BWatch: A Non-invasive Blood Leakage Detection Device using Robust Reflectance-based Sensing

Tan, Chee How; Khaw, Jien-Yi; Wong, Ying Ching; Chionh, Chang Yin; Foong, Shaohui

doi:10.1109/cis-ram47153.2019.9095847

Cited by 3 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Shimazaki et al [10] proposed the use of LED color sensors to detect blood leakage; however, their system requires an external battery. Tan et al [11] also used LED light intensity to detect blood leakage, but with the alarm unit and battery attached to the arm. Lee et al [26] used deep learning to determine whether the data from LED sensors were indications of blood leakage; however, the success rate of their system was only 83.7%.…”

Section: Proposed System Versus Similar Sensing Devices In the Litera...mentioning

confidence: 99%

“…Shimazaki et al [10] employed the evolution of color (chroma) in color sensors to detect blood leakage without the risk of malfunction due to chemical leakage or interference from obstacles along the light path. Tan et al [11] detected blood leakage by examining changes in the intensity of LED light using principal components analysis (PCA). The three most common commercial devices used for the detection of blood leakage during dialysis include the Redsense ® Monitor TM (Redsense ® Medical Inc., Halmstad, Sweden, FDA-approved); HEMOdialert TM (Azacare Inc., Waikanae, New Zealand), and Leak Detector (Nipro Inc., Osaka, Japan) [12][13][14].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Flexible Ring Sensor Array and Machine Learning Model for the Early Blood Leakage Detection during Dialysis

Huang

Lin

2022

Processes

View full text Add to dashboard Cite

Severe blood leakage resulting from the detachment of dialysis tubing is often difficult to detect by nurses in busy clinics. This paper presents a flexible blood leakage detection system featuring a ring-light sensor array with an operating wavelength of 500–700 nm, which is held in place by the gauze covering the dialysis puncture site. A ring-light sensor is connected to a bidirectional hetero-associative memory network, which interprets detected changes in signal strength, the output signal of which is transmitted via WiFi to a server at the nursing station where a machine learning algorithm determines whether blood leakage has occurred. The compact design of this early warning system greatly enhances the comfort and mobility of patients undergoing dialysis. The efficacy of the proposed system was demonstrated in experiments involving artificial blood.

show abstract

Section: Proposed System Versus Similar Sensing Devices In the Litera...mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Flexible Ring Sensor Array and Machine Learning Model for the Early Blood Leakage Detection during Dialysis

Huang

Lin

2022

Processes

View full text Add to dashboard Cite

show abstract

“…Through a research collaboration between the hospital and a technological university, supported by a national innovation grant, a device was developed to try to meet the specified requirements. The technological concept was presented in engineering and technology conferences 15,16 . In brief, the device is a stand-alone, disc-shaped device (43 mm in diameter, 12 mm thick, weight 11.5 g).…”

mentioning

confidence: 99%

A device for surveillance of vascular access sites for bleeding: results from a clinical evaluation trial

Chionh

Soh

Tan

et al. 2020

Sci Rep

Self Cite

View full text Add to dashboard Cite

Post-procedural wound haemorrhage is a potentially life-threatening complication. For haemodialysis patients, bleeding is often encountered after vascular access procedures and fatal episodes have been reported. Visual monitoring for bleeding is manpower intensive and bleeding episodes may still be missed between inspections. A device, Blood WArning Technology with Continuous Haemoglobin sensor (BWATCH), was developed to detect bleeding from wounds. This a prospective, observational clinical trial on patients who have had a dialysis catheter inserted or removed. The battery-powered, disc-shaped device (43 mm diameter, 12 mm height) was placed over the dressing for at least six hours. The device detects reflected light with characteristics specific for haemoglobin and an alarm would be triggered if bleeding occurs. There were 250 participants (177 post-insertion, 73 post-removal) and 36 episodes of bleeding occurred. The device alarm was triggered in all instances but there were also 9 false alarms. Specificity was 95.8%, false positive rate was 4.2% and positive predictive value was 80.0%. Sensitivity and negative predictive value were 100% but detection failure may still occur due to improper application or device maintenance. The use of technological aids for monitoring improves patient safety and may reduce demand on manpower.

show abstract

Evaluation of factors associated with bleeding following haemodialysis catheter-related procedures and the risk with anti-platelet agents

Koduri,

Keng Chionh,

Khaw

et al. 2023

J Vasc Access

View full text Add to dashboard Cite

Background: Bleeding is a potential complication following haemodialysis catheter-related procedures. Besides uraemia, bleeding risk is perceived to be even higher in patients receiving antiplatelets. This study aims to evaluate the risk factors for bleeding following dialysis catheter-related procedures. Methods: This is a secondary analysis of a single-centre, prospective cohort study between March 2019 and June 2020. Potential risk factors for bleeding were collected, including use of antiplatelets and anticoagulants, serum urea and haematological results. Patients were observed closely for external bleeding following haemodialysis catheter-related procedures. Results: From 413 patients screened, 250 were recruited. Of these, 177 underwent dialysis catheter insertion (157 tunnelled and 20 non-tunnelled) while 73 had dialysis catheter removed (35 tunnelled and 38 non-tunnelled). One hundred and four patients (41.6%) were on a single anti-platelet agent, of whom 75 (30.0%) were on aspirin and 29 (11.6%) had clopidogrel alone. Twenty-nine patients (11.6%) were on both aspirin and clopidogrel. There were 36 episodes (14.4%) of bleeding. The risk of bleeding was not significantly higher with the use of aspirin alone (odds ratio = 0.85, 95% CI: 0.36–2.02, p = 0.709), clopidogrel alone (odds ratio = 1.04, 95% CI: 0.31–3.49, p = 0.953) and both aspirin and clopidogrel (odds ratio = 0.95, 95% CI: 0.28–3.25, p = 0.938). In a multivariate analysis, none of the known bleeding risk factors had a statistically significant association with bleeding. Conclusions: Overall, the use of antiplatelet agents was not associated with an increased risk of bleeding.

show abstract

BWatch: A Non-invasive Blood Leakage Detection Device using Robust Reflectance-based Sensing

Cited by 3 publications

References 10 publications

Flexible Ring Sensor Array and Machine Learning Model for the Early Blood Leakage Detection during Dialysis

Flexible Ring Sensor Array and Machine Learning Model for the Early Blood Leakage Detection during Dialysis

A device for surveillance of vascular access sites for bleeding: results from a clinical evaluation trial

Evaluation of factors associated with bleeding following haemodialysis catheter-related procedures and the risk with anti-platelet agents

Contact Info

Product

Resources

About