The sudden deterioration of patients with novel coronavirus disease 2019 (COVID-19) into critical illness is of major concern. It is imperative to identify these patients early. We show that a deep learning-based survival model can predict the risk of COVID-19 patients developing critical illness based on clinical characteristics at admission. We develop this model using a cohort of 1590 patients from 575 medical centers, with internal validation performance of concordance index 0.894 We further validate the model on three separate cohorts from Wuhan, Hubei and Guangdong provinces consisting of 1393 patients with concordance indexes of 0.890, 0.852 and 0.967 respectively. This model is used to create an online calculation tool designed for patient triage at admission to identify patients at risk of severe illness, ensuring that patients at greatest risk of severe illness receive appropriate care as early as possible and allow for effective allocation of health resources.
Microsatellite instability (MSI) has been approved as a pan-cancer biomarker for immune checkpoint blockade (ICB) therapy. However, current MSI identification methods are not available for all patients. We proposed an ensemble multiple instance deep learning model to predict microsatellite status based on histopathology images, and interpreted the pathomics-based model with multi-omics correlation. Methods: Two cohorts of patients were collected, including 429 from The Cancer Genome Atlas (TCGA-COAD) and 785 from an Asian colorectal cancer (CRC) cohort (Asian-CRC). We established the pathomics model, named Ensembled Patch Likelihood Aggregation (EPLA), based on two consecutive stages: patch-level prediction and WSI-level prediction. The initial model was developed and validated in TCGA-COAD, and then generalized in Asian-CRC through transfer learning. The pathological signatures extracted from the model were analyzed with genomic and transcriptomic profiles for model interpretation. Results: The EPLA model achieved an area-under-the-curve (AUC) of 0.8848 (95% CI: 0.8185-0.9512) in the TCGA-COAD test set and an AUC of 0.8504 (95% CI: 0.7591-0.9323) in the external validation set Asian-CRC after transfer learning. Notably, EPLA captured the relationship between pathological phenotype of poor differentiation and MSI ( P < 0.001). Furthermore, the five pathological imaging signatures identified from the EPLA model were associated with mutation burden and DNA damage repair related genotype in the genomic profiles, and antitumor immunity activated pathway in the transcriptomic profiles. Conclusions: Our pathomics-based deep learning model can effectively predict MSI from histopathology images and is transferable to a new patient cohort. The interpretability of our model by association with pathological, genomic and transcriptomic phenotypes lays the foundation for prospective clinical trials of the application of this artificial intelligence (AI) platform in ICB therapy.
Nanomedicines achieve tumor-targeted delivery mainly through enhanced permeability and retention (EPR) effect following intravenous (IV) administration. Unfortunately, the EPR effect is severely compromised in pancreatic cancer due to hypovascularity and dense desmoplastic stroma. Intraperitoneal (IP) administration may be an effective EPR-independent local delivery approach to target peritoneal tumors. Besides improved delivery, effective combination delivery strategies are needed to improve pancreatic cancer therapy by targeting both cancer cells and cellular interactions within the tumor stroma. Here, we described simple cholesterol-modified polymeric CXCR4 antagonist (PCX) nanoparticles (to block cancer-stroma interactions) for codelivery of anti-miR-210 (to inactivate stroma-producing pancreatic stellate cells (PSCs)) and siKRAS G12D (to kill pancreatic cancer cells). IP administration delivered the nanoparticles to an orthotopic syngeneic pancreatic tumors as a result of preferential localization to the tumors and metastases with disrupted mesothelium and effective tumor penetration. The local IP delivery resulted in nearly 15-fold higher tumor accumulation than delivery by IV injection. Through antagonism of CXCR4 and downregulation of miR-210/KRAS G12D , the triple-action nanoparticles favorably modulated desmoplastic tumor microenvironment via inactivating PSCs and promoting the infiltration of cytotoxic T cells. The combined therapy displayed improved therapeutic effect when compared with individual therapies as documented by the delayed tumor growth, depletion of stroma, reduction of immunosuppression, inhibition of metastasis, and prolonged survival. Overall, we present data that a local IP delivery of a miRNA/siRNA combination holds the potential to improve pancreatic cancer therapy.
Purpose Microvascular invasion (MVI) is a valuable predictor of survival in hepatocellular carcinoma (HCC) patients. This study developed predictive models using eXtreme Gradient Boosting (XGBoost) and deep learning based on CT images to predict MVI preoperatively. Methods In total, 405 patients were included. A total of 7302 radiomic features and 17 radiological features were extracted by a radiomics feature extraction package and radiologists, respectively. We developed a XGBoost model based on radiomics features, radiological features and clinical variables and a three-dimensional convolutional neural network (3D-CNN) to predict MVI status. Next, we compared the efficacy of the two models. Results Of the 405 patients, 220 (54.3%) were MVI positive, and 185 (45.7%) were MVI negative. The areas under the receiver operating characteristic curves (AUROCs) of the Radiomics-Radiological-Clinical (RRC) Model and 3D-CNN Model in the training set were 0.952 (95% confidence interval (CI) 0.923–0.973) and 0.980 (95% CI 0.959–0.993), respectively (p = 0.14). The AUROCs of the RRC Model and 3D-CNN Model in the validation set were 0.887 (95% CI 0.797–0.947) and 0.906 (95% CI 0.821–0.960), respectively (p = 0.83). Based on the MVI status predicted by the RRC and 3D-CNN Models, the mean recurrence-free survival (RFS) was significantly better in the predicted MVI-negative group than that in the predicted MVI-positive group (RRC Model: 69.95 vs. 24.80 months, p < 0.001; 3D-CNN Model: 64.06 vs. 31.05 months, p = 0.027). Conclusion The RRC Model and 3D-CNN models showed considerable efficacy in identifying MVI preoperatively. These machine learning models may facilitate decision-making in HCC treatment but requires further validation.
We describe the expression of gpIRK1, an inwardly rectifying K+ channel obtained from guinea pig cardiac cDNA. gpIRK1 is a homologue of the mouse IRK1 channel identified in macrophage cells. Expression of gpIRK1 in Xenopus oocytes produces inwardly rectifying K+ current, similar to the cardiac inward rectifier current IK1. This current is blocked by external Ba2+ and Cs+. Plasmids containing the gpIRK1 coding region under the transcriptional control of constitutive (PGK) or inducible (GAL) promoters were constructed for expression in Saccharomyces cerevisiae. Several observations suggest that gpIRK1 forms functional ion channels when expressed in yeast. gpIRK1 complements a trk1 delta trk2 delta strain, which is defective in potassium uptake. Expression of gpIRK1 in this mutant restores growth on low potassium media. Growth dependent on gpIRK1 is inhibited by external Cs+. The strain expressing gpIRK1 provides a versatile genetic system for studying the assembly and composition of inwardly rectifying K+ channels.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.