Machine learning for improved medical device management: A focus on dialysis machines
Mato Martinović1, Milena Kosović1, Lemana Spahić2,3
1Faculty of Information Systems and Technologies, University of Donja Gorica, Oktoih 1, 81000 Podgorica, Montenegro.
Summary
Machine learning models can predict dialysis machine performance and errors, reducing patient deaths and repair costs. This predictive maintenance approach enhances treatment quality and aids clinical engineering departments.
Area of Science:
- Biomedical Engineering
- Health Technology Management
- Machine Learning in Healthcare
Background:
- Dialysis is a critical treatment for millions, but technical errors in dialysis machines cause approximately 10% of patient deaths.
- Predictive maintenance using machine learning offers a solution to mitigate risks associated with dialysis device failures.
Purpose of the Study:
- To predict dialysis machine performance status and identify potential errors using various regression models.
- To enhance the reliability and safety of dialysis treatments through advanced technological management.
Main Methods:
- A seven-step methodology involving data collection, preprocessing (1034 measurements), model selection, training, evaluation, fine-tuning, and prediction.
- Twelve machine learning models were trained to predict machine performance, temperature, and conductivity errors.
Main Results:
- Logistic regression showed the highest accuracy in predicting dialysis machine performance.
- Support Vector Machine (SVM) achieved the lowest Mean Squared Error (MSE) on the testing dataset for both temperature and conductivity predictions.
- Various models demonstrated effectiveness in predicting specific parameters, with Lasso and Linear regression showing strong performance for temperature and Decision Tree for conductivity.
Conclusions:
- The study highlights the potential of automated systems for advanced dialysis machine management within clinical engineering and health technology departments.
- Implementing these machine learning models can significantly improve the quality of care and reduce operational costs associated with dialysis treatments.
Related Concept Videos
01:27Dialysis
231
Renal failure occurs when the kidneys lose their ability to filter waste products from the blood effectively. It can be classified into two types: acute renal failure (ARF) and chronic renal failure (CRF).
Acute kidney injury develops suddenly and can be caused by pre-renal causes (e.g., hypovolemia, shock), intrinsic renal causes (e.g., acute tubular necrosis), or post-renal causes (e.g., urinary obstruction). In contrast, chronic renal failure progresses gradually over time and is often...
Acute kidney injury develops suddenly and can be caused by pre-renal causes (e.g., hypovolemia, shock), intrinsic renal causes (e.g., acute tubular necrosis), or post-renal causes (e.g., urinary obstruction). In contrast, chronic renal failure progresses gradually over time and is often...
231
01:22Heart Failure Drugs: Diuretics
294
Heart failure and kidney perfusion are interconnected in a complex way. Reduced renal perfusion and venous congestion are two significant factors that contribute to renal dysfunction in heart failure. The kidneys, primarily responsible for fluid balance in the body, are adversely affected due to compromised cardiac output and increased venous pressure. In response to reduced renal perfusion, the kidneys activate neurohumoral mechanisms to restore balance. However, these mechanisms can be...
294