Search Results (3)

Background: Pancreatic cancer is among the most lethal malignancies, with poor prognosis and limited survival despite treatment advances. Accurate survival modeling is critical for prognostication and clinical decision-making. This study had three primary aims: (1) to determine the best-fitting survival distribution among patients diagnosed and deceased from pancreatic cancer across stages and treatment types; (2) to construct and compare predictive risk classification models; and (3) to evaluate survival probabilities using parametric, semi-parametric, non-parametric, machine learning, and deep learning methods for Stage IV patients receiving both chemotherapy and radiation. Methods: Using data from the SEER database, parametric models (Generalized Extreme Value, Generalized Pareto, Log-Pearson 3), semi-parametric (Cox), and non-parametric (Kaplan–Meier) methods were compared with four machine learning models (gradient boosting, neural network, elastic net, and random forest). Survival probability heatmaps were constructed, and six classification models were developed for risk stratification. ROC curves, accuracy, and goodness-of-fit tests were used for model validation. Statistical tests included Kruskal–Wallis, pairwise Wilcoxon, and chi-square. Results: Generalized Extreme Value (GEV) was found to be the best-fitting distribution in most of the scenarios. Stage-specific survival differences were statistically significant. The highest predictive accuracy (AUC: 0.947; accuracy: 56.8%) was observed in patients receiving both chemotherapy and radiation. The gradient boosting model predicted the most optimistic survival, while random forest showed a sharp decline after 15 months. Conclusions: This study emphasizes the importance of selecting appropriate analytical models for survival prediction and risk classification. Adopting these innovations, with the help of advanced machine learning and deep learning models, can enhance patient outcomes and advance precision medicine initiatives. Full article

Heterogeneity has been one of the main barriers to understanding and treatment of autism spectrum disorder (ASD). Previous studies have identified several subtypes of ASD through unsupervised clustering analysis. However, most of them primarily depicted the pairwise similarity between individuals through second-order relationships, relying solely on patient data for their calculation. This leads to an underestimation of the complexity inherent in inter-individual relationships and the diagnostic information provided by typical development (TD). To address this, we utilized an elastic net model to construct an individual deviation-based hypergraph (ID-Hypergraph) based on functional MRI data. We then conducted a novel community detection clustering algorithm to the ID-Hypergraph, with the aim of identifying subtypes of ASD. By applying this framework to the Autism Brain Imaging Data Exchange repository data (discovery: 147/125, ASD/TD; replication: 134/132, ASD/TD), we identified four reproducible ASD subtypes with roughly similar patterns of ALFF between the discovery and replication datasets. Moreover, these subtypes significantly varied in communication domains. In addition, we achieved over 80% accuracy for the classification between these subtypes. Taken together, our study demonstrated the effectiveness of identifying subtypes of ASD through the ID-hypergraph, highlighting its potential in elucidating the heterogeneity of ASD and diagnosing ASD subtypes. Full article

The representation-based algorithm has raised a great interest in hyperspectral image (HSI) classification. $l_1$-minimization-based sparse representation (SR) attempts to select a few atoms and cannot fully reflect within-class information, while $l_2$-minimization-based collaborative representation (CR) tries to use all of the atoms leading to mixed-class information. Considering the above problems, we propose the pairwise elastic net representation-based classification (PENRC) method. PENRC combines the $l_1$-norm and $l_2$-norm penalties and introduces a new penalty term, including a similar matrix between dictionary atoms. This similar matrix enables the automatic grouping selection of highly correlated data to estimate more robust weight coefficients for better classification performance. To reduce computation cost and further improve classification accuracy, we use part of the atoms as a local adaptive dictionary rather than the entire training atoms. Furthermore, we consider the neighbor information of each pixel and propose a joint pairwise elastic net representation-based classification (J-PENRC) method. Experimental results on chosen hyperspectral data sets confirm that our proposed algorithms outperform the other state-of-the-art algorithms. Full article