No abstract

Multi-parameter patient monitors (MPMs) have become increasingly important in providing quality healthcare to patients. It is well known in the medical community that there exists an intrinsic relationship between different vital parameters in a healthy person, these include heart rate, blood pressure, respiration rate and oxygen saturation. For example, an increase in blood pressure would lead to a decrease in the heart rate, and vice versa. Although it is likely to improve the performance of MPM systems, this fact is not explored in engineering research. In this work, experiments show that deriving additional features to capture the intrinsic relationship between the vital parameters, the alarm accuracy (sensitivity), no-alarm accuracy (specificity) and the overall performance of MPMs can be improved. The geometric mean of the product of all the vital parameters taken in pairs of two was used to capture the intrinsic relationship between the different parameters. An improvement of 10.55% for sensitivity, 0.32% for specificity and an overall performance improvement of 1.03% was obtained, compared to the baseline system using classification and regression tree with the four vital parameters.

Multi-parameter patient monitors (MPMs) have become increasingly important in providing quality health care to patients. A high alarm accuracy (sensitivity) will need a lower threshold for alarm detection which will lead to lower no-alarm accuracy (specificity) and viceversa. MPMs when used in an intensive care unit (ICU) need to have high sensitivity. However they need to have high specificity when used in in-patient wards for regular health check-ups. Proposed is a novel algorithm to trade-off specificity for sensitivity and viceversa depending on the application. The proposed method is referred as detection error trade-off, trade-off specificity for better sensitivity and vice-versa. The algorithm will help to extend the application of MPMs from ICUs to in-patient wards and thus enhance the quality of health care. Experiments have been conducted with an MPM using the classification and regression tree algorithm. By using the proposed algorithm, an improvement of 10.18% in sensitivity was obtained by trading-off 0.40% in specificity. Furthermore, the overall performance of the refined system is 1.15% better than the baseline system.Introduction: Multi-parameter patient monitors (MPMs) [1] are systems that use patients' vital signs (measurement of the body's physiological functions) such as heart rate, arterial blood pressure, respiration rate and oxygen saturation (SpO 2 ). Zhang [1] described the use of the ID3 [2] decision-tree algorithm for multi-parameter patient monitoring and states that the system consumes more time for efficient performance. However, in real time analysis, it would be ideal if the MPMs learn the trends in the patient's vital signs in a short time and predict his/ her status of health based on continuous monitoring. In addition, it is important that the system should have low probability for missing an alarm, P miss , and low false alarm probability, P fa , a no-alarm condition getting reported as an alarm. This means that the alarm accuracy, sensitivity and the no-alarm accuracy, specificity, should be as a high as possible. However, for an MPM when used in an intensive care unit (ICU), we cannot afford to miss an alarm, whereas we could afford to have a few more false alarms. Similarly, if an MPM is deployed in an in-patient ward, we may like to have high specificity.In this Letter, we focus on how we can trade-off specificity for better sensitivity, and vice-versa, to fine tune the performance of the MPM towards the application. We use a decision-tree learning algorithm, classification and regression tree (CART) [3], the decision-tree learning algorithm using Gini-impurity index as the parameter for constructing the tree. The system developed in the present work focuses on efficiently learning the trends in vital signs, acquired from the MIMIC II database [4,5] in a short time.