Closing the Loop

2014 ◽  
Vol 3 (1) ◽  
pp. 269-272
Author(s):  
Keith Karn ◽  
Kathryn Rieger ◽  
Eric Bergman ◽  
Bruce Hallbert ◽  
Andrew W. Gellatly ◽  
...  
Keyword(s):  
Human Factors ◽  
Medical Technology ◽  
Closed Loop ◽  
Artificial Pancreas ◽  
Subject Matter Experts ◽  
Aircraft Control ◽  
Closed Loop Systems ◽  
Power Plant Control ◽  
Closing The Loop

There has been considerable study and discussion regarding the appropriate role of the human operator in automated systems. Closed-loop systems are commonplace in manufacturing, power plant control, and aircraft control, and there is a growing body of research and public discussion related to automobile control. Closed-loop systems are less common in healthcare with some notable exceptions. The Artificial Pancreas Project is an example of a medical technology where system designers are facing difficult decisions related to removing the human from the control loop. This panel presented an opportunity for open, professional discussion on such closed-loop systems in healthcare that included subject matter experts not only from healthcare human factors, but also from the nuclear, automotive, and aviation human factors domains.

scholarly journals A Deep Learning Framework for Automatic Meal Detection and Estimation in Artificial Pancreas Systems

Sensors ◽  
2022 ◽  
Vol 22 (2) ◽  
pp. 466
Author(s):  
John Daniels ◽  
Pau Herrero ◽  
Pantelis Georgiou
Keyword(s):  
Deep Learning ◽  
Quantile Regression ◽  
Glucose Control ◽  
Closed Loop ◽  
Artificial Pancreas ◽  
Postprandial Glucose ◽  
User Engagement ◽  
Frequent User ◽  
Learning Framework ◽  
Closed Loop Systems

Current artificial pancreas (AP) systems are hybrid closed-loop systems that require manual meal announcements to manage postprandial glucose control effectively. This poses a cognitive burden and challenge to users with T1D since this relies on frequent user engagement to maintain tight glucose control. In order to move towards fully automated closed-loop glucose control, we propose an algorithm based on a deep learning framework that performs multitask quantile regression, for both meal detection and carbohydrate estimation. Our proposed method is evaluated in silico on 10 adult subjects from the UVa/Padova simulator with a Bio-inspired Artificial Pancreas (BiAP) control algorithm over a 2 month period. Three different configurations of the AP are evaluated -BiAP without meal announcement (BiAP-NMA), BiAP with meal announcement (BiAP-MA), and BiAP with meal detection (BiAP-MD). We present results showing an improvement of BiAP-MD over BiAP-NMA, demonstrating 144.5 ± 6.8 mg/dL mean blood glucose level (−4.4 mg/dL, p< 0.01) and 77.8 ± 6.3% mean time between 70 and 180 mg/dL (+3.9%, p< 0.001). This improvement in control is realised without a significant increase in mean in hypoglycaemia (+0.1%, p= 0.4). In terms of detection of meals and snacks, the proposed method on average achieves 93% precision and 76% recall with a detection delay time of 38 ± 15 min (92% precision, 92% recall, and 37 min detection time for meals only). Furthermore, BiAP-MD handles hypoglycaemia better than BiAP-MA based on CVGA assessment with fewer control errors (10% vs. 20%). This study suggests that multitask quantile regression can improve the capability of AP systems for postprandial glucose control without increasing hypoglycaemia.

scholarly journals Progress in Development of an Artificial Pancreas

2009 ◽  
Vol 3 (5) ◽  
pp. 1002-1004 ◽  
Author(s):  
David C. Klonoff ◽  
Claudio Cobelli ◽  
Boris Kovatchev ◽  
Howard C. Zisser
Keyword(s):  
Closed Loop ◽  
Artificial Pancreas ◽  
Insulin Delivery ◽  
The Novel ◽  
Closed Loop System ◽  
Time Activity ◽  
Glucose Levels ◽  
Closed Loop Systems ◽  
Patients With Diabetes ◽  
Novel Approaches

This issue of Journal of Diabetes Science and Technology contains a collection of 12 original articles describing the latest advances in the development of algorithms for controlling insulin delivery in an artificial pancreas. Algorithms presented in this issue are affected by numerous quantifiable factors, including insulin pharmacokinetics, timing of meal carbohydrate appearance, meal size, amount of exercise, presence of stress, day-to-day variations in insulin sensitivity, insulin time-activity profiles, accuracy of glucose monitor calibration, metabolic profiles of both adults and neonates, and risks of hypoglycemia/hyperglycemia. These articles present theoretical advances in insulin delivery algorithms from modeled in silico patients, as well as clinical data from actual patients who have used closed loop systems. The novel approaches described in these articles are expected to bring us much closer to realization of a commercially available closed loop system for controlling glucose levels in patients with diabetes.

Asiana Airlines Flight 214

2014 ◽  
Vol 4 (2) ◽  
pp. 113-121 ◽  
Author(s):  
Stephanie Chow ◽  
Stephen Yortsos ◽  
Najmedin Meshkati
Keyword(s):  
Human Factors ◽  
Aviation Safety ◽  
Cultural Factors ◽  
Vital Role ◽  
Cultural Issues ◽  
Flight Crew ◽  
Pilot Performance ◽  
Engineering Designs ◽  
Flight Deck

This article focuses on a major human factors–related issue that includes the undeniable role of cultural factors and cockpit automation and their serious impact on flight crew performance, communication, and aviation safety. The report concentrates on the flight crew performance of the Boeing 777–Asiana Airlines Flight 214 accident, by exploring issues concerning mode confusion and autothrottle systems. It also further reviews the vital role of cultural factors in aviation safety and provides a brief overview of past, related accidents. Automation progressions have been created in an attempt to design an error-free flight deck. However, to do that, the pilot must still thoroughly understand every component of the flight deck – most importantly, the automation. Otherwise, if pilots are not completely competent in terms of their automation, the slightest errors can lead to fatal accidents. As seen in the case of Asiana Flight 214, even though engineering designs and pilot training have greatly evolved over the years, there are many cultural, design, and communication factors that affect pilot performance. It is concluded that aviation systems designers, in cooperation with pilots and regulatory bodies, should lead the strategic effort of systematically addressing the serious issues of cockpit automation, human factors, and cultural issues, including their interactions, which will certainly lead to better solutions for safer flights.

Mock Trial: Role of Human Factors in Litigation Involving an Automated External Defibrillator (AED)

2007 ◽  
Author(s):  
Mike Kalsher ◽  
Caroline G.L. Cao ◽  
Matt Weinger ◽  
Alison Vredenburgh ◽  
Ed Israelski ◽  
...  
Keyword(s):  
Human Factors ◽  
Automated External Defibrillator ◽  
Mock Trial ◽  
External Defibrillator
Sign in / Sign up

Export Citation Format

Share Document