Key result
Naive Bayes machine learning accurately classifies blood pressure levels from 24-hour ABPM data.
Why the study?
Hypertension requires early diagnosis and management to avert adverse effects, and ABPM is essential for proper diagnosis especially in the presence of white coat effect or masked hypertension.
Does a Naive Bayes machine learning algorithm accurately classify blood pressure levels using 24-hour ABPM data?
Does a Naive Bayes machine learning algorithm accurately classify blood pressure levels using 24-hour ABPM data?
Answers are grounded in this paper and cite their sources.
A Naive Bayes machine learning model can effectively classify blood pressure levels using 24-hour ambulatory blood pressure monitoring data.
Background: Hypertension requires the need for diagnosing and management as early as possible to avert its adverse effects. It is still one of the most critical concerns facing the health sector globally. ABPM is essential for the proper diagnosis of hypertension, especially in the presence of white coat effect or masked hypertension. The methodology of the current research work adopted the collection of continuous 24hour ABPM recording data, this brought major physiological characteristics to the work. Because of its high classification accuracy rate for blood pressure, the Naive Bayes technique in our research has given valuable results applied to the actual ABPM database. This model is of utility in identifying complex interactions of the physiological indicators in the classification of hypertension. Experiment results confirm the efficiency of our knowledge-driven approach, strengthened by the Naive Bayes model while dealing with ABPM data analysis. This model demonstrates an exciting capability for the correct categorization of blood pressure levels thus; it would be useful to generate invaluable insights into effective strategies to manage hypertension.
No takes yet. Share an insight, caveat, or question.
Shanmugapriya et al. (2024) studied Hypertension. Naive Bayes machine learning algorithm was evaluated on Classification accuracy rate for blood pressure. A Naive Bayes machine learning model applied to 24-hour ambulatory blood pressure monitoring data demonstrated high classification accuracy for categorizing blood pressure levels.
Synapse has enriched 10 related papers. Consider them for comparative context: