Transcriptomic profiling of adjuvant colorectal cancer identifies three key prognostic biological processes and a disease specific role for granzyme B

Background Colorectal cancer (CRC) is a leading cause of cancer-related deaths, with a 5% 5-year survival rate for metastatic disease, yet with limited therapeutic advancements due to insufficient understanding of and inability to accurately capture high-risk CRC patients who are most likely to recur. We aimed to improve high-risk classification by identifying biological pathways associated with outcome in adjuvant stage II/III CRC. Methods and findings We included 1062 patients with stage III or high-risk stage II colon carcinoma from the prospective three-arm randomized phase 3 AVANT trial, and performed expression profiling to identify a prognostic signature. Data from validation cohort GSE39582, The Cancer Genome Atlas, and cell lines were used to further validate the prognostic biology. Our retrospective analysis of the adjuvant AVANT trial uncovered a prognostic signature capturing three biological functions—stromal, proliferative and immune—that outperformed the Consensus Molecular Subtypes (CMS) and recurrence prediction signatures like Oncotype Dx in an independent cohort. Importantly, within the immune component, high granzyme B (GZMB) expression had a significant prognostic impact while other individual T-effector genes were less or not prognostic. In addition, we found GZMB to be endogenously expressed in CMS2 tumor cells and to be prognostic in a T cell independent fashion. A limitation of our study is that these results, although robust and derived from a large dataset, still need to be clinically validated in a prospective study. Conclusions This work furthers our understanding of the underlying biology that propagates stage II/III CRC disease progression and provides scientific rationale for future high-risk stratification and targeted treatment evaluation in biomarker defined subpopulations of resectable high-risk CRC. Our results also shed light on an alternative GZMB source with context-specific implications on the disease’s unique biology.

Privacy-preserving breast cancer recurrence prediction based on homomorphic encryption and secure two party computation

Protecting patients’ privacy is one of the most important tasks when developing medical artificial intelligence models since medical data is the most sensitive personal data. To overcome this privacy protection issue, diverse privacy-preserving methods have been proposed. We proposed a novel method for privacy-preserving Gated Recurrent Unit (GRU) inference model using privacy enhancing technologies including homomorphic encryption and secure two party computation. The proposed privacy-preserving GRU inference model validated on breast cancer recurrence prediction with 13,117 patients’ medical data. Our method gives reliable prediction result (0.893 accuracy) compared to the normal GRU model (0.895 accuracy). Unlike other previous works, the experiment on real breast cancer data yields almost identical results for privacy-preserving and conventional cases. We also implement our algorithm to shows the realistic end-to-end encrypted breast cancer recurrence prediction.

Predicting Central Serous Chorioretinopathy Recurrence Using Machine Learning

Purpose: To predict central serous chorioretinopathy (CSC) recurrence 3 and 6 months after laser treatment by using machine learning.Methods: Clinical and imaging features of 461 patients (480 eyes) with CSC were collected at Zhongshan Ophthalmic Center (ZOC) and Xiamen Eye Center (XEC). The ZOC data (416 eyes of 401 patients) were used as the training dataset and the internal test dataset, while the XEC data (64 eyes of 60 patients) were used as the external test dataset. Six different machine learning algorithms and an ensemble model were trained to predict recurrence in patients with CSC. After completing the initial detailed investigation, we designed a simplified model using only clinical data and OCT features.Results: The ensemble model exhibited the best performance among the six algorithms, with accuracies of 0.941 (internal test dataset) and 0.970 (external test dataset) at 3 months and 0.903 (internal test dataset) and 1.000 (external test dataset) at 6 months. The simplified model showed a comparable level of predictive power.Conclusion: Machine learning achieves high accuracies in predicting the recurrence of CSC patients. The application of an intelligent recurrence prediction model for patients with CSC can potentially facilitate recurrence factor identification and precise individualized interventions.

5-year Recurrence Prediction After Hepatocellular Carcinoma Resection Using Deep Learning and Cox Regression Models: A Large Prospective Study

BackgroundRisk of hepatocellular carcinoma (HCC) recurrence after surgical resection is unknown. Therefore, the aim of this study was 5-year recurrence prediction after HCC resection using deep learning and Cox regression models.MethodsThis study recruited 520 HCC patients who had undergone surgical resection at three medical centers in southern Taiwan between April, 2011, and December, 2015. Two popular deep learning algorithms: a deep neural network (DNN) model and a recurrent neural network (RNN) model and a Cox proportional hazard (CPH) regression model were designed to solve both classification problems and regression problems in predicting HCC recurrence. A feature importance analysis was also performed to identify confounding factors in the prediction of HCC recurrence in patients who had undergone resection.ResultsAll performance indices for the DNN model were significantly higher than those for the RNN model and the traditional CPH model (p<0.001). The most important confounding factor in 5-year recurrence after HCC resection was surgeon volume followed by, in order of importance, hospital volume, preoperative Beck Depression Scale score, preoperative Beck Anxiety Scale score, co-residence with family, tumor stage, and tumor size. ConclusionsThe DNN model is useful for early baseline prediction of 5-year recurrence after HCC resection. Its prediction accuracy can be improved by further training with temporal data collected from treated patients. The feature importance analysis performed in this study to investigate model interpretability provided important insights into the potential use of deep learning models for predicting recurrence after HCC resection and for identifying predictors of recurrence.

Machine Learning for Recurrence Prediction of Gynecologic Cancers Using Lynch Syndrome-Related Screening Markers

To support the implementation of genome-based precision medicine, we developed machine learning models that predict the recurrence of patients with gynecologic cancer in using immune checkpoint inhibitors (ICI) based on clinical and pathologic characteristics, including Lynch syndrome-related screening markers such as immunohistochemistry (IHC) and microsatellite instability (MSI) tests. To accomplish our goal, we reviewed the patient demographics, clinical data, and pathological results from their medical records. Then we identified seven potential characteristics (four MMR IHC [MLH1, MSH2, MSH6, and PMS2], MSI, Age 60, and tumor size). Following that, predictive models were built based on these variables using six machine learning algorithms: logistic regression (LR), support vector machine (SVM), naive Bayes (NB), random forest (RF), gradient boosting (GB), and extreme gradient boosting (EGB) (XGBoost). The experimental results showed that the RF-based model performed best at predicting gynecologic cancer recurrence, with AUCs of 0.818 and 0.826 for the 5-fold cross-validation (CV) and 5-fold CV with 10 repetitions, respectively. This study provides novel and baseline results about predicting the recurrence of gynecologic cancer in patients using ICI by using machine learning methods based on Lynch syndrome-related screening markers.

Derivation and Clinical Validation of a Redox-Driven Prognostic Signature for Colorectal Cancer

Colorectal cancer (CRC), a seriously threat that endangers public health, has a striking tendency to relapse and metastasize. Redox-related signaling pathways have recently been extensively studied in cancers. However, the study and potential role of redox in CRC remain unelucidated. We developed and validated a risk model for prognosis and recurrence prediction in CRC patients via identifying gene signatures driven by redox-related signaling pathways. The redox-driven prognostic signature (RDPS) was demonstrated to be an independent risk factor for patient survival (including OS and RFS) in four public cohorts and one clinical in-house cohort. Additionally, there was an intimate association between the risk score and tumor immune infiltration, with higher risk score accompanied with less immune cell infiltration. In this study, we used redox-related factors as an entry point, which may provide a broader perspective for prognosis prediction in CRC and have the potential to provide more promising evidence for immunotherapy.