Purpose: We aimed to evaluate the time and cost of developing prompts using large language model (LLM), tailored to extract clinical factors in breast cancer patients and their accuracy.Materials and Methods: We collected data from reports of surgical pathology and ultrasound from breast cancer patients who underwent radiotherapy from 2020 to 2022. We extracted the information using the Generative Pre-trained Transformer (GPT) for Sheets and Docs extension plugin and termed this the “LLM” method. The time and cost of developing the prompts with LLM methods were assessed and compared with those spent on collecting information with “full manual” and “LLM-assisted manual” methods. To assess accuracy, 340 patients were randomly selected, and the extracted information by LLM method were compared with those collected by “full manual” method.Results: Data from 2,931 patients were collected. We developed 12 prompts for Extract function and 12 for Format function to extract and standardize the information. The overall accuracy was 87.7%. For lymphovascular invasion, it was 98.2%. Developing and processing the prompts took 3.5 hours and 15 minutes, respectively. Utilizing the ChatGPT application programming interface cost US $65.8 and when factoring in the estimated wage, the total cost was US $95.4. In an estimated comparison, “LLM-assisted manual” and “LLM” methods were time- and cost-efficient compared to the “full manual” method.Conclusion: Developing and facilitating prompts for LLM to derive clinical factors was efficient to extract crucial information from huge medical records. This study demonstrated the potential of the application of natural language processing using LLM model in breast cancer patients. Prompts from the current study can be re-used for other research to collect clinical information.

Some patients with glioblastoma show a worsening presentation in imaging after concurrent chemoradiation, even when they receive gross total resection. Previously, we showed the feasibility of a machine learning model to predict pseudoprogression (PsPD) versus progressive disease (PD) in glioblastoma patients. The previous model was based on the dataset from two institutions (termed as the Seoul National University Hospital (SNUH) dataset, N = 78). To test this model in a larger dataset, we collected cases from multiple institutions that raised the problem of PsPD vs. PD diagnosis in clinics (Korean Radiation Oncology Group (KROG) dataset, N = 104). The dataset was composed of brain MR images and clinical information. We tested the previous model in the KROG dataset; however, that model showed limited performance. After hyperparameter optimization, we developed a deep learning model based on the whole dataset (N = 182). The 10-fold cross validation revealed that the micro-average area under the precision-recall curve (AUPRC) was 0.86. The calibration model was constructed to estimate the interpretable probability directly from the model output. After calibration, the final model offers clinical probability in a web-user interface.

Suh KJ, et al. J Breast Cancer. 2022 Jun;25:e30. https://doi.org/10.4048/jbc.2022.25.e30

Background: We hypothesized that lower socioeconomic status (SES) was associated with higher all‐cause mortality in patients newly diagnosed with cancer, particularly in the elderly population.Methods: We collected study patients from the stratified random sample of Korean National Health Insurance Elderly Cohort (2002‐2015). The Cox's proportional hazards model was used to investigate the risk factors for mortality. Income level and composite deprivation index (CDI) 2010 were used to define the SES: low, intermediate, and high SES groups. The comorbidities were measured using Charlson Comorbidity Index score. After a wash‐out period (2002), the final study population was 108 626 (2003‐2015).Results: In multivariate analysis, low SES was associated with poor overall survival (OS) (HR = 1.08, 95% CI: 1.05‐1.12, P < 0.001) and cancer‐specific survival (CSS) (HR = 1.11, 95% CI: 1.06‐1.16, P < 0.001) particularly for patients aged 70‐79 years. High SES was favorable prognostic factor of OS in patients aged 60‐69 years (HR = 0.85, 95% CI: 0.81‐0.89, P < 0.001), 70‐79 years (HR = 0.90, 95% CI: 0.87‐0.93, P < 0.001), and ≥80 years (HR = 0.91, 95% CI: 0.87‐0.96, P < 0.001). However, SES was not associated with CSS in advanced age patients (≥80 years). Patients with low SES manifesting colorectal, urinary, liver, gastric, melanoma, and esophageal cancers demonstrated worse OS, compared to patients with intermediate SES. Also, low SES patients with urinary, liver, or colorectal cancers or melanoma demonstrated worse CSS compared to those with intermediate SES.Conclusion: Low SES at the time of cancer diagnosis is associated with increased risk of OS and CSS in elderly patients. Depending on cancer sites, different patterns of OS and CSS were observed according to SES. Further elucidation of the causes underlying these phenomena is needed along with appropriate support for elderly cancer patients with low SES.