Nicolas Carl

Dr. Nicolas Carl

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
18 February 2025 in BJU International
Verified
Journal Article
Open access
NCNicolas Carl
Nicolas Carl
SHSarah Haggenmüller
Sarah Haggenmüller
CWChristoph Wies
Christoph Wies
LNLisa Nguyen
Lisa Nguyen
JWJana Theres Winterstein
Jana Theres Winterstein
FWFrederik Wessels
Frederik Wessels
Objectives: To explore the interaction of real‐world patients with a chatbot in a clinical setting, investigating key aspects of medical information provided by large language models (LLMs). Patients and methods: The study enrolled 300 patients seeking urological counselling between February and July 2024. First, participants voluntarily conversed with a Generative Pre‐trained Transformer 4 (GPT‐4) powered chatbot to ask questions related to their medical situation. In the following survey, patients rated the perceived utility, completeness, and understandability of the information provided during the simulated conversation as well as user‐friendliness. Finally, patients were asked which, in their experience, best answered their questions: LLMs, urologists, or search engines. Results: A total of 292 patients completed the study. The majority of patients perceived the chatbot as providing useful, complete, and understandable information, as well as being user‐friendly. However, the ability of human urologists to answer medical questions in an understandable way was rated higher than of LLMs. Interestingly, 53% of participants rated the question‐answering ability of LLMs higher than search engines. Age was not associated with preferences. Limitations include social desirability and sampling biases. Discussion: This study highlights the potential of LLMs to enhance patient education and communication in clinical settings, with patients valuing their user‐friendliness and comprehensiveness for medical information. By addressing preliminary questions, LLMs could potentially relieve time constraints on healthcare providers, enabling medical personnel to focus on complex inquiries and patient care.

11 December 2025 in European Journal of Cancer
Verified
Journal Article
Open access
NCNicolas Carl
Nicolas Carl
MHMartin Joachim Hetz
Martin Joachim Hetz
CWChristoph Wies
Christoph Wies
SHSarah Haggenmüller
Sarah Haggenmüller
JWJana Winterstein
Jana Winterstein
TBTitus Josef Brinker
Titus Josef Brinker
Large language models (LLMs) are utilized to answer queries in urology and oncology, yet the performance is limited due to outdated data and missing source transparency, which undermines clinical reliability and therefore adoption. We developed UroBot, a urology-specific chatbot integrating retrieval-augmented generation (RAG) to provide in-line references and source text previews for each response. In a randomized controlled reader study, UroBot and ChatGPT were compared across ten uro-oncological case rounds. Thirty urologists assessed recommendation correctness, source verifiability and trust with preference ratings collected after each round. UroBot performed significantly better than ChatGPT in recommendation correctness (73 % vs. 50 %; p < 0.001), source attribution (74 % vs. 30 %; p < 0.001) and verifiability of sources (84 % vs. 35 %; p < 0.001). Furthermore, clinicians consistently preferred UroBot for accuracy, source verifiability and trust. Qualitative analysis showed that ChatGPT often produced vague or incorrect citations, with 28 % being non-existent or outdated and 83 % lacking specific sections, whereas UroBot achieved complete alignment on guideline sub-section and page level. These gains in citation precision were mirrored by higher clinician ratings for verifiability and trust. Limitations include the small sample size of ten cases due to feasibility, which may not cover the full uro-oncological spectrum. Our findings show that combining LLMs with RAG with in-line references and source text previews markedly enhances perceived source attribution and verifiability compared to state-of-the-art conventional LLMs. Importantly, this approach is readily transferable across medical subspecialties, enabling reliable and up-to-date clinical decision support.

19 October 2025 in Current Oncology
Verified
Journal Article
Open access
PDF file
LMLasse Maywald
Lasse Maywald
LNLisa Thuy Nguyen
Lisa Thuy Nguyen
JWJana Winterstein
Jana Winterstein
MHMartin Joachim Hetz
Martin Joachim Hetz
MMMaurin Helen Mangold
Maurin Helen Mangold
NCNicolas Carl
Nicolas Carl
Large language models (LLMs) are increasingly explored as chatbots for patient education, including applications in urooncology. Since only 12% of adults have proficient health literacy and most patient information materials exceed recommended reading levels, improving readability is crucial. Although LLMs could potentially increase the readability of medical information, evidence is mixed, underscoring the need to assess chatbot outputs in clinical settings. Therefore, this study evaluates the measured and perceived readability of chatbot responses in speech-based interactions with urological patients. Urological patients engaged in unscripted conversations with a GPT-4-based chatbot. Transcripts were analyzed using three readability indices: Flesch–Reading-Ease (FRE), Lesbarkeitsindex (LIX) and Wiener-Sachtextformel (WSF). Perceived readability was assessed using a survey covering technical language, clarity and explainability. Associations between measured and perceived readability were analyzed. Knowledge retention was not assessed in this study. A total of 231 conversations were evaluated. The most frequently addressed topics were prostate cancer (22.5%), robotic-assisted prostatectomy (19.9%) and follow-up (18.6%). Objectively, responses were classified as difficult to read (FRE 43.1 ± 9.1; LIX 52.8 ± 6.2; WSF 11.2 ± 1.6). In contrast, perceived readability was rated highly for technical language, clarity and explainability (83–90%). Correlation analyses revealed no association between objective and perceived readability. Chatbot responses were objectively written at a difficult reading level, exceeding recommendations for optimized health literacy. Nevertheless, most patients perceived the information as clear and understandable. This discrepancy suggests that perceived comprehensibility is influenced by factors beyond measurable linguistic complexity.

30 August 2024 in Urologia Internationalis
Verified
Journal Article
Closed access
PDF file
NCNicolas Carl
Nicolas Carl
LSLeah Schmidt
Leah Schmidt
BBBjoern Buedenbender
Bjoern Buedenbender
ABAnja K. Blum
Anja K. Blum
MNMalin Nientiedt
Malin Nientiedt
BGBritta Grüne
Britta Grüne
Introduction: Systematic evaluations focusing on the perception of body image and social support in relation to quality of life (QoL) outcomes in patients radical cystectomy (RC) with urinary diversion (UD) are currently lacking. This study investigated the relationship between body image perception, social support, and QoL in bladder cancer patients who underwent RC with UD. Methods: A cross-sectional survey was conducted using validated general oncology tools to assess QoL in relation to newly implemented tools assessing body image perception and social support. Body image perception was assessed with the Self-Image Scale, and social support was assessed using the Illness-Specific Social Support Scale. Logistic regression models were used to analyze factors associated with QoL and body image, respectively. Results: The survey revealed a significant association of body image perception with QoL, as well as social support with body image perception. This is the first study to systematically evaluate these psychosocial factors in the context of QoL for RC patients, highlighting their critical role in patient-reported outcomes. Conclusion: Body image perception and social support are important psychosociological factors that affect QoL of bladder cancer patients post-RC. Targeted psychosocial interventions could be promising for improving QoL patients post-RC.

14 August 2025 in World Journal of Urology
Verified
Journal Article
Closed access
PDF file
NCNicolas Carl
Nicolas Carl
SHSarah Haggenmüller
Sarah Haggenmüller
JWJana Theres Winterstein
Jana Theres Winterstein
LNLisa Nguyen
Lisa Nguyen
CWChristoph Wies
Christoph Wies
FWFrederik Wessels
Frederik Wessels

19 May 2026 in Die Urologie
Verified
Journal Article
Open access
NCNicolas Carl
Nicolas Carl
FWFrederik Wessels
Frederik Wessels
JJJonathan Jeutner
Jonathan Jeutner
SFSebastian Frees
Sebastian Frees
MWMike Wenzel
Mike Wenzel
SRSeverin Rodler
Severin Rodler
Zusammenfassung: Hintergrund: Die urologische Versorgung in Deutschland ist im Wandel und neue Anwendungen mit künstlicher Intelligenz (KI) bieten das Potential, Prozesse zu automatisieren und Personal zu entlasten. Ziel war es daher, die Arbeitsbelastung, aktuelle KI-Nutzung sowie Vertrauen und Erwartungen im Kontext der aktuellen Versorgungslage systematisch zu beschreiben. Methoden: Deutschlandweite, anonyme Querschnittbefragung im urologischen Versorgungsbereich von Januar bis April 2026. Die Auswertung erfolgte explorativ und deskriptiv. Ergebnisse: Insgesamt nahmen 433 Personen teil, überwiegend Ärzt:innen. 79 % berichteten über ein gestiegenes Patientenaufkommen, 69 % gaben an, dass die verfügbare Zeit für eine qualitativ hochwertige Versorgung nicht ausreiche. Als Haupttreiber des Zeitdrucks wurde administrativer und dokumentationsbezogener Aufwand genannt (93,1 %). Allgemein zugängliche KI-Tools werden deutlich häufiger genutzt, 74,6 % verwenden KI privat und/oder beruflich, während medizinisch zugelassene Systeme nur von einer Minderheit eingesetzt werden. Die Nutzung konzentriert sich auf informations- und textbasierte Aufgaben wie Recherche, Übersetzung und Textentwürfe. Gleichzeitig bestehen Hinweise für einen hohen, bislang ungedeckter Bedarf, insbesondere für Kodierung, Dokumentation, Bildanalyse und Medikationsmanagement. Angegebene Voraussetzungen für Vertrauen in KI sind überprüfbare Qualität (82,4 %), evidenzbasierte Datenquellen (72,1 %), klare regulatorische Rahmenbedingungen (70,0 %) und Integration in IT-Strukturen (63,7 %). Siebenundfünfzig Prozent der Teilnehmenden erwarten künftig eine Zeitersparnis durch KI. Fazit: Die urologische Versorgung wird von den Befragten als zunehmend verdichtet wahrgenommen. KI wird bereits breit genutzt, derzeit jedoch v. a. in Form allgemein zugänglicher Anwendungen. Die Ergebnisse deuten zudem auf einen bislang nicht gedeckten Bedarf an KI-Anwendungen für ausgewählte kleinteilige Alltagsaufgaben hin, insbesondere sofern Anforderungen an Qualität, Transparenz und Governance erfüllt sind.