data augmentation in colorectal histopathology images,» Proceedings of machine learning research, vol. 10, p. 116, 2019.

[21] P. Chlap, H. Min, N. Vandenberg, J. Dowling, L. Holloway e A. Haworth, «A review of medical image data augmentation techniques for deep learning applications,» Journal of Medical Imaging and Radiation Oncology, vol. 65, n. 5, pp. 545-563, 2021.

[22] B. Longstaff, S. Reddy e D. Estrin, «Improving activity classification for health applications on mobile devices using active and semi-supervised learning,» 2010 4th International Conference on Pervasive Computing Technologies for Healthcare, vol. IEEE, pp. 1-7, 2010.

[23] V. C. Pezoulas, T. P. Exarchos, A. G. Tzioufas e D. I. Fotiadis, «Multiple additive regression trees with hybrid loss for classification tasks across heterogeneous clinical data in distributed environments: a case study,» 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), vol. IEEE, pp. 1670-1673, 2021.

[24] A. Aminifar, F. Rabbi, V. K. I. Pun e Y. Lamo, «Monitoring Motor Activity Data for Detecting Patients’ Depression Using Data Augmentation and Privacy-Preserving Distributed Learning,» 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society, pp. 2163-2169, 2021 .

[25] Z. Che, Y. Cheng, S. Zhai, Z. Sun e Y. Liu, «Boosting deep learning risk prediction with generative adversarial networks for electronic health records,» IEEE International Conference on Data Mining (ICDM), n. IEEE, pp. 787-792, 2017 .

[26] M. Ghalwash, Z. Yao, P. Chakrabotry, J. Codella e D. Sow, «ODVICE: An Ontology-Driven Visual Analytic Tool for Interactive Cohort Extraction,» arXiv preprint arXiv:2005.06434, 2020.

[27] C. Lu, B. Huang, K. Wang, J. M. Hernández-Lobato, K. Zhang e B. Schölkopf, «Sample efficient reinforcement learning via counterfactual-based data augmentation» arXiv preprint arXiv:2012.09092, 2020.

[28] A. Massaro, V. Maritati, D. Giannone, D. Convertini e A. Galiano, «LSTM DSS automatism and dataset optimization for diabetes prediction,» Applied Sciences, vol. 17, n. 3532, p. 9, 2019.

[29] H. P. Das, R. Tran, J. Singh, X. Yue, G. Tison, A. Sangiovanni-Vincentelli e C. J. Spanos, «Conditional Synthetic Data Generation for Robust Machine Learning Applications with Limited Pandemic Data,» arXiv preprint arXiv:2109.06486, 2021.

[30] N. Sangari e Y. Qu, «A ComparMachine Learning Algorithms for Predicting Breast Cancer Prognosis in Improving Clinical Trials,» 2020 International Conference on Computational Science and Computational Intelligence (CSCI), pp. 813-818, 2020.

[31] A. Massaro, «Electronics in Advanced Research Industries: Industry 4.0 to Industry 5.0 Advances,» John Wiley & Sons, 2021.

[32] A. Massaro, «Human–Machine Interfaces,» Electronics in Advanced Research Industries: Industry 4.0 to Industry 5.0 Advances, vol. 10.1002/9781119716907.ch3, pp. 103-153, 2022.

[33] A. Massaro, G. Mastandrea, L. D'Oriano, G. R. Rana, N. Savino e A. Galiano, «Systems for an intelligent application of automated processes in industry: A case study from “PMI IoT Industry 4.0” project,» IEEE International Workshop on Metrology for Industry 4.0 & IoT, vol. IEEE, pp. 21- 26, 2020.

[34] A. Massaro, G. Cosoli, V. Giardinelli, A. Leogrande, N. Magaletti, (2022). An Approach Generating Augmented Data For Machine Learning Data Processing, Zenodo. https://doi.org/10.5281/zenodo.6362964