Search

The early prediction of deterioration could have an important role in supporting healthcare professionals, as an estimated 11% of deaths in hospital follow a failure to promptly recognize and treat deteriorating patients 1 . To achieve this goal requires predictions of patient risk that are continuously updated and accurate, and delivered at an individual level with sufficient context and enough time to act. Here we develop a deep learning approach for the continuous risk prediction of future deterioration in patients, building on recent work that models adverse events from electronic health records 2-17 and using acute kidney injury-a common and potentially life-threatening condition 18 -as an exemplar. Our model was developed on a large, longitudinal dataset of electronic health records that cover diverse clinical environments, comprising 703,782 adult patients across 172 inpatient and 1,062 outpatient sites. Our model predicts 55.8% of all inpatient episodes of acute kidney injury, and 90.2% of all acute kidney injuries that required subsequent administration of dialysis, with a lead time of up to 48 h and a ratio of 2 false alerts for every true alert. In addition to predicting future acute kidney injury, our model provides confidence assessments and a list of the clinical features that are most salient to each prediction, alongside predicted future trajectories for clinically relevant blood tests 9 . Although the recognition and prompt treatment of acute kidney injury is known to be challenging, our approach may offer opportunities for identifying patients at risk within a time window that enables early treatment.

One of the goals of forensic science is to identify individuals and their lifestyle by analyzing the trace signatures left behind in built environments. Here, microbiome and metabolomic methods were used to see how its occupants used an office and to also gain insights into the lifestyle characteristics such as diet, medications, and personal care products of the occupants. 3D molecular cartography, a molecular visualization technology, was used in combination with mass spectrometry and microbial inventories to highlight human-environmental interactions. Molecular signatures were correlated with the individuals as well as their interactions with this indoor environment. There are person-specific chemical and microbial signatures associated with this environment that directly relate who had touched objects such as computers, computer mice, cell phones, desk phone, table or desks. By combining molecular and microbial investigation forensic strategies, this study offers novel insights to investigators who value the reconstructing of human lifestyle and characterization of human environmental interaction.