Miriam Kopperstad Wolff

Miriam Kopperstad Wolff

Auto-generated profile, based on publicly available information

Miriam Kopperstad Wolff

Department of ICT and Natural Sciences, Norwegian University of Science and Technology, Ålesund, Norway

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 January 2024 in IEEE Access
Verified
Journal Article
Open access
MWMiriam K. Wolff
Miriam K. Wolff
HSHans Georg Schaathun
Hans Georg Schaathun
AFAnders Lyngvi Fougner
Anders Lyngvi Fougner
MSMartin Steinert
Martin Steinert
RVRune Volden
Rune Volden
In the field of blood glucose prediction, the literature is abounded with algorithms that demonstrate potential in glucose management. However, these propositions face an issue common to many machine learning algorithms: the repeated reuse of datasets (overfitting) and a tendency to develop algorithms in isolation, detached from practical scenarios. Compounding these challenges is that many insulin pump vendors and continuous glucose monitor vendors use closed and proprietary protocols, restricting researchers’ data access and the ability to deploy complex, multivariate optimizers. This study seeks to bridge the gap between theoretical algorithms and their real-world applications by devising a software development kit. This kit collects real-time data from continuous glucose monitors, carbohydrate intake, insulin deliveries from insulin management systems, and metrics like physical activity, stress, and sleep from wearables. Our methodology leverages the open-source insulin management system, Loop, integrated with Apple Health and various wearable devices. Although navigating through diverse communication protocols to link these devices presented challenges, we succeeded in aggregating a comprehensive dataset for blood glucose predictions. To underscore the utility of our software development kit, we executed a technical proof-of-concept on this platform, illustrating real-time, individualized, data-driven multivariate blood glucose predictions. We hope that our platform can contribute to transforming machine learning algorithms from technical developments into actionable tools with real-world benefits in blood glucose management. It provides a foundation for researchers to refine their predictive algorithms and decision support systems within a more dynamic, data-rich environment.

1 October 2025 in Diabetes Technology & Therapeutics
Verified
Journal Article
Closed access
MWMiriam K. Wolff
Miriam K. Wolff
HSHans Georg Schaathun
Hans Georg Schaathun
SGSebastien Gros
Sebastien Gros
RVRune Volden
Rune Volden
MSMartin Steinert
Martin Steinert
AFAnders L. Fougner
Anders L. Fougner
Background: The root mean squared error (RMSE) is commonly used to evaluate blood glucose prediction algorithms. However, it primarily measures how well predictions align with the most likely future values, rather than supporting optimal and proactive treatment decisions. Since diabetes management data predominantly features blood glucose values within the target range, RMSE tends to favor models that consistently predict target-range values, often at the expense of detecting clinically critical events such as rapid fluctuations, hypoglycemia, or hyperglycemia. This study examines how and why RMSE biases evaluations toward trivial models, highlighting the need for alternative performance criteria that better reflect clinical priorities. Methods: We developed the composite glucose prediction metric (CGPM) to integrate three components: RMSE, temporal gain and geometric mean (glycemic event prediction). A custom loss function was designed to emphasize clinically critical predictions during model training. Pareto frontier analysis was used to assess trade-offs among models with comparable performance. Results: CGPM was computed for five blood glucose prediction techniques (zero-order hold, naïve linear regression, ridge regression, ridge regression trained with a custom loss function, and a physiology-based model) applied to the OhioT1DM dataset. The data-driven model with the lowest RMSE performed poorly on glycemic event prediction, highlighting RMSE’s bias toward target-range predictions. In contrast, the ridge regressor trained with the custom loss function improved event prediction, showing that clinically weighted optimization mitigates biases. Conclusions: Blood glucose prediction algorithms require evaluation and optimization criteria beyond accuracy to better support optimal treatment decisions. This study introduced the CGPM as an alternative evaluation framework, along with a loss function designed for model optimization that emphasizes clinically critical but rare events. Further clinical validation is needed to refine these criteria and ensure they align more closely with the needs of diabetes management.

17 February 2025 in Data in Brief
Verified
Journal Article
Open access
MWMiriam K. Wolff
Miriam K. Wolff
SRSam Royston
Sam Royston
AFAnders L. Fougner
Anders L. Fougner
HSHans Georg Schaathun
Hans Georg Schaathun
MSMartin Steinert
Martin Steinert
RVRune Volden
Rune Volden
Diabetes management datasets are often compiled from various sensors and devices, including diabetes technology, activity trackers, and other health-related equipment, resulting in heterogeneous data formats. Despite the abundance of available data, inconsistencies in dataset formats and data-sharing practices limit the ability to build on prior work and compare results across studies. Standardizing data-sharing formats can improve consistency, facilitate dataset consolidation, and reduce the data processing burden for researchers. This article explores the current state of data-sharing practices in diabetes management research and proposes guidelines for harmonizing datasets using a unified time-aligned tabular format. We demonstrate the application of these guidelines on three widely used datasets and highlight key challenges in achieving data harmonization. We call on the broader research community to develop and adopt detailed recommendations for standardized data-sharing practices.

28 March 2025 in Journal of Diabetes Science and Technology
Verified
Journal Article
Open access
PRPietro Randine
Pietro Randine
MWMiriam Kopperstad Wolff
Miriam Kopperstad Wolff
MPMatthias Pocs
Matthias Pocs
ICIan R. O. Connell
Ian R. O. Connell
JCJoseph A. Cafazzo
Joseph A. Cafazzo
EÅEirik Årsand
Eirik Årsand
Background: In today’s data-driven era, openness promotes transparency and accessibility, particularly in health initiatives like the European Health Data Space. Diabetes management relies on real-time data from medical devices, such as continuous glucose monitors (CGMs), insulin pumps, and hybrid closed-loop systems. These devices provide critical insights for treatment adjustments, making real-time data access essential. Methods: This article explores real-time data access for third-party applications, focusing on primary (treatment) and secondary (research) use. We examine how application programming interfaces (APIs) enable secure data retrieval and assess the impact of terms of service and copyright law on patient-driven innovation in open-source communities. Our research evaluates diabetes medical devices and software solutions in Norway, assessing their real-time data access and API functionalities. In addition, we analyze legal frameworks governing these technologies, focusing on challenges faced by open-source solutions. Based on our findings, we propose an interoperability model to improve data accessibility while ensuring security and transparency. Results: Findings reveal seven diabetes devices and nine regulated software solutions, with only one offering a publicly accessible API. This emphasizes a significant gap in real-time data access. Comparisons between vendor-specific and open-source software expose interoperability and accessibility challenges. While Do-It-Yourself (DIY) solutions foster innovation, they face technical and legal barriers. Conclusion: Real-time diabetes management presents security, transparency, and access challenges. Regulatory decisions are needed to implement an interoperability model. The lack of real-time data access highlights the necessity of publicly accessible APIs that prioritize transparency, accessibility, and patient-driven innovation—marking a shift from today’s constrained diabetes management landscape.

26 April 2026 in Journal of Diabetes Science and Technology
Verified
Journal Article
Closed access
MWMiriam Kopperstad Wolff
Miriam Kopperstad Wolff
PCPeter Calhoun
Peter Calhoun
EAEleonora Maria Aiello
Eleonora Maria Aiello
YQYao Qin
Yao Qin
SRSam Fox Royston
Sam Fox Royston
Background: Progress in type 1 diabetes (T1D) algorithm development is limited by the fragmentation and lack of standardization across existing T1D management data sets. Current data sets differ substantially in structure and are time-consuming to access and process, which impedes data integration and reduces the comparability and generalizability of algorithmic developments. This work aims to establish a unified and accessible data resource for T1D algorithm development. Method: Multiple publicly available T1D data sets were harmonized into a unified resource, termed the MetaboNet data set. Inclusion required the availability of both continuous glucose monitoring (CGM) data and corresponding insulin pump dosing records. In addition, auxiliary information such as reported carbohydrate intake and physical activity was retained when present. Results: The MetaboNet data set comprises 3135 subjects and 1228 patient-years of overlapping CGM and insulin data, making it substantially larger than existing standalone benchmark data sets. The resource is distributed as a fully public subset available for immediate download at https://metabo-net.org/ , and with a data use agreement (DUA)-restricted subset accessible through their respective application processes. For the data sets in the latter subset, processing pipelines are provided to automatically convert the data into the standardized MetaboNet format. Conclusions: A harmonized public data set for T1D research is presented, and the access pathways for both its unrestricted and DUA-governed components are described. The resulting data set covers a broad range of glycemic profiles and demographics and thus can yield more generalizable algorithmic performance than individual data sets.

26 September 2024 in Journal of Open Source Software
Verified
Journal Article
Open access
PDF file
MWMiriam Kopperstad Wolff
Miriam Kopperstad Wolff
SRSam Royston
Sam Royston
RVRune Volden
Rune Volden