Listening to the patients

Research projects

Listening to their gut to improve the lives of people with type I diabetes.

Highlights 2023

The purpose of the project is to explore the use of advanced monitoring and processing of abdominal sounds to identify meal intake in patients with type 1 diabetes soon after meal onset. An early and reliable meal detection will allow for earlier insulin dosing for meals, which is essential to keeping a patient’s glucose levels in the normal or close to normal range. A reliable meal onset detection system may be used by an artificial pancreas to automatically deliver meal insulin instead of requiring the patients to notify the system of every meal. For people who use manual glucose control, the same system can remind or advise about missed meal boluses.

During 2023, our research focused on using ECG for early detection of food intake. This appears to be a faster sensor modality than sound (for meal onset detection). In particular, we focused on how to avoid false positive meal identifications, e.g. due to physical activity or other disturbances, which would be unacceptable in an artificial pancreas. A combination of sound, ECG, and glucose sensors may provide the sensory input needed for a reliable early meal onset detection.

One highlight of 2023 has been that we have shown that by mixing micro-amounts of glucagon in fast acting insulin solution we get an even faster insulin absorption and effect on glucose levels. Used in an artificial pancreas combined with ECG and sound based early identification of food intake, this can make a fully automated artificial pancreas with superior glucose control possible. NTNU TTO has a pending patent application on this new, innovative and contra-intuitive use of glucagon.

For us the added value of being a part of a transdisciplinary centre is having courses and meetings (e.g.,through the DLN Research School) that our PhD candidates and postdocs can participate in.

Project overview

Project lead: Sven Magnus Carlsen
Institution: NTNU
Partner: SINTEF Digital AS
Funding: Research Council of Norway
Duration: 4 years (2019–2022)
Follow in social media: XX
See also Artificial Pancreas Trondheim (APT) and the Double Intraperitoneal Artificial Pancreas (DIAP) project, SINTEF Digital and Prediktor Medical

Åm, Marte Kierulf; Teigen, Ingrid Anna; Riaz, Misbah; Fougner, Anders Lyngvi; Christiansen, Sverre Christian & Carlsen, Sven Magnus (2023). The artificial pancreas: two alternative approaches to achieve a fully closed-loop system with optimal glucose control. Journal of Endocrinological Investigation. ISSN 0391-4097. 46. doi: 10.1007/s40618-023-02193-2. Full text in Research Archive
Cheema, Muhammad Asaad; Patil, Pallavi; Siddiqui, Salman Ijaz; Salvo Rossi, Pierluigi; Stavdahl, Øyvind & Fougner, Anders Lyngvi (2023). Data-Driven Classifiers for Early Meal Detection Using ECG. IEEE Sensors Letters. ISSN 2475-1472. 7(9), p. 1–4. doi: 10.1109/LSENS.2023.3307106. Full text in Research Archive Show summary
This study investigates the potential of the electrocardiogram (ECG) to perform early meal detection, which is critical for developing a fully-functional automatic artificial pancreas. The study was conducted in a group of healthy subjects with different ages and genders. Two classifiers were trained: one based on neural networks (NNs) and working on features extracted from the signals; one based on convolutional NNs (CNNs) and working directly on raw data. During the test phase, both classifiers correctly detected all the meals, with the CNN outperforming the NN in terms of misdetected meals (MMs) and detection time (DT). Reliable meal onset detection with short detection time has significant practical implications: it reduces the risk of postprandial hyperglycemia and hypoglycemia, it reduces the mental burden of meal documentation for patients and related stress.
Teigen, Ingrid Anna; Riaz, Misbah; Åm, Marte Kierulf; Christiansen, Sverre Christian & Carlsen, Sven Magnus (2022). Vasodilatory effects of glucagon: A possible new approach to enhanced subcutaneous insulin absorption in artificial pancreas devices. Frontiers in Bioengineering and Biotechnology. ISSN 2296-4185. 10. doi: 10.3389/fbioe.2022.986858. Full text in Research Archive
Teigen, Ingrid Anna; Åm, Marte Kierulf; Carlsen, Sven Magnus & Christiansen, Sverre Christian (2022). Pharmacokinetics of glucagon after intravenous, intraperitoneal and subcutaneous administration in a pig model. Basic & Clinical Pharmacology & Toxicology. ISSN 1742-7835. 130(6), p. 623–631. doi: 10.1111/bcpt.13731.
Cheema, Muhammad Asaad; Siddiqui, Salman Ijaz & Salvo Rossi, Pierluigi (2022). Comparison of Different Classifiers for Early Meal Detection Using Abdominal Sounds. Proceedings of the IEEE Sensor Array and Multichannel Signal Processing Workshop. ISSN 1551-2282. doi: 10.1109/SAM53842.2022.9827841.
Davari Benam, Karim; Khoshamadi, Hasti; Åm, Marte Kierulf; Stavdahl, Øyvind; Gros, Sebastien & Fougner, Anders Lyngvi (2022). Identifiable Prediction Animal Model for the Bi-Hormonal Intraperitoneal Artificial Pancreas. Journal of Process Control. ISSN 0959-1524. 121, p. 13–29. doi: 10.1016/j.jprocont.2022.11.008. Full text in Research Archive Show summary
To achieve a fully automatic artificial pancreas (AP), i.e., an AP without the need for meal announcements, the intraperitoneal (IP) route is explored. This route has faster dynamics than the typical subcutaneous (SC) route. Model predictive control (MPC) is the most promising control algorithm, but it requires a predictive and identifiable model. This paper presents the design of such a model for MPC-based dual hormone IP APs. This model is trained and tested on recorded data from anesthetized pigs. Animal experiments show that the saturation of the hepatic first-pass effect is essential in how IP insulin and IP glucagon affect glucose levels. These physiological phenomena must be modeled to estimate the system behavior for various conditions. This, in turn, increases the number of parameters and complicates system identification. The availability of rich experimental data from 26 animal trials motivated the design of a technique to exploit this prior information to ensure the identifiability of our model. Through this technique, most parameters were either modeled as body weight functions or common among animals. The correlation between parameter values and body weight is discovered utilizing prior data from various animal experiments, such as blood glucose, plasma insulin, and glucagon levels, in which hormones were administered intraperitoneally or intravenously. This method simplifies the system identification for every new subject while keeping the model’s essential details that improve the prediction capability relative to comparable models. The model can be exploited in MPC or any other model-based controller of a bi-hormonal IP AP. It can also be used as a simulator to develop control approaches for single and bi-hormonal IP APs.
Teigen, Ingrid Anna; Åm, Marte Kierulf; Carlsen, Sven Magnus & Christiansen, Sverre Christian (2021). Pharmacokinetics of Intraperitoneally Delivered Glucagon in Pigs: A Hypothesis of First Pass Metabolism. European journal of drug metabolism and pharmacokinetics. ISSN 0378-7966. doi: 10.1007/s13318-021-00692-2. Full text in Research Archive Show summary
Background and Objective Artificial pancreases administering low-dose glucagon in addition to insulin have the scope to improve glucose control in patients with diabetes mellitus type 1. If such a device were to deliver both hormones intraperitoneally, it would mimic normal physiology, which may be beneficial. However, the pharmacokinetic properties of glucagon after intraperitoneal administration are not well known. Hence, the current study aims to evaluate the relationship between the amount of intraperitoneally delivered glucagon and pharmacokinetic variables in a pig model. Methods Pharmacokinetic data was retrieved from experiments on 19 anaesthetised pigs and analysed post hoc. The animals received a single intraperitoneal bolus of glucagon ranging from 0.30 to 4.46 µg/kg. Plasma glucagon was measured every 2–10 min for 50 min. Results Peak plasma concentration and area under the time–plasma concentration curve of glucagon correlated positively with the administered dose, and larger boluses provided a relatively greater increase. The mean (standard deviation) time to maximum glucagon concentration in plasma was 11 (5) min, and the mean elimination half-life of glucagon in plasma was 19 (7) min. Conclusions Maximum plasma concentration and area under the time–plasma concentration curve of glucagon increase nonlinearly in relation to the intraperitoneally administered glucagon dose. We hypothesise that the results are compatible with a satiable first-pass metabolism in the liver. Time to maximum glucagon concentration in plasma and the elimination half-life of glucagon in plasma seem independent of the drug dose.
Setti, Sunilkumar Telagam; Søiland, Elise; Stavdahl, Øyvind & Fougner, Anders Lyngvi (2020). Pilot study of Early Meal Onset Detection from Abdominal Sounds. In Costin, Hariton (Eds.), IEEE International Conference on e-Health and Bioengineering (EHB 2019), Proceedings of the. IEEE (Institute of Electrical and Electronics Engineers). ISSN 978-1-7281-2603-6. doi: 10.1109/EHB47216.2019.8969901. Full text in Research Archive
Kölle, Konstanze; Aftab, Muhammad Faisal; Andersson, Leif Erik; Fougner, Anders Lyngvi & Stavdahl, Øyvind (2019). Data driven filtering of bowel sounds using multivariate empirical mode decomposition. Biomedical engineering online. ISSN 1475-925X. 18(28), p. 1–20. doi: 10.1186/s12938-019-0646-1. Full text in Research Archive
Kölle, Konstanze; Fougner, Anders Lyngvi; Ellingsen, Reinold; Carlsen, Sven Magnus & Stavdahl, Øyvind (2019). Feasibility of early meal detection based on abdominal sound. IEEE Journal of Translational Engineering in Health and Medicine. ISSN 2168-2372. 7:3300212, p. 1–12. doi: 10.1109/JTEHM.2019.2940218. Full text in Research Archive

View all works in Cristin

Carlsen, Sven Magnus (2023). Kunstig pankreas, - en oppdatering.
Setti, Sunilkumar Telagam; Holten, Andrea; Patil, Pallavi; Lema Perez, Laura; Stavdahl, Øyvind & Fougner, Anders Lyngvi (2023). Feasibility of Meal Onset Detection Using Electrocardiograms.
Patil, Pallavi; Lema Perez, Laura; Siddiqui, Salman Ijaz; Stavdahl, Øyvind & Fougner, Anders Lyngvi (2023). Electrocardiogram as a Predictor for Early and Robust Meal Onset Detection in Artificial Pancreas.
Teigen, Ingrid Anna; Åm, Marte Kierulf; Carlsen, Sven Magnus & Christiansen, Sverre Christian (2022). Glucagon Pharmacokinetics in a Pig Model.
Tabella, Gianluca; Siddiqui, Salman Ijaz & Salvo Rossi, Pierluigi (2022). Quickest Meal Detection Using Statistical Machine Learning.
Siddiqui, Salman Ijaz; Isifan, Ahmed Khalil Omar; Klavins, Davis & Fougner, Anders Lyngvi (2022). Early Meal Detection Based on Different Body Sounds.
Åm, Marte Kierulf; Munkerud, Erlend Yttersian; Berge, Mathilde Hallem; Christiansen, Sverre Christian & Carlsen, Sven Magnus (2022). Glucagon and local subcutaneous blood flow; a proof-of-concept study.
Setti, Sunilkumar Telagam; Søiland, Elise; Stavdahl, Øyvind & Fougner, Anders Lyngvi (2020). Pilot Study of Exploiting Abdominal Sound for Early Meal Onset Detection.
Setti, Sunilkumar Telagam; Søiland, Elise; Stavdahl, Øyvind & Fougner, Anders Lyngvi (2019). Pilot study of Early Meal Onset Detection from Abdominal Sounds.
Teigen, Ingrid Anna; Carlsen, Sven Magnus & Christiansen, Sverre Christian (2023). The Bihormonal Artificial Pancreas: New Perspectives on the Pharmacokinetics and Pharmacodynamics of Glucagon. Norges teknisk-naturvitenskapelige universitet. ISSN 978-82-326-6877-9. 2023(106).
Kölle, Konstanze; Stavdahl, Øyvind; Fougner, Anders Lyngvi & Carlsen, Sven Magnus (2018). Towards a Safe Artificial Pancreas: Meal Detection and the Intraperitoneal Route. Norges teknisk-naturvitenskapelige universitet. ISSN 978-82-326-3559-7. 2018(385).

View all works in Cristin

Research group

Andrea Holten

Former MSc student

NTNU
Anders Lyngvi Fougner

Associate Professor

NTNU

Profile
Dag Roar Hjelme

Professor

NTNU

Profile
Einar Henriksen

MSc student

NTNU
Elise Søyland

Former MSc student

NTNU
Ingrid Anna Teigen

PhD candidate

NTNU

Profile
Nora Lyngstad Røste

Former MSc student

NTNU
Pallavi Ajay Patil

PhD candidate

NTNU

Profile
Project lead: Sven Magnus Carlsen

Professor

NTNU

Profile
Reinold Ellingsen

Innovation Manager

NTNU

Profile
Sunilkumar Telagam Setti

Former postdoctoral research fellow

NTNU

Profile
Øyvind Stavdahl

Professor

NTNU

Profile

Listening to the Patients is developing a sound-based meal detection system to improve artificial pancreases. Timing insulin delivery with a meal is an important part of controlling blood glucose levels and avoiding long-term complications. Accomplishing this high-risk goal will be a major step toward improving the lives of people with diabetes.

Many people with type I diabetes are treated with glucose monitors and insulin pumps delivering insulin in subcutaneous tissue. By combining a glucose monitor and an insulin pump one can make a devise delivering insulin based on the measured glucose levels. Such a devise is called an artificial pancreas. However, subcutaneous insulin delivery carries inherent delays in the effect on glucose levels making it hard to achieve good glucose control.

To reduce the delays associated with the subcutaneous approach, the Artificial Pancreas Trondheim (APT) research group work on intraperitoneal glucose monitoring and delivery, i.e. between the intestines. With this “double intraperitoneal” approach for an artificial pancreas the absorption of insulin and the effect on glucose levels are much faster.However, such an artificial pancreas will still struggle to handle increasing glucose levels after meals. It takes at least 30 minutes for the artificial pancreas to detect this rise after a meal, far too long a delay to control glucose properly. Over time, insufficient glucose control can lead to long-term issues like kidney disease, cardiovascular disease or even blindness.

Listening to the Patients’s bold new approach analyzes sounds in the gastrointestinal tract with external microphones for telltale sounds of a meal. The researchers will correlate this information with blood glucose levels to administer the correct dosage of insulin much closer to meal intake than current devices. In a recent pilot study, they were able to detect a meal in as little as 10 minutes after consumption.

This research has great potential for developing a vastly improved artificial pancreas, but it is also highly risky: their detection algorithm must be extremely accurate because administering a meal dose of insulin to a patient that has not eaten can be deadly. To ensure their algorithm meets this high standard, the Listening to the Patients team consists of engineering physicists, sound engineers, cyberneticists, physicians, and endocrinologists. They are using machine learning based on the principles of speech recognition and their knowledge of engineering and physiology to identify meal sounds and eliminate extraneous sounds. They expect to have a proof of concept listening device ready for testing within one year.

The Listening to the Patients team is working closely with people with diabetes to ensure a positive user experience. Privacy is a major concern with audio systems so their algorithm will identify and eliminate speech from the recordings. When fully developed, the system will analyze data real time and not store sound recordings.

Listening to the Patients project is part of the Artificial Pancreas Trondheim (APT) research group at The Norwegian University of Science and Technology (NTNU) in Trondheim. It is funded by the Research Council of Norway and is one of the multidisciplinary research projects within Centre for Digital Life Norway.

By Matthew Davidson

Latest news from the project

To be announced