Search

An improved DeepSurv model is proposed for predicting the prognosis of colorectal cancer patients at stage IV. Our model, called as PseudoDeepSurv, is optimized by a novel loss function, which is the combination of the average negative log partial likelihood and the mean-squared error derived from the pseudo-observations approach. The public BioStudies dataset including 999 patients was utilized for performance evaluation. Our PseudoDeepSurv model produced a C-index of 0.684 and 0.633 on the training and testing dataset, respectively. While for the original DeepSurv model, the corresponding values are 0.671 and 0.618, respectively. [ABSTRACT FROM AUTHOR]

Lung cancer recurrence seems to be the most leading cause of death as well as deterioration of lifespan. Proper assessment of the probability of recurrence in early-stage lung cancer is necessary to push up the treatment progress. We therefore employed machine-learning technologies to forecast post-operative recurrence risks using 174 lung cancer patient records. Six classification algorithms logistic regression, SVM, decision tree classification, random forest classification, XGBoost and lightGBM were used to predict the cancer recurrence. The patient samples were divided into training and test group with the split ratio of 3:1 for model generation and the accuracy were validated using k-fold cross-validation method. It is worth noting that the logistic regression model outperformed all the models in both training (Accuracy = 0.82) and test set (Accuracy = 0.79) on k-fold validation. Further, the optimal features (n = 7) identified using the RFE method is certainly helpful to improve the model in a high precision. The imperative risk factors associated with recurrence were identified using three feature selection methods. Importantly, our research showed that age is an important prognostic factor to be considered during the recurrence prediction. Indeed, severe concern on the identified risk factors combined with predictive models assists the physician to reduce the cancer recurrence rate in patients with lung cancer. [ABSTRACT FROM AUTHOR]

Background and objectives: Ulcerative colitis is a chronic recurrent intestinal inflammatory disease, and its recurrence is difficult to predict. In this review, we summarized the objective indicators that can be used to evaluate intestinal inflammation, the purpose is to better predict the clinical recurrence of UC, formulate individualized treatment plan during remission of UC, and improve the level of diagnosis and treatment of UC. Methods: Based on the search results in the PUBMED database, we explored the accuracy and value of these methods in predicting the clinical recurrence of UC from the following three aspects: endoscopic and histological scores, serum biomarkers and fecal biomarkers. Results: Colonoscopy with biopsy is the gold standard for assessing intestinal inflammation, but it is invasive, inconvenient and expensive. At present, there is no highly sensitive and specific endoscopic or histological score to predict the clinical recurrence of UC. Compared with serum biomarkers, fecal biomarkers have higher sensitivity and specificity because they are in direct contact with the intestine and are closer to the site of intestinal inflammation. Fecal calprotectin is currently the most studied and meaningful fecal biomarker. Lactoferrin and S100A12, as novel biomarkers, have no better performance than FC in predicting the recurrence of UC. Conclusions: FC is currently the most promising predictive marker, but it lacks an accurate cut-off value. Combining patient symptoms, incorporating multiple indicators to construct a UC recurrence prediction model, and formulating individualized treatment plans for high recurrence risk patients will be the focus of UC remission management. [ABSTRACT FROM AUTHOR]

To identify the relevant CpG sites as molecular markers, for the diagnosis and to distinguish the indolent and aggressive prostate tumors, we have determined the methylation status of 8 genes, including FLNC, EFS, ECRG4, RARB2, PITX2, GSTP1, PDLIM4, and KCNMA1 in 32 nonrecurrent, 32 recurrent primary prostate tumors, and 32 benign prostate tissues using EpiTYPER technology. Specific CpG site hypermethylation of RARB2 and GSTP1 CpG sites were useful for diagnosis of prostate cancer. Furthermore, CpG site hypermethylation of genes FLNC, EFS, ECRG4, PITX2, PDLIM4, and KCNMA1 were associated with prediction of biochemical, local, and systemic recurrence of prostate cancer. [ABSTRACT FROM AUTHOR]