Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain
the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in
Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles
and JavaScript.
Hu et al. track 299 kidney cysts from 37 ADPKD subjects on 203 MRI scans over 8+ years of follow-up to explore their natural history. Cyst diameter predicts kidney function decline and simple cysts follow logistic growth, periodically transitioning to shrinking, hemorrhaging, or disappearing with transitions.
Schmidt et al. develop sentence-level datasets for Crohn’s phenotypes and compare rule-based NLP with GPT-4 to extract disease behavior and age at diagnosis from EHR notes. Both methods achieve high recall on notes; GPT-4 perfectly identifies age at diagnosis and simple ensembles improve precision and enable chart-review prioritization.
Vicente Puig et al. develop a volumetric electrocardiographic imaging approach that estimates cardiac sources to reconstruct three-dimensional myocardial activation. They show improved localization of arrhythmia origins, including septal and intramural sites, with higher accuracy in simulations and concordance with invasive maps in clinical data.
Scholze et al. investigate individual UV exposure and 25(OH)D3 metabolism in a one-year observational study. While UV exposure triggers vitamin D3 production, the body strongly modulates the resulting 25(OH)D3 concentrations through 25(OH)D3 synthesis efficiency and degradation, with the seasonal pattern mirroring local temperature fluctuations.
Ngwang et al. perform an ecological cross-sectional study to assess how the protracted Anglophone Crisis influences antenatal care utilisation across the nation of Cameroon. They find that the intensity of the conflict negatively impacts healthcare utilisation, especially among non-Christian and young mothers.
Horvat-Menih et al. use hyperpolarised 13C-pyruvate MRI (HP 13C-MRI) to assess 13C-lactate generation in a patient with a fumarate hydratase-deficient renal cell carcinoma (FHd-RCC), and correlate imaging findings with genetic and metabolic analysis on post-operative tissue samples. HP 13C-MRI reveals two metabolically distinct tumour regions.
Zhu, Zhao, Wang et al. describe G-NECNet, a deep learning model for detecting gastric neuroendocrine carcinoma (G-NEC) from H&E-stained biopsy whole-slide images without the need for additional immunohistochemistry. G-NECNet achieves high diagnostic accuracy across multiple datasets.
Martinot et al. examine the relationship between the percentage of sleep time spent with increased respiratory effort (REMOV) and OSA symptoms. Findings reveal that REMOV is significantly associated with sleepiness, fatigue, and depression, particularly among patients with mild OSA.
Iktilat et al. examine associations between gut microbiota, exposure to violence during adolescence, and psychological distress in a midlife cohort. They identify distinct microbial patterns linked to violence and distress and show that combined microbiome and exposure data modestly predict distress levels.
Li et al. apply machine learning to longitudinal clinical notes to improve prediction of Alzheimer’s disease. They find that Alzheimer’s-related keywords occur more often in patients who later develop the disease, rising sharply before diagnosis and helping identify high-risk individuals.
Maldonado, Lopez-Hernandez, et al. use a matched case-control study to compare E. coli-infected patients with or without sepsis. Their analysis shows that the ST69 clone is associated with risk of sepsis development, and certain genetic factors such as adhesion genes papC and fdeC were associated with a protective effect.
Liu, Chen, Yang et al. investigate the effect of GLP-1 receptor activation on ovarian cancer risk across different subtypes. They show that it specifically lowers the risk of one subtype, endometrioid ovarian cancer, mediated in part by specific metabolic factors.
Hou, Li, Moi et al., find that long-term endocrine therapy does not alter overall gut microbiota composition in breast cancer patients, but recurrence is linked to reduced microbial diversity and specific bacterial signatures. These gut microbiota patterns predict poorer outcomes independent of established genetic risk scores, suggesting added value for recurrence risk stratification
Assaad, Hadi and Levine et al. develop a whole-genome sequencing classifier to improve the detection of homologous recombination deficiency (HRD) across a pan cancer cohort. The classifier detects HRD beyond BRCA1/2 mutations, reveals HRD-related genomic events, and correlates with treatment response in a subset of patients.
Zeng et al. investigate the role of adult lifestyle on the associations between childhood body size and subsequent risks of mortality and non-communicable diseases. Their findings suggest that adherence to a healthier lifestyle in adulthood may attenuate these risks, especially among those with larger childhood body size.
Sheng et al. characterize features associated with neuroinflammation-related genes and cognitive resilience using a neuroimaging biomarker. The pathological effect of the MST1 gene on cognitive resilience is mediated by the mismatch between metabolic fluctuation coupling in the limbic orbital frontal cortex and amyloid protein deposition.
Heritz et al. use an orthogonal approach to identify a selective inhibitor for HIF2α that disrupts its interaction with the molecular chaperone Hsp70. This inhibitor utilizes an alternative mechanism of action to previous HIF2α antagonists, providing a promising approach in addressing kidney cancer drug resistance.
Vincens et al. investigate how traffic noise and masking pink noise impact physiological sleep, cognition, and metabolic blood biomarkers. Traffic noise acutely fragments sleep even while total sleep time is preserved, and is followed by metabolic disturbances, the effects of which are attenuated by continuous pink noise.
Haspels et al. developed a high-throughput assay facilitated by automatic spheroid segmentation using deep learning. Measured differences in treatment response between cisplatin-sensitive and resistant tumors faithfully correspond with expected in vivo responses and the assay is able to discriminate between olaparib-sensitive and resistant tumors.
Vishnyakova et al. develop a metabolomic aging biomarker based on optimal metabolite levels, or “sweet spots.” They show that this biomarker predicts mortality and the onset of age-related diseases.
