scholarly journals Explainable AI reveals changes in skin microbiome composition linked to phenotypic differences

2020 ◽  
Author(s):  
Anna Paola Carrieri ◽  
Niina Haiminen ◽  
Sean Maudsley-Barton ◽  
Laura-Jayne Gardiner ◽  
Barry Murphy ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Smoking Status ◽  
Menopausal Status ◽  
Human Microbiome ◽  
Skin Aging ◽  
Skin Hydration ◽  
Skin Microbiome ◽  
Microbial Composition ◽  
Microbiome Composition ◽  
Non Invasive

AbstractAlterations in the human microbiome have been observed in a variety of conditions such has asthma, gingivitis, dermatitis and cancer, and much remains to be learned about the links between the microbiome and human health. The fusion of artificial intelligence with rich microbiome datasets can offer an improved understanding of the microbiome’s role in our health. To gain actionable insights it is essential to consider both the predictive power and the transparency of the models by providing explanations for the predictions.We combine the effort of collecting a corpus of leg skin microbiome samples of two healthy cohorts of women with the development of an explainable artificial intelligence (EAI) approach that provides accurate predictions of phenotypes and explanations. The explanations are expressed in terms of variations in the abundance of key microbes that drive the predictions.We predict skin hydration, subject’s age, pre/post-menopausal status and smoking status from the leg skin microbiome. The key changes in microbial composition linked to skin hydration can accelerate the development of personalised treatments for healthy skin, while those associated with age may offer insights into the skin aging process. The leg microbiome signatures associated with smoking and menopausal status are consistent with previous findings from oral/respiratory tract microbiomes and vaginal microbiomes respectively. This suggests that easily accessible microbiome samples could be used to investigate health-related phenotypes, offering potential for non-invasive diagnosis and condition monitoring.Our EAI approach sets the stage for new work focused on understanding the complex relationships between microbial communities and phenotypes. Our approach can be applied to predict any conditions from microbiome samples and has the potential to accelerate the development of microbiome-based personalised therapeutics and non-invasive diagnostics.

scholarly journals Explainable AI reveals changes in skin microbiome composition linked to phenotypic differences

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Anna Paola Carrieri ◽  
Niina Haiminen ◽  
Sean Maudsley-Barton ◽  
Laura-Jayne Gardiner ◽  
Barry Murphy ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Human Health ◽  
Smoking Status ◽  
Menopausal Status ◽  
Human Microbiome ◽  
Skin Aging ◽  
Skin Hydration ◽  
Skin Microbiome ◽  
Microbial Composition ◽  
Non Invasive

AbstractAlterations in the human microbiome have been observed in a variety of conditions such as asthma, gingivitis, dermatitis and cancer, and much remains to be learned about the links between the microbiome and human health. The fusion of artificial intelligence with rich microbiome datasets can offer an improved understanding of the microbiome’s role in human health. To gain actionable insights it is essential to consider both the predictive power and the transparency of the models by providing explanations for the predictions. We combine the collection of leg skin microbiome samples from two healthy cohorts of women with the application of an explainable artificial intelligence (EAI) approach that provides accurate predictions of phenotypes with explanations. The explanations are expressed in terms of variations in the relative abundance of key microbes that drive the predictions. We predict skin hydration, subject's age, pre/post-menopausal status and smoking status from the leg skin microbiome. The changes in microbial composition linked to skin hydration can accelerate the development of personalized treatments for healthy skin, while those associated with age may offer insights into the skin aging process. The leg microbiome signatures associated with smoking and menopausal status are consistent with previous findings from oral/respiratory tract microbiomes and vaginal/gut microbiomes respectively. This suggests that easily accessible microbiome samples could be used to investigate health-related phenotypes, offering potential for non-invasive diagnosis and condition monitoring. Our EAI approach sets the stage for new work focused on understanding the complex relationships between microbial communities and phenotypes. Our approach can be applied to predict any condition from microbiome samples and has the potential to accelerate the development of microbiome-based personalized therapeutics and non-invasive diagnostics.

scholarly journals Molecular Reconstruction of the Diet in Human Stool Samples

mSystems ◽  
2019 ◽  
Vol 4 (6) ◽  
Author(s):  
Frank Maixner
Keyword(s):  
Human Subjects ◽  
Human Microbiome ◽  
Microbial Composition ◽  
Microbiome Composition ◽  
Diet Surveys ◽  
Dna Metabarcoding ◽  
Microbiome Research ◽  
Dietary Records ◽  
Stool Samples ◽  
Chloroplast Dna Markers

ABSTRACT Understanding dietary effects on the gut microbial composition is one of the key questions in human microbiome research. It is highly important to have reliable dietary data on the stool samples to unambiguously link the microbiome composition to food intake. Often, however, self-reported diet surveys have low accuracy and can be misleading. Thereby, additional molecular biology-based methods could help to revise the diet composition. The article by Reese et al. [A. T. Reese, T. R. Kartzinel, B. L. Petrone, P. J. Turnbaugh, et al., mSystems 4(5):e00458-19, 2019, https://doi.org/10.1128/mSystems.00458-19] in a recent issue of mSystems describes a DNA metabarcoding strategy targeting chloroplast DNA markers in stool samples from 11 human subjects consuming both controlled and freely selected diets. The aim of this study was to evaluate the efficiency of this molecular method in detecting plant remains in the sample compared to the written dietary records. This study displays an important first step in implementing molecular dietary reconstructions in stool microbiome studies which will finally help to increase the accuracy of dietary metadata.

scholarly journals New Insights into the Intrinsic and Extrinsic Factors That Shape the Human Skin Microbiome

mBio ◽  
2019 ◽  
Vol 10 (4) ◽  
Author(s):  
Pedro A. Dimitriu ◽  
Brandon Iker ◽  
Kausar Malik ◽  
Hilary Leung ◽  
W. W. Mohn ◽  
...  
Keyword(s):  
Human Skin ◽  
North American ◽  
Skin Aging ◽  
Physiological Parameters ◽  
Host Factors ◽  
Chronological Age ◽  
Skin Microbiome ◽  
Physiological Factors ◽  
Modeling Tools ◽  
Microbiome Composition

ABSTRACT Despite recognition that biogeography and individuality shape the function and composition of the human skin microbiome, we know little about how extrinsic and intrinsic host factors influence its composition. To explore the contributions of these factors to skin microbiome variation, we profiled the bacterial microbiomes of 495 North American subjects (ages, 9 to 78 years) at four skin surfaces plus the oral epithelium using 16S rRNA gene amplicon sequencing. We collected subject metadata, including host physiological parameters, through standardized questionnaires and noninvasive biophysical methods. Using a combination of statistical modeling tools, we found that demographic, lifestyle, and physiological factors collectively explained 12 to 20% of the variability in microbiome composition. The influence of health factors was strongest on the oral microbiome. Associations between host factors and the skin microbiome were generally dominated by operational taxonomic units (OTUs) affiliated with the Clostridiales and Prevotella. A subset of the correlations between microbial features and host attributes were site specific. To further explore the relationship between age and the skin microbiome of the forehead, we trained a Random Forest regression model to predict chronological age from microbial features. Age was associated mostly with two mutually coexcluding Corynebacterium OTUs. Furthermore, skin aging variables (wrinkles and hyperpigmented spots) were independently correlated to these taxa. IMPORTANCE Many studies have highlighted the importance of body site and individuality in shaping the composition of the human skin microbiome, but we still have a poor understanding of how extrinsic (e.g., lifestyle) and intrinsic (e.g., age) factors influence its composition. We characterized the bacterial microbiomes of North American volunteers at four skin sites and the mouth. We also collected extensive subject metadata and measured several host physiological parameters. Integration of host and microbial features showed that the skin microbiome was predominantly associated with demographic, lifestyle, and physiological factors. Furthermore, we uncovered reproducible associations between chronological age, skin aging, and members of the genus Corynebacterium. Our work provides new understanding of the role of host selection and lifestyle in shaping skin microbiome composition. It also contributes to a more comprehensive appreciation of the factors that drive interindividual skin microbiome variation.

scholarly journals Cohort profile: CROSS-TRACKS: a population-based open cohort across healthcare sectors in Denmark

BMJ Open ◽  
2020 ◽  
Vol 10 (10) ◽  
pp. e039996
Author(s):  
Anders Hammerich Riis ◽  
Pia Kjær Kristensen ◽  
Matilde Grøndahl Petersen ◽  
Ninna Hinchely Ebdrup ◽  
Simon Meyer Lauritsen ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Primary Care ◽  
Hospital Admissions ◽  
Smoking Status ◽  
Population Based ◽  
Fertility Treatment ◽  
Study Patient ◽  
Transfer Payment ◽  
Sociodemographic Characteristics ◽  
Patient Pathways

PurposeThis paper describes the open cohort CROSS-TRACKS, which comprises population-based data from primary care, secondary care and national registries to study patient pathways and transitions across sectors while adjusting for sociodemographic characteristics.ParticipantsA total of 221 283 individuals resided in the four Danish municipalities that constituted the catchment area of Horsens Regional Hospital in 2012–2018. A total of 96% of the population used primary care, 35% received at least one transfer payment and 66% was in contact with a hospital at least once in the period. Additional clinical information is available for hospital contacts (eg, alcohol intake, smoking status, body mass index and blood pressure). A total of 23% (n=8191) of individuals aged ≥65 years had at least one potentially preventable hospital admission, and 73% (n=5941) of these individuals had more than one.Findings to dateThe cohort is currently used for research projects in epidemiology and artificial intelligence. These projects comprise a prediction model for potentially preventable hospital admissions, a clinical decision support system based on artificial intelligence, prevention of medication errors in the transition between sectors, health behaviour and sociodemographic characteristics of men and women prior to fertility treatment, and a recently published study applying machine learning methods for early detection of sepsis.Future plansThe CROSS-TRACKS cohort will be expanded to comprise the entire Central Denmark Region consisting of 1.3 million residents. The cohort can provide new knowledge on how to best organise interventions across healthcare sectors and prevent potentially preventable hospital admissions. Such knowledge would benefit both the individual citizen and society as a whole.

scholarly journals Taxonomic signatures of cause-specific mortality risk in human gut microbiome

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Aaro Salosensaari ◽  
Ville Laitinen ◽  
Aki S. Havulinna ◽  
Guillaume Meric ◽  
Susan Cheng ◽  
...  
Keyword(s):  
Mortality Risk ◽  
Gut Microbiome ◽  
Human Gut ◽  
Cross Sectional ◽  
Microbiome Composition ◽  
Human Gut Microbiome ◽  
Non Invasive ◽  
Sequencing Technologies

AbstractThe collection of fecal material and developments in sequencing technologies have enabled standardised and non-invasive gut microbiome profiling. Microbiome composition from several large cohorts have been cross-sectionally linked to various lifestyle factors and diseases. In spite of these advances, prospective associations between microbiome composition and health have remained uncharacterised due to the lack of sufficiently large and representative population cohorts with comprehensive follow-up data. Here, we analyse the long-term association between gut microbiome variation and mortality in a well-phenotyped and representative population cohort from Finland (n = 7211). We report robust taxonomic and functional microbiome signatures related to the Enterobacteriaceae family that are associated with mortality risk during a 15-year follow-up. Our results extend previous cross-sectional studies, and help to establish the basis for examining long-term associations between human gut microbiome composition, incident outcomes, and general health status.

scholarly journals Association between central non-dipping pattern and platelet morphology in adults with type 1 diabetes without cardiovascular disease: a cross-sectional study

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Michal Kulecki ◽  
Dariusz Naskret ◽  
Mikolaj Kaminski ◽  
Dominika Kasprzak ◽  
Pawel Lachowski ◽  
...  
Keyword(s):  
Blood Pressure ◽  
Type 1 Diabetes ◽  
Smoking Status ◽  
Cross Sectional Study ◽  
Cross Sectional ◽  
Distribution Width ◽  
Non Invasive ◽  
Platelet Morphology ◽  
Oscillometric Device

AbstractThe non-dipping pattern is nighttime systolic blood pressure (SBP) fall of less than 10%. Several studies showed that the non-dipping pattern, increased mean platelet volume (MPV), and platelet distribution width (PDW) are associated with elevated cardiovascular risk. Hypertensives with the non-dipping pattern have higher MPV than the dippers but this relationship was never investigated among people with type 1 diabetes mellitus (T1DM). This study aimed to investigate the association between the central dipping pattern and platelet morphology in T1DM subjects. We measured the central and brachial blood pressure with a validated non-invasive brachial oscillometric device—Arteriograph 24—during twenty-four-hour analysis in T1DM subjects without diagnosed hypertension. The group was divided based on the central dipping pattern for the dippers and the non-dippers. From a total of 62 subjects (32 males) aged 30.1 (25.7–37) years with T1DM duration 15.0 (9.0–20) years, 36 were non-dippers. The non-dipper group had significantly higher MPV (MPV (10.8 [10.3–11.5] vs 10.4 [10.0–10.7] fl; p = 0.041) and PDW (13.2 [11.7–14.9] vs 12.3 [11.7–12.8] fl; p = 0.029) than dipper group. Multivariable logistic regression revealed that MPV (OR 3.74; 95% CI 1.48–9.45; p = 0.005) and PDW (OR 1.91; 95% CI 1.22–3.00; p = 0.005) were positively associated with central non-dipping pattern adjusting for age, sex, smoking status, daily insulin intake, and height. MPV and PDW are positively associated with the central non-dipping pattern among people with T1DM.

scholarly journals SkinBug: an artificial intelligence approach to predict human skin microbiome-mediated metabolism of biotics and xenobiotics

iScience ◽  
2021 ◽  
Vol 24 (1) ◽  
pp. 101925
Author(s):  
Shubham K. Jaiswal ◽  
Shitij Manojkumar Agarwal ◽  
Parikshit Thodum ◽  
Vineet K. Sharma
Keyword(s):  
Artificial Intelligence ◽  
Human Skin ◽  
Skin Microbiome ◽  
Intelligence Approach ◽  
Artificial Intelligence Approach

scholarly journals Exploring the microbiome in health and disease

2017 ◽  
Vol 1 ◽  
pp. 239784731774188 ◽  
Author(s):  
Elena Scotti ◽  
Stéphanie Boué ◽  
Giuseppe Lo Sasso ◽  
Filippo Zanetti ◽  
Vincenzo Belcastro ◽  
...  
Keyword(s):  
Human Health ◽  
Metabolic Diseases ◽  
Skin Diseases ◽  
Human Microbiome ◽  
Chronic Obstructive ◽  
Microbial Composition ◽  
Obstructive Pulmonary Disease ◽  
New Findings ◽  
Dynamics And Function ◽  
And Function

The analysis of human microbiome is an exciting and rapidly expanding field of research. In the past decade, the biological relevance of the microbiome for human health has become evident. Microbiome comprises a complex collection of microorganisms, with their genes and metabolites, colonizing different body niches. It is now well known that the microbiome interacts with its host, assisting in the bioconversion of nutrients and detoxification, supporting immunity, protecting against pathogenic microbes, and maintaining health. Remarkable new findings showed that our microbiome not only primarily affects the health and function of the gastrointestinal tract but also has a strong influence on general body health through its close interaction with the nervous system and the lung. Therefore, a perfect and sensitive balanced interaction of microbes with the host is required for a healthy body. In fact, growing evidence suggests that the dynamics and function of the indigenous microbiota can be influenced by many factors, including genetics, diet, age, and toxicological agents like cigarette smoke, environmental contaminants, and drugs. The disruption of this balance, that is called dysbiosis, is associated with a plethora of diseases, including metabolic diseases, inflammatory bowel disease, chronic obstructive pulmonary disease, periodontitis, skin diseases, and neurological disorders. The importance of the host microbiome for the human health has also led to the emergence of novel therapeutic approaches focused on the intentional manipulation of the microbiota, either by restoring missing functions or eliminating harmful roles. In the present review, we outline recent studies devoted to elucidate not only the role of microbiome in health conditions and the possible link with various types of diseases but also the influence of various toxicological factors on the microbial composition and function.

scholarly journals The Prenatal Microbiome: A New Player for Human Health

2018 ◽  
Vol 7 (4) ◽  
pp. 38 ◽  
Author(s):  
Valeria D’Argenio
Keyword(s):  
Health Status ◽  
Microbial Communities ◽  
Fetal Development ◽  
Reproductive Medicine ◽  
Current Knowledge ◽  
Human Microbiome ◽  
Future Perspectives ◽  
Microbiome Composition ◽  
Umbilical Blood ◽  
Technological Advances

The last few years have featured an increasing interest in the study of the human microbiome and its correlations with health status. Indeed, technological advances have allowed the study of microbial communities to reach a previously unthinkable sensitivity, showing the presence of microbes also in environments usually considered as sterile. In this scenario, microbial communities have been described in the amniotic fluid, the umbilical blood cord, and the placenta, denying a dogma of reproductive medicine that considers the uterus like a sterile womb. This prenatal microbiome may play a role not only in fetal development but also in the predisposition to diseases that may develop later in life, and also in adulthood. Thus, the aim of this review is to report the current knowledge regarding the prenatal microbiome composition, its association with pathological processes, and the future perspectives regarding its manipulation for healthy status promotion and maintenance.

scholarly journals Artificial Intelligence Framework for Efficient Detection and Classification of Pneumonia Using Chest Radiography Images

2021 ◽  
Author(s):  
Ali Mohammad Alqudah ◽  
Shoroq Qazan ◽  
Ihssan S. Masad
Keyword(s):  
Artificial Intelligence ◽  
Input Image ◽  
Image Size ◽  
X Ray ◽  
Softmax Classifier ◽  
Non Invasive ◽  
Efficient Detection ◽  
X Ray Imaging ◽  
Chest X Ray

Abstract BackgroundChest diseases are serious health problems that threaten the lives of people. The early and accurate diagnosis of such diseases is very crucial in the success of their treatment and cure. Pneumonia is one of the most widely occurred chest diseases responsible for a high percentage of deaths especially among children. So, detection and classification of pneumonia using the non-invasive chest x-ray imaging would have a great advantage of reducing the mortality rates.ResultsThe results showed that the best input image size in this framework was 64 64 based on comparison between different sizes. Using CNN as a deep features extractor and utilizing the 10-fold methodology the propose artificial intelligence framework achieved an accuracy of 94% for SVM and 93.9% for KNN, a sensitivity of 93.33% for SVM and 93.19% for KNN and a specificity of 96.68% for SVM and 96.60% for KNN.ConclusionsIn this study, an artificial intelligence framework has been proposed for the detection and classification of pneumonia based on chest x-ray imaging with different sizes of input images. The proposed methodology used CNN for features extraction that were fed to two different types of classifiers, namely, SVM and KNN; in addition to the SoftMax classifier which is the default CNN classifier. The proposed CNN has been trained, validated, and tested using a large dataset of chest x-ray images contains in total 5852 images.

Sign in / Sign up

Export Citation Format

Share Document