Background: Predicting hypoglycemia while maintaining a low false alarm rate is a challenge for the wide adoption of continuous glucose monitoring (CGM) devices in diabetes management. One small study suggested that a deep learning model based on the long short-term memory (LSTM) network had better performance in hypoglycemia prediction than traditional machine learning algorithms in European patients with type 1 diabetes. However, given that many well-recognized deep learning models perform poorly outside the training setting, it remains unclear whether the LSTM model could be generalized to different populations or patients with other diabetes subtypes. Objective: The aim of this study was to validate LSTM hypoglycemia prediction models in more diverse populations and across a wide spectrum of patients with different subtypes of diabetes. Methods: We assembled two large data sets of patients with type 1 and type 2 diabetes. The primary data set including CGM data from 192 Chinese patients with diabetes was used to develop the LSTM, support vector machine (SVM), and random forest (RF) models for hypoglycemia prediction with a prediction horizon of 30 minutes. Hypoglycemia was categorized into mild (glucose=54-70 mg/dL) and severe (glucose<54 mg/dL) levels. The validation data set of 427 patients of European-American ancestry in the United States was used to validate the models and examine their generalizations. The predictive performance of the models was evaluated according to the sensitivity, specificity, and area under the receiver operating characteristic curve (AUC). Results: For the difficult-to-predict mild hypoglycemia events, the LSTM model consistently achieved AUC values greater than 97% in the primary data set, with a less than 3% AUC reduction in the validation data set, indicating that the model was robust and generalizable across populations. AUC values above 93% were also achieved when the LSTM model was applied to both type 1 and type 2 diabetes in the validation data set, further strengthening the generalizability of the model. Under different satisfactory levels of sensitivity for mild and severe hypoglycemia prediction, the LSTM model achieved higher specificity than the SVM and RF models, thereby reducing false alarms. Conclusions: Our results demonstrate that the LSTM model is robust for hypoglycemia prediction and is generalizable across populations or diabetes subtypes. Given its additional advantage of false-alarm reduction, the LSTM model is a strong candidate to be widely implemented in future CGM devices for hypoglycemia prediction.
Background: Increasing evidence have depicted that DNA repair-related genes (DRGs) are associated with the prognosis of colorectal cancer (CRC) patients. Thus, the aim of this study was to evaluate the impact of DNA repair-related gene signature (DRGS) in predicting the prognosis of CRC patients. Method: In this study, we retrospectively analyzed the gene expression profiles from six CRC cohorts. A total of 1,768 CRC patients with complete prognostic information were divided into the training cohort (n = 566) and two validation cohorts (n = 624 and 578, respectively). The LASSO Cox model was applied to construct a prediction model. To further validate the clinical significance of the model, we also validated the model with Genomics of Drug Sensitivity in Cancer (GDSC) and an advanced clear cell renal cell carcinoma (ccRCC) immunotherapy data set. Results: We constructed a prognostic DRGS consisting of 11 different genes to stratify patients into high- and low-risk groups. Patients in the high-risk groups had significantly worse disease-free survival (DFS) than those in the low-risk groups in all cohorts [training cohort: hazard ratio (HR) = 2.40, p < 0.001, 95% confidence interval (CI) = 1.67-3.44; validation-1: HR = 2.20, p < 0.001, 95% CI = 1.38-3.49 and validation-2 cohort: HR = 2.12, p < 0.001, 95% CI = 1.40-3.21). By validating the model with GDSC, we could see that among the chemotherapeutic drugs such as oxaliplatin, 5-fluorouracil, and irinotecan, the IC50 of the cell line in the low-risk group was lower. By validating the model with the ccRCC immunotherapy data set, we can clearly see that the overall survival (OS) of the objective response rate (ORR) with complete response (CR) and partial response (PR) in the low-risk group was the best. Conclusions: DRGS is a favorable prediction model for patients with CRC, and our model can predict the response of cell lines to chemotherapeutic agents and potentially predict the response of patients to immunotherapy.
Background: Radiomics refers to the extraction of a large amount of image information from medical images, which can provide decision support for clinicians. In this study, we developed and validated a radiomics-based nomogram to predict the prognosis of colorectal cancer (CRC). Methods: A total of 381 patients with colorectal cancer (primary cohort: n = 242; validation cohort: n = 139) were enrolled and radiomic features were extracted from the vein phase of preoperative computed tomography (CT). The radiomics score was generated by using the least absolute shrinkage and selection operator algorithm (LASSO). A nomogram was constructed by combining the radiomics score with clinicopathological risk factors for predicting the prognosis of CRC patients. The performance of the nomogram was evaluated by the calibration curve, receiver operating characteristic (ROC) curve and C-index statistics. Functional analysis and correlation analysis were used to explore the underlying association between radiomic feature and the gene-expression patterns. Results: Five radiomic features were selected to calculate the radiomics score by using the LASSO regression model. The Kaplan-Meier analysis showed that radiomics score was significantly associated with disease-free survival (DFS) [primary cohort: hazard ratio (HR): 5.65, 95% CI: 2.26-14.13, P < 0.001; validation cohort: HR: 8.49, 95% CI: 2.05-35.17, P < 0.001]. Multivariable analysis confirmed the independent prognostic value of radiomics score (primary cohort: HR: 5.35, 95% CI: 2.14-13.39, P < 0.001; validation cohort: HR: 5.19, 95% CI: 1.22-22.00, P = 0.026). We incorporated radiomics signature with the TNM stage to build a nomogram, which performed better than TNM stage alone. The C-index of the nomogram achieved 0.74 (0.69-0.80) in the primary cohort and 0.82 (0.77-0.87) in the validation cohort. Functional analysis and correlation analysis found that the radiomic signatures were mainly associated with metabolism related pathways. Conclusions: The radiomics score derived from the preoperative CT image was an independent prognostic factor and could be a complement to the current staging strategies of colorectal cancer.
