Diagnostic Performance of Large Language Models Using FDG PET-Derived Z-Score Profiles and Structured Clinical Information in Neurodegenerative Diseases

INTRODUCTION: To evaluate the diagnostic performance of large language models (LLMs) with FDG PET-derived Z-score profiles and structured clinical information in patients with suspected neurodegenerative diseases (NDs).
METHODS: This retrospective study included patients who underwent FDG-PET imaging of the brain for suspected NDs. FDG PET brain imaging Z-score derived from a database and anonymized structured clinical information were provided to four LLMs (ChatGPT, Grok, Gemini, and DeepSeek). Each model generated a single diagnosis among Alzheimer’s disease, frontotemporal dementia, dementia with Lewy bodies, vascular dementia, primary progressive aphasia, or normal/nonspecific. A multidisciplinary consensus diagnosis served as the reference standard. LLM outputs were stratified into subgroups: overall, high diagnostic confidence (HC; ≥85%), epicenter concordance (EC), and combined (HC + EC). Diagnostic agreement was assessed using Cohen’s kappa (κ).
RESULTS: A total of 80 patients (42 females, 38 males) were included. All LLMs showed significant agreement with the diagnosis. ChatGPT had the highest agreement (κ=0.760), followed by Grok (κ=0.648) and DeepSeek (κ=0.639). In the HC subgroup, agreement improved across all models, with ChatGPT reaching κ=0.872, followed by DeepSeek (κ=0.789), Grok (κ=0.711), and Gemini (κ=0.676). In the EC subgroup, ChatGPT (κ=0.828) and Grok (κ=0.799) show substantial concordance, and DeepSeek (κ=0.682) and Gemini (κ=0.542) demonstrate moderate agreement. In the combined HC + EC subgroup, ChatGPT achieved the strongest performance (κ=0.860), followed by Grok (κ=0.824) and DeepSeek (κ=0.786), while Gemini reached moderate agreement (κ=0.652).
DISCUSSION AND CONCLUSION: LLMs showed moderate-to-high agreement with multidisciplinary consensus diagnoses in patients with suspected NDs. Agreement was higher in cases with high diagnostic confidence and epicenter concordance.

Keywords: fluorodeoxyglucose positron emission tomography, brain imaging, neurodegenerative diseases, large language models, artificial intelligence, decision support systems.