Explore the vast range of titles available.

Growing evidence suggests that the gut microbiota modulates the efficacy and toxicity of cancer therapy, most notably immunotherapy and its immune-related adverse effects. The poor response to immunotherapy in patients treated with antibiotics supports this influential role of the microbiota. Until recently, results pertaining to the identification of the microbial species responsible for these effects were incongruent, and relatively few studies analysed the underlying mechanisms. A better understanding of the taxonomy of the species involved and of the mechanisms of action has since been achieved. Defined bacterial species have been shown to promote an improved response to immune-checkpoint inhibitors by producing different products or metabolites. However, a suppressive effect of Gram-negative bacteria may be dominant in some unresponsive patients. Machine learning approaches trained on the microbiota composition of patients can predict the ability of patients to respond to immunotherapy with some accuracy. Thus, interest in modulating the microbiota composition to improve patient responsiveness to therapy has been mounting. Clinical proof-of-concept studies have demonstrated that faecal microbiota transplantation or dietary interventions might be utilized clinically to improve the success rate of immunotherapy in patients with cancer. Here, we review recent advances and discuss emerging strategies for microbiota-based cancer therapies.The gut microbiota has been shown to regulate responses to various cancer therapies, and the microbial species involved and their underlying mechanisms have begun to be unravelled. In this Perspective, Fernandes and colleagues present this evidence and then outline how it could be used to develop microbiota-based therapies for patients with cancer.

An unresolved question for the understanding of Alzheimer’s disease (AD) pathophysiology is why a significant percentage of amyloid-β (Aβ)-positive cognitively unimpaired (CU) individuals do not develop detectable downstream tau pathology and, consequently, clinical deterioration. In vitro evidence suggests that reactive astrocytes unleash Aβ effects in pathological tau phosphorylation. Here, in a biomarker study across three cohorts ( n  = 1,016), we tested whether astrocyte reactivity modulates the association of Aβ with tau phosphorylation in CU individuals. We found that Aβ was associated with increased plasma phosphorylated tau only in individuals positive for astrocyte reactivity (Ast + ). Cross-sectional and longitudinal tau–positron emission tomography analyses revealed an AD-like pattern of tau tangle accumulation as a function of Aβ only in CU Ast + individuals. Our findings suggest astrocyte reactivity as an important upstream event linking Aβ with initial tau pathology, which may have implications for the biological definition of preclinical AD and for selecting CU individuals for clinical trials. Cross-sectional and longitudinal analyses of tau pathology in preclinical Alzheimer’s disease reveal that tau tangles accumulate as a function of amyloid-β burden only in individuals positive for an astrocyte reactivity biomarker.

Biological aging of human organ systems reflects the interplay of age, chronic disease, lifestyle and genetic risk. Using longitudinal brain imaging and physiological phenotypes from the UK Biobank, we establish normative models of biological age for three brain and seven body systems. Here we find that an organ’s biological age selectively influences the aging of other organ systems, revealing a multiorgan aging network. We report organ age profiles for 16 chronic diseases, where advanced biological aging extends from the organ of primary disease to multiple systems. Advanced body age associates with several lifestyle and environmental factors, leukocyte telomere lengths and mortality risk, and predicts survival time (area under the curve of 0.77) and premature death (area under the curve of 0.86). Our work reveals the multisystem nature of human aging in health and chronic disease. It may enable early identification of individuals at increased risk of aging-related morbidity and inform new strategies to potentially limit organ-specific aging in such individuals. Organ-specific aging clocks for multiple brain and body systems show that the biological age of one organ system selectively influences the aging of multiple other systems via characteristic aging pathways.

The rapid development of deep learning, a family of machine learning techniques, has spurred much interest in its application to medical imaging problems. Here, we develop a deep learning algorithm that can accurately detect breast cancer on screening mammograms using an “end-to-end” training approach that efficiently leverages training datasets with either complete clinical annotation or only the cancer status (label) of the whole image. In this approach, lesion annotations are required only in the initial training stage, and subsequent stages require only image-level labels, eliminating the reliance on rarely available lesion annotations. Our all convolutional network method for classifying screening mammograms attained excellent performance in comparison with previous methods. On an independent test set of digitized film mammograms from the Digital Database for Screening Mammography (CBIS-DDSM), the best single model achieved a per-image AUC of 0.88, and four-model averaging improved the AUC to 0.91 (sensitivity: 86.1%, specificity: 80.1%). On an independent test set of full-field digital mammography (FFDM) images from the INbreast database, the best single model achieved a per-image AUC of 0.95, and four-model averaging improved the AUC to 0.98 (sensitivity: 86.7%, specificity: 96.1%). We also demonstrate that a whole image classifier trained using our end-to-end approach on the CBIS-DDSM digitized film mammograms can be transferred to INbreast FFDM images using only a subset of the INbreast data for fine-tuning and without further reliance on the availability of lesion annotations. These findings show that automatic deep learning methods can be readily trained to attain high accuracy on heterogeneous mammography platforms, and hold tremendous promise for improving clinical tools to reduce false positive and false negative screening mammography results. Code and model available at: https://github.com/lishen/end2end-all-conv .

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. A deep learning approach that predicts the risk of acute kidney injury may help to identify patients at risk of health deterioration within a time window that enables early treatment.

Epilepsy is a common disorder characterized by recurrent seizures. An overwhelming majority of people with epilepsy regard the unpredictability of seizures as a major issue. More than 30 years of international effort have been devoted to the prediction of seizures, aiming to remove the burden of unpredictability and to couple novel, time-specific treatment to seizure prediction technology. A highly influential review published in 2007 concluded that insufficient evidence indicated that seizures could be predicted. Since then, several advances have been made, including successful prospective seizure prediction using intracranial EEG in a small number of people in a trial of a real-time seizure prediction device. In this Review, we examine advances in the field, including EEG databases, seizure prediction competitions, the prospective trial mentioned and advances in our understanding of the mechanisms of seizures. We argue that these advances, together with statistical evaluations, set the stage for a resurgence in efforts towards the development of seizure prediction methodologies. We propose new avenues of investigation involving a synergy between mechanisms, models, data, devices and algorithms and refine the existing guidelines for the development of seizure prediction technology to instigate development of a solution that removes the burden of the unpredictability of seizures.

Among many populations of blood cells, high dimensional analysis using mass cytometry reveals classical monocyte frequency as strong predictors of response to PD-1 blockade therapy of melanoma. Immune-checkpoint blockade has revolutionized cancer therapy. In particular, inhibition of programmed cell death protein 1 (PD-1) has been found to be effective for the treatment of metastatic melanoma and other cancers. Despite a dramatic increase in progression-free survival, a large proportion of patients do not show durable responses. Therefore, predictive biomarkers of a clinical response are urgently needed. Here we used high-dimensional single-cell mass cytometry and a bioinformatics pipeline for the in-depth characterization of the immune cell subsets in the peripheral blood of patients with stage IV melanoma before and after 12 weeks of anti-PD-1 immunotherapy. During therapy, we observed a clear response to immunotherapy in the T cell compartment. However, before commencing therapy, a strong predictor of progression-free and overall survival in response to anti-PD-1 immunotherapy was the frequency of CD14 + CD16 − HLA-DR hi monocytes. We confirmed this by conventional flow cytometry in an independent, blinded validation cohort, and we propose that the frequency of monocytes in PBMCs may serve in clinical decision support.

Programmed death ligand-1 (PD-L1) has been recently adopted for breast cancer as a predictive biomarker for immunotherapies. The cost, time, and variability of PD-L1 quantification by immunohistochemistry (IHC) are a challenge. In contrast, hematoxylin and eosin (H&E) is a robust staining used routinely for cancer diagnosis. Here, we show that PD-L1 expression can be predicted from H&E-stained images by employing state-of-the-art deep learning techniques. With the help of two expert pathologists and a designed annotation software, we construct a dataset to assess the feasibility of PD-L1 prediction from H&E in breast cancer. In a cohort of 3,376 patients, our system predicts the PD-L1 status in a high area under the curve (AUC) of 0.91 – 0.93. Our system is validated on two external datasets, including an independent clinical trial cohort, showing consistent prediction performance. Furthermore, the proposed system predicts which cases are prone to pathologists miss-interpretation, showing it can serve as a decision support and quality assurance system in clinical practice. Programmed death ligand-1 (PD-L1) has been recently adopted for breast cancer as a predictive biomarker for immunotherapies. Here, the authors show that PD-L1 expression can be predicted from H&E-stained images using deep learning.

Patients with rheumatoid arthritis (RA) receive highly targeted biologic therapies without previous knowledge of target expression levels in the diseased tissue. Approximately 40% of patients do not respond to individual biologic therapies and 5–20% are refractory to all. In a biopsy-based, precision-medicine, randomized clinical trial in RA (R4RA; n  = 164), patients with low/absent synovial B cell molecular signature had a lower response to rituximab (anti-CD20 monoclonal antibody) compared with that to tocilizumab (anti-IL6R monoclonal antibody) although the exact mechanisms of response/nonresponse remain to be established. Here, in-depth histological/molecular analyses of R4RA synovial biopsies identify humoral immune response gene signatures associated with response to rituximab and tocilizumab, and a stromal/fibroblast signature in patients refractory to all medications. Post-treatment changes in synovial gene expression and cell infiltration highlighted divergent effects of rituximab and tocilizumab relating to differing response/nonresponse mechanisms. Using ten-by-tenfold nested cross-validation, we developed machine learning algorithms predictive of response to rituximab (area under the curve (AUC) = 0.74), tocilizumab (AUC = 0.68) and, notably, multidrug resistance (AUC = 0.69). This study supports the notion that disease endotypes, driven by diverse molecular pathology pathways in the diseased tissue, determine diverse clinical and treatment–response phenotypes. It also highlights the importance of integration of molecular pathology signatures into clinical algorithms to optimize the future use of existing medications and inform the development of new drugs for refractory patients. Biomarker analysis of the phase 4 R4RA trial identifies pretreatment synovial biopsy features selectively associated with response to rituximab or tocilizumab, and leads to the development of models that might predict treatment benefit in patients with rheumatoid arthritis

The relationship between microbiota, short chain fatty acids (SCFAs), and obesity remains enigmatic. We employ amplicon sequencing and targeted metabolomics in a large ( n  = 1904) African origin cohort from Ghana, South Africa, Jamaica, Seychelles, and the US. Microbiota diversity and fecal SCFAs are greatest in Ghanaians, and lowest in Americans, representing each end of the urbanization spectrum. Obesity is significantly associated with a reduction in SCFA concentration, microbial diversity, and SCFA synthesizing bacteria, with country of origin being the strongest explanatory factor. Diabetes, glucose state, hypertension, obesity, and sex can be accurately predicted from the global microbiota, but when analyzed at the level of country, predictive accuracy is only universally maintained for sex. Diabetes, glucose, and hypertension are only predictive in certain low-income countries. Our findings suggest that adiposity-related microbiota differences differ between low-to-middle-income compared to high-income countries. Further investigation is needed to determine the factors driving this association. Here, using amplicon sequencing and metabolomics in a large multi-country cohort, the authors find that adiposity-related microbiota differences differ between low-to-middle-income compared to high-income countries.