Suicide remains a leading cause of preventable death worldwide, despite advances in research and decreases in mental health stigma through government health campaigns. Machine learning (ML), a type of artificial intelligence (AI), is the use of algorithms to simulate and imitate human cognition. Given the lack of improvement in clinician-based suicide prediction over time, advancements in technology have allowed for novel approaches to predicting suicide risk. This systematic review and meta-analysis aimed to synthesize current research regarding data sources in ML prediction of suicide risk, incorporating and comparing outcomes between structured data (human interpretable such as psychometric instruments) and unstructured data (only machine interpretable such as electronic health records). Online databases and gray literature were searched for studies relating to ML and suicide risk prediction. There were 31 eligible studies. The outcome for all studies combined was AUC = 0.860, structured data showed AUC = 0.873, and unstructured data was calculated at AUC = 0.866. There was substantial heterogeneity between the studies, the sources of which were unable to be defined. The studies showed good accuracy levels in the prediction of suicide risk behavior overall. Structured data and unstructured data also showed similar outcome accuracy according to meta-analysis, despite different volumes and types of input data.

The total amount of data created, captured, copied, and consumed globally is forecast to increase rapidly, reaching 149 zettabytes in 2024. Over the next five years up to 2028, global data creation is projected to grow to more than 394 zettabytes. In 2020, the amount of data created and replicated reached a new high. The growth was higher than previously expected, caused by the increased demand due to the COVID-19 pandemic, as more people worked and learned from home and used home entertainment options more often. Storage capacity also growing Only a small percentage of this newly created data is kept though, as just two percent of the data produced and consumed in 2020 was saved and retained into 2021. In line with the strong growth of the data volume, the installed base of storage capacity is forecast to increase, growing at a compound annual growth rate of 19.2 percent over the forecast period from 2020 to 2025. In 2020, the installed base of storage capacity reached 6.7 zettabytes.

Prediction and control of the spread of infectious disease in human populations benefits greatly from our growing capacity to quantify human movement behavior. Here we develop a mathematical model for non-transmissible infections contracted from a localized environmental source, informed by a detailed description of movement patterns of the population of Great Britain. The model is applied to outbreaks of Legionnaires' disease, a potentially life-threatening form of pneumonia caused by the bacteria Legionella pneumophilia. We use case-report data from three recent outbreaks that have occurred in Great Britain where the source has already been identified by public health agencies. We first demonstrate that the amount of individual-level heterogeneity incorporated in the movement data greatly influences our ability to predict the source location. The most accurate predictions were obtained using reported travel histories to describe movements of infected individuals, but using detailed simulation models to estimate movement patterns offers an effective fast alternative. Secondly, once the source is identified, we show that our model can be used to accurately determine the population likely to have been exposed to the pathogen, and hence predict the residential locations of infected individuals. The results give rise to an effective control strategy that can be implemented rapidly in response to an outbreak.

The first was obtained by downloading gene families annotation from https://www.genenames.org/download/statistics-and-files/, applying a hypergeometric test (R version 4.1.2) using all the genes in the DepMap matrix as background. The GO-BP enrichment, instead, was performed by using DAVID Bioinformatics tool (https://david.ncifcrf.gov/tools.jsp). Each sheet is named according to the content “tissue_enrichment_class”. The columns’ content is detailed in each sheet. (XLSX)

Description of all features used in this work.

We use open source human gut microbiome data to learn a microbial "language" model by adapting techniques from Natural Language Processing (NLP). Our microbial "language" model is trained in a self-supervised fashion (i.e., without additional external labels) to capture the interactions among different microbial species and the common compositional patterns in microbial communities. The learned model produces contextualized taxa representations that allow a single bacteria species to be represented differently according to the specific microbial environment it appears in. The model further provides a sample representation by collectively interpreting different bacteria species in the sample and their interactions as a whole. We show that, compared to baseline representations, our sample representation consistently leads to improved performance for multiple prediction tasks including predicting Irritable Bowel Disease (IBD) and diet patterns. Coupled with a simple ensemble strategy, it produces a highly robust IBD prediction model that generalizes well to microbiome data independently collected from different populations with substantial distribution shift.

We visualize the contextualized taxa representations and find that they exhibit meaningful phylum-level structure, despite never exposing the model to such a signal. Finally, we apply an interpretation method to highlight bacterial species that are particularly influential in driving our model's predictions for IBD.

The number of microbiome-related studies has notably increased the availability of data on human microbiome composition and function. These studies provide the essential material to deeply explore host-microbiome associations and their relation to the development and progression of various complex diseases. Improved data-analytical tools are needed to exploit all information from these biological datasets, taking into account the peculiarities of microbiome data, i.e., compositional, heterogeneous and sparse nature of these datasets. The possibility of predicting host-phenotypes based on taxonomy-informed feature selection to establish an association between microbiome and predict disease states is beneficial for personalized medicine. In this regard, machine learning (ML) provides new insights into the development of models that can be used to predict outputs, such as classification and prediction in microbiology, infer host phenotypes to predict diseases and use microbial communities to stratify patients by their characterization of state-specific microbial signatures. Here we review the state-of-the-art ML methods and respective software applied in human microbiome studies, performed as part of the COST Action ML4Microbiome activities. This scoping review focuses on the application of ML in microbiome studies related to association and clinical use for diagnostics, prognostics, and therapeutics. Although the data presented here is more related to the bacterial community, many algorithms could be applied in general, regardless of the feature type. This literature and software review covering this broad topic is aligned with the scoping review methodology. The manual identification of data sources has been complemented with: (1) automated publication search through digital libraries of the three major publishers using natural language processing (NLP) Toolkit, and (2) an automated identification of relevant software repositories on GitHub and ranking of the related research papers relying on learning to rank approach.

Supertypes according to Sydney J. et al 2008 BMC Immunology 9:1. (XLSX)

Example proteins and validated epitopes present in the IEDB 3.0 database.