Chest radiograph interpretation, assisted by a deep learning–based automatic detection algorithm, can reduce the number of overlooked lung cancers without increasing the frequency of chest CT follo... Background It is uncertain whether a deep learning–based automatic detection algorithm (DLAD) for identifying malignant nodules on chest radiographs will help diagnose lung cancers. Purpose To eval...

Yoo SM, et al. Korean J Radiol. 2020 Jul;21:e136. https://doi.org/10.3348/kjr.2020.0064

Background: Traditional rule-based natural language processing approaches in electronic health record systems are effective but are often time-consuming and prone to errors when handling unstructured data. This is primarily due to the substantial manual effort required to parse and extract information from diverse types of documentation. Recent advancements in large language model (LLM) technology have made it possible to automatically interpret medical context and support pathologic staging. However, existing LLMs encounter challenges in rapidly adapting to specialized guideline updates. In this study, we fine-tuned an LLM specifically for lung cancer pathologic staging, enabling it to incorporate the latest guidelines for pathologic TN classification. Objective: This study aims to evaluate the performance of fine-tuned generative language models in automatically inferring pathologic TN classifications and extracting their rationale from lung cancer surgical pathology reports. By addressing the inefficiencies and extensive parsing efforts associated with rule-based methods, this approach seeks to enable rapid and accurate reclassification aligned with the latest cancer staging guidelines. Methods: We conducted a comparative performance evaluation of 6 open-source LLMs for automated TN classification and rationale generation, using 3216 deidentified lung cancer surgical pathology reports based on the American Joint Committee on Cancer (AJCC) Cancer Staging Manual8th edition, collected from a tertiary hospital. The dataset was preprocessed by segmenting each report according to lesion location and morphological diagnosis. Performance was assessed using exact match ratio (EMR) and semantic match ratio (SMR) as evaluation metrics, which measure classification accuracy and the contextual alignment of the generated rationales, respectively. Results: Among the 6 models, the Orca2_13b model achieved the highest performance with an EMR of 0.934 and an SMR of 0.864. The Orca2_7b model also demonstrated strong performance, recording an EMR of 0.914 and an SMR of 0.854. In contrast, the Llama2_7b model achieved an EMR of 0.864 and an SMR of 0.771, while the Llama2_13b model showed an EMR of 0.762 and an SMR of 0.690. The Mistral_7b and Llama3_8b models, on the other hand, showed lower performance, with EMRs of 0.572 and 0.489, and SMRs of 0.377 and 0.456, respectively. Overall, the Orca2 models consistently outperformed the others in both TN stage classification and rationale generation. Conclusions: The generative language model approach presented in this study has the potential to enhance and automate TN classification in complex cancer staging, supporting both clinical practice and oncology data curation. With additional fine-tuning based on cancer-specific guidelines, this approach can be effectively adapted to other cancer types.

Background: Digital transformation, particularly the integration of medical imaging with clinical data, is vital in personalized medicine. The Observational Medical Outcomes Partnership (OMOP) Common Data Model (CDM) standardizes health data. However, integrating medical imaging remains a challenge. Objective: This study proposes a method for combining medical imaging data with the OMOP CDM to improve multimodal research. Methods: Our approach included the analysis and selection of digital imaging and communications in medicine header tags, validation of data formats, and alignment according to the OMOP CDM framework. The Fast Healthcare Interoperability Resources ImagingStudy profile guided our consistency in column naming and definitions. Imaging Common Data Model (I-CDM), constructed using the entity-attribute-value model, facilitates scalable and efficient medical imaging data management. For patients with lung cancer diagnosed between 2010 and 2017, we introduced 4 new tables—IMAGING_STUDY, IMAGING_SERIES, IMAGING_ANNOTATION, and FILEPATH—to standardize various imaging-related data and link to clinical data. Results: This framework underscores the effectiveness of I-CDM in enhancing our understanding of lung cancer diagnostics and treatment strategies. The implementation of the I-CDM tables enabled the structured organization of a comprehensive data set, including 282,098 IMAGING_STUDY, 5,674,425 IMAGING_SERIES, and 48,536 IMAGING_ANNOTATION records, illustrating the extensive scope and depth of the approach. A scenario-based analysis using actual data from patients with lung cancer underscored the feasibility of our approach. A data quality check applying 44 specific rules confirmed the high integrity of the constructed data set, with all checks successfully passed, underscoring the reliability of our findings. Conclusions: These findings indicate that I-CDM can improve the integration and analysis of medical imaging and clinical data. By addressing the challenges in data standardization and management, our approach contributes toward enhancing diagnostics and treatment strategies. Future research should expand the application of I-CDM to diverse disease populations and explore its wide-ranging utility for medical conditions.

Introduction: Unlike its well-established role in lung cancer staging, positron emission tomography /computed tomography (PET/CT)'s role in guiding lung biopsies remains unclear and underutilized, despite its potential to distinguish metabolically active regions from areas of necrosis or fibrosis within lesions. Objective: This study aims to assess the diagnostic efficacy of PET/CT-aided versus conventional CT-guided lung biopsy by comparing the incidences of non-diagnostic results, false results, and complications. Methods: Studies comparing PET/CT-aided and conventional CT-guided lung biopsy were identified through an intensive search of PubMed, Embase, and the Cochrane Library. Data on nondiagnostic results, false results, and complications were extracted. Risk ratios (RRs) with 95% confidence intervals (CIs) were calculated using a random-effects model. Results: Seven studies involving 1,661 procedures were included. PET/CT-aided lung biopsy significantly reduced nondiagnostic results compared to conventional CT-guided biopsy (2.8% vs. 9.1%; pooled RR: 0.38, 95% CI: 0.20–0.70, P = 0.002). False results were also significantly fewer in the PET/CT-aided group (6.5% vs. 17.0%; pooled RR: 0.48, 95% CI: 0.35–0.65, P < 0.001). There was no statistically significant difference in overall complication rates (28.1% vs. 32.5%; pooled RR: 0.92, 95% CI: 0.77–1.10, P = 0.352), while PET/CT-aided biopsy showed a slight tendency toward fewer major complications (0.9% vs. 1.7%; pooled RR: 0.67, 95% CI: 0.30–1.44, P = 0.303). Conclusion: PET/CT-aided CT-guided lung biopsy offers advantages over conventional CT-guided lung biopsy by significantly reducing nondiagnostic and false results, without significant differences in the risk of complications.