The local environment and germline genetic variation predict cancer risk in the UK Biobank prospective cohort.

BACKGROUND: There is a growing body of evidence on the effect of the local environment exposure on cancer susceptibility. Nonetheless, several of the associations remain controversial. Moreover, our understanding of the possible interaction between the local environment and the genetic variability is still very limited. OBJECTIVE: The aim of this study was to clarify the role of the local environment and its possible interplay with genetics on common cancers development. METHODS: Using the UK Biobank (UKBB) prospective cohort, we selected 12 local environment exposures: nitrogen oxides, nitrogen dioxides, particulate matter (10 and 2.5 µm), noise pollution, urban traffic, living distance from the coast, percentage of greenspace, natural environment, water, and domestic garden within 1000 m from the residential coordinates of each participant. All these exposures were tested for association with 17 different types of cancer for a total of 53,270 cases and 302,645 controls. Additionally, a polygenic score (PGS) was computed for each cancer, to test possible gene-environment interactions. Finally, mediation analyses were carried out. RESULTS: Thirty-six statistically significant associations considering multiple testing (p < 2.19 × 10-4) were observed. Among the novel associations we observed that individuals living farther from the coast had a higher risk of developing prostate cancer (OR = 1.13, CI95% = 1.06-1.20, P = 1.98 × 10-4). This association was partially mediated by physical activity (indirect effect (IE) = -8.48 × 10-7) and the time spent outdoor (IE = 9.07 × 10-6). All PGSs showed statistically significant associations. Finally, genome-environment interaction analysis showed that local environment and genetic variability affect cancer risk independently. DISCUSSION: Living close to the coast and air pollution were associated with a decreased risk of prostate cancer and skin melanoma, respectively. These findings from the UKBB support the role of the local environment on cancer development, which is independent from genetics and may be mediated by several lifestyle factors.

Towards Transparent Healthcare: Advancing Local Explanation Methods in Explainable Artificial Intelligence.

This paper focuses on the use of local Explainable Artificial Intelligence (XAI) methods, particularly the Local Rule-Based Explanations (LORE) technique, within healthcare and medical settings. It emphasizes the critical role of interpretability and transparency in AI systems for diagnosing diseases, predicting patient outcomes, and creating personalized treatment plans. While acknowledging the complexities and inherent trade-offs between interpretability and model performance, our work underscores the significance of local XAI methods in enhancing decision-making processes in healthcare. By providing granular, case-specific insights, local XAI methods like LORE enhance physicians' and patients' understanding of machine learning models and their outcome. Our paper reviews significant contributions to local XAI in healthcare, highlighting its potential to improve clinical decision making, ensure fairness, and comply with regulatory standards.

Analysis of exposome and genetic variability suggests stress as a major contributor for development of pancreatic ductal adenocarcinoma.

BACKGROUND: The current knowledge on pancreatic ductal adenocarcinoma (PDAC) risk factors is limited and no study has comprehensively tested the exposome in combination with the genetic variability in relation to the disease susceptibility. AIM: The aim of this study was to analyze the exposome and its interaction with known genetic susceptibility loci, in relation to PDAC risk. METHODS: A case-control study nested in UK Biobank cohort was conducted on 816 PDAC cases and 302,645 controls. A total of 347 exposure variables, and a polygenic risk score (PRS) were analyzed through logistic regression. Gene-environment interaction analyses were conducted. RESULTS: A total of 52 associations under the Bonferroni corrected threshold of p < 1.46 × 10-4 were observed. Known risk factors such as smoking, pancreatitis, diabetes, PRS, heavy alcohol drinking and overweight were replicated in this study. As for novel associations, a clear indication for length and intensity of mobile phone use and the stress-related factors and stressful events with increase of PDAC risk was observed. Although the PRS was associated with PDAC risk (P = 2.09 × 10-9), statistically significant gene-exposome interactions were not identified. CONCLUSION: In conclusion, our results suggest that a stressful lifestyle and sedentary behaviors may play a major role in PDAC susceptibility independently from the genetic background.