Diabetes prediction using a context-adaptive activation neural network

Ren Chen; Chao Wang; Fulong Chen; Ren Chen; Chao Wang; Fulong Chen

doi:10.3934/bioeng.2026012

AIMS Bioengineering

2026, Volume 13, Issue 2: 261-280. doi: 10.3934/bioeng.2026012

Previous Article Next Article

Review

Diabetes prediction using a context-adaptive activation neural network

1.
School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui Province 230026, China
2.
School of Computer and Information, Anhui Normal University, Wuhu, Anhui Province 241002, China

Received: 10 April 2026 Revised: 28 May 2026 Accepted: 03 June 2026 Published: 22 June 2026

This paper describes a novel diabetes prediction framework underpinned by a neural network architecture which features a parameterized activation function, called the Self-Learning Activation Linear Unit (SLALU). The proposed diabetes prediction model is composed of multiple self-learning activation linear units with parameters, and this SLALU can fit most of the traditional activation functions, including but not limited to the Rectified Linear Unit (ReLU) and the Parametric Rectified Linear Unit (PReLU). This self-adjusting activation approach provides a flexible bending ability, thereby outperforming the bending capabilities of traditional activation functions and reducing the intricacy involved in their manual selection. The design of our neuron model improves the network's representational capacity and fitting ability. Deployed in diabetes prediction, our advanced network model demonstrated superior performance across a suite of metrics, thereby recording an accuracy of 98.18%, thus outperforming several existing models.
- diabetes prediction,
- attention mechanism,
- deep neural networks,
- adjustable activation neural networks
Citation: Ren Chen, Chao Wang, Fulong Chen. Diabetes prediction using a context-adaptive activation neural network[J]. AIMS Bioengineering, 2026, 13(2): 261-280. doi: 10.3934/bioeng.2026012

Related Papers:

Abstract

This paper describes a novel diabetes prediction framework underpinned by a neural network architecture which features a parameterized activation function, called the Self-Learning Activation Linear Unit (SLALU). The proposed diabetes prediction model is composed of multiple self-learning activation linear units with parameters, and this SLALU can fit most of the traditional activation functions, including but not limited to the Rectified Linear Unit (ReLU) and the Parametric Rectified Linear Unit (PReLU). This self-adjusting activation approach provides a flexible bending ability, thereby outperforming the bending capabilities of traditional activation functions and reducing the intricacy involved in their manual selection. The design of our neuron model improves the network's representational capacity and fitting ability. Deployed in diabetes prediction, our advanced network model demonstrated superior performance across a suite of metrics, thereby recording an accuracy of 98.18%, thus outperforming several existing models.

Acknowledgments

This research is partially supported by National Natural Science Foundation of China (61972438) and Wuhu Science and Technology Plan Project (2023yf117). The authors would like to thank their colleagues and students at Anhui Provincial Engineering Research Center of Medical Big Data Intelligent System.

^*

http://www.kaggle.com

Conflict of interest

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Author contributions

Ren Chen proposed the conceptualization and reviewed & edited the manuscript. Chao Wang conducted the experiment and wrote the original draft. Fulong supervised this study and validated it. All authors reviewed the manuscript.

Novelty claim

The proposed novel diabetes prediction framework underpinned by a neural network architecture featuring a parameterized activation function, called the Self-Learning Activation Linear Unit (SLALU), is a classifier model equipped with an automatically adjustable activation neural network alongside a one-dimensional self-attention mechanism.

Ethics approval of research

The Ethics Committee of Anhui Normal University, approved all procedures. The datasets PIDD and LMCH for this study can be found in Kaggle (www.kaggle.com).

References

[1]	Khan R, Chua Z, Tan J, et al. (2019) From pre-diabetes to diabetes: diagnosis, treatments and translational research. Medicina 55: 546. https://doi.org/10.3390/medicina55090546
[2]	Vaishali R, Sasikala R, Ramasubbareddy S, et al. (2017) Genetic algorithm based feature selection and moe fuzzy classification algorithm on pima indians diabetes dataset. International Conference on Computing Networking and Informatics (ICCNI) : 1-5. https://doi.org/10.1109/ICCNI.2017.8123815
[3]	Cheng Y, Caughey A (2008) Gestational diabetes: diagnosis and management. J Perinatol 28: 657-664. https://doi.org/10.1038/jp.2008.62
[4]	Bukhari M, Alkhamees B, Hussain S, et al. (2021) An improved artificial neural network model for effective diabetes prediction. Complexity 2021: 5525271. https://doi.org/10.1155/2021/5525271
[5]	Khanam J, Foo S (2021) A comparison of machine learning algorithms for diabetes prediction. Ict Express 7: 432-439. https://doi.org/10.1016/j.icte.2021.02.004
[6]	Naz H, Ahuja S (2020) Deep learning approach for diabetes prediction using pima indian dataset. J Diabetes Metab Disord 19: 391-403. https://doi.org/10.1007/s40200-020-00520-5
[7]	Alam T, Iqbal M, Ali Y (2019) A model for early prediction of diabetes. Inf Med Unlocked 16: 100204. https://doi.org/10.1016/j.imu.2019.100204
[8]	Fröhlich W, Rigo S, Bez M (2024) Athena i—an architecture for near real-time physiological signal monitoring and pattern detection. Future Gener Comp Sy 150: 395-411. https://doi.org/10.1016/j.future.2023.09.010
[9]	Liu J, Xiao Z, Lu S, et al. (2023) Infrastructure-level support for gpu-enabled deep learning in dataview. Future Gener Comp Sy 141: 723-737. https://doi.org/10.1016/j.future.2022.12.014
[10]	Sivaranjani S, Ananya S, Aravinth J, et al. (2021) Diabetes prediction using machine learning algorithms with feature selection and dimensionality reduction. 7th International Conference on Advanced Computing and Communication Systems (ICACCS) 1: 141-146. https://doi.org/10.1109/ICACCS51430.2021.9441935
[11]	Gnanadass I (2020) Prediction of gestational diabetes by machine learning algorithms. IEEE Potentials 39: 32-37. https://doi.org/10.1109/MPOT.2020.3015190
[12]	Hasan M, Alam M, Das D, et al. (2020) Diabetes prediction using ensembling of different machine learning classifiers. IEEE Access 8: 76516-76531. https://doi.org/10.1109/ACCESS.2020.2989857
[13]	Dwivedi AK (2018) Analysis of computational intelligence techniques for diabetes mellitus prediction. Neural Comput Appl 30: 3837-3845. https://doi.org/10.1007/s00521-017-2969-9
[14]	Shen L, Chen H, Yu Z, et al. (2016) Evolving support vector machines using fruit fly optimization for medical data classification. Knowl-Based Syst 96: 61-75. https://doi.org/10.1016/j.knosys.2016.01.002
[15]	Wu Y, Zhang Q, Hu Y, et al. (2022) Novel binary logistic regression model based on feature transformation of XGBoost for type 2 diabetes mellitus prediction in healthcare systems. Future Gener Comp Sy 129: 1-12. https://doi.org/10.1016/j.future.2021.11.003
[16]	Ma N, Zhang X, Liu M, et al. (2021) Activate or not: learning customized activation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition : 8032-8042. https://doi.org/10.1109/CVPR46437.2021.00794
[17]	Nair V, Hinton G (2010) Rectified linear units improve restricted boltzmann machines. 27th international conference on machine learning (ICML) : 807-814. https://doi.org/10.5555/3104322.3104425
[18]	He K, Zhang X, Ren S, et al. (2015) Delving deep into rectifiers: surpassing human-level performance on imagenet classification. Proceedings of the IEEE international conference on computer vision : 1026-1034. https://doi.org/10.1109/ICCV.2015.123
[19]	Godfrey L, Gashler M (2015) A continuum among logarithmic, linear, and exponential functions, and its potential to improve generalization in neural networks. 7th international joint conference on knowledge discovery, knowledge engineering and knowledge management (IC3K) 1: 481-486. https://doi.org/10.48550/arXiv.1602.01321
[20]	Trottier L, Giguere P, Chaib-Draa B (2017) Parametric exponential linear unit for deep convolutional neural networks. 16th IEEE international conference on machine learning and applications (ICMLA) : 207-214. https://doi.org/10.1109/ICMLA.2017.00038
[21]	Zhuang K, Zhang C, Chen Z, et al. (2025) Integrating convolutional neural networks with ensemble methods for enhanced diabetes diagnosis: a multi-dataset evaluation. Front Med 12: 1657889. https://doi.org/10.3389/fmed.2025.1657889
[22]	Tian G, Yang Y, Wen S (2025) Time-series stock price forecasting based on neural networks: a comprehensive survey. Artif Intell Sci Eng 1: 255-277. https://doi.org/10.23919/AISE.2025.000018
[23]	Whig P, Gupta K, Jiwani N, et al. (2023) A novel method for diabetes classification and prediction with pycaret. Microsyst Technol 29: 1479-1487. https://doi.org/10.1007/s00542-023-05473-2
[24]	AlZu'bi S, Elbes M, Mughaid A, et al. (2023) Diabetes monitoring system in smart health cities based on big data intelligence. Future Int 15: 85. https://doi.org/10.3390/fi15020085
[25]	Smith JW, Everhart JE, Dickson WC, et al. (1988) Using the ADAP learning algorithm to forecast the onset of diabetes mellitus. Proceedings of the annual symposium on computer application in medical care 9: 261-265.
[26]	Saxena R, Sharma SK, Gupta M, et al. (2022) A novel approach for feature selection and classification of diabetes mellitus: machine learning methods. Comput Intel Neurosce 2022: 3820360. https://doi.org/10.1155/2022/3820360
[27]	Mushtaq Z, Ramzan MF, Ali S, et al. (2022) Voting classification-based diabetes mellitus prediction using hypertuned machine-learning techniques. Mob Inf Syst 2022: 6521532. https://doi.org/10.1155/2022/6521532
[28]	Chou CY, Hsu DY, Chou CH (2023) Predicting the onset of diabetes with machine learning methods. J Pers Med 13: 406. https://doi.org/10.3390/jpm13030406
[29]	Al Reshan MS, Amin S, Zeb MA, et al. (2024) An innovative ensemble deep learning clinical decision support system for diabetes prediction. IEEE Access 12: 106193-106210. https://doi.org/10.1109/ACCESS.2024.3436641
[30]	Waughfa ZM, Adnan II, Sultana SS, et al. (2024) Diabetes prediction: a comprehensive study integrating deep learning and machine learning approaches. Proceedings of the 3rd International Conference on Computing Advancements : 520-526. https://doi.org/10.1145/3723178.3723247
[31]	Soltanizadeh S, Mobini M, Naghibi SS (2025) Design of a low-complexity deep learning model for diagnosis of type 2 diabetes. Curr Diabetes Rev 21: E15733998307556. https://doi.org/10.2174/0115733998307556240819093038
[32]	Rahaman MA, Idris RM, Zuveriya S, et al. (2024) Enhancing diabetes mellitus onset prediction through advanced ensemble learning techniques. JOSMA 6: 11-28. https://doi.org/10.22452/josma.vol6no2.2
[33]	Andrade-Arenas L, Yactayo-Arias C (2025) Comparative evaluation of machine learning models for diabetes prediction: a focus on ensemble methods. Ingenierie des Systemes d'Information 30: 1795. https://doi.org/10.18280/isi.300712
[34]	Landau S, Everitt B (2003) A Handbook of Statistical Analyses using SPSS. New York: CRC Press. https://doi.org/10.1201/9780203009765

Reader Comments

Your name:*

Email:*
© 2026 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)