BioStats GmbH supports manufacturers and developers of medical devices with comprehensive statistical expertise throughout the MDR-compliant approval process. From study design to statistical evaluation, we ensure that your clinical studies meet regulatory requirements and deliver scientifically valid results.

We also bring proven expertise in the field of artificial intelligence (AI) as a medical device. We help you design valid study concepts for AI-based applications that provide the necessary scientific evidence for safety and performance.

Example of a Supported Project: Development and implementation of software with machine-learning algorithms for patient monitoring in intensive care units.

The early detection of patient deterioration in intensive care units represents a central challenge in modern intensive care medicine. Within the scope of this project, Dr. Alexander Krannich developed a machine learning algorithm that supports continuous health monitoring and enables early risk detection (e.g., sepsis). The algorithm for predictive analysis of patient data was successfully designed and implemented. Due to its innovative character, it was filed as a European patent (Figure 1) [1].

Figure 1: Patent 23176088.5

The results of the project were published in an international peer-reviewed journal with Dr. Krannich as co-author (Figure 2).

Figure 2: Scientific Publication

The study demonstrates that the developed approach enables more precise prediction of clinical deterioration compared to existing methods [2].

Following successful validation, the associated company, with Dr. Krannich as the responsible lead for the scientific process, was certified according to ISO 13485. Subsequently, the developed software received CE marking as a Class IIa medical device, enabling its use in routine clinical practice (Figure 3) [3].

The study demonstrates that the developed approach enables more precise prediction of clinical deterioration compared to existing methods [2].

Following successful validation, the associated company, with Dr. Krannich as the responsible lead for the scientific process, was certified according to ISO 13485. Subsequently, the developed software received CE marking as a Class IIa medical device, enabling its use in routine clinical practice (Figure 3) [3].

Abbildung 3: EU-Listung Medical Device 426243535SP018R

The product is currently in use at several hospitals worldwide, supporting real-time monitoring and the early identification of high-risk patients. FDA submission is in preparation.

References: [1] “European Patent Register.” Accessed: Aug. 22, 2025. [Online]. Available: https://register.epo.org/ipfwretrieve?apn=US.202318330426.A&lng=de [2] D. Thiele et al., “Machine Learning Models for the Early Real-Time Prediction of Deterioration in Intensive Care Units-A Novel Approach to the Early Identification of High-Risk Patients,” J Clin Med, vol. 14, no. 2, p. 350, Jan. 2025, doi: 10.3390/jcm14020350. [3] “Devices/SPPs - EUDAMED.” Accessed: Aug. 22, 2025. [Online]. Available: https://ec.europa.eu/tools/eudamed/#/screen/search-device?basicUdi=426243535SP018R&deviceStatusCode=refdata.device-model-status.on-the-market&paging=%7B%22pageIndex%22:0,%22pageSize%22:25,%22selectedRowIndex%22:0%7D&sorting=%7B%22sortField%22:%22primaryDi%22,%22sortDirection%22:%22desc%22%7D&submitted=true&scrollTop=281