Ansgar Beuse

Mr. Ansgar Beuse


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
16 October 2024 in Ophthalmology Science
Verified
Journal Article
Open access
ABAnsgar Beuse
Ansgar Beuse
DWDaniel Alexander Wenzel
Daniel Alexander Wenzel
MSMartin Stephan Spitzer
Martin Stephan Spitzer
KBKarl Ulrich Bartz-Schmidt
Karl Ulrich Bartz-Schmidt
MSMaximilian Schultheiss
Maximilian Schultheiss
CGCarsten Grohmann
Carsten Grohmann
To demonstrate the capability of a deep learning model to detect central retinal artery occlusion (CRAO), a retinal pathology with significant clinical urgency, using OCT data. Retrospective, external validation study analyzing OCT and clinical baseline data of 2 institutions via deep learning classification analysis. Patients presenting to the University Medical Center Tübingen and the University Medical Center Hamburg-Eppendorf in Germany. OCT data of patients suffering from CRAO, differential diagnosis with (sub) acute visual loss (central retinal vein occlusion, diabetic macular edema, nonarteritic ischemic optic neuropathy), and from controls were expertly graded and distinguished into 3 groups. Our methodological approach involved a nested multiclass five fold cross-validation classification scheme. Area under the curve (AUC). The optimal performance of our algorithm was observed using 30 epochs, complemented by an early stopping mechanism to prevent overfitting. Our model followed a multiclass approach, distinguishing among the 3 different classes: control, CRAO, and differential diagnoses. The evaluation was conducted by the "one vs. all" area under the receiver operating characteristics curve (AUC) method. The results demonstrated AUC of 0.96 (95% confidence interval [CI], ± 0.01); 0.99 (95% CI, ± 0.00); and 0.90 (95% CI, ± 0.03) for each class, respectively. Our machine learning algorithm (MLA) exhibited a high AUC, as well as sensitivity and specificity in detecting CRAO and the differential classes, respectively. These findings underscore the potential for deploying MLAs in the identification of less common etiologies within an acute emergency clinical setting. Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Verified
Journal Article
Open access
PDF file
HJHelen Jerratsch
Helen Jerratsch
ABAnsgar Beuse
Ansgar Beuse
Martin SpitzerMartin Spitzer
Martin Spitzer
CGCarsten Grohmann
Carsten Grohmann
(1) With persistent symptoms emerging as a possible global consequence of COVID-19, the need to understand, diagnose, and treat them is paramount. This systematic review aims to explore the potential of optical coherence tomography (OCT) and/or optical coherence tomography angiography (OCTA) in effectively diagnosing long COVID. (2) The database PubMed and, to reduce selection bias, the AI research assistant Elicit, were used to find relevant publications in the period between February 2021 and March 2024. Included publications on OCT and OCTA analysis of participants with acute COVID symptoms, those after recovery, and participants with long COVID symptoms were organized in a table. Studies with participants under the age of 18, case reports, and unrelated studies, such as pure slit-lamp examinations and subgroup analyses were excluded. (3) A total of 25 studies involving 1243 participants and 960 controls were reviewed, revealing several changes in the posterior eye. Long COVID participants displayed significant thinning in retinal layers in the OCT, including the macular retinal nerve fiber layer (mRNFL), ganglion cell layer (GCL), and inner plexiform layer (IPL). Divergent findings in recovered cohorts featured mRNFL reduction, GCL increase and decrease, and GCL-IPL decrease. Long COVID OCTA results revealed reduced vessel density (VD) in the superficial capillary plexus (SCP), intermediate capillary plexus (ICP), and deep capillary plexus (DCP). In recovered patients, SCP consistently showed a reduction, and DCP exhibited a decrease in five out of six publications. The foveal avascular zone (FAZ) was enlarged in five out of nine publications in recovered participants. (4) During various stages of COVID-19, retinal changes were observed, but a comparison between long COVID and recovered cohorts was aggravated by diverse inclusion and exclusion criteria as well as small sample sizes. Changes in long COVID were seen in most OCT examinations as thinning or partial thinning of certain retinal layers, while in OCTA a consistently reduced vessel density was revealed. The results suggest retinal alterations after COVID that are variable in OCT and more reliably visible in OCTA. Further research with larger samples is important for advancing long COVID diagnosis and management.

2 September 2025 in PLOS ONE
Verified
Journal Article
Open access
PDF file
ABAnsgar Beuse
Ansgar Beuse
ILInês V. Lopes
Inês V. Lopes
Martin SpitzerMartin Spitzer
Martin Spitzer
VDVasyl Druchkiv
Vasyl Druchkiv
CGCarsten Grohmann
Carsten Grohmann
CSChristos Skevas
Christos Skevas
Objective: To test the applicability of deep learning models for detecting and staging rhegmatogenous retinal detachment (RRD) based on morphological features using two- and three-dimensional optical coherence tomography (OCT) scans. Design: Retrospective study using deep learning-based image classification analysis of 2D and 3D OCT scans combined with clinical baseline data. Subjects: Adult patients presenting to the University Medical Center Hamburg-Eppendorf in Germany. Methods: A total of 252 eyes with RRD and 770 control eyes were included. All OCT scans and clinical baseline data were reviewed and graded. Binary and multiclass classification approaches were applied. Main outcome measures: Area under the curve (AUC) and precision-recall area under the curve (PR AUC) for detection, stage classification and duration estimation of RRD. Results: We employed both statistical and deep learning-based approaches using 2D and 3D OCT data. We evaluated an automated 3D OCT classification model in a multiclass analysis to distinguish RRD scans by macula status from a non-RRD group with macula-on cases (PR AUC = 0.66 ± 0.12, AUC = 0.96 ± 0.01) vs. macula-off cases (PR AUC = 0.86 ± 0.07, 0.98 ± 0.01) against non-RRD cases (PR AUC = 1.00, AUC = 1.00) Furthermore, the 3D model was able to classify the duration of macula-off status (< 3 days) with a PR AUC of 0.68 ± 0.2 and a AUC of 0.97 ± 0.2 when compared to a mixed group including longer macular-off, macular-on and non RRD cases. Lastly, manually graded RRD Stages were correlated with best corrected visual acuity (BCVA), as well as macula-off Duration and classified via a 2D model. A 2D model used for RRD stage classification achieved its best performance for stage 4, with a PR AUC of 0.56 ± 0.11 and an AUC of 0.94 ± 0.02. Conclusion: The machine learning models demonstrated strong performance in classifying RRD stages, macula status and duration based on OCT imaging. These findings highlight the potential of deep learning methods to support clinical decision-making and surgical planning in RRD management.

2 June 2025 in Klinische Monatsblätter für Augenheilkunde
Verified
Journal Article
Closed access
PDF file
ABAnsgar Beuse
Ansgar Beuse
CGCarsten Grohmann
Carsten Grohmann
HSHauke M. Schadwinkel
Hauke M. Schadwinkel
CSChristos Skevas
Christos Skevas
MSMartin S. Spitzer
Martin S. Spitzer
Zusammenfassung: Früherkennung und rechtzeitige Behandlung können in über 90% der diabetischen Retinopathie einen schweren Sehverlust verhindern. Die deutsche Nationale Versorgungsleitlinie empfiehlt, dass Personen mit Diabetes jährliche bzw. 2-jährliche Augenuntersuchungen zur Erkennung einer behandlungsbedürftigen diabetischen Retinopathie erhalten. Um den Herausforderungen gerecht zu werden, wurden KI-Algorithmen entwickelt, um DR autonom aus Fundusfotografien ohne menschliche Beurteilung zu erkennen. In den letzten Jahren haben viele KI-Algorithmen eine gute Sensitivität und Spezifität für die Erkennung einer behandlungsbedürftigen DR im Vergleich zu menschlichen Beurteilern erzielt. Bislang kommt ein KI-basiertes DR-Screening auch in Ländern mit besser entwickelter digitaler Infrastruktur als Deutschland nur in geringem Umfang zum Einsatz, denn viele Fragen wie Akzeptanz, Kosteneffektivität, Haftungsrisiken, IT-Sicherheit und die Kostenerstattung sind noch unzureichend beantwortet. In dieser Übersicht über KI-Anwendungen zum DR-Screening werden wichtige Konzepte in der Entwicklung und aktuell zugelassene KI-Algorithmen vorgestellt, die im Vergleich mit menschlichen Bewertern validiert worden sind.

2 June 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
HBHegi Beliu
Hegi Beliu
CGCarsten Grohmann
Carsten Grohmann
VDVasyl Druchkiv
Vasyl Druchkiv
EBElena Butenko
Elena Butenko
ABAnsgar Beuse
Ansgar Beuse
CWChristian Wolfram
Christian Wolfram
To the best of our knowledge, population-based studies about the prevalence of dry eye in Germany are rare. The aim of our study was to reintroduce the topic of dry eye in the conversation about ophthalmological diseases and to identify relevant risk factors by assessing the usage of artificial tears as a proxy for treated dry eye in an older German population. For this, data was gathered from the medication plan of the first cohort of participants of the Hamburg City Health Study (n= 10 000, aged 46 – 78 years old). The calculated prevalence of self-reported artificial tears’ usage in Hamburg was 4.7% (CI – 95% [4.2%; 5.1%]), with women being four times more likely to use them than men. Since artificial tears are a fundamental part of the dry eye therapy, in this study we defined dry eye as the consistent use of artificial tears. Based on this definition, the prevalence of self-reported dry eye was 7.5% among women and 1.7% among men. A significant in-crease in the dry eye prevalence above the age of 58 was noticed as well. Lifestyle choices, pre-existing conditions and other medication were tested as possible risk factors. In conclusion, this study provides empirical evidence of the dry eye’s distribution and its risk factors.

8 October 2026 in European Journal of Epidemiology
Verified
Journal Article
Open access
PDF file
MTMargaretha Amanda Bernadette Tiemens
Margaretha Amanda Bernadette Tiemens
DHDirk J. van Hemert
Dirk J. van Hemert
SLSena T. Lemma
Sena T. Lemma
SQSara W. Quist
Sara W. Quist
KWKun Shi - van Wielink
Kun Shi - van Wielink
KWKatie M. Williams
Katie M. Williams
Myopia is a childhood-onset condition driven by excessive axial ocular elongation, associated with increased risk of sight-threatening complications and irreversible visual impairment. Despite rising global prevalence, epidemiological data on long-term trends in Europe remain limited. This study examines temporal trends in myopia prevalence and axial length (AL) across European adult birth cohorts. We conducted a comparative birth-cohort analysis using harmonised data from 28 population-based studies (n = 81,828) across nine countries participating in the European Eye Epidemiology (E3) Consortium. Myopia prevalence (overall, by severity, and sex) were estimated using individual participant data random-effects meta-analysis. AL distributions were assessed by estimating percentiles across birth cohorts. Myopia prevalence more than tripled across 20th-century birth cohorts, rising from 18.0% (95% confidence interval [CI]: 15.2%, 21.3%) in the 1900s to 61.4% (95% CI: 55.5%, 66.9%) in the 1990s (p < 0.001), with increased prevalence across all severity levels. Standardised to the 2024 European population, myopia prevalence was estimated at 42.7% (95% CI: 40.2%, 45.1%). Myopia prevalence was similar between males and females overall. AL was longer in successive decades (1920–1970) across all population centiles (p < 0.001), indicating a population-wide shift. Myopia prevalence and AL have increased markedly across European birth cohorts throughout the twentieth century, affecting all severity levels and both sexes. These findings underscore the importance of preventive strategies targeting modifiable environmental risk factors, alongside continued evaluation of interventions intended to slow myopia progression, as continued increases may strain healthcare systems and society.