Performance Comparison of a Neural Network and a Regression Linear Model for Predictive Maintenance in Dialysis Machine Components

Ensuring the reliability of dialysis machines and their components, such as sensors and actuators, is critical for maintaining continuous and safe dialysis treatment for patients with chronic kidney disease. This study investigates the application of Artificial Intelligence for detecting drift in dialysis machine components by comparing a Long Short-Term Memory (LSTM) neural network with a traditional linear regression model. Both models were trained to learn normal patterns from time-dependent signals monitoring the performance of specific components of a dialytic machine, such as a weight loss sensor in the present case, enabling the detection of anomalies related to sensor degradation or failure. Real-world data from multiple clinical cases were used to validate the approach. The LSTM model achieved high reconstruction accuracy on normal signals (most errors < 0.02, maximum ≈ 0.08), and successfully detected anomalies exceeding this threshold in complaint cases, where the model anticipated failures up to five days in advance. On the contrary, the linear regression model was limited to detecting only major deviations. These findings highlighted the advantages of AI-based methods in equipment monitoring, minimizing unplanned downtime, and supporting preventive maintenance strategies within dialysis care. Future work will focus on integrating this model into both clinical and home dialysis settings, aiming to develop a scalable, adaptable, and generalizable solution capable of operating effectively across various conditions.