Severin Schramm

Severin Schramm

Auto-generated profile, based on publicly available information

Severin Schramm

Department of Diagnostic and Interventional Neuroradiology, TUM University Hospital, School of Medicine and Health, Technical University of Munich, Munich, Germany

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
1 January 2025 in Radiology
Verified
Journal Article
Closed access
SSSeverin Schramm
Severin Schramm
SPSilas Preis
Silas Preis
MMMarie-Christin Metz
Marie-Christin Metz
KJKirsten Jung
Kirsten Jung
BSBenita Schmitz-Koep
Benita Schmitz-Koep
SKSu Hwan Kim
Su Hwan Kim
Textual descriptions of radiologic image findings play a critical role in GPT-4 with vision–based differential diagnosis, underlining the importance of radiologist experts even in multimodal large language models.

13 May 2025 in Brain Stimulation
Verified
Journal Article
Open access
UVUlrike Vogelmann
Ulrike Vogelmann
MSMatthias Stadler
Matthias Stadler
ASAldo Soldini
Aldo Soldini
KCKai-Yen Chang
Kai-Yen Chang
MCMiaoxi Chen
Miaoxi Chen
FPFrank Padberg
Frank Padberg
The application of transcranial direct current stimulation (tDCS) at home for the treatment of depression and other neuropsychiatric disorders presents both significant opportunities and inherent challenges. Ensuring safety and maintaining high-quality stimulation are paramount for the efficacy and safety of at-home tDCS. This study investigates tDCS quality based on its technical parameters as well as safety of at-home and in-clinic tDCS applications comparing the data from two randomized controlled trials in patients with major depressive disorder. We analyzed 229 active stimulation sessions from the HomeDC study (at-home tDCS) and 835 sessions from the DepressionDC study (in-clinic tDCS). Notably, five adverse events (skin lesions) were reported exclusively in the at-home cohort, highlighting the critical need for enhanced safety protocols in unsupervised environments. The analysis revealed a significant difference in the average variability of impedances between at-home and in-clinic applications (F1,46 = 4.96, p = .031, η2 = .097). The at-home tDCS sessions exhibited higher impedance variability (M = 837, SD = 328) compared to in-clinic sessions (M = 579, SD = 309). Furthermore, at-home tDCS sessions resulting in adverse events (AEs) were associated with significantly higher average impedances than sessions without such issues. The study demonstrates that monitoring the technical parameters of at-home tDCS used in this study is essential. However, it may be not sufficient for ensuring safety and promptly detecting or preventing adverse events. Quality control protocols including digital training and monitoring techniques should be systematically developed and tested for a reliable and safe application of at-home tDCS therapies.

11 March 2025 in Neurology
Verified
Journal Article
Closed access
SSSeverin Schramm
Severin Schramm
CBCorinna Börner-Schröder
Corinna Börner-Schröder
MRMiriam Reichert
Miriam Reichert
CRConstanze Ramschütz
Constanze Ramschütz
XAXiao Michelle Androulakis
Xiao Michelle Androulakis
Nico SollmannNico Sollmann
Nico Sollmann
Migraine is a multifaceted primary headache disorder. In neuroimaging of migraine, fMRI has been used to elucidate pathophysiology or monitor treatment effects. The current literature, however, is highly heterogeneous regarding reported variables and methodologies. This begets a lack of comparability and complicates synthesis of results across studies. We developed a framework for standardized reporting of fMRI studies in migraine. Experts on fMRI in migraine were identified from the literature and subjected to structured questionnaires in 2 iterations of 3 rounds according to the DELPHI method. A total of 157 statements across 17 reporting domains were rated on 5-point Likert scales (strong support to strong opposition). The first iteration covered demographic data, migraine-specific factors, medication, scan timing, healthy controls (HCs), participant sampling/recruiting, standardized forms, study preregistration, region of interest (ROI) analyses, validation data sets, data sharing, preprocessing documentation, and analysis software. The second iteration of the questionnaire covered scanner-related factors, sequence-related factors, physiology monitoring, and stimulation-related factors. Items showing strong consensus/consensus (≥90%/≥75% of participants indicating scores 4 or 5) were included as standard reporting items. All 3 rounds of the first/second iteration were completed by 29 and 26 researchers (age 46 ± 11 years; 38% female/age 46 ± 12 years; 44% female) from 23 and 21 institutions. Across both iterations, strong consensus and consensus was achieved for 34 (3 scanner-related factors, 9 sequence-related factors, 1 stimulation-related factor, 2 demographic factors, 7 migraine-specific factors, 2 medication-factors, 2 scan timing factors, 4 HC factors, 1 preregistration factor, 1 analysis software factor, and 2 ROI analyses factors) and 33 (1 scanner-related factors, 4 sequence related factors, 1 factor related to physiology monitoring, 1 stimulation-related factor, 3 demographic factors, 6 migraine-specific factors, 4 medication factors, 3 HC factors, 2 sampling factors, 1 standardized form, 1 preregistration factor, 1 data sharing factor, 2 analysis software factors, and 3 ROI analyses factors) items, respectively. From these, a checklist covering 63 items from 14 reporting domains was created. We present an expert-based framework for reporting standards in fMRI studies of migraine, which can be used for future studies to homogenize cohort characterization, fMRI acquisitions, and analysis protocols.

1 May 2026 in Radiology
Verified
Journal Article
Closed access
SSSeverin Schramm
Severin Schramm
BGBastien Le Guellec
Bastien Le Guellec
MTMarlene Topka
Marlene Topka
MSMortimer Svec
Mortimer Svec
PBPaul Backhaus
Paul Backhaus
SKSu Hwan Kim
Su Hwan Kim
With increasing reader experience, large language model accuracy improved, whereas diagnostic gains from model assistance paradoxically diminished, highlighting the divergence between model performance and clinically relevant benefits for readers.

5 July 2024 in medRxiv
Verified
Preprint
Open access
PDF file
SKSu Hwan Kim
Su Hwan Kim
SSSeverin Schramm
Severin Schramm
JWJonas Wihl
Jonas Wihl
PRPhilipp Raffler
Philipp Raffler
MTMarlene Tahedl
Marlene Tahedl
DHDennis M. Hedderich
Dennis M. Hedderich
Purpose To evaluate the impact of a structured tutorial on the use of a large language model (LLM)-based search engine on radiology residents’ performance in LLM-assisted brain MRI differential diagnosis. Materials & Methods In this retrospective study, nine radiology residents determined the three most likely differential diagnoses for three sets of ten brain MRI cases with a challenging yet definite diagnosis. Each set of cases was assessed 1) with the support of conventional internet search, 2) using an LLM-based search engine (© Perplexity AI) without prior training, or 3) with LLM assistance after a structured 10-minute tutorial on how to effectively use the tool for differential diagnosis. The tutorial content was based on the results of two studies on LLM-assisted radiological diagnosis and included a prompt template. Reader responses were rated using a binary and numeric scoring system. Reading times were tracked and confidence levels were recorded on a 5-point Likert scale. Binary and numeric scores were analyzed using chi-square tests and pairwise Mann-Whitney U tests each. Search engine logs were examined to quantify user interaction metrics, and to identify hallucinations and misinterpretations in LLM responses. Results Radiology residents achieved the highest accuracy when employing the LLM-based search engine following the tutorial, indicating the correct diagnosis among the top three differential diagnoses in 62.5% of cases (55/88). This was followed by the LLM-assisted workflow before the tutorial (44.8%; 39/87) and the conventional internet search workflow (32.2%; 28/87). The LLM tutorial led to significantly higher performance (binary scores: p = 0.042, numeric scores: p = 0.016) and confidence (p = 0.006) but resulted in no relevant differences in reading times. Hallucinations were found in 5.1% of LLM queries. Conclusion A structured 10-minute LLM tutorial increased performance and confidence levels in LLM-assisted brain MRI differential diagnosis among radiology residents. Clinical Relevance Statement Our findings highlight the considerable benefits that even low-cost, low-effort educational interventions on LLMs can provide. Integrating LLM education in radiology training programs could augment practitioners’ capacity to harness AI technologies effectively.