In this study, we constructed a quality risk early warning model for blood diagnostic reagents based on big data, integrating Random Forest, Support Vector Machine and Long and Short Term Memory Network algorithms, which achieved an early warning accuracy of 87.6%, and identified the potential risks 15.3 days in advance on average. By analysing data from 12,456 batches of reagents, the model identified key risk factors and their interactions, such as the coefficient of variation between batches of raw materials (0.187) and fluctuations in environmental temperature and humidity (0.165). The validation results show that the accuracy of the model in predicting the risks of raw materials and production environment reaches 92.1% and 89.3%, respectively, and 17 quality problems were successfully avoided in 5 enterprises in 6 months, which provides an accurate and intelligent solution for the quality risk management of medical devices.

Ruoyun Zou. Research on quality risk early warning model of blood diagnostic reagents based on big data analysis. Academic Journal of Computing & Information Science(2025), Vol. 8, Issue 3: 109-115. https://doi.org/10.25236/AJCIS.2025.080315.

[1] Oeschger T M, McCloskey D S, Buchmann R M, et al. Early warning diagnostics for emerging infectious diseases in developing into late-stage pandemics[J]. Accounts of Chemical Research, 2021, 54(19): 3656-3666.

[2] Hulsen T, Friedecký D, Renz H, et al. From big data to better patient outcomes[J]. Clinical Chemistry and Laboratory Medicine (CCLM), 2023, 61(4): 580-586.

[3] Zhou W, Li S, Sun G, et al. Early warning of ischemic stroke based on atherosclerosis index combined with serum markers[J]. The Journal of Clinical Endocrinology & Metabolism, 2022, 107(7): 1956-1964.

[4] Zhou W, Li S, Sun G, et al. Early warning of ischemic stroke based on atherosclerosis index combined with serum markers[J]. The Journal of Clinical Endocrinology & Metabolism, 2022, 107(7): 1956-1964.

[5] Kaur N, Bhattacharya S, Butte A J. Big data in nephrology[J]. Nature Reviews Nephrology, 2021, 17(10): 676-687.

[6] Zhang X, Zheng M H, Liu D, et al. A blood-based biomarker panel for non-invasive diagnosis of metabolic dysfunction-associated steatohepatitis[J]. Cell Metabolism, 2025, 37(1): 59-68. e3.

[7] Kaur N, Bhattacharya S, Butte A J. Big data in nephrology[J]. Nature Reviews Nephrology, 2021, 17(10): 676-687.

[8] Baldeh M , Bawa F K , Bawah F U ,et al. Lessons from the pandemic: new best practices in selecting molecular diagnostics for point-of-care testing of infectious diseases in sub-Saharan Africa [J].Expert Review of Molecular Diagnostics, 2024, 24(3):8.DOI:10.1080/14737159.2023.2277368.

[9] Saeed R, Zhang L, Cai Z, et al. Multisensor monitoring and water quality prediction for live ornamental fish transportation based on artificial neural network[J]. Aquaculture Research, 2022, 53(7): 2833-2850.

[10] Korpi-Steiner N, Horowitz G, Tesfazghi M, et al. Current issues in blood gas analysis[J]. The journal of applied laboratory medicine, 2023, 8(2): 372-381.

[11] Peeling R W, Sia S K. Lessons from COVID-19 for improving diagnostic access in future pandemics[J]. Lab on a Chip, 2023, 23(5): 1376-1388.

[12] Ma, K., & Shen, J. (2024). Interpretable Machine Learning Enhances Disease Prognosis: Applications on COVID-19 and Onward. arXiv preprint arXiv:2405.11672.

[13] Ma, K. (2024). Employee Satisfaction and Firm Performance: Evidence from a Company Review Website. International Journal of Global Economics and Management, 4(2), 407-416.

[14] Wu Y, Yang Y, Xiao J S, et al. Invariant Spatiotemporal Representation Learning for Cross-patient Seizure Classification[C]//The First Workshop on NeuroAI@ NeurIPS2024.

[15] Ma J, Duan Z, Zheng L, Nguyen C. Multiview detection with cardboard human modeling[C]//Computer Vision – ACCV 2024. Lecture Notes in Computer Science, Vol. 15477. Asian Conference on Computer Vision. Berlin, Heidelberg: Springer, 2024: 53-70.

[16] Cheng Y, Yang Q, Wang L, Xiang A, Zhang J. Research on credit risk early warning model of commercial banks based on neural network algorithm[J]. Financial Engineering and Risk Management, 2024, 7(4): 20-395. 

[17] Wang L, Cheng Y, Gong H, et al. Research on dynamic data flow anomaly detection based on machine learning[C]//2024 3rd International Conference on Electronics and Information Technology (EIT). IEEE, 2024: 953-956.

[18] Liang Y, Xie S, Zheng X, et al. Predicting higher risk factors for COVID-19 short-term reinfection in patients with rheumatic diseases: a modeling study based on XGBoost algorithm[J]. Journal of Translational Medicine, 2024, 22: 1144.

[19] .Gao Y , Wang J , Gao S ,et al.An Integrated Robust Design and Robust Control Strategy Using the Genetic Algorithm[J].IEEE Transactions on Industrial Informatics, 2021, 17(12): 8378-8386.

[20] Yang C. CM-Net: concentric mask based arbitrary-shaped text detection[J]. IEEE Transactions on Image Processing, 2022, 31: 2864-2877.