arXiv subjects

Chris Varghese

Publications and source records attributed to Chris Varghese.

4 recordsLinked to original sources

arXiv2026

Automated Prediction of Postoperative Pancreatic Fistula Using Preoperative Computed Tomography

Postoperative pancreatic fistula (POPF) is a serious complication after pancreatic resection, increasing morbidity, hospital stay, and healthcare costs. We present an automatic, end-to-end deep learning pipeline-from pancreatic segmentation to classification-for preoperative POPF risk estimation and stratification using preoperative CT scans. A data set with auto-segmented pancreas volumes and surgical outcomes was used to evaluate multiple architectures, including a custom lightweight 3D CNN baseline (CNN3D), R(2+1)D ResNet-18, and ResNet-MC3-18 models. Evaluation across multiple 3D architectures demonstrated promising predictive performance. This approach offers a clinically valuable tool and a methodological benchmark for pancreas-specific CT classification, supporting improved preoperative decision-making in pancreatic surgery.

cs.CV↗

arXiv2026

Digitally enriching a screening population for pancreatic cancer using routine blood-based measures and clinical histories

Earlier detection of pancreatic cancer is key to enabling wider access to curative treatment and reducing cancer deaths; however, screening is presently not viable. Latent indicators of pathology are evident in an individual's disease and blood test trajectories and may predict the development of pancreatic cancer. Longitudinal sequences of coded diagnoses and blood test values accrued by patients throughout their clinical interactions were used to train a custom Transformer-based neural network with a multi-head attention mechanism to predict risk of pancreatic cancer with a multi-year lead time and risk-stratify populations for targeted screening. The cohort comprised 6,017 adults with pancreatic cancer and 177,081 controls (overall median age 75, 45% female) with median 12 years (interquartile range 6.9-16.2) of medical history prior to pancreatic cancer diagnosis. External validation via leave-one-site-out, out-of-sample testing predicting pancreatic cancer 1-, 2-, and 3-years prior to diagnosis demonstrated mean area under the receiver operating characteristic of 0.837 (95% confidence interval 0.827-0.848), 0.797 (95% confidence interval 0.782-0.813), and 0.760 (95% confidence interval 0.745-0.776), respectively. Estimated pancreatic cancer risks were well-calibrated (calibration plot slope 1.08, intercept of -0.077; Brier score 0.025), and a Bayesian population pancreatic cancer prevalence update allows estimated cancer risk outputs to be transportable across settings. At testing, a screening threshold of >3.3% risk of pancreatic cancer in 1-year offered a diagnostic odds ratio of 18.2. Our work therefore lays the foundation for a first population-level digital enrichment tool to widen access to curative-intent management of pancreatic cancer.

cs.LG↗

arXiv2014

Spatial networks evolving to reduce length

Motivated by results of Henry, Pralat and Zhang (PNAS 108.21 (2011): 8605-8610), we propose a general scheme for evolving spatial networks in order to reduce their total edge lengths. We study the properties of the equilbria of two networks from this class, which interpolate between three well studied objects: the Erdős-Rényi random graph, the random geometric graph, and the minimum spanning tree. The first of our two evolutions can be used as a model for a social network where individuals have fixed opinions about a number of issues and adjust their ties to be connected to people with similar views. The second evolution which preserves the connectivity of the network has potential applications in the design of transportation networks and other distribution systems.

physics.soc-ph↗

arXiv2013

Phase Transitions in the Quadratic Contact Process on Complex Networks

The quadratic contact process (QCP) is a natural extension of the well studied linear contact process where infected (1) individuals infect susceptible (0) neighbors at rate $λ$ and infected individuals recover ($1 \longrightarrow 0$) at rate 1. In the QCP, a combination of two 1's is required to effect a $0 \longrightarrow 1$ change. We extend the study of the QCP, which so far has been limited to lattices, to complex networks. \comment{as a model for the change in a population through sexual reproduction and death.} We define two versions of the QCP -- vertex centered (VQCP) and edge centered (EQCP) with birth events $1-0-1 \longrightarrow 1-1-1$ and $1-1-0 \longrightarrow 1-1-1$ respectively, where `$-$' represents an edge. We investigate the effects of network topology by considering the QCP on random regular, Erdős-Rényi and power law random graphs. We perform mean field calculations as well as simulations to find the steady state fraction of occupied vertices as a function of the birth rate. We find that on the random regular and Erdős-Rényi graphs, there is a discontinuous phase transition with a region of bistability, whereas on the heavy tailed power law graph, the transition is continuous. The critical birth rate is found to be positive in the former but zero in the latter.

physics.soc-ph↗