Artificial Intelligence Based on Machine Learning in Pharmacovigilance: A Scoping Review

INTRODUCTION

Artificial intelligence based on machine learning has made large advancements in many fields of science and medicine but its impact on pharmacovigilance is yet unclear.

OBJECTIVE

The present study conducted a scoping review of the use of artificial intelligence based on machine learning to understand how it is used for pharmacovigilance tasks, characterize differences with other fields, and identify opportunities to improve pharmacovigilance through the use of machine learning.

DESIGN

The PubMed, Embase, Web of Science, and IEEE Xplore databases were searched to identify articles pertaining to the use of machine learning in pharmacovigilance published from the year 2000 to September 2021. After manual screening of 7744 abstracts, a total of 393 papers met the inclusion criteria for further analysis. Extraction of key data on study design, data sources, sample size, and machine learning methodology was performed. Studies with the characteristics of good machine learning practice were defined and manual review focused on identifying studies that fulfilled these criteria and results that showed promise.

RESULTS

The majority of studies (53%) were focused on detecting safety signals using traditional statistical methods. Of the studies that used more recent machine learning methods, 61% used off-the-shelf techniques with minor modifications. Temporal analysis revealed that newer methods such as deep learning have shown increased use in recent years. We found only 42 studies (10%) that reflect current best practices and trends in machine learning. In the subset of 154 papers that focused on data intake and ingestion, 30 (19%) were found to incorporate the same best practices.

CONCLUSION

Advances from artificial intelligence have yet to fully penetrate pharmacovigilance, although recent studies show signs that this may be changing.

Learning, visualizing and exploring 16S rRNA structure using an attention-based deep neural network

Recurrent neural networks with memory and attention mechanisms are widely used in natural language processing because they can capture short and long term sequential information for diverse tasks. We propose an integrated deep learning model for microbial DNA sequence data, which exploits convolutional neural networks, recurrent neural networks, and attention mechanisms to predict taxonomic classifications and sample-associated attributes, such as the relationship between the microbiome and host phenotype, on the read/sequence level. In this paper, we develop this novel deep learning approach and evaluate its application to amplicon sequences. We apply our approach to short DNA reads and full sequences of 16S ribosomal RNA (rRNA) marker genes, which identify the heterogeneity of a microbial community sample. We demonstrate that our implementation of a novel attention-based deep network architecture, Read2Pheno, achieves read-level phenotypic prediction. Training Read2Pheno models will encode sequences (reads) into dense, meaningful representations: learned embedded vectors output from the intermediate layer of the network model, which can provide biological insight when visualized. The attention layer of Read2Pheno models can also automatically identify nucleotide regions in reads/sequences which are particularly informative for classification. As such, this novel approach can avoid pre/post-processing and manual interpretation required with conventional approaches to microbiome sequence classification. We further show, as proof-of-concept, that aggregating read-level information can robustly predict microbial community properties, host phenotype, and taxonomic classification, with performance at least comparable to conventional approaches. An implementation of the attention-based deep learning network is available at https://github.com/EESI/sequence_attention (a python package) and https://github.com/EESI/seq2att (a command line tool).

Does getting defensive get you anywhere?-Seasonal balancing selection, temperature, and parasitoids shape real-world, protective endosymbiont dynamics in the pea aphid

Facultative, heritable endosymbionts are found at intermediate prevalence within most insect species, playing frequent roles in their hosts' defence against environmental pressures. Focusing on Hamiltonella defensa, a common bacterial endosymbiont of aphids, we tested the hypothesis that such pressures impose seasonal balancing selection, shaping a widespread infection polymorphism. In our studied pea aphid (Acyrthosiphon pisum) population, Hamiltonella frequencies ranged from 23.2% to 68.1% across a six-month longitudinal survey. Rapid spikes and declines were often consistent across fields, and we estimated that selection coefficients for Hamiltonella-infected aphids changed sign within this field season. Prior laboratory research suggested antiparasitoid defence as the major Hamiltonella benefit, and costs under parasitoid absence. While a prior field study suggested these forces can sometimes act as counter-weights in a regime of seasonal balancing selection, our present survey showed no significant relationship between parasitoid wasps and Hamiltonella prevalence. Field cage experiments provided some explanation: parasitoids drove modest ~10% boosts to Hamiltonella frequencies that would be hard to detect under less controlled conditions. They also showed that Hamiltonella was not always costly under parasitoid exclusion, contradicting another prediction. Instead, our longitudinal survey - and two overwintering studies - showed temperature to be the strongest predictor of Hamiltonella prevalence. Matching some prior lab discoveries, this suggested that thermally sensitive costs and benefits, unrelated to parasitism, can shape Hamiltonella dynamics. These results add to a growing body of evidence for rapid, seasonal adaptation in multivoltine organisms, suggesting that such adaptation can be mediated through the diverse impacts of heritable bacterial endosymbionts.

Emerging Priorities for Microbiome Research

Microbiome research has increased dramatically in recent years, driven by advances in technology and significant reductions in the cost of analysis. Such research has unlocked a wealth of data, which has yielded tremendous insight into the nature of the microbial communities, including their interactions and effects, both within a host and in an external environment as part of an ecological community. Understanding the role of microbiota, including their dynamic interactions with their hosts and other microbes, can enable the engineering of new diagnostic techniques and interventional strategies that can be used in a diverse spectrum of fields, spanning from ecology and agriculture to medicine and from forensics to exobiology. From June 19-23 in 2017, the NIH and NSF jointly held an Innovation Lab on Quantitative Approaches to Biomedical Data Science Challenges in our Understanding of the Microbiome. This review is inspired by some of the topics that arose as priority areas from this unique, interactive workshop. The goal of this review is to summarize the Innovation Lab's findings by introducing the reader to emerging challenges, exciting potential, and current directions in microbiome research. The review is broken into five key topic areas: (1) interactions between microbes and the human body, (2) evolution and ecology of microbes, including the role played by the environment and microbe-microbe interactions, (3) analytical and mathematical methods currently used in microbiome research, (4) leveraging knowledge of microbial composition and interactions to develop engineering solutions, and (5) interventional approaches and engineered microbiota that may be enabled by selectively altering microbial composition. As such, this review seeks to arm the reader with a broad understanding of the priorities and challenges in microbiome research today and provide inspiration for future investigation and multi-disciplinary collaboration.

Exploring thematic structure and predicted functionality of 16S rRNA amplicon data

Analysis of microbiome data involves identifying co-occurring groups of taxa associated with sample features of interest (e.g., disease state). Elucidating such relations is often difficult as microbiome data are compositional, sparse, and have high dimensionality. Also, the configuration of co-occurring taxa may represent overlapping subcommunities that contribute to sample characteristics such as host status. Preserving the configuration of co-occurring microbes rather than detecting specific indicator species is more likely to facilitate biologically meaningful interpretations. Additionally, analyses that use taxonomic relative abundances to predict the abundances of different gene functions aggregate predicted functional profiles across taxa. This precludes straightforward identification of predicted functional components associated with subsets of co-occurring taxa. We provide an approach to explore co-occurring taxa using "topics" generated via a topic model and link these topics to specific sample features (e.g., disease state). Rather than inferring predicted functional content based on overall taxonomic relative abundances, we instead focus on inference of functional content within topics, which we parse by estimating interactions between topics and pathways through a multilevel, fully Bayesian regression model. We apply our methods to three publicly available 16S amplicon sequencing datasets: an inflammatory bowel disease dataset, an oral cancer dataset, and a time-series dataset. Using our topic model approach to uncover latent structure in 16S rRNA amplicon surveys, investigators can (1) capture groups of co-occurring taxa termed topics; (2) uncover within-topic functional potential; (3) link taxa co-occurrence, gene function, and environmental/host features; and (4) explore the way in which sets of co-occurring taxa behave and evolve over time. These methods have been implemented in a freely available R package: https://cran.r-project.org/package=themetagenomics, https://github.com/EESI/themetagenomics.

Opportunities and obstacles for deep learning in biology and medicine

Deep learning describes a class of machine learning algorithms that are capable of combining raw inputs into layers of intermediate features. These algorithms have recently shown impressive results across a variety of domains. Biology and medicine are data-rich disciplines, but the data are complex and often ill-understood. Hence, deep learning techniques may be particularly well suited to solve problems of these fields. We examine applications of deep learning to a variety of biomedical problems-patient classification, fundamental biological processes and treatment of patients-and discuss whether deep learning will be able to transform these tasks or if the biomedical sphere poses unique challenges. Following from an extensive literature review, we find that deep learning has yet to revolutionize biomedicine or definitively resolve any of the most pressing challenges in the field, but promising advances have been made on the prior state of the art. Even though improvements over previous baselines have been modest in general, the recent progress indicates that deep learning methods will provide valuable means for speeding up or aiding human investigation. Though progress has been made linking a specific neural network's prediction to input features, understanding how users should interpret these models to make testable hypotheses about the system under study remains an open challenge. Furthermore, the limited amount of labelled data for training presents problems in some domains, as do legal and privacy constraints on work with sensitive health records. Nonetheless, we foresee deep learning enabling changes at both bench and bedside with the potential to transform several areas of biology and medicine.

Metagenomic characterization of ambulances across the USA

BACKGROUND

Microbial communities in our built environments have great influence on human health and disease. A variety of built environments have been characterized using a metagenomics-based approach, including some healthcare settings. However, there has been no study to date that has used this approach in pre-hospital settings, such as ambulances, an important first point-of-contact between patients and hospitals.

RESULTS

We sequenced 398 samples from 137 ambulances across the USA using shotgun sequencing. We analyzed these data to explore the microbial ecology of ambulances including characterizing microbial community composition, nosocomial pathogens, patterns of diversity, presence of functional pathways and antimicrobial resistance, and potential spatial and environmental factors that may contribute to community composition. We found that the top 10 most abundant species are either common built environment microbes, microbes associated with the human microbiome (e.g., skin), or are species associated with nosocomial infections. We also found widespread evidence of antimicrobial resistance markers (hits ~ 90% samples). We identified six factors that may influence the microbial ecology of ambulances including ambulance surfaces, geographical-related factors (including region, longitude, and latitude), and weather-related factors (including temperature and precipitation).

CONCLUSIONS

While the vast majority of microbial species classified were beneficial, we also found widespread evidence of species associated with nosocomial infections and antimicrobial resistance markers. This study indicates that metagenomics may be useful to characterize the microbial ecology of pre-hospital ambulance settings and that more rigorous testing and cleaning of ambulances may be warranted.

Engineering Human Microbiota: Influencing Cellular and Community Dynamics for Therapeutic Applications

The complex relationship between microbiota, human physiology, and environmental perturbations has become a major research focus, particularly with the arrival of culture-free and high-throughput approaches for studying the microbiome. Early enthusiasm has come from results that are largely correlative, but the correlative phase of microbiome research has assisted in defining the key questions of how these microbiota interact with their host. An emerging repertoire for engineering the microbiome places current research on a more experimentally grounded footing. We present a detailed look at the interplay between microbiota and host and how these interactions can be exploited. A particular emphasis is placed on unstable microbial communities, or dysbiosis, and strategies to reestablish stability in these microbial ecosystems. These include manipulation of intermicrobial communication, development of designer probiotics, fecal microbiota transplantation, and synthetic biology.

Long-Term Urban Market Dynamics Reveal Increased Bushmeat Carcass Volume despite Economic Growth and Proactive Environmental Legislation on Bioko Island, Equatorial Guinea

Bushmeat hunting is extensive in west and central Africa as both a means for subsistence and for commercial gain. Commercial hunting represents one of the primary threats to wildlife in the region, and confounding factors have made it challenging to examine how external factors influence the commercial bushmeat trade. Bioko Island, Equatorial Guinea is a small island with large tracts of intact forest that support sizeable populations of commercially valuable vertebrates, especially endemic primates. The island also has a low human population and has experienced dramatic economic growth and rapid development since the mid-1990's. From October 1997 - September 2010, we monitored the largest bushmeat market on Bioko in Malabo, recording over 197,000 carcasses for sale. We used these data to analyze the dynamics of the market in relation to political events, environmental legislation, and rapid economic growth. Our findings suggest that bushmeat hunting and availability increased in parallel with the growth of Equatorial Guinea's GDP and disposable income of its citizens. During this 13-year study, the predominant mode of capture shifted from trapping to shotguns. Consequently, carcass volume and rates of taxa typically captured with shotguns increased significantly, most notably including intensified hunting of Bioko's unique and endangered monkey fauna. Attempts to limit bushmeat sales, including a 2007 ban on primate hunting and trade, were only transiently effective. The hunting ban was not enforced, and was quickly followed by a marked increase in bushmeat hunting compared to hunting rates prior to the ban. Our results emphasize the negative impact that rapid development and unenforced legislation have had on Bioko's wildlife, and demonstrate the need for strong governmental support if conservation strategies are to be successful at preventing extinctions of tropical wildlife.

Renin-angiotensin-aldosterone system inhibitors in pediatric focal segmental glomerulosclerosis

BACKGROUND

Conventional immunosuppressive therapy for primary pediatric focal segmental glomerulosclerosis (FSGS) is potentially toxic and only moderate evidence supports its effectiveness. Renin-angiotensin-aldosterone (RAAS) inhibition monotherapy is anecdotally used in selected patients as an alternative to conventional therapy.

METHODS

We performed a retrospective cohort study of children with primary FSGS seen at a tertiary care academic hospital between 1986 and 2008. We classified patients into two groups based upon initial treatment: RAAS inhibition monotherapy (RIM) and conventional therapy (CT). The primary endpoint was progression to end-stage renal disease (ESRD). Secondary endpoints were remission of proteinuria, relapse, and death.

RESULTS

The cohort consisted of 67 patients. Mean baseline urine protein/creatinine ratio (Up/c) was 8.0 (5.2, 10.7) mg/mg, and mean baseline estimated glomerular filtration rate (eGFR) was 115.0 (101.8, 128.1) mL/min/1.73 m(2). Patients in the RIM group were more likely to have lower eGFR (100.8 mL/min/1.73 m(2) vs 132.9 mL/min/1.73 m(2), p = 0.01) and less proteinuria (4.4 vs.14.4, p < 0.01). Renal failure occurred in 22.9% of the RIM group vs 40.6% in the CT group (log-rank p = 0.07). After adjustment for African-American race, time period of presentation, baseline age, eGFR, and Up/c, patients in the RIM group had a 0.11 hazard ratio of progressing to renal failure compared with patients in the CT group (p < 0.01).

CONCLUSIONS

Children treated initially with RIM may have better outcomes than those treated with CT.