Search

BACKGROUND/OBJECTIVES: There is currently no widely accepted approach to identify patients at increased risk for sporadic pancreatic cancer (PC). We aimed to compare the performance of two machine-learning models with a regression-based model in predicting pancreatic ductal adenocarcinoma (PDAC), the most common form of PC. METHODS: This retrospective cohort study consisted of patients 50-84 years of age enrolled in either Kaiser Permanente Southern California (KPSC, model training, internal validation) or the Veterans Affairs (VA, external testing) between 2008 and 2017. The performance of random survival forests (RSF) and eXtreme gradient boosting (XGB) models were compared to that of COX proportional hazards regression (COX). Heterogeneity of the three models were assessed. RESULTS: The KPSC and the VA cohorts consisted of 1.8 and 2.7 million patients with 1792 and 4582 incident PDAC cases within 18 months, respectively. Predictors selected into all three models included age, abdominal pain, weight change, and glycated hemoglobin (A1c). Additionally, RSF selected change in alanine transaminase (ALT), whereas the XGB and COX selected the rate of change in ALT. The COX model appeared to have lower AUC (KPSC: 0.737, 95% CI 0.710-0.764; VA: 0.706, 0.699-0.714), compared to those of RSF (KPSC: 0.767, 0.744-0.791; VA: 0.731, 0.724-0.739) and XGB (KPSC: 0.779, 0.755-0.802; VA: 0.742, 0.735-0.750). Among patients with top 5% predicted risk from all three models (N = 29,663), 117 developed PDAC, of which RSF, XGB and COX captured 84 (9 unique), 87 (4 unique), 87 (19 unique) cases, respectively. CONCLUSIONS: The three models complement each other, but each has unique contributions.

Prior research extensively investigates the delayed influence of El Niño‐Southern Oscillation (ENSO) events on subsequent summer climates, with persistent sea surface temperature anomalies (SSTAs) in remote tropical oceans serving as crucial pathways. This study unveils a previously overlooked midlatitude pathway. During the developing winter, El Niño events induce basin‐scale cold SSTAs in the central North Pacific, which can persist into the following summer. These anomalies significantly influence early‐summer atmospheric circulation by enhancing atmospheric baroclinicity and transient eddy activities. Primarily driven by transient eddy vorticity forcing, an equivalent barotropic geopotential low anomaly emerges over the North Pacific. Enhanced by the southwesterly winds of the atmospheric low, tropical moisture is transported farther northeastward in the early summer, resulting in increased rainfall in the Pacific Northwest region. By elucidating this meridional pathway, our study advances the understanding of ENSO's delayed impacts and associated dynamical processes, in which the midlatitude oceanic feedbacks are emphasized. Plain Language Summary: The El Niño‐Southern Oscillation (ENSO) events are considered as a primary driver of climate anomalies. Even during their decaying phase, its impact on the Northern Hemisphere summer climate remains notable. This study delves into the intricate mechanisms underlying the delayed impacts of ENSO events on subsequent summer climates. While prior research has extensively explored the zonal pathways involving tropical Indian and Atlantic oceans, this study illuminates a previously overlooked meridional pathway. It reveals that El Niño events trigger significant cold sea surface temperature anomalies (SSTAs) in the North Pacific during their mature phase in winter, which persist into the following summer. These SSTAs wield substantial influence over early‐summer atmospheric circulation, fostering atmospheric baroclinicity and transient eddy activities. Consequently, an anomalous low‐pressure system emerges over the North Pacific in early summer, enhancing southwesterly winds and transporting tropical moisture farther northeastward. This moisture influx results in increased rainfall in the Pacific Northwest region. By elucidating this meridional pathway, the study advances our comprehension of ENSO's delayed impacts, highlighting the crucial role of midlatitude oceanic feedbacks. In essence, it demonstrates how ENSO events can influence North American climate anomalies during subsequent early summer, shedding light on a previously unrecognized pathway of ENSO's effect. Key Points: Cold central North Pacific sea surface temperature anomalies (SSTAs), initiated by El Niño events, can endure into the subsequent summerBy transient eddy forcing, these cold SSTAs induce a whole‐layer geopotential low anomaly over North Pacific in post‐El Niño early summerThus, northeastward moisture transport strengthens, boosting increased early‐summer rainfall in Pacific Northwest after El Niño events [ABSTRACT FROM AUTHOR]

Xinjiang suffers compound hot and drought events under global warming. However, less attention has been paid to physical mechanisms of the variability of compound hot and drought events in this region. This article investigates the interannual variation of summer (June–August) compound hot and drought events in Xinjiang and its relationship with the sea surface temperature (SST) over the North Atlantic. The results show that its first empirical orthogonal function (EOF) mode features a spatially homogenous pattern. This mode is closely connected with the simultaneous meridional negative–positive–negative SST anomalies over the North Atlantic. The summer North Atlantic tripole SST anomalies can trigger a remarkable wave train extending from the North Atlantic to Eurasia, consequently inducing an anomalous high pressure system over the Iran–Pamir Plateau, which is conducive to the increase in air temperature from the surface to the upper troposphere over Xinjiang. The warmer troposphere further strengthens the western Asian subtropical meridional temperature gradient and thereby enhances the westerly wind to the north flank of the West Asian subtropical westerly jet (WASWJ). As a result, the WASWJ is displaced northward, which intensifies the sinking motion and prevents the water vapor transport to Xinjiang, leading to a decrease in precipitation in the target region. The higher temperature and less precipitation contribute to the occurrence of compound hot and drought events over Xinjiang. Numerical simulations based on the Community Atmosphere Model, version 4 (CAM4), further confirm the relationship between the North Atlantic tripole SST anomalies and compound hot and drought events in Xinjiang during summer on the interannual time scale. Significance Statement: Xinjiang, located in northwest China, suffers from frequent and intense compound hot and drought events in recent decades. It is thus urgent to understand the physical mechanisms associated with its occurrence in order for disaster prevention and mitigation. In this study, we reveal that the leading mode of summer compound hot and drought events over Xinjiang, featuring a spatially homogenous pattern, is closely correlated with the simultaneous meridional negative–positive–negative SST anomalies over the North Atlantic. The North Atlantic tripole SST anomalies can lead to an anomalous high pressure system over the Iran–Pamir Plateau and a northward shift of the West Asian subtropical westerly jet through exciting a wave train propagating from the North Atlantic to Eurasia, which consequently contributes to the occurrence of compound hot and drought events over Xinjiang. [ABSTRACT FROM AUTHOR]