Abstract
Cardiovascular disease is the most important reason for death worldwide and significant public health distress. Timely prevention and treatment are possible by early prediction of the disease. However, there is necessary to include or vary new risk factors to improve the prediction models’ performance. It is one of the best ways to make development towards human-level AI. The machine learning (ML) algorithms PCA (Principal Component Algorithm) and XGboost classification are used to process the user queries and send the prediction. A major constraint is to secure the user queries submitted to the prediction models in order that the patient can submit their questions in an encrypted format to ensure security. It motivates us to develop a predictive model PHML which combines Partial Homomorphic Encryption and Machine Learning algorithms PCA and XGboost classification. The model is implemented in Amazon SageMaker with the dataset stored in Amazon S3 using the above algorithms. The patient query was submitted to the cloud with the encrypted format by the proposed partial homomorphic encryption algorithm. The machine learning algorithms predict the user queries, which are in encrypted form. The dataset includes multiple attributes like age, height, weight, gender, smoking, alcohol intake, physical activity, systolic blood pressure, cholesterol, glucose, diastolic blood pressure, and medical notes. With all features, doctors try to predict whether our individual has a high risk of cardiovascular.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Abbreviations
- \(\mathrm{ct}\) :
-
Ciphertext
- \(\mathrm{g}\) :
-
Generator
- \(\mathrm{p}\) :
-
Large prime number
- \(\mathrm{pk},\mathrm{sk}\) :
-
Pk-public key, sk-secret key
- \(\mathrm{pt}\) :
-
Plain text
- \(\mathrm{r}1,\mathrm{r}2\) :
-
Random numbers
- \({\mathrm{Z}}_{\mathrm{p}}^{*}\) :
-
Multiplicative group of a finite field
- \((\mathrm{m},\mathrm{n})\) :
-
Ciphertext generated by encryption function
- \(\uptheta \) :
-
\(\uptheta ={\upmu }^{\mathrm{g}}\mathrm{ mod}\,{\text{p}}\), Pre-computed parameter
- \(\upmu \) :
-
Secret key
- PCA:
-
Principal Component Algorithm
- CVD:
-
Cardiovascular disease
- gcd:
-
Greatest common divisor
- PHML:
-
Partially Homomorphic Machine Learning
- OW-CCA:
-
One Way-Chosen Ciphertext Attack
- PRG:
-
Pseudorandom generator
- PPT:
-
Probabilistic Polynomial Time
- ML:
-
Machine Learning
- AI:
-
Artificial Intelligence
References
Yi X, Paulet R, Bertino E (2014) Homomorphic encryption and applications. SpringerBriefs in computer science. SCS. Springer, Cham. https://doi.org/10.1007/978-3-319-12229-8
Halevi S, Polyakov Y, Shoup V (2019) An improved RNS variant of the BFV homomorphic encryption scheme. In: Matsui M (eds) Topics in cryptology – CT-RSA 2019. LNCS, vol. 11405, pp 83–105. Springer, Cham. https://doi.org/10.1007/978-3-030-12612-4_5
Min Zhao E, Geng Y (2019) Homomorphic encryption technology for cloud computing. Procedia Comput Sci 154, 73–83
Hazay C, Mikkelsen GL, Rabin T, Toft T (2012) Efficient RSA key generation and threshold Paillier in the two-party setting. In: Dunkelman O (eds) Topics in cryptology – CT-RSA 2012. LNCS, vol 7178, pp 313–331. Springer, Heidelberg. https://doi.org/10.1007/978-3-642-27954-6_20
Sharan Monica L, Sathees Kumar B (2016) Analysis of CardioVasular disease prediction using data mining techniques. Int J Mod Comput Sci 4:55–58
Shedole SS, Deepika K (2016) Predictive analytics to prevent and control chronic disease, January 2016. https://www.researchgate.net/punlication/316530782
Khazaee A (2013) Heartbeat classification using particle swarm optimization. Intell Syst Appl 5(6):25–33
Soni J, Ansari U, Dipesh S (2011) Predictive data mining for medical diagnosis: an overview of heart disease prediction. Int J Comput Appl 17(8):43–48 (0975-8887)
Sharma S, Parmar M (2020) Heart diseases prediction using deep learning neural network model. Int J Innov Technol Explor Eng (IJITEE) 9(3), 2244–2248. ISSN: 2278-3075
Marimuthu M, Abinaya M, Hariesh KS, Madhankumar K, Pavithra V (2018) Review on heart disease prediction using machine learning and data analytics approach. Int J Comput Appl 181(18):20–25
Kishore A, Kumar A, Singh K, Punia M, Hambir Y (2018) Heart attack prediction using deep learning. Int Res J Eng Technol (IRJET) 5(4), p-ISSN: 2395-0072
WHO (2012) Cardiovascular diseases (CVDs) Technical report, World Health Organization, Geneva, Switzerland
Naghavi M, Libby P, Falk E et al (2003) From vulnerable plaque to vulnerable patient: a call for new definitions and risk assessment strategies: part II. Circulation 108(15):1772–1778
Mackay J, Mensah GA, Mendis S, Greenlund K (2004) The atlas of heart disease and stroke. Technical report, World Health Organization, Geneva, Switzerland
Gupta P, Prieto-Merino D, Ajay VS, Singh K (2019) Cardiovascular risk prediction in India: comparison of the original and recalibrated Framingham prognostic models in urban populations. Wellcome open research
Chauhan KK, Sanger AKS, Verma A (2015) Homomorphic encryption for data security in cloud computing. In: 2015 international conference on information technology (ICIT), Bhubaneswar, India, pp 206–209
Vengadapurvaja AM, Nisha G, Aarthy R, Sasikaladevi N (2017) An efficient homomorphic medical image encryption algorithm for cloud storage security. In: 7th international conference on advances in computing & communications, ICACC-2017, Cochin, India, pp 643–650
Sinha K, Majumder P, Ghosh SK (2020) Fully homomorphic encryption based privacy-preserving data acquisition and computation for contact tracing. In: 2020 IEEE international conference on advanced networks and telecommunications systems (ANTS), covidwho-1284982, pp 1–6
Tamilarasi K, Jawahar A (2020) Medical data security for healthcare applications using hybrid lightweight encryption and swarm optimization algorithm. Wirel Pers Commun 114:1865–1886
Paddock S, Abedtash H, Zummo J, Thomas S (2019) Proof-of-concept study: homomorphically encrypted data can support real-time learning in personalized cancer medicine. BMC Med Inform Decis Making 19:255
Kocabas O, Soyata T, Couderc J, Aktas M, Xia J, Huang M (2013) Assessment of cloud-based health monitoring using Homomorphic Encryption. In: 2013 IEEE 31st international conference on computer design (ICCD), Asheville, North Carolina, pp 443–446
Tang W, Ren J, Deng K, Zhang Y (2019) Secure data aggregation of lightweight e-healthcare IOT devices with fair incentives. IEEE Internet Things J 6(5):8714–8726
Kumar AV, Sujith MS, Sai KT, Rajesh G, Yashwanth DJ (2020) Secure multiparty computation enabled E-Healthcare system with Homomorphic encryption. In: International conference on recent advancements in engineering and management (ICRAEM-2020), Warangal, India 2020, vol 981, 022079
Min Z, Yang G, Sangaiah AK, Bai S, Liu G (2019) A privacy protection-oriented parallel fully homomorphic encryption algorithm in cyber-physical systems. EURASIP J Wirel Commun Netw 15. https://doi.org/10.1186/s13638-018-1317-9
Aparna P, Kishore PVV (2017) An efficient medical image watermarking technique in e-healthcare application using hybridization of compression and cryptography algorithm. J Intell Syst 27(1):115–133
Bos JW, Lauter K, Naehrig M (2014) Private predictive analysis on encrypted medical data. J Biomed Inform 50:234–243
Kim D, Son Y, Kim D, Kim A, Hong S, Cheon JH (2020) Privacy-preserving approximate GWAS computation based on homomorphic encryption. BMC Med Genomics 13:77
Page O, Kocabas S, Ames M, Soyata VT (2014) Cloud-based secure health monitoring: optimizing fully-homomorphic encryption for streaming algorithms. In: IEEE Globecom workshops (GC Wkshps), Austin, TX, USA, pp 48–52
Sudha I, Nedunchelian R (2019) A secure data protection technique for healthcare data in the cloud using homomorphic encryption and Jaya-Whale optimization algorithm. Int J Model Simul Sci Comput 10(6):1–22
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Boomija, M.D., Kasmir Raja, S.V. (2022). Secure Predictive Analysis on Heart Diseases Using Partially Homomorphic Machine Learning Model. In: Uddin, M.S., Jamwal, P.K., Bansal, J.C. (eds) Proceedings of International Joint Conference on Advances in Computational Intelligence. Algorithms for Intelligent Systems. Springer, Singapore. https://doi.org/10.1007/978-981-19-0332-8_42
Download citation
DOI: https://doi.org/10.1007/978-981-19-0332-8_42
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-0331-1
Online ISBN: 978-981-19-0332-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)