Martin Haimerl

Martin Haimerl

Auto-generated profile, based on publicly available information

Martin Haimerl

Furtwangen University

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
11 March 2025 in BMC Medical Informatics and Decision Making
Verified
Journal Article
Open access
MHMartin Haimerl
Martin Haimerl
CRChristoph Reich
Christoph Reich
Background: In the future, more medical devices will be based on machine learning (ML) methods. In general, the consideration of risks is a crucial aspect for evaluating medical devices. Accordingly, risks and their associated costs should be taken into account when assessing the performance of ML-based medical devices. This paper addresses the following three research questions towards a risk-based evaluation with a focus on ML-based classification models. Methods: First, we analyzed how often risk-based metrics are currently utilized in the context of ML-based classification models. This was performed using a literature research based on a sample of recent scientific publications. Second, we introduce an approach for evaluating such models where expected risks and associated costs are integrated into the corresponding performance metrics. Additionally, we analyze the impact of different risk ratios on the resulting overall performance. Third, we elaborate how such risk-based approaches relate to regulatory requirements in the field of medical devices. A set of use case scenarios were utilized to demonstrate necessities and practical implications, in this regard. Results: First, it was shown that currently most scientific publications do not include risk-based approaches for measuring performance. Second, it was demonstrated that risk-based considerations have a substantial impact on the outcome. The relative increase of the resulting overall risks can go up to 196% when the ratio between different types of risks (false negatives vs. false positives) changes by a factor of 10.0. Third, we elaborated that risk-based considerations need to be included into the assessment of ML-based medical devices, according to the relevant EU regulations and standards. In particular, this applies when a substantial impact on the clinical outcome / in terms of the risk-benefit relationship occurs. Conclusion: In summary, we demonstrated the necessity of a risk-based approach for the evaluation of medical devices which include ML-based classification methods. We showed that currently many scientific papers in this area do not include risk considerations. We developed basic steps towards a risk-based assessment of ML-based classifiers and elaborated consequences that could occur, when these steps are neglected. And, we demonstrated the consistency of our approach with current regulatory requirements in the EU.

1 February 2022 in Human Movement Science
Verified
Journal Article
Closed access
MHMartin Haimerl
Martin Haimerl
INIman Nebel
Iman Nebel
ALAlina Linkerhägner
Alina Linkerhägner
JKJürgen Konradi
Jürgen Konradi
CWClaudia Wolf
Claudia Wolf
UBUlrich Betz
Ulrich Betz

21 January 2026 in Frontiers in Medicine
Verified
Journal Article
Open access
PDF file
MHMartin Haimerl
Martin Haimerl
MDMichael D’aGosto
Michael D’aGosto
MFMike Fornefett
Mike Fornefett
MKMassimo Kubon
Massimo Kubon
TSThomas Schiepp
Thomas Schiepp
Introduction: The EU Medical Device Regulation (MDR) was developed to improve the safety of medical devices as well as the smooth functioning of the market in this field. Since it entered into force in 2017, there have been continuous debates about the actual success thereof. However, no consequent analysis was provided until now. In this paper, we contribute to this endeavor. We analyzed whether the MDR meets appropriate standards that it requires for the development of medical products. In other words, we raised the question of whether the MDR could be placed on the market if we were to apply the rules of the MDR to itself. Methods: For this purpose, the analysis was based on the MDR and its Recitals, Articles, and Annexes, as well as the components implementing the regulatory system based on it. We checked whether basic principles for product development and the setup of regulatory systems in the field of medical devices are fulfilled. We asked whether basic development steps for the MDR have been realized appropriately, according to these principles and standards. Results: The analysis showed that the MDR contains substantial deficiencies regarding a consequent implementation of product development standards. For example, this applies to core principles like transparency, clarity, and traceability of requirements, appropriate implementation of risk management and validation steps, or realization of governance structures. According to our findings, the MDR would fail when we applied its own rules. In particular, central goals of the MDR like the smooth functioning of the market and the safety of the regulatory system were not addressed consequently. Discussion: According to the high impact the MDR has on the medical device sector but also on the healthcare system in general, our analysis motivates improvements of the MDR-based regulatory system that take these deficiencies into account. This paper provides basic insights into the application of basic principles regarding the implementation of regulatory systems. This should be complemented by further evaluation steps regarding the actual performance of the MDR during its operational phase. Based on this, consequent steps for the actual improvement should be derived to finally achieve a high-quality regulatory system.

13 September 2023 in Research Square
Verified
Preprint
Open access
PDF file
MHMartin Haimerl
Martin Haimerl
CRChristoph Reich
Christoph Reich
Background: In the future, more and more medical devices will be based on machine learning (ML) methods. For such medical devices, the rating of risks is a crucial aspect and should be considered when evaluating their performance. This means that an integration of risks and their associated costs into the corresponding metrics should be taken into account. This paper addresses three key issues towards a risk-based evaluation of ML-based classification models. Methods: First, it analyzes a selected set of scientific publications for determining how often risk-based metrics are currently utilized in the context of ML-based classification models. Second, it introduces an approach for evaluating such models where expected risks and associated costs are integrated into the corresponding performance metrics. Additionally, it analyzes the impact of different risk ratios on the resulting overall performance. For this purpose, an artificial model was used which allows to easily adapt key parameters. Third, the paper elaborates how such risk-based approaches relate to regulatory requirements in the field of medical devices. A set of use case scenarios were utilized to demonstrate necessities and practical implications, in this regard. Results: With respect to the first research question, it was shown that currently most scientific publications do not include risk-based approaches for measuring performance. For the second topic, it was demonstrated that risk-based considerations have a substantial impact on the outcome. The relative increase of the resulting overall risks can go up 198%, i.e. the risk value almost triples, when the ratio between different types of risks (risk of false negatives in comparison to false positives) goes down/up to 0.1 or 10.0. As discussed within the third research question, this situation typically represents a case where the risk increases one level in the corresponding risk matrix. Based on this, it was demonstrated that differences in parameter settings lead to a substantially different behavior when risk factors are not addressed properly. Conclusion: In summary, the paper demonstrates the necessity of a risk-based approach for the evaluation of ML-based medical devices, develops basic steps towards such an approach, and elaborates consequences which occur, when these steps are neglected.

26 April 2023 in Data in Brief
Verified
Journal Article
Open access
MHMartin Haimerl
Martin Haimerl
ALAlina Linkerhägner
Alina Linkerhägner
JKJürgen Konradi
Jürgen Konradi
CWClaudia Wolf
Claudia Wolf
PDPhilipp Drees
Philipp Drees
UBUlrich Betz
Ulrich Betz
Spinal function is substantially related to the motion of the particular vertebrae and the spine as a whole. For systematic assessment of individual motion, data sets are required which cover the kinematics comprehensively. Additionally, the data should enable a comparison of inter- and intraindividual variation of vertebral orientation in dedicated motion tasks like gait. For this purpose, this article provides surface topography (ST) data which were acquired while the individual test persons were walking on a treadmill at three different speed levels (2 km/h, 3 km/h, 4 km/h). In each recording, ten full walking cycles were included per test case to enable a detailed analysis of motion patterns. The provided data reflects asymptomatic and pain-free volunteers. Each data set contains the vertebral orientation in all three motion directions for the vertebra prominens down to L4 as well as the pelvis. Additionally, spinal parameters like balance, slope, and lordosis / kyphosis parameters as well as an assignment of the motion data to single gait cycles are included. The complete raw data set without any preprocessing is provided. This allows to apply a broad range of further signal processing and evaluation steps in order to identify characteristic motion patterns as well as intra- and inter-individual variation of vertebral motion.

14 November 2022 in Human Movement Science
Verified
Journal Article
Closed access
MHMartin Haimerl
Martin Haimerl
INIman Nebel
Iman Nebel
ALAlina Linkerhägner
Alina Linkerhägner
JKJürgen Konradi
Jürgen Konradi
CWClaudia Wolf
Claudia Wolf
UBUlrich Betz
Ulrich Betz