إحداث ثورة في توقع أمراض القلب باستخدام التعلم الآلي المعزز بالكمّ

خلفية الدراسة

النتائج الرئيسية للدراسة

• تم استعراض أنظمة التشخيص الآلي للقلب التي تم تطويرها باستخدام تقنيات التعلم الآلي حيث أن أمراض القلب هي السبب الرئيسي لوفيات البشر في عالم اليوم، لذا يجب تطوير نظام تشخيص فعال ودقيق لإنقاذ الأرواح البشرية.
• من الدراسة أعلاه، لوحظ أن العديد من الباحثين كانوا مهتمين بالتعلم الآلي لتشخيص أمراض القلب لأنه يساعد في تقليل وقت التشخيص وزيادة الدقة.
• من الدراسة، تتنافس كل طريقة جديدة مع الأخرى لتحقيق معدل دقة أكبر.
• يتم اعتبار SVM المعتمد على التعزيز ومجموعة المصنفات كأكثر الطرق الواعدة التي حققت أعلى دقة تم رؤيتها على الإطلاق.
• قد تعمل خوارزمية واحدة بشكل جيد لمجموعة بيانات واحدة بينما لا يمكن أن تعمل بشكل جيد لمجموعة بيانات أخرى.

• قد تعتمد دقة النظام على جودة مجموعات البيانات المستخدمة.
• يمكن أن تحتوي بعض مجموعات البيانات على قيم مفقودة، وتكرارات، وضوضاء مما يجعل البيانات غير مناسبة. يمكن حل هذه الشكوك من خلال تطبيق تقنيات معالجة البيانات مثل التطبيع، وإدخال القيم المفقودة، وما إلى ذلك.
• قد تحتوي بعض مجموعات البيانات على عدد كبير جدًا من السمات مما قد يهدد أداء التعلم الآلي من حيث الدقة ووقت الحساب. يمكن تحسين ذلك من خلال تطبيق استراتيجيات اختيار الميزات المناسبة لإجراء التنبؤ بأكثر الميزات معلوماتية.

الدافع للدراسة

مواد وطرق النظام
وصف مجموعة البيانات

المنهجيات المقترحة

تحليل البيانات الاستكشافي (EDA)

الشكل 1. الخطوات المستخدمة في QuEML.

تقييم كاي-تربيع (CSE)

إطار عمل QuEML

Input: Datasets HDD
Output: prediction of HD + and HD - cases.
Begin
Do
For each row in HDD
    Apply EDA to generate preprocessed dataset HDD_P
End
Do
    Execute CSE on HDD_P to retain top ranked feature set HDD_TRF
End
Split HDD_TRF into training and testing set
Apply Quantum approach on training split
Do
    Specify Qubits Qb
    Then apply entangling Qb based feature mapping
    Then generate Quantum Circuit Qc
End
Do till reaches Max_Iteration
    Execute QuEML approaches on training split using Qc to train the model
End
Evaluate QuEML approaches using testing split
Stop

الشكل 2. العثور على القيم الفارغة.

النتائج والمناقشات

الشكل 3. توزيع الميزات.

الشكل 4. هيكل QANN.

الشكل 5. تقدير تداخل الحالة: العمق .

الشكل 6. دائرة كمومية لـ QBE.

الخاتمة

الشكل 7. مقابل مقابل من QBE.

أداء QSVM

الشكل 9. مقابل مقابل من قن.

توفر البيانات

References

1. Ramalingam, V.-V., Dandapath, A. & Raja, M. Heart disease prediction using machine learning techniques: A survey. Int. J. Eng. Technol. 7(28), 684-687 (2018).
2. Mendis, S., Puska, P., Norrving, B. & World Health Organization. Global Atlas on Cardiovascular Disease Prevention and Control. (World Health Organization, 2011).
3. Katarya, R. & Srinivas, P. Predicting heart disease at early stages using machine learning: A survey. Int. Conf. Electron. Sustain. Commun. Syst. 8, 302-305 (2020).
4. Li, J.-P. et al. Heart disease identification method using machine learning classification in e-healthcare. IEEE Access. 8, 107562107582 (2022).
5. Arabasadi, Z., Alizadehsani, R., Roshanzamir, M., Moosaei, H. & Yarifard, A. A. Computer aided decision making for heart disease detection using hybrid neural network-genetic algorithm. Comput. Methods Progr. Biomed. 141, 19-26 (2017).
6. Alizadehsani, R. et al. A data mining approach for diagnosis of coronary artery disease. Comput. Methods Progr. Biomed. 111, 52-61 (2013).
7. Nahar, J., Imam, T., Tickle, K.-S. & Chen, Y.-P. Computational intelligence for heart disease diagnosis: A medical knowledge driven approach. Expert Syst. Appl. 40, 96-104 (2013).
8. Nahar, J., Imam, T., Tickle, K.-S. & Chen, Y.-P. Association rule mining to detect factors which contribute to heart disease in males and females. Expert Syst. Appl. 40, 1086-1093 (2013).
9. Tsipouras, M.-G. et al. Automated diagnosis of coronary artery disease based on data mining and fuzzy modeling. IEEE Trans. Inf. Technol. Biomed. 12, 447-458 (2008).
10. Anooj, P.-K. Clinical decision support system: Risk level prediction of heart disease using weighted fuzzy rules. J. King Saud Univ. Comput. Inf. Sci. 24, 27-40 (2012).
11. Pal, D., Mandana, K.-D., Pal, S., Sarkar, D. & Chakraborty, C. Fuzzy expert system approach for coronary artery disease screening using clinical parameters. Knowl. Based Syst. 36, 162-174 (2012).
12. Kavitha, S. S. & Kaulgud, N. Quantum K-means clustering method for detecting heart disease using quantum circuit approach. Soft Comput. 3, 1-14 (2022).
13. Shah, S. M. S., Shah, F. A., Hussain, S. A. & Batool, S. Support vector machines-based heart disease diagnosis using feature subset wrapping selection and extraction methods. Comput. Electr. Eng. 84, 106628 (2020).
14. Son, Y.-J., Kim, H.-G., Kim, E.-H., Choi, S. & Lee, S.-K. Application of support vector machine for prediction of medication adherence in heart failure patients. Healthc. Inform. Res. 16(4), 253-259 (2010).
15. Owusu, E., Boakye-Sekyerehene, P., Appati, J. K. & Ludu, J. Y. Computer-aided diagnostics of heart disease risk prediction using boosting support vector machine. Comput. Intell. Neurosci. 23, 5132 (2021).
16. Medhekar, D., Mayur, S., Bote, P. & Deshmukh, S.D. Heart disease prediction system using naive Bayes. Int. J. Enhanced Res. Sci. Technol. Eng. 2, 3 (2013).
17. Miranda, E., Irwansyah, E., Amelga, A.-Y., Maribondang, M.-M. & Salim, M. Detection of cardiovascular disease risk’s level for adults using naive bayes classifier. Healthc. Inform. Res. 22(3), 196-205 (2016).
18. Vembandasamy, K., Sasipriya, R. & Deepa, E. Heart diseases detection using Naive Bayes algorithm. Int. J. Innov. Sci. Eng. Technol. 4, 441-444 (2015).
19. Miray, A., Sönmez, Ö.E. & Özcan, T. Diagnosis of heart disease using an intelligent method: A hybrid ANN-GA approach. InInternational Conference on Intelligent and Fuzzy Systems. 1250-1257 (Springer, 2019).
20. Khemphila, A. & Boonjing, V. Heart disease classification using neural network and feature selection. In: 21st International Conference on Systems Engineering (IEEE, 2011).
21. Kim, J. K. & Kang, S. Neural network-based coronary heart disease risk prediction using feature correlation analysis. J. Healthc. Eng. 3, 406-409 (2017).
22. Deekshatulu, B.-L. & Chandra, P. Classification of heart disease using k-nearest neighbor and genetic algorithm. Proc. Technol. 10, 85-94 (2013).
23. Enriko, I., Agung, K., Suryanegara, M. & Gunawan, D. Heart disease prediction system using k-Nearest neighbor algorithm with simplified patient’s health parameters. J. Telecommun. Electron. Comput. Eng. (JTEC) 8(12), 59-65 (2016).
24. Pandey, A.-K., Pandey, P., Jaiswal, K.-L. & Sen, A.-K. A heart disease prediction model using decision tree. IOSR J. Comput. Eng. (IOSR-JCE) 12(6), 83-86 (2013).
25. Zhang, Z. et al. Application of decision trees to the determination of the year-end level of a carryover storage reservoir based on the iterative dichotomizer 3. Int. J. Electr. Power Energy Syst. 64, 375-383 (2015).
26. Ambrish, G., Ganesh, B., Ganesh, A., Srinivas, C. & Mensinkal, K. Logistic regression technique for prediction of cardiovascular disease. In Global Transitions Proceedings (2022).
27. Soleimani, P. & Neshati, A. Applying the regression technique for prediction of the acute heart attack. Int. J. Biomed. Biol. Eng. 9(11), 767-771 (2015).
28. Singh, Y.K., Sinha, N. & Singh, S.K. Heart disease prediction system using random forest. In International Conference on Advances in Computing and Data Sciences. 613-623 (Springer, 2016).
29. Javeed, A. et al. An intelligent learning system based on random search algorithm and optimized random forest model for improved heart disease detection. IEEE Access. 7, 180235-180243 (2019).
30. Jabbar, M.-A., Deekshatulu, B.-L. & Chandra, P. Intelligent heart disease prediction system using random forest and evolutionary approach. J. Netw. Innov. Comput. 4(2016), 175-184 (2016).
31. Abdollahi, J. & Nouri-Moghaddam, B. A hybrid method for heart disease diagnosis utilizing feature selection based ensemble classifier model generation. Iran J. Comput. Sci. 4, 1-18 (2022).
32. Yekkala, I., Dixit, S. & Jabbar, M.-A. Prediction of heart disease using ensemble learning and particle swarm optimization. In International Conference on Smart Technologies for Smart Nation (SmartTechCon) (IEEE, 2017)
33. Tiwari, P. & Melucci, M. Towards a quantum-inspired binary classifier. IEEE Access. 7, 42354-42372 (2019).
34. Khan, T.-M. & Robles-Kelly, A. Machine learning: Quantum vs classical. IEEE Access. 8, 219275-219294 (2020).
35. Tiwari, P. & Melucci, M. Towards a quantum-inspired binary classifier. IEEE Access 7, 42354-42372 (2019).
36. Wereszczynski, K., Michalczuk, A., Josinski, H. & Polanski, A. Quantum computing for clustering big datasets. Appl. Electromagnet. Mod. Tech. Med. (PTZE) 4, 276-280 (2018).
37. Dang, Y., Jiang, N., Hu, H. Z., Ji, X. & Zhang, W. Image classification based on quantum K-nearest-neighbor algorithm. Quantum Inf. Process. 17, 9 (2018).
38. Lu, S. & Braunstein, S. Quantum decision tree classifier. Quantum Inf. Process. 13(3), 757-770 (2014).
39. Amin, J., Sharif, M., Gul, N., Kadry, S. & Chakraborty, C. Quantum machine learning architecture for COVID-19 classification based on synthetic data generation using conditional adversarial neural network. Cognit. Comput. 13, 1-12 (2021).
40. Sharma, S. Qeml (quantum enhanced machine learning): Using quantum computing to enhance ml classifiers and feature spaces. arXiv preprint arXiv:2002.10453 (2020).
41. Sharma, S., Rastogi, S. & Devanssh, M. Quantum computing will completely change the healthcare infrastructure to new level and -help transform the healthcare from preventive to predictive healthcare: A future perspective. Innov. J. 9, 2020-2277 (2020).
42. Chalumuri, A., Kune, R. & Manoj, B.-S. Training an artificial neural network using qubits as artificial neurons: A quantum computing approach. Proc. Comput. Sci. 171, 568-575 (2020).
43. Vashisth, S., Dhall, I. & Aggarwal, G. Design and analysis of quantum powered support vector machines for malignant breast cancer diagnosis. J. Intell. Syst. 30(1), 998-1013 (2021).
44. Macaluso, A., Lodi, S. & Sartori, C. Quantum algorithm for ensemble learning. In Italian Conference on Theoretical Computer Science (ICTCS).149-154 (2020).
45. Haq, A. U. et al. DACBT: Deep learning approach for classification of brain tumors using MRI data in IoT healthcare environment. Sci. Rep. 12, 15331 (2022).
46. Haq, A., Li, J.P., Kumar, R. et al. MCNN: A multi-level CNN model for the classification of brain tumors in IoT-healthcare system. J. Ambient Intell. Hum. Comput. (2022).
47. ul Haq, A. et al. A survey of deep learning techniques-based Parkinson’s disease recognition methods employing clinical data. Exp. Syst. Appl. 208, 118045 (2022).

مساهمات المؤلفين

المصالح المتنافسة

معلومات إضافية

Revolutionizing heart disease prediction with quantum-enhanced machine learning

Background of study

Major findings of the study

• Automatic heart diagnostic systems that were developed using ML techniques were surveyed as heart disease is the major cause of human deaths in today’s world, so an effective and accurate diagnosis system is to be developed to save human lives.
• From the above study, it is observed that many researchers were interested in machine learning for heart disease diagnosis since it helps to reduce diagnosis time and increases accuracy.
• From the study, every new approach competes with one another to win a greater accuracy rate.
• Boosting-based SVM and an Ensemble of classifiers are being seen as the most promising methods that yielded the greater accuracy ever seen.
• One algorithm may work well for one dataset while cannot work well for another dataset.

• The accuracy of the system may rely on the quality of the datasets used.
• Some datasets can have missing values, redundancies, and noises which makes data to be unsuitable. Such uncertainty can be resolved by applying data preprocessing techniques such as normalization, missing value imputation, etc.
• Some datasets may have too many attributes which may threaten the performance of ML in accuracy and computational time. It can be improved by applying suitable feature selection strategies to perform prediction with the most informative features.

Motivation for the study

System materials and methods
Dataset description

Proposed methodologies

Exploratory data analysis (EDA)

Figure 1. Steps used in QuEML.

Chi-square evaluation (CSE)

QuEML framework

Input: Datasets HDD
Output: prediction of HD + and HD - cases.
Begin
Do
For each row in HDD
    Apply EDA to generate preprocessed dataset HDD_P
End
Do
    Execute CSE on HDD_P to retain top ranked feature set HDD_TRF
End
Split HDD_TRF into training and testing set
Apply Quantum approach on training split
Do
    Specify Qubits Qb
    Then apply entangling Qb based feature mapping
    Then generate Quantum Circuit Qc
End
Do till reaches Max_Iteration
    Execute QuEML approaches on training split using Qc to train the model
End
Evaluate QuEML approaches using testing split
Stop

Figure 2. Finding null values.

Results and discussions