Several studies suggest that delay in the surgical treatment of breast cancer is significantly associated with lower survival. This study evaluated the tumor growth rate (TGR) of invasive breast cancers during wait times for surgery quantitatively using ultrasonography (US) and identified clinicopathologic factors associated with TGR. This retrospective study was approved by our institutional review board and the requirement for written informed consent was waived. Between August 2013 and September 2014, a total of 323 unifocal invasive breast cancers in 323 women with serial US images at the time of diagnosis and surgery were included. Tumor diameters and volumes were measured using 2-orthogonal US images. TGR during wait times for surgery was quantified as specific growth rates (SGR; %/day) and was compared with clinicopathologic variables using univariate and multivariate analyses. Median time from diagnosis to surgery was 31 days (range, 8–78 days). Maximum tumor diameters and volumes at the time of surgery (mean, 15.6 mm and 1.6 cm3) were significantly larger than at diagnosis (14.7 mm and 1.3 cm3) (P < 0.001). On multivariate analysis, surrogate molecular subtype was a significant independent factor of SGR (P = 0.001); triple negative cancers showed the highest SGR (1.003%/day) followed by HER2-positive (0.859 %/day) and luminal cancers (luminal B, 0.208 %/day; luminal A, 0.175%/day) (P < 0.001). Clinical T stage was more frequently upgraded in nonluminal (triple negative, 18% [12/67]; HER2-positive, 14% [3/22]) than luminal cancers (luminal B, 3% [1/30]; luminal A, 2% [4/204]) (P < 0.001). Invasive breast cancers with aggressive molecular subtypes showed faster TGR and more frequent upgrading of clinical T stage during wait times for surgery.

Yoon SH, et al. J Korean Med Sci. 2020 Nov;35(46):e413. https://doi.org/10.3346/jkms.2020.35.e413

Background: An artificial intelligence (AI) model using chest radiography (CXR) may provide good performance in making prognoses for COVID-19. Objective: We aimed to develop and validate a prediction model using CXR based on an AI model and clinical variables to predict clinical outcomes in patients with COVID-19. Methods: This retrospective longitudinal study included patients hospitalized for COVID-19 at multiple COVID-19 medical centers between February 2020 and October 2020. Patients at Boramae Medical Center were randomly classified into training, validation, and internal testing sets (at a ratio of 8:1:1, respectively). An AI model using initial CXR images as input, a logistic regression model using clinical information, and a combined model using the output of the AI model (as CXR score) and clinical information were developed and trained to predict hospital length of stay (LOS) ≤2 weeks, need for oxygen supplementation, and acute respiratory distress syndrome (ARDS). The models were externally validated in the Korean Imaging Cohort of COVID-19 data set for discrimination and calibration. Results: The AI model using CXR and the logistic regression model using clinical variables were suboptimal to predict hospital LOS ≤2 weeks or the need for oxygen supplementation but performed acceptably in the prediction of ARDS (AI model area under the curve [AUC] 0.782, 95% CI 0.720-0.845; logistic regression model AUC 0.878, 95% CI 0.838-0.919). The combined model performed better in predicting the need for oxygen supplementation (AUC 0.704, 95% CI 0.646-0.762) and ARDS (AUC 0.890, 95% CI 0.853-0.928) compared to the CXR score alone. Both the AI and combined models showed good calibration for predicting ARDS (P=.079 and P=.859). Conclusions: The combined prediction model, comprising the CXR score and clinical information, was externally validated as having acceptable performance in predicting severe illness and excellent performance in predicting ARDS in patients with COVID-19.