A Hybrid Deep Learning Architecture for Cost-Effective, Real-Time IV Infusion Anomaly Detection using IoT Sensors

Muhammad Brian Nafis; Cinantya Paramita; Sasha-Gay Wright

doi:10.52436/1.jutif.2025.6.6.5440

Authors

Muhammad Brian Nafis Faculty of Computer Science, Universitas Dian Nuswantoro, Semarang, Indonesia
Cinantya Paramita Dinus Research Group for AI in Medical Science (DREAMS), Universitas Dian Nuswantoro, Semarang, Indonesia
Sasha-Gay Wright Biomedical Engineering, Faculty of Engineering, University of the West Indies Mona, Jamaica

DOI:

https://doi.org/10.52436/1.jutif.2025.6.6.5440

Keywords:

Anomaly Detection, Deep Learning, Ensemble Learning, Internet of Things, Infusion Monitoring, Real-Time Systems

Abstract

Intravenous (IV) infusion therapy is a critical medical procedure, yet manual monitoring increases the risk of complications such as air embolism and irregular infusion flow, particularly in resource-constrained environments. Although several automated infusion monitoring systems have been proposed, their high implementation cost limits practical adoption. This research develops a low-cost IoT-based infusion monitoring system capable of real-time anomaly detection using a multi-architecture machine learning approach. The proposed prototype integrates an ESP32 microcontroller with load cell (HX711) and optical (LM393) sensors to acquire time-series infusion data. Ten models from classical machine learning, deep learning, hybrid, and ensemble categories were evaluated using a dataset of 10,420 records under a unified experimental setup. The results show that XGBoost had a perfect recall (1.0000) and a strong PRAUC, while the LSTM Autoencoder had the highest F1-Score (0.9343) and precision (0.8934). The best overall performance came from hybrid and ensemble methods, with CNN–LSTM having an F1-Score of 0.89, a recall of 0.99, and a precision of 0.80. This means they would be great for clinics where being sensitive is very important. The research shows that using a low-cost IoT infrastructure with carefully chosen deep learning or ensemble models can help find problems in real time. A web dashboard explains how the technology operates and its capabilities. This study examines a cost-effective and easily scalable method to enhance infusion safety in hospitals with limited financial resources.

Downloads

Download data is not yet available.

References

S. K. Kuitunen, I. Niittynen, M. Airaksinen, and A.-R. Holmström, “Systemic Defenses to Prevent Intravenous Medication Errors in Hospitals: A Systematic Review,” J Patient Saf, vol. 17, no. 8, pp. e1669–e1680, Dec. 2021, doi: 10.1097/PTS.0000000000000688.

S. Rajakumar, R. Rajah, S. Thanimalai, F. B. M. Mokhtar, and D. S. Ramachandram, “Intravenous Medication Administration Errors in Hospitalised Patients: An Updated Systematic Review,” Evaluation Clinical Practice, vol. 31, no. 4, p. e70167, June 2025, doi: 10.1111/jep.70167.

R. Maniktalia, S. Tanwar, R. Billa, and D. K, “IoT Based Drip Infusion Monitoring System,” in 2022 IEEE Delhi Section Conference (DELCON), Feb. 2022, pp. 1–6. doi: 10.1109/DELCON54057.2022.9753052.

S. Kuitunen, I. Niittynen, M. Airaksinen, and A.-R. Holmström, “Systemic Causes of In-Hospital Intravenous Medication Errors: A Systematic Review,” J Patient Saf, vol. 17, no. 8, pp. e1660–e1668, Dec. 2021, doi: 10.1097/PTS.0000000000000632.

W. Ahmed et al., “Addressing Critical Mistakes in Administering Intravenous Medications at Omdurman Military Hospital, Khartoum, Sudan,” IJGM, vol. Volume 18, pp. 123–133, Jan. 2025, doi: 10.2147/IJGM.S497591.

A. Sutherland, M. Canobbio, J. Clarke, M. Randall, T. Skelland, and E. Weston, “Incidence and prevalence of intravenous medication errors in the UK: a systematic review,” Eur J Hosp Pharm, vol. 27, no. 1, pp. 3–8, Jan. 2020, doi: 10.1136/ejhpharm-2018-001624.

World Health Organization (WHO), “Patient Safety — Factsheet,” 2023. [Online]. Available: https://www.who.int/news-room/fact-sheets/detail/patient-safety

J. G. Jessurun, N. G. M. Hunfeld, J. Van Rosmalen, M. Van Dijk, and P. M. L. A. Van Den Bemt, “Prevalence and determinants of intravenous admixture preparation errors: A prospective observational study in a university hospital,” Int J Clin Pharm, vol. 44, no. 1, pp. 44–52, Feb. 2022, doi: 10.1007/s11096-021-01310-6.

K. Kwiecień-Jaguś, W. Mędrzycka-Dąbrowska, and M. Kopeć, “Understanding Medication Errors in Intensive Care Settings and Operating Rooms—A Systematic Review,” Medicina, vol. 61, no. 3, p. 369, Feb. 2025, doi: 10.3390/medicina61030369.

M. R. K K, M. N. M, R. Zidan, I. Alsarraj, and B. Hasan, “IOT-Based Wireless Patient Monitor Using ESP32 Microcontroller,” in 2023 24th International Arab Conference on Information Technology (ACIT), Dec. 2023, pp. 1–6. doi: 10.1109/ACIT58888.2023.10453847.

P. Gupta, A. Rao, P. Chimurkar, and P. Kasambe, “An Automated IoT-Enabled Real-Time Intravenous Infusion cum Remote Patient Monitoring System,” in 2025 International Conference on Emerging Smart Computing and Informatics (ESCI), Mar. 2025, pp. 1–6. doi: 10.1109/ESCI63694.2025.10988336.

C. L. Kok, T. H. Teo, Y. Y. Koh, Y. Dai, B. K. Ang, and J. P. Chai, “Development and Evaluation of an IoT-Driven Auto-Infusion System with Advanced Monitoring and Alarm Functionalities,” in 2024 IEEE International Symposium on Circuits and Systems (ISCAS), May 2024, pp. 1–5. doi: 10.1109/ISCAS58744.2024.10558602.

S. Meenatchi Sundaram, J. R. Naik, M. Natarajan, and A. Acharya K, “Design and development of an IoT-based trolley for weighing the patient in lying condition,” Front. Digit. Health, vol. 6, p. 1339184, Sept. 2024, doi: 10.3389/fdgth.2024.1339184.

C. G. Babu, J. R. D. Kumar, V. R. Balaji, K. Priyadharsini, and S. P. Karthi, “Performance Analysis of Smart Intravenous Infusion Systems using Machine Learning,” in 2021 Smart Technologies, Communication and Robotics (STCR), Sathyamangalam, India: IEEE, Oct. 2021, pp. 1–7. doi: 10.1109/STCR51658.2021.9588997.

G. M. Nagamani and C. K. Kumar, “Design of an improved graph-based model for real-time anomaly detection in healthcare using hybrid CNN-LSTM and federated learning,” Heliyon, vol. 10, no. 24, p. e41071, Dec. 2024, doi: 10.1016/j.heliyon.2024.e41071.

M. A. Morid, O. R. L. Sheng, and J. Dunbar, “Time Series Prediction Using Deep Learning Methods in Healthcare,” ACM Trans. Manage. Inf. Syst., vol. 14, no. 1, pp. 1–29, Mar. 2023, doi: 10.1145/3531326.

Z. Z. Darban, G. I. Webb, S. Pan, C. C. Aggarwal, and M. Salehi, “Deep Learning for Time Series Anomaly Detection: A Survey,” ACM Comput. Surv., vol. 57, no. 1, pp. 1–42, Jan. 2025, doi: 10.1145/3691338.

M. Obuseh, D. Yu, and P. DeLaurentis, “Detecting Unusual Intravenous Infusion Alerting Patterns with Machine Learning Algorithms,” 2022.

L. Meneghetti, E. Dassau, F. J. Doyle, and S. Del Favero, “Machine Learning-Based Anomaly Detection Algorithms to Alert Patients Using Sensor Augmented Pump of Infusion Site Failures,” J Diabetes Sci Technol, vol. 16, no. 3, pp. 641–648, May 2022, doi: 10.1177/1932296821997854.

L. Kirichenko, Y. Koval, S. Yakovlev, and D. Chumachenko, “Anomaly Detection in Fractal Time Series with LSTM Autoencoders,” Mathematics, vol. 12, no. 19, p. 3079, Oct. 2024, doi: 10.3390/math12193079.

M. Hizem, L. Bousbia, Y. Ben Dhiab, M. O.-E. Aoueileyine, and R. Bouallegue, “Reliable ECG Anomaly Detection on Edge Devices for Internet of Medical Things Applications,” Sensors, vol. 25, no. 8, p. 2496, Apr. 2025, doi: 10.3390/s25082496.

S. Rani et al., “Machine Learning-Powered Smart Healthcare Systems in the Era of Big Data: Applications, Diagnostic Insights, Challenges, and Ethical Implications,” Diagnostics, vol. 15, no. 15, p. 1914, July 2025, doi: 10.3390/diagnostics15151914.

S. Ustebay, A. Sarmis, G. K. Kaya, and M. Sujan, “A comparison of machine learning algorithms in predicting COVID-19 prognostics,” Intern Emerg Med, vol. 18, no. 1, pp. 229–239, Jan. 2023, doi: 10.1007/s11739-022-03101-x.

H. Luo et al., “SHAP based predictive modeling for 1 year all-cause readmission risk in elderly heart failure patients: feature selection and model interpretation,” Sci Rep, vol. 14, no. 1, p. 17728, July 2024, doi: 10.1038/s41598-024-67844-7.

A. Naik, G. G. Tejani, and S. J. Mousavirad, “SGO enhanced random forest and extreme gradient boosting framework for heart disease prediction,” Sci Rep, vol. 15, no. 1, p. 18145, May 2025, doi: 10.1038/s41598-025-02525-7.

R. Samuel and T. Pandi, “Optimizing brain stroke detection with a weighted voting ensemble machine learning model,” Sci Rep, vol. 15, no. 1, p. 31215, Aug. 2025, doi: 10.1038/s41598-025-14358-5.

P. Mahajan, S. Uddin, F. Hajati, and M. A. Moni, “Ensemble Learning for Disease Prediction: A Review,” Healthcare, vol. 11, no. 12, p. 1808, June 2023, doi: 10.3390/healthcare11121808.

S. M. Ganie, P. K. D. Pramanik, and Z. Zhao, “Ensemble learning with explainable AI for improved heart disease prediction based on multiple datasets,” Sci Rep, vol. 15, no. 1, p. 13912, Apr. 2025, doi: 10.1038/s41598-025-97547-6.

C. Paramita, C. Supriyanto, P. Šolić, C. Wada, and A. A. Dzaky, “Performance Evaluation of YOLOv8 Models for Multi-Class Skin Lesion Detection from Dermoscopic Images,” in 2025 International Conference on Smart Computing, IoT and Machine Learning (SIML), Surakarta, Indonesia: IEEE, June 2025, pp. 1–6. doi: 10.1109/SIML65326.2025.11080819.

B. A. Mahendra, C. Supriyanto, C. Paramita, N. Z. B. M. Safar, and I. N. Dewi, “Development of a Smartphone-Based Cataract Detection System Using YOLOv10x and Ionic Framework with a UI/UX Centric Approach,” in 2025 International Conference on Smart Computing, IoT and Machine Learning (SIML), Surakarta, Indonesia: IEEE, June 2025, pp. 1–5. doi: 10.1109/SIML65326.2025.11081150.

E. R. Subhiyakto et al., “Evaluation of Resampling Techniques in CNN-Based Heartbeat Classification,” ISI, vol. 29, no. 4, pp. 1323–1332, Aug. 2024, doi: 10.18280/isi.290408.

K. Anggriani, S. Az Zahra, and A. Susanto, “Enhancing Malware Detection in IoT Networks using Ensemble Learning on IoT-23 Dataset,” J. Tek. Inform. (JUTIF), vol. 6, no. 4, pp. 1985–2000, Aug. 2025, doi: 10.52436/1.jutif.2025.6.4.4782.

P. S. Chirumamilla, G. Sunitha, A. Sneha, V. Thirupathi, C. R. Naidu, and A. L. Rao, “A Hybrid Approach for IoT Sensor Anomaly Detection with LSTM and Autoencoder-Based Preprocessing,” in 2025 International Conference on Advances in Modern Age Technologies for Health and Engineering Science (AMATHE), Apr. 2025, pp. 1–6. doi: 10.1109/AMATHE65477.2025.11081356.

A. Iqbal, R. Amin, F. S. Alsubaei, and A. Alzahrani, “Anomaly detection in multivariate time series data using deep ensemble models,” PLoS ONE, vol. 19, no. 6, p. e0303890, June 2024, doi: 10.1371/journal.pone.0303890.

A. G. Ayad, N. A. Sakr, and N. A. Hikal, “A hybrid approach for efficient feature selection in anomaly intrusion detection for IoT networks,” J Supercomput, vol. 80, no. 19, pp. 26942–26984, Dec. 2024, doi: 10.1007/s11227-024-06409-x.

Doreswamy, M. K. Hooshmand, and I. Gad, “Feature selection approach using ensemble learning for network anomaly detection,” CAAI Trans on Intel Tech, vol. 5, no. 4, pp. 283–293, Dec. 2020, doi: 10.1049/trit.2020.0073.

Kurniabudi, D. Stiawan, Darmawijoyo, M. Y. Bin Idris, A. M. Bamhdi, and R. Budiarto, “CICIDS-2017 Dataset Feature Analysis With Information Gain for Anomaly Detection,” IEEE Access, vol. 8, pp. 132911–132921, 2020, doi: 10.1109/ACCESS.2020.3009843.

Y. Yin et al., “IGRF-RFE: a hybrid feature selection method for MLP-based network intrusion detection on UNSW-NB15 dataset,” J Big Data, vol. 10, no. 1, p. 15, Feb. 2023, doi: 10.1186/s40537-023-00694-8.

N. Anil Kumar, S. Kuchi, S. V. Krishna, P. L. Narasimha, K. S. Sree, and B. Ashreetha, “Voice-Based Detection of Parkinson’s Disease: A Multi-Machine Learning Model Approach,” in 2025 International Conference on Knowledge Engineering and Communication Systems (ICKECS), Apr. 2025, pp. 1–9. doi: 10.1109/ICKECS65700.2025.11034824.