Alessia Spitaleri
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Alessia Spitaleri has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
Amato Antonio Stabile Ianora
Interdisciplinary Department of Medicine, Section of Radiology and Radiation Oncology, University of Bari "Aldo Moro", Bari, Italy
1 shared publicationChiara Morelli
Interdisciplinary Department of Medicine, Section of Radiology and Radiation Oncology, University of Bari "Aldo Moro", Bari, Italy
1 shared publication- Chiara Morelli
Interdisciplinary Department of Medicine, Section of Radiology and Radiation Oncology, University of Bari “Aldo Moro”, 70124 Bari, Italy
1 shared publication - Francesca Troise
Interdisciplinary Department of Medicine, Section of Radiology and Radiation Oncology, University of Bari “Aldo Moro”, 70124 Bari, Italy
1 shared publication Giorgio Ruscino
Interdisciplinary Department of Medicine, Section of Radiology and Radiation Oncology, University of Bari "Aldo Moro", Bari, Italy
1 shared publicationGiovanni Lorusso
Interdisciplinary Department of Medicine, Section of Radiology and Radiation Oncology, University of Bari "Aldo Moro", Bari, Italy
1 shared publication
Latest Publications
- Open Access
- 22 April 2026
- Published by Springer Nature in Insights into Imaging
- Vol. 17 (1)
Comparative evaluation of large language models for generating CAD-RADS 2.0-compliant diagnostic conclusions in cardiac CT reports
Objectives: Coronary computed tomography angiography (CCTA) has become a cornerstone in non-invasive CAD diagnosis and risk stratification. To standardize reporting and improve clinical decision-making, the CAD-RADS 2.0 system was introduced. This study evaluates the performance of four LLMs, GPT-4o, Gemini 2.0 Flash, DeepSeek V, and Copilot in generating CAD-RADS 2.0-compliant conclusions from standardized CCTA reports. Materials and methods: A total of 196 anonymized CCTA reports were retrospectively analyzed. Each LLM was prompted to provide CAD-RADS 2.0 classifications and follow-up recommendations. Ground truth labels were assigned by a senior radiologist. Performance metrics (accuracy, precision, recall, F1-score), execution times, and agreement (Cohen’s kappa) with expert interpretation were computed. Interobserver agreement between junior and senior radiologists was also assessed. Results: LLMs demonstrated good-to-excellent agreement with expert classifications: DeepSeek V (κ = 0.771), Copilot (κ = 0.761), GPT-4o (κ = 0.759), and Gemini 2.0 Flash (κ = 0.634). DeepSeek V achieved the highest accuracy (91.83%). Intra-model consistency was perfect (κ = 1). However, LLMs failed to assign CAD-RADS modifiers. ChatGPT-4o provided the most accurate follow-up recommendations (71.94%). All LLMs outperformed radiologists in execution time (3–9 s vs. 15–20 s; p < 0.05). Conclusions: Generic LLMs demonstrate promising performance in automating CAD-RADS 2.0 classification from CCTA reports. However, limitations in modifier assignment and recommendation accuracy highlight areas for refinement before clinical integration. Critical relevance statement: This study explores the potential of large language models to facilitate standardized CAD-RADS 2.0 reporting from coronary CT angiography, highlighting a possible avenue to support workflow efficiency and clinical decision-making in non-invasive coronary artery disease evaluation. Key Points: LLMs demonstrated strong potential in automating CAD-RADS 2.0-compliant structured reporting for CCTA. LLMs could significantly enhance efficiency in radiological reporting. LLMs need further optimization before clinical integration. Graphical
- 22 April 2026
- Published by Springer Nature in Insights into Imaging
- Vol. 17 (1)
Open AccessComparative evaluation of large language models for generating CAD-RADS 2.0-compliant diagnostic conclusions in cardiac CT reports
Objectives: Coronary computed tomography angiography (CCTA) has become a cornerstone in non-invasive CAD diagnosis and risk stratification. To standardize reporting and improve clinical decision-making, the CAD-RADS 2.0 system was introduced. This study evaluates the performance of four LLMs, GPT-4o, Gemini 2.0 Flash, DeepSeek V, and Copilot in generating CAD-RADS 2.0-compliant conclusions from standardized CCTA reports. Materials and methods: A total of 196 anonymized CCTA reports were retrospectively analyzed. Each LLM was prompted to provide CAD-RADS 2.0 classifications and follow-up recommendations. Ground truth labels were assigned by a senior radiologist. Performance metrics (accuracy, precision, recall, F1-score), execution times, and agreement (Cohen’s kappa) with expert interpretation were computed. Interobserver agreement between junior and senior radiologists was also assessed. Results: LLMs demonstrated good-to-excellent agreement with expert classifications: DeepSeek V (κ = 0.771), Copilot (κ = 0.761), GPT-4o (κ = 0.759), and Gemini 2.0 Flash (κ = 0.634). DeepSeek V achieved the highest accuracy (91.83%). Intra-model consistency was perfect (κ = 1). However, LLMs failed to assign CAD-RADS modifiers. ChatGPT-4o provided the most accurate follow-up recommendations (71.94%). All LLMs outperformed radiologists in execution time (3–9 s vs. 15–20 s; p < 0.05). Conclusions: Generic LLMs demonstrate promising performance in automating CAD-RADS 2.0 classification from CCTA reports. However, limitations in modifier assignment and recommendation accuracy highlight areas for refinement before clinical integration. Critical relevance statement: This study explores the potential of large language models to facilitate standardized CAD-RADS 2.0 reporting from coronary CT angiography, highlighting a possible avenue to support workflow efficiency and clinical decision-making in non-invasive coronary artery disease evaluation. Key Points: LLMs demonstrated strong potential in automating CAD-RADS 2.0-compliant structured reporting for CCTA. LLMs could significantly enhance efficiency in radiological reporting. LLMs need further optimization before clinical integration. Graphical
- Open Access
- 17 March 2026
- Published by MDPI AG in Diagnostics
- Vol. 16 (6) , 886
Rare Combination of Partial ARCAPA and Dual LAD: Insights into Complex Coronary Variants
This case report highlights the coexistence of two rare coronary artery anomalies assessed by computed coronary tomography angiography (CCTA). We present the case of a 51-year-old hypertensive patient with a type II double left anterior descending artery (LAD) and an anomalous infundibular branch originating from the pulmonary artery (partial ARCAPA). This association may have contributed to a limited ischemic burden, explaining the patient’s asymptomatic state. Knowledge of these rare coronary anatomies is essential for accurate diagnosis and management.
- 17 March 2026
- Published by MDPI AG in Diagnostics
- Vol. 16 (6) , 886
Open AccessRare Combination of Partial ARCAPA and Dual LAD: Insights into Complex Coronary Variants
This case report highlights the coexistence of two rare coronary artery anomalies assessed by computed coronary tomography angiography (CCTA). We present the case of a 51-year-old hypertensive patient with a type II double left anterior descending artery (LAD) and an anomalous infundibular branch originating from the pulmonary artery (partial ARCAPA). This association may have contributed to a limited ischemic burden, explaining the patient’s asymptomatic state. Knowledge of these rare coronary anatomies is essential for accurate diagnosis and management.