Lee SH, et al. Korean J Radiol. 2020 Jul;21(7):779-792. https://doi.org/10.3348/kjr.2019.0855

Background: Many studies have successfully identified radiomics features reflecting macroscale tumor features and tumor microenvironment for various organs. There is an increased interest in applying these radiomics features found in a given organ to other organs. Here, we explored whether common radiomics features could be identified over target organs in vastly different environments. Methods: Four datasets of three organs were analyzed. One radiomics model was constructed from the training set (lungs, n = 401), and was further evaluated in three independent test sets spanning three organs (lungs, n = 59; kidneys, n = 48; and brains, n = 43). Intensity histograms derived from the whole organ were compared to establish organ-level differences. We constructed a radiomics score based on selected features using training lung data over the tumor region. A total of 143 features were computed for each tumor. We adopted a feature selection approach that favored stable features, which can also capture survival. The radiomics score was applied to three independent test data from lung, kidney, and brain tumors, and whether the score could be used to separate high- and low-risk groups, was evaluated. Results: Each organ showed a distinct pattern in the histogram and the derived parameters (mean and median) at the organ-level. The radiomics score trained from the lung data of the tumor region included seven features, and the score was only effective in stratifying survival for other lung data, not in other organs such as the kidney and brain. Eliminating the lung-specific feature (2.5 percentile) from the radiomics score led to similar results. There were no common features between training and test sets, but a common category of features (texture category) was identified. Conclusion: Although the possibility of a generally applicable model cannot be excluded, we suggest that radiomics score models for survival were mostly specific for a given organ; applying them to other organs would require careful consideration of organ-specific properties.

Background/Aims: Sedation has become a standard practice for patients undergoing gastrointestinal (GI) endoscopy. However, considering the serious cardiopulmonary adverse events associated with sedatives, it is important to identify patients at high risk. Machine learning can generate reasonable prediction for a wide range of medical conditions. This study aimed to evaluate the risk factors associated with sedation during GI endoscopy and develop a predictive model for hypoxia during endoscopy under sedation.Methods: This prospective observational study enrolled 446 patients who underwent sedative endoscopy at the Korea University Ansan Hospital. Clinical data were used as predictor variables to construct predictive models using the random forest method that is a machine learning algorithm.Results: Seventy-two of the 446 patients (16.1%) experienced life-threatening hypoxia requiring immediate medical intervention. Patients who developed hypoxia had higher body weight, body mass index (BMI), neck circumference, and Mallampati scores. Propofol alone and higher initial and total dose of propofol were significantly associated with hypoxia during sedative endoscopy. Among these variables, high BMI, neck circumference, and Mallampati score were independent risk factors for hypoxia. The area under the receiver operating characteristic curve for the random forest-based predictive model for hypoxia during sedative endoscopy was 0.82 (95% confidence interval, 0.79–0.86) and displayed a moderate discriminatory power.Conclusions: High BMI, neck circumference, and Mallampati score were independently associated with hypoxia during sedative endoscopy. We constructed a model with acceptable performance for predicting hypoxia during sedative endoscopy.

We aimed to investigate the relationship between tumor radiomic margin characteristics and prognosis in patients with lung cancer. We enrolled 334 patients who underwent complete resection for lung adenocarcinoma. A quantitative computed tomography analysis was performed, and 76 radiomic margin characteristics were extracted. The radiomic margin characteristics were correlated with overall survival. The selected clinical variables and radiomic margin characteristics were used to calculate a prognostic model with subsequent internal and external validation. Nearly all of the radiomic margin characteristics showed excellent reproducibility. The least absolute shrinkage and selection operator (LASSO) method was used to select eight radiomic margin characteristics. When compared to the model with clinical variables only (C-index = 0.738), the model incorporating clinical variables and radiomic margin characteristics (C-index = 0.753) demonstrated a higher C-index for predicting overall survival. In the model integrating both clinical variables and radiomic margin characteristics, convexity, a Laplace of Gaussian (LoG) kurtosis of 3, and the roundness factor were each independently predictive of overall survival. In addition, radiomic margin characteristics were also correlated with the micropapillary subtype, and the sphericity value was able to predict the presence of the micropapillary subtype. In conclusion, our study showed that radiomic margin characteristics helped predict overall survival in patients with lung adenocarcinomas, thus implying that the tumor margin contains prognostic information.