Model and Strategy for Predicting and Discovering Drug-Drug Interactions.

Taking several medications at the same time is an increasingly common phenomenon in our society. The combination of drugs is certainly not without risk of potentially dangerous interactions. Taking into account all possible interactions is a very complex task as it is not yet known what all possible interactions between drugs and their types are. Machine learning based models have been developed to help with this task. However, the output of these models is not structured enough to be integrated in a clinical reasoning process on interactions. In this work, we propose a clinically relevant and technically feasible model and strategy for drug interactions.

Early Prediction of All-Cause Clinical Deterioration in General Wards Patients: Development and Validation of a Biomarker-Based Machine Learning Model Derived From Rapid Response Team Activations.

OBJECTIVE: The aim of the study is to evaluate the performance of a biomarker-based machine learning (ML) model (not including vital signs) derived from reviewed rapid response team (RRT) activations in predicting all-cause deterioration in general wards patients. DESIGN: This is a retrospective single-institution study. All consecutive adult patients' cases on noncritical wards identified by RRT calls occurring at least 24 hours after patient admission, between April 2018 and June 2020, were included. The cases were reviewed and labeled for clinical deterioration by a multidisciplinary expert consensus panel. A supervised learning approach was adopted based on a set of biomarkers and demographic data available in the patient's electronic medical record (EMR). SETTING: The setting is a 250-bed tertiary university hospital with a basic EMR, with adult (>18 y) patients on general wards. PATIENTS: The study analyzed the cases of 514 patients for which the RRT was activated. Rapid response teams were extracted from the hospital telephone log data. Two hundred eighteen clinical deterioration cases were identified in these patients after expert chart review and complemented by 146 "nonevent" cases to build the training and validation data set. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: The best performance was achieved with the random forests algorithm, with a maximal area under the receiver operating curve of 0.90 and F1 score of 0.85 obtained at prediction time T0-6h, slightly decreasing but still acceptable (area under the receiver operating curve, >0.8; F1 score, >0.75) at T0-42h. The system outperformed most classical track-and-trigger systems both in terms of prediction performance and prediction horizon. CONCLUSIONS: In hospitals with a basic EMR, a biomarker-based ML model could be used to predict clinical deterioration in general wards patients earlier than classical track-and-trigger systems, thus enabling appropriate clinical interventions for patient safety and improved outcomes.

A Qualitative Method for Learning Medical Expert Reasoning.

The aim of this paper is to propose a qualitative method for learning a model that represents the closest possible experts reasoning and strategies to provide recommendations of antibiotics. The learned model contains an integrity constraint and a preference formula. The former indicates the features that an antibiotic should have to be recommended. The later indicates the rank of recommendation of an antibiotic.

Speak-PIM, Towards a Framework for the Automatic Detection of Potentially Inappropriate Prescriptions.

Potentially inappropriate medications (PIMs) have adverse health consequences, particularly in elderly patients. Various explicit criteria have been developed to detect PIMs. However, it is difficult to apply these criteria without the help of an electronic decision support tool. Programming these tools can be very complex. Indeed, for computer scientists it is difficult to understand medical issues and for clinicians it is difficult to program in a computer programming language. In this work we present Speak-PIM, a framework for formalizing the PIM's rules. Speak-PIM is based on a very simple semantics which is suitable for the declaration of PIMs without embarking on all the complexity of description logic or computer languages. It aims to offer an efficient collaboration between the computer scientists and clinicians.

Genetic diversity and connectivity of the Ostreid herpesvirus 1 populations in France: A first attempt to phylogeographic inference for a marine mollusc disease.

The genetic diversity of viral populations is a key driver of the spatial and temporal diffusion of viruses; yet, studying the diversity of whole genomes from natural populations still remains a challenge. Phylodynamic approaches are commonly used for RNA viruses harboring small genomes but have only rarely been applied to DNA viruses with larger genomes. Here, we used the Pacific oyster mortality syndrome (a disease that affects oyster farms around the world) as a model to study the genetic diversity of its causative agent, the Ostreid herpesvirus 1 (OsHV-1) in the three main French oyster-farming areas. Using ultra-deep sequencing on individual moribund oysters and an innovative combination of bioinformatics tools, we de novo assembled twenty-one OsHV-1 new genomes. Combining quantification of major and minor genetic variations, phylogenetic analysis, and ancestral state reconstruction of discrete traits approaches, we assessed the connectivity of OsHV-1 viral populations between the three oyster-farming areas. Our results suggest that the Marennes-Oléron Bay represents the main source of OsHV-1 diversity, from where the virus has dispersed to other farming areas, a scenario consistent with current practices of oyster transfers in France. We demonstrate that phylodynamic approaches can be applied to aquatic DNA viruses to determine how epidemiological, immunological, and evolutionary processes act and potentially interact to shape their diversity patterns.

Decision-support systems for managing polypharmacy in the elderly: A scoping review.

Polypharmacy, the consuming of more than five drugs, is a public health problem. It can lead to many interactions and adverse drug reactions and is very expensive. Therapeutic guidelines for managing polypharmacy in the elderly have been issued, but are highly complex, limiting their use. Decision-support systems have therefore been developed to automate the execution of these guidelines, or to provide information about drugs adapted to the context of polypharmacy. These systems differ widely in terms of their technical design, knowledge sources and evaluation methods. We present here a scoping review of electronic systems for supporting the management, by healthcare providers, of polypharmacy in elderly patients. Most existing reviews have focused mainly on evaluation results, whereas the present review also describes the technical design of these systems and the methodologies for developing and evaluating them. A systematic bibliographic search identified 19 systems differing considerably in terms of their technical design (rule-based systems, documentary approach, mixed); outputs (textual report, alerts and/or visual approaches); and evaluations (impact on clinical practices, impact on patient outcomes, efficiency and/or user satisfaction). The evaluations performed are minimal (among all the systems identified, only one system has been evaluated according to all the criteria mentioned above) and no machine learning systems and/or conflict management systems were retrieved. This review highlights the need to develop new methodologies, combining various approaches for decision support system in polypharmacy.

ABiMed: Towards an Innovative Clinical Decision Support System for Medication Reviews and Polypharmacy Management.

Polypharmacy in elderly is a public health problem with both clinical (increase of adverse drug events) and economic issues. One solution is medication review, a structured assessment of patients' drug orders by the pharmacist for optimizing the therapy. However, this task is tedious, cognitively complex and error-prone, and only a few clinical decision support systems have been proposed for supporting it. Existing systems are either rule-based systems implementing guidelines, or documentary systems presenting drug knowledge. In this paper, we present the ABiMed research project, and, through literature reviews and brainstorming, we identified five candidate innovations for a decision support system for medication review: patient data transfer from GP to pharmacists, use of semantic technologies, association of rule-based and documentary approaches, use of machine learning, and a two-way discussion between pharmacist and GP after the medication review.

Automated Clinical Practice Guideline Recommendations for Hereditary Cancer Risk Using Chatbots and Ontologies: System Description.

BACKGROUND: Identifying patients at risk of hereditary cancer based on their family health history is a highly nuanced task. Frequently, patients at risk are not referred for genetic counseling as providers lack the time and training to collect and assess their family health history. Consequently, patients at risk do not receive genetic counseling and testing that they need to determine the preventive steps they should take to mitigate their risk. OBJECTIVE: This study aims to automate clinical practice guideline recommendations for hereditary cancer risk based on patient family health history. METHODS: We combined chatbots, web application programming interfaces, clinical practice guidelines, and ontologies into a web service-oriented system that can automate family health history collection and assessment. We used Owlready2 and Protégé to develop a lightweight, patient-centric clinical practice guideline domain ontology using hereditary cancer criteria from the American College of Medical Genetics and Genomics and the National Cancer Comprehensive Network. RESULTS: The domain ontology has 758 classes, 20 object properties, 23 datatype properties, and 42 individuals and encompasses 44 cancers, 144 genes, and 113 clinical practice guideline criteria. So far, it has been used to assess >5000 family health history cases. We created 192 test cases to ensure concordance with clinical practice guidelines. The average test case completes in 4.5 (SD 1.9) seconds, the longest in 19.6 seconds, and the shortest in 2.9 seconds. CONCLUSIONS: Web service-enabled, chatbot-oriented family health history collection and ontology-driven clinical practice guideline criteria risk assessment is a simple and effective method for automating hereditary cancer risk screening.

Prevalence and polymorphism of a mussel transmissible cancer in Europe.

Transmissible cancers are parasitic malignant cell lineages that have acquired the ability to infect new hosts from the same species, or sometimes related species. First described in dogs and Tasmanian devils, transmissible cancers were later discovered in some marine bivalves affected by a leukaemia-like disease. In Mytilus mussels, two lineages of bivalve transmissible neoplasia (BTN) have been described to date (MtrBTN1 and MtrBTN2), both of which emerged in a Mytilus trossulus founder individual. Here, we performed extensive screening of genetic chimerism, a hallmark of transmissible cancer, by genotyping 106 single nucleotide polymorphisms of 5,907 European Mytilus mussels. Genetic analysis allowed us to simultaneously obtain the genotype of hosts - Mytilus edulis, M. galloprovincialis or hybrids - and the genotype of tumours of heavily infected individuals. In addition, a subset of 222 individuals were systematically genotyped and analysed by histology to screen for possible nontransmissible cancers. We detected MtrBTN2 at low prevalence in M. edulis, and also in M. galloprovincialis and hybrids although at a much lower prevalence. No MtrBTN1 or new BTN were found, but eight individuals with nontransmissible neoplasia were observed at a single polluted site on the same sampling date. We observed a diversity of MtrBTN2 genotypes that appeared more introgressed or more ancestral than MtrBTN1 and reference healthy M. trossulus individuals. The observed polymorphism is probably due to somatic null alleles caused by structural variations or point mutations in primer-binding sites leading to enhanced detection of the host alleles. Despite low prevalence, two sublineages divergent by 10% fixed somatic null alleles and one nonsynonymous mtCOI (mitochondrial cytochrome oxidase I) substitution are cospreading in the same geographical area, suggesting a complex diversification of MtrBTN2 since its emergence and host species shift.

Differences in chemical contaminants bioaccumulation and ecotoxicology biomarkers in Mytilus edulis and Mytilus galloprovincialis and their hybrids.

The Mytilus mussels are spread all over the world and many related species coexist in several areas and can produce hybrid offspring. Mussels have been used for decades in national and international programs to monitor chemical contamination in the environment. Differences in bioaccumulation and biotransformation abilities between species and their hybrids should be evaluated to assess the comparability of the results obtained within the international biomonitoring programs. The objective of this study was to characterize bioaccumulation abilities and biomarker responses in Mytilus edulis, Mytilus galloprovincialis and their hybrids via an in situ transplantation experimentation on their progenies. Four mussel groups (M. edulis, M. galloprovincialis and two hybrids batches) issued from genetically characterized parents were transplanted for one year in Charente Maritime (France) to ensure their exposure to identical sources of contamination. The bioaccumulation of several families of contaminants (trace metals, polycyclic aromatic hydrocarbons, polybrominated diphenyl ethers, polychlorinated biphenyls), the response of several biomarkers (DNA strand breaks level, lysosomal membrane stability, metallothionein content, acetylcholine esterase activity) and some physiological parameters (growth, mortality, gonadal development), were analyzed. Differences were observed between species, however they were contaminant-specific. Variations in contaminants levels were observed between progenies, with higher levels of Cu, PBDE, PCB in M. edulis, and higher levels of Cd, Hg, Zn in M galloprovincialis. This study demonstrated that variations in contaminant bioaccumulation and different biomarker responses exist between Mytilus species in the field. Data on species or the presence of hybrid individuals (or introgression) is an important additional parameter to add to biomonitoring programs databases.

Gonadal transcriptomes associated with sex phenotypes provide potential male and female candidate genes of sex determination or early differentiation in Crassostrea gigas, a sequential hermaphrodite mollusc.

BACKGROUND: In the animal kingdom, mollusca is an important phylum of the Lophotrochozoa. However, few studies have investigated the molecular cascade of sex determination/early gonadal differentiation within this phylum. The oyster Crassostrea gigas is a sequential irregular hermaphrodite mollusc of economic, physiological and phylogenetic importance. Although some studies identified genes of its sex-determining/-differentiating pathway, this particular topic remains to be further deepened, in particular with regard to the expression patterns. Indeed, these patterns need to cover the entire period of sex lability and have to be associated to future sex phenotypes, usually impossible to establish in this sequential hermaphrodite. This is why we performed a gonadal RNA-Seq analysis of diploid male and female oysters that have not changed sex for 4 years, sampled during the entire time-window of sex determination/early sex differentiation (stages 0 and 3 of the gametogenetic cycle). This individual long-term monitoring gave us the opportunity to explain the molecular expression patterns in the light of the most statistically likely future sex of each oyster. RESULTS: The differential gene expression analysis of gonadal transcriptomes revealed that 9723 genes were differentially expressed between gametogenetic stages, and 141 between sexes (98 and 43 genes highly expressed in females and males, respectively). Eighty-four genes were both stage- and sex-specific, 57 of them being highly expressed at the time of sex determination/early sex differentiation. These 4 novel genes including Trophoblast glycoprotein-like, Protein PML-like, Protein singed-like and PREDICTED: paramyosin, while being supported by RT-qPCR, displayed sexually dimorphic gene expression patterns. CONCLUSIONS: This gonadal transcriptome analysis, the first one associated with sex phenotypes in C. gigas, revealed 57 genes highly expressed in stage 0 or 3 of gametogenesis and which could be linked to the future sex of the individuals. While further study will be needed to suggest a role for these factors, some could certainly be original potential actors involved in sex determination/early sex differentiation, like paramyosin and could be used to predict the future sex of oysters.

Genomic Diversity of the Ostreid Herpesvirus Type 1 Across Time and Location and Among Host Species.

The mechanisms underlying virus emergence are rarely well understood, making the appearance of outbreaks largely unpredictable. This is particularly true for pathogens with low per-site mutation rates, such as DNA viruses, that do not exhibit a large amount of evolutionary change among genetic sequences sampled at different time points. However, whole-genome sequencing can reveal the accumulation of novel genetic variation between samples, promising to render most, if not all, microbial pathogens measurably evolving and suitable for analytical techniques derived from population genetic theory. Here, we aim to assess the measurability of evolution on epidemiological time scales of the Ostreid herpesvirus 1 (OsHV-1), a double stranded DNA virus of which a new variant, OsHV-1 µVar, emerged in France in 2008, spreading across Europe and causing dramatic economic and ecological damage. We performed phylogenetic analyses of heterochronous (n = 21) OsHV-1 genomes sampled worldwide. Results show sufficient temporal signal in the viral sequences to proceed with phylogenetic molecular clock analyses and they indicate that the genetic diversity seen in these OsHV-1 isolates has arisen within the past three decades. OsHV-1 samples from France and New Zealand did not cluster together suggesting a spatial structuration of the viral populations. The genome-wide study of simple and complex polymorphisms shows that specific genomic regions are deleted in several isolates or accumulate a high number of substitutions. These contrasting and non-random patterns of polymorphism suggest that some genomic regions are affected by strong selective pressures. Interestingly, we also found variant genotypes within all infected individuals. Altogether, these results provide baseline evidence that whole genome sequencing could be used to study population dynamic processes of OsHV-1, and more broadly herpesviruses.

Visual Comparison of Guidelines: Method and Application to Potentially Inappropriate Medication Lists.

Therapeutic guidelines developed by experts are essential tools for improving therapy and drug prescription. Several guidelines often exist that target the same patient, from different organizations and countries. The case of lists for the detection of potentially inappropriate medications (PIMs) is an example which illustrates how these guidelines can be varied and multiple. In order to have an overview to the divergences and similarities between different lists of PIMs, we propose a visual method to compare PIMs lists, based on set visualization, and we apply it to 5 guidelines.

A data science approach to drug safety: Semantic and visual mining of adverse drug events from clinical trials of pain treatments.

Clinical trials are the basis of Evidence-Based Medicine. Trial results are reviewed by experts and consensus panels for producing meta-analyses and clinical practice guidelines. However, reviewing these results is a long and tedious task, hence the meta-analyses and guidelines are not updated each time a new trial is published. Moreover, the independence of experts may be difficult to appraise. On the contrary, in many other domains, including medical risk analysis, the advent of data science, big data and visual analytics allowed moving from expert-based to fact-based knowledge. Since 12 years, many trial results are publicly available online in trial registries. Nevertheless, data science methods have not yet been applied widely to trial data. In this paper, we present a platform for analyzing the safety events reported during clinical trials and published in trial registries. This platform is based on an ontological model including 582 trials on pain treatments, and uses semantic web technologies for querying this dataset at various levels of granularity. It also relies on a 26-dimensional flower glyph for the visualization of the Adverse Drug Events (ADE) rates in 13 categories and 2 levels of seriousness. We illustrate the interest of this platform through several use cases and we were able to find back conclusions that were initially found during meta-analyses. The platform was presented to four experts in drug safety, and is publicly available online, with the ontology of pain treatment ADE.

How to interact with medical terminologies? Formative usability evaluations comparing three approaches for supporting the use of MedDRA by pharmacovigilance specialists.

BACKGROUND: Medical terminologies are commonly used in medicine. For instance, to answer a pharmacovigilance question, pharmacovigilance specialists (PVS) search in a pharmacovigilance database for reports in relation to a given drug. To do that, they first need to identify all MedDRA terms that might have been used to code an adverse reaction in the database, but terms may be numerous and difficult to select as they may belong to different parts of the hierarchy. In previous studies, three tools have been developed to help PVS identify and group all relevant MedDRA terms using three different approaches: forms, structured query-builder, and icons. Yet, a poor usability of the tools may increase PVS' workload and reduce their performance. This study aims to evaluate, compare and improve the three tools during two rounds of formative usability evaluation. METHODS: First, a cognitive walkthrough was performed. Based on the design recommendations obtained from this evaluation, designers made modifications to their tools to improve usability. Once this re-engineering phase completed, six PVS took part in a usability test: difficulties, errors and verbalizations during their interaction with the three tools were collected. Their satisfaction was measured through the System Usability Scale. The design recommendations issued from the tests were used to adapt the tools. RESULTS: All tools had usability problems related to the lack of guidance in the graphical user interface (e.g., unintuitive labels). In two tools, the use of the SNOMED CT to find MedDRA terms hampered their use because French PVS were not used to it. For the most obvious and common terms, the icons-based interface would appear to be more useful. For the less frequently used MedDRA terms or those distributed in different parts of the hierarchy, the structured query-builder would be preferable thanks to its great power and flexibility. The form-based tool seems to be a compromise. CONCLUSION: These evaluations made it possible to identify the strengths of each tool but also their weaknesses to address them before further evaluation. Next step is to assess the acceptability of tools and the expressiveness of their results to help identify and group MedDRA terms.

Implementation of an ontological reasoning to support the guideline-based management of primary breast cancer patients in the DESIREE project.

The DESIREE project has developed a platform offering several complementary therapeutic decision support modules to improve the quality of care for breast cancer patients. All modules are operating consistently with a common breast cancer knowledge model (BCKM) following the generic entity-attribute-value model. The BCKM is formalized as an ontology including both the data model to represent clinical patient information and the termino-ontological model to represent the application domain concepts. This ontological model is used to describe data semantics and to allow for reasoning at different levels of abstraction. We present the guideline-based decision support module (GL-DSS). Three breast cancer clinical practice guidelines have been formalized as decision rules including evidence levels, conformance levels, and two types of dependency, "refinement" and "complement", used to build complete care plans from the reconciliation of atomic recommendations. The system has been assessed on 138 decisions previously made without the system and re-played with the system after a washout period on simulated tumor boards (TBs) in three pilot sites. When TB clinicians changed their decision after using the GL-DSS, it was for a better decision than the decision made without the system in 75 % of the cases.

Comparison of Machine Learning Algorithms for Classifying Adverse-Event Related 30-Day Hospital Readmissions: Potential Implications for Patient Safety.

Studies in the last decade have focused on identifying patients at risk of readmission using predictive models, in an objective to decrease costs to the healthcare system. However, real-time models specifically identifying readmissions related to hospital adverse-events are still to be elaborated. A supervised learning approach was adopted using different machine learning algorithms based on features available directly from the hospital information system and on a validated dataset elaborated by a multidisciplinary expert consensus panel. Accuracy results upon testing were in line with comparable studies, and variable across algorithms, with the highest prediction given by Artificial Neuron Networks. Features importances relative to the prediction were identified, in order to provide better representation and interpretation of results. Such a model can pave the way to predictive models for readmissions related to patient harm, the establishment of a learning platform for clinical quality measurement and improvement, and in some cases for an improved clinical management of readmitted patients.

Iconic Visualization of Sickle Cell Patients Current and Past Health Status.

Rapid access to patient overall health status is essential for a physician during a medical consultation. The use of a HIS for the management of neonatal screening and follow-up of sickle cell disease patients at CERPAD in the Saint-Louis region of Senegal leads the patient electronic records growing in volume and complexity. To facilitate access to relevant information and shortens the time required to analyze and understand these clinical data, an original solution is to set up a data visualization system. In this article, we propose the integration of two iconic visualization tools into the SIMENS-CERPAD module designed for sickle cell screening and healthcare. The two tools use the VCM iconic language and consist of a simplified anatomical schema showing the current health status of the patient and a timeline to visualize its temporal evolution.

Visualization of Potential Drug Synergies.

Drug synergy must be taken into account when prescribing several drugs for treating the same disorder. Synergies are sometimes known from clinical trials, but they are not systematically studied. In this paper, we present a visual approach for identifying and explaining the potential synergies between the 2-15 drugs available for a given disorder. It is based on the chaining of two bioinformatics databases, Drug Bank and Signor, and relies on set visualization with rainbow boxes. We apply this approach to antihypertensive drugs, and show that some European recommendations can be visually deduced and explained.

Visualization of Drug Interactions for Supporting Medication Review.

The number of elderly patients with multimorbidities has considerably increased since recent years. These patients are often polymedicated and at higher risk of safety incidents due to polypharmacy. To reduce polypharmacy, one solution is Medication review (MR). MR aimed at optimizing drug treatments, is unfortunately not very frequent in practice. Indeed, consulting the properties of 5-20 drugs in parallel is a cognitively complex task. It is therefore necessary to develop software for supporting MR. The existing tools only list alerts concerning drugs and their interactions. The objective of our work is to facilitate the pharmacist's access to the medical knowledge necessary for drug interactions. Using visual analytics, we propose an interactive tool that synthesizes information on drug interactions. It shows an overview of drug treatment and make it visually accessible by the pharmacist to facilitate MR.