On the utility of ChatGPT in conducting a literature review on deep learning for dopamine transporter SPECT with [¹²³I]ioflupane
Nuklearmedizin - NuclearMedicine · 01.08.2026 · 65 (04) · 255-264
DOI: 10.1055/a-2890-8325 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift Nuklearmedizin - NuclearMedicine, erschienen am 01.08.2026. Verfasst von Thomas Buddenkotte und 6 weiteren Autor:innen. Beteiligte Einrichtung: University Medical Center Hamburg-Eppendorf, Department of Diagnostic and Interventional Radiology and Nuclear Medicine, Germany, Hamburg. Hauptthemen laut MEDLINE: Tomography, Emission-Computed, Single-Photon, Nortropanes, Dopamine Plasma Membrane Transport Proteins, Deep Learning. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 98 Literaturangaben.
Abstract (Originalsprache)
This study evaluated ChatGPT (GPT-5.2) for drafting a review paper on deep learning in dopamine transporter (DAT)-SPECT with [¹²³I]ioflupane. The review workflow consisted of 3 steps: (i) literature search, (ii) generation of structured summaries with 24 predefined fields for each publication, and (iii) drafting a review paper based on the structured summaries across all publications. A detailed prompt for ChatGPT was iteratively designed for each step with ChatGPT support. A manual literature search was independently performed by an expert in DAT-SPECT and deep learning. ChatGPT-generated structured summaries were manually fact-checked against the full publications and corrected where necessary. The review draft generated by ChatGPT was checked against the corrected summaries. When prompted to compile an exhaustive list of publications, ChatGPT cited 13 papers, whereas the manual search identified 70 relevant publications, 67 of which were included. Corrections to ChatGPT-generated structured summaries were required in 27 cases (40.3%), affecting one or two of the 24 predefined fields, while no changes were necessary in 40 publications (59.7%). Most corrections could likely have been avoided by more precise prompting. All numerical information (dataset sizes, train-test splits, performance metrics) was correct. The review draft (~950 words) generated by ChatGPT was content-wise meaningful and accurate, but contained referencing errors, including incorrect citations, missing references, and citations of non-existent publications. ChatGPT is a highly effective tool for drafting review manuscripts in nuclear medicine imaging, but its limitations in literature retrieval and referencing require careful expert supervision.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- University Medical Center Hamburg-Eppendorf, Department of Diagnostic and Interventional Radiology and Nuclear Medicine, Germany, Hamburg.
- jung diagnostics GmbH, Germany, Hamburg.
- German Center for Neurodegenerative Diseases (DZNE), Germany, Bonn.
- University Hospital Bonn, Clininical Functional Imaging Group, Department of Nuclear Medicine, Germany, Bonn.
ORCID-Profile: Ralph Buchert
Zitieren
APA
Buddenkotte, T., Apostolova, I. I., Opfer, R., Klutmann, S., Braren, R., Boecker, H., & Buchert, R. (2026). On the utility of ChatGPT in conducting a literature review on deep learning for dopamine transporter SPECT with [¹²³I]ioflupane. Nuklearmedizin - NuclearMedicine, 65(04), 255-264. https://doi.org/10.1055/a-2890-8325
Vancouver
Buddenkotte T, Apostolova II, Opfer R, Klutmann S, Braren R, Boecker H, et al. On the utility of ChatGPT in conducting a literature review on deep learning for dopamine transporter SPECT with [¹²³I]ioflupane. Nuklearmedizin - NuclearMedicine. 2026;65(04):255-264. doi:10.1055/a-2890-8325
BibTeX
@article{Buddenkotte2026,
author = {Buddenkotte, Thomas and Apostolova, Ivayla Ilieva and Opfer, Roland and Klutmann, Susanne and Braren, Rickmer and Boecker, Henning and Buchert, Ralph},
title = {On the utility of ChatGPT in conducting a literature review on deep learning for dopamine transporter SPECT with [¹²³I]ioflupane},
journal = {Nuklearmedizin - NuclearMedicine},
year = {2026},
volume = {65},
number = {04},
pages = {255--264},
doi = {10.1055/a-2890-8325}
}
EUVIMED