Robert I Fearn, MD1, David Ziring, MD2, Karen Solis, MEd3, Irina Dorofeeva, MSc3, Chris Landon, MD4. 1Homerton University Hospital, 2Cedars Sinai Hospital, 311 Health and Technologies Inc., 4Ventura County Medical Center
Background: Intestinal stomas are frequently constructed by colorectal surgeons either electively or emergently. Perioperative high stoma output is associated with increased length of stay, readmission and renal failure. Leakage results in reduced quality of life and skin complications. Patients and healthcare professionals struggle to measure stoma output accurately. A novel technology aims to monitor stoma output and skin condition with the objective of providing accurate data to the patient and their clinical teams so that they may intervene appropriately to prevent post-operative morbidity.
Description of Technology: The Alfred SmartBag System (11 Health and Technologies Inc.) is an FDA approved medical device that integrates sensing technology into an otherwise conventional stoma bag and base-plate. It is intended to be used as a continuous ostomy monitoring system by tracking a) the volumetric filling of the pouch through integrated thermistor and capacitive sensors and b) potential leakage and skin irritation development through integrated thermistors in the base-plate. Information is relayed to the patient via a Bluetooth connection to a smartphone and displayed in an installed application to the patient and clinical team.
Preliminary Results: As a proof of concept, an array of 64 thermistors and 12 capacitive sensors arranged in a grid were embedded into a standard 350ml drainable ostomy bag along with a base-plate containing 40 thermistors arranged in two circular arrays. Sensors transmitted data wirelessly to an evaluation station. Infusion of simulated stool in 50ml aliquots resulted in a detectable spike in thermistor temperature along the flow-path and a thermal margin corresponding to the accumulated level of bag content. Leakage under the base-plate was detected as a sharp increase of temperature along the flow-path. A neural network model was used to derive predicted output and leakage events from the data.
Ten existing ileostomy patients (7F, median age 33) were recruited to a single center. Data was collected prospectively, and the device performance was described. Participants wore the device for up to 7 hours (median 2.9 hours) and all stoma output was recorded. The primary outcome was validation of the algorithm to calculate stoma output volume from thermal and capacitive measurement within the SmartBag system. A total of 40.5 bag hours of data were collected. In this time 1394ml of stoma output was measured. Mean (standard deviation) stoma output across all participants was 48.8 (36.4) ml/h. The algorithm predicted output of 1372ml in the same time period, providing a predicted mean stoma output per participant of 48.4 (39.1) ml/h.
Conclusions: In this study of a novel connected “smart” stoma bag, a neural network algorithm was derived and validated to accurately determine output volume. We show that artificial intelligence can be used to improve the accuracy of a remote monitoring solution that relies on sensors never previously deployed in this role. Complications in patients with intestinal stomas frequently result from challenges in monitoring this group. When combined with application-based resources and a telehealth communication link to the clinical team, this innovation can result in clinical interventions which might lead to improved patient outcomes.
Presented at the SAGES 2017 Annual Meeting in Houston, TX.
Abstract ID: 98699
Program Number: ETP772
Presentation Session: Emerging Technology Poster Session (Non CME)
Presentation Type: Poster