Global S&T Development Trend Analysis Platform of Resources and Environment
Screening mammography aims to identify breast cancer at earlier stages of the disease, when treatment can be more successful(1). Despite the existence of screening programmes worldwide, the interpretation of mammograms is affected by high rates of false positives and false negatives(2). Here we present an artificial intelligence (AI) system that is capable of surpassing human experts in breast cancer prediction. To assess its performance in the clinical setting, we curated a large representative dataset from the UK and a large enriched dataset from the USA. We show an absolute reduction of 5.7% and 1.2% (USA and UK) in false positives and 9.4% and 2.7% in false negatives. We provide evidence of the ability of the system to generalize from the UK to the USA. In an independent study of six radiologists, the AI system outperformed all of the human readers: the area under the receiver operating characteristic curve (AUC-ROC) for the AI system was greater than the AUC-ROC for the average radiologist by an absolute margin of 11.5%. We ran a simulation in which the AI system participated in the double-reading process that is used in the UK, and found that the AI system maintained non-inferior performance and reduced the workload of the second reader by 88%. This robust assessment of the AI system paves the way for clinical trials to improve the accuracy and efficiency of breast cancer screening.
The biosynthetic pathway that produces the secondary bile acids DCA and LCA in human gut microbes has been fully characterized, engineered into another bacterial host, and used to confer DCA production in germ-free mice-an important proof-of-principle for the engineering of gut microbial pathways.
The gut microbiota synthesize hundreds of molecules, many of which influence host physiology. Among the most abundant metabolites are the secondary bile acids deoxycholic acid (DCA) and lithocholic acid (LCA), which accumulate at concentrations of around 500 mu M and are known to block the growth ofClostridium difficile(1), promote hepatocellular carcinoma(2)and modulate host metabolism via the G-protein-coupled receptor TGR5 (ref.(3)). More broadly, DCA, LCA and their derivatives are major components of the recirculating pool of bile acids(4)
Metabolomics data from germ-free and specific-pathogen-free mice reveal effects of the microbiome on host chemistry, identifying conjugations of bile acids that are also enriched in patients with inflammatory bowel disease or cystic fibrosis.
A mosaic of cross-phylum chemical interactions occurs between all metazoans and their microbiomes. A number of molecular families that are known to be produced by the microbiome have a marked effect on the balance between health and disease(1-9). Considering the diversity of the human microbiome (which numbers over 40,000 operational taxonomic units(10)), the effect of the microbiome on the chemistry of an entire animal remains underexplored. Here we use mass spectrometry informatics and data visualization approaches(11-13) to provide an assessment of the effects of the microbiome on the chemistry of an entire mammal by comparing metabolomics data from germ-free and specific-pathogen-free mice. We found that the microbiota affects the chemistry of all organs. This included the amino acid conjugations of host bile acids that were used to produce phenylalanocholic acid, tyrosocholic acid and leucocholic acid, which have not previously been characterized despite extensive research on bile-acid chemistry(14). These bile-acid conjugates were also found in humans, and were enriched in patients with inflammatory bowel disease or cystic fibrosis. These compounds agonized the farnesoid X receptor in vitro, and mice gavaged with the compounds showed reduced expression of bile-acid synthesis genes in vivo. Further studies are required to confirm whether these compounds have a physiological role in the host, and whether they contribute to gut diseases that are associated with microbiome dysbiosis.