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.
Temperatures that deviate from long-term local norms affect human health and are projected to become more frequent as the global climate changes. In this issue, Parks et al. report an association between anomalously warm temperatures and deaths from intentional and unintentional injuries, with increases in deaths from drownings, transport, assault and suicide. The cover art is an illustrated portrayal of the association between rising temperatures and increased injury mortality, and how big data has made such insights possible.
Large-scale multi-modal information on patients’ health is ever increasing, providing an opportunity to use big data for taking individualized medicine to a global scale.
Xiling Shen is the Hawkins Family Associate Professor of Biomedical Engineering and director of the Woo Center for Big Data and Precision Health at Duke University. He is a National Science Foundation early-career awardee, chair of the National Cancer Institute’s Patient-Derived Models of Cancer consortium and an Israeli faculty fellow.
Thinking the e-mail was a system error, she almost didn’t learn that her genetic test result had been revised. With the advent of commercial genomic screening, who is ethically responsible for communicating variant reclassification?
Healthcare is an imperfect practice, with disparities in care reflecting those in society. While algorithms may be misued to amplify biases, they may also be used to identify and correct disparities.
Although examples of algorithms designed to improve healthcare delivery abound, for many, clinical integration will not be achieved. The deployment cost of machine learning models is an underappreciated barrier to success. Experts propose three criteria that, assessed early, could help estimate the deployment cost.
Among the many promises of big data, one of the most exciting could be the potential to unlock the detection of cancer before advanced malignancy ensures, which means opening up a whole new understanding of the disease.
A statistical model based on an analysis of routinely collected data from 1980 to 2017 predicts 1,601 excess injury deaths per year in the contiguous USA if average temperatures rise by 1.5 °C.
A recent analysis highlighting the potential for algorithms to perpetuate existing racial biases in healthcare underscores the importance of thinking carefully about the labels used during algorithm development.
Sequencing of paternal sperm DNA allows the identification of male germline mosaicism and may assist with recurrence risk prediction of de novo genetic variants associated with autism in some families.
Health data are being generated and collected at an unprecedented scale, but whether big data will truly revolutionize healthcare is still a matter of much debate.
Analysis of a mass cytometry dataset for different human solid tumors coupled with murine reverse translational experiments suggests that targeting CD73 could enhance the efficacy of checkpoint inhibitor therapy in glioblastoma.
Results from an expansion cohort of the PROFILE 1001 trial describe the anti-tumor activity of crizotinib in people with non-small-cell lung cancer harboring a MET exon 14 alteration.
A prospective, multicenter, case–control clinical trial evaluates the potential of artificial intelligence for providing accurate bedside diagnosis of patients with brain tumors.
Expansion of pathogenic Candida species coupled with bacterial dysbiosis in the gut precedes Candida bloodstream infections in hematopoietic cell transplant recipients.
Bayesian spatio-temporal modeling of mortality from injuries in the contiguous USA shows increases in the number of deaths attributable to abnormal temperature fluctuations due to global heating.
Leveraging the availability of nationwide electronic health records from over 500,000 pregnancies in Israel, a machine-learning approach offers an alternative means of predicting gestational diabetes at high accuracy in the early stages of pregnancy.
A retrospective analysis of existing computed tomography scans shows the feasibility of an automated process for evaluating osteoporotic fracture risk that could be used as an initial screening tool when FRAX inputs are unavailable.
Cross-sectional analysis of data from the Adolescent Brain Cognitive Development Study shows that children from families with low income are at increased risk of cognitive impairment associated with high lead-exposure risk when compared with children from families with high income.
Integrated use of an animal model, a biobank for common diseases and a rare Mendelian disease leads to the discovery of a new syndrome and its pathological mechanism.
Comprising data from over 18,000 people, a new atlas of drug–metabolite associations for 87 commonly prescribed drugs and 150 metabolites assessed by proton nuclear magnetic resonance provides a web-based tool to aid research on drug efficacy, safety and repurposing.
Injection of AAV–shRNA below the pial surface of the spinal cord prevents onset or ameliorates progression in a mouse model of ALS, and achieves widespread delivery to the spinal cord and brain motor centers in adult pigs and non-human primates.
Single-nucleus RNA sequencing in a mouse model of Aβ accumulation and postmortem brain tissue from people with Alzheimer’s disease reveals substantial species-specific differences in transcriptional signatures, but both point to the contribution of glia and the importance of TREM2.
Genetic analysis of paternal sperm from families with a child affected by autism reveals that the recurrent risk for transmitting disease-associated de novo mutations to future offspring is near 0% for most couples but is substantially higher for a small fraction of couples.