P1559PERFORMANCE EVALUATION OF REAL-TIME MULTI-BED MONITORING SYSTEM FOR BLOOD LEAKAGE IN DIALYSIS

Abstract

Abstract Background and Aims In HD treatment, venous needle dislodgement (VND) is a major concern in healthcare systems worldwide. Although VND is not an extremely common occurrence, it could be life-threatening or even cause death. The report of the Taiwan Patient Safety Reporting System listed the dislodgement of needles, catheters, and similar devices as third among thirteen common incident types that threaten patient safety. Hospitals are jointly liable for the blood leakage and have to provide emergency treatment such as emergency hemostasis, blood transfusion, Erythropoietin (EPO) injection and hospitalization. To a worse extent, hospitals, physicians and paramedics have to face criminal charges and the claims raised by the patients’ families. This study employed digital technology to develop a real-time multi-bed monitoring system to detect fluid leakage and control the state of multi-bed blood leakage simultaneously, allowing paramedics to respond to and solve issues swiftly. The research evaluated the IoT system for the leakage detector system with multi-bed monitoring interface by clinical trials. Method Our research used the Acusense IoT platform, which is a multi-bed monitoring system that includes leakage detection device, IoT gateway, and cloud analysis system to monitor multiple HD patients in real-time. Any single IoT gateway can be utilized to pair with eight blood leakage detection devices and collects data with multi-point Bluetooth 4.2, and the information gathered by IoT gateway will be uploaded to database via WiFi. The selecting criteria for participants, who has low risk of blood leakage and the participants who did not have blood leakage within two months, were all excluded from our analysis. Before a clinical trial, 20 nurses were trained to use the leakage detection system for two times. And then we have set this platform on different areas for 1 month. For the results of blood leakage detection system in the clinical settings, we calculated accuracy, recall, precision, and averaged F score, which are the most common metrics for evaluating the performance of binary classification. Results In this study, a total of 50 subjects with an average age and standard deviation (SD) of 62.2 and 9.1 were recruited from the Tainan Municipal An-Nan Hospital (TMANH) in Taiwan. After deploying Acusense IoT platform in clinical workflow, there were a total of 682 dialysis sessions and 15 events of venous needle dislodgement or bleeding occurred of which 13 were detected by the device. The performance metrics reach 99.7% accuracy, 100% recall, 99.7% precision, and 99.9% Averaged F-measure. There are no adverse reactions to patients. It indicates that the proposed blood leakage detection system showed favorable performance, and was proven to be capable of accurately detecting blood leakage. Conclusion The blood leakage detector combined with information system realizes the multi-bed monitoring system and provides support for real-time clinical decision support system. When venous needle dislodgement happens, the monitoring system will timely warn nurse to increase the relationship between doctors and patients. It may result in the prevention of VND, and decreased hospitalization to reduce the side effects of hemodialysis.