A machine learning approach to identify clinical trials involving nanodrugs and nanodevices from ClinicalTrials.gov

BACKGROUND: Clinical Trials (CTs) are essential for bridging the gap between experimental research on new drugs and their clinical application. Just like CTs for traditional drugs and biologics have helped accelerate the translation of biomedical findings into medical practice, CTs for nanodrugs and nanodevices could advance novel nanomaterials as agents for diagnosis and therapy. Although there is publicly available information about nanomedicine-related CTs, the online archiving of this information is carried out without adhering to criteria that discriminate between studies involving nanomaterials or nanotechnology-based processes (nano), and CTs that do not involve nanotechnology (non-nano). Finding out whether nanodrugs and nanodevices were involved in a study from CT summaries alone is a challenging task. At the time of writing, CTs archived in the well-known online registry ClinicalTrials.gov are not easily told apart as to whether they are nano or non-nano CTs-even when performed by domain experts, due to the lack of both a common definition for nanotechnology and of standards for reporting nanomedical experiments and results. METHODS: We propose a supervised learning approach for classifying CT summaries from ClinicalTrials.gov according to whether they fall into the nano or the non-nano categories. Our method involves several stages: i) extraction and manual annotation of CTs as nano vs. non-nano, ii) pre-processing and automatic classification, and iii) performance evaluation using several state-of-the-art classifiers under different transformations of the original dataset. RESULTS AND CONCLUSIONS: The performance of the best automated classifier closely matches that of experts (AUC over 0.95), suggesting that it is feasible to automatically detect the presence of nanotechnology products in CT summaries with a high degree of accuracy. This can significantly speed up the process of finding whether reports on ClinicalTrials.gov might be relevant to a particular nanoparticle or nanodevice, which is essential to discover any precedents for nanotoxicity events or advantages for targeted drug therapy.

Identifying the semantics of eligibility criteria of clinical trials based on relevant medical ontologies

An important objective of the INTEGRATE project1 is to build tools that support the efficient execution of post-genomic multi-centric clinical trials in breast cancer, which includes the automatic assessment of the eligibility of patients for available trials. The population suited to be enrolled in a trial is described by a set of free-text eligibility criteria that are both syntactically and semantically complex. At the same time, the assessment of the eligibility of a patient for a trial requires the (machineprocessable) understanding of the semantics of the eligibility criteria in order to further evaluate if the patient data available for example in the hospital EHR satisfies these criteria. This paper presents an analysis of the semantics of the clinical trial eligibility criteria based on relevant medical ontologies in the clinical research domain: SNOMED-CT, LOINC, MedDRA. We detect subsets of these widely-adopted ontologies that characterize the semantics of the eligibility criteria of trials in various clinical domains and compare these sets. Next, we evaluate the occurrence frequency of the concepts in the concrete case of breast cancer (which is our first application domain) in order to provide meaningful priorities for the task of binding/mapping these ontology concepts to the actual patient data. We further assess the effort required to extend our approach to new domains in terms of additional semantic mappings that need to be developed.

Iterative determination of clinical beam phase space from dose measurements

Monte Carlo (MC) method can accurately compute the dose produced by medical linear accelerators. However, these calculations require a reliable description of the electron and/or photon beams delivering the dose, the phase space (PHSP), which is not usually available. A method to derive a phase space model from reference measurements that does not heavily rely on a detailed model of the accelerator head is presented. The iterative optimization process extracts the characteristics of the particle beams which best explains the reference dose measurements in water and air, given a set of constrains

Tenerife South Airport (Phase III)

An architecture of light and shadows is proposed for this airport for the twenty-first century. A great concrete and stone box to frame the incredible view south towards a red mountain that rests Sphinx-like over the Atlantic. = Se propone para este aeropuerto para el siglo XXI una arquitectura construída con la luz y con las sombras. Una gran caja de hormigón que enmarca un maravilloso paisaje: el océano atlántico al sur con la montaña roja que se acuesta sobre el mar como si de una esfinge se tratara.

Supporting patient screening to identify suitable clinical trials.

To support the efficient execution of post-genomic multi-centric clinical trials in breast cancer we propose a solution that streamlines the assessment of the eligibility of patients for available trials. The assessment of the eligibility of a patient for a trial requires evaluating whether each eligibility criterion is satisfied and is often a time consuming and manual task. The main focus in the literature has been on proposing different methods for modelling and formalizing the eligibility criteria. However the current adoption of these approaches in clinical care is limited. Less effort has been dedicated to the automatic matching of criteria to the patient data managed in clinical care. We address both aspects and propose a scalable, efficient and pragmatic patient screening solution enabling automatic evaluation of eligibility of patients for a relevant set of trials. This covers the flexible formalization of criteria and of other relevant trial metadata and the efficient management of these representations.

ACGT: advancing clinico-genomic trials on cancer - four years of experience.

The challenges regarding seamless integration of distributed, heterogeneous and multilevel data arising in the context of contemporary, post-genomic clinical trials cannot be effectively addressed with current methodologies. An urgent need exists to access data in a uniform manner, to share information among different clinical and research centers, and to store data in secure repositories assuring the privacy of patients. Advancing Clinico-Genomic Trials (ACGT) was a European Commission funded Integrated Project that aimed at providing tools and methods to enhance the efficiency of clinical trials in the -omics era. The project, now completed after four years of work, involved the development of both a set of methodological approaches as well as tools and services and its testing in the context of real-world clinico-genomic scenarios. This paper describes the main experiences using the ACGT platform and its tools within one such scenario and highlights the very promising results obtained.

Implementación del modelo RIM de HL7 v3 en orientación a objetos y su uso en procesos de interoperabilidad semántica

El trabajo ha sido realizado dentro del marco de los proyectos EURECA (Enabling information re-Use by linking clinical REsearch and Care) e INTEGRATE (Integrative Cancer Research Through Innovative Biomedical Infrastructures), en los que colabora el Grupo de Informática Biomédica de la UPM junto a otras universidades e instituciones sanitarias europeas. En ambos proyectos se desarrollan servicios e infraestructuras con el objetivo principal de almacenar información clínica, procedente de fuentes diversas (como por ejemplo de historiales clínicos electrónicos de hospitales, de ensayos clínicos o artículos de investigación biomédica), de una forma común y fácilmente accesible y consultable para facilitar al máximo la investigación de estos ámbitos, de manera colaborativa entre instituciones. Esta es la idea principal de la interoperabilidad semántica en la que se concentran ambos proyectos, siendo clave para el correcto funcionamiento del software del que se componen. El intercambio de datos con un modelo de representación compartido, común y sin ambigüedades, en el que cada concepto, término o dato clínico tendrá una única forma de representación. Lo cual permite la inferencia de conocimiento, y encaja perfectamente en el contexto de la investigación médica. En concreto, la herramienta a desarrollar en este trabajo también está orientada a la idea de maximizar la interoperabilidad semántica, pues se ocupa de la carga de información clínica con un formato estandarizado en un modelo común de almacenamiento de datos, implementado en bases de datos relacionales. El trabajo ha sido desarrollado en el periodo comprendido entre el 3 de Febrero y el 6 de Junio de 2014. Se ha seguido un ciclo de vida en cascada para la organización del trabajo realizado en las tareas de las que se compone el proyecto, de modo que una fase no puede iniciarse sin que se haya terminado, revisado y aceptado la fase anterior. Exceptuando la tarea de documentación del trabajo (para la elaboración de esta memoria), que se ha desarrollado paralelamente a todas las demás. ----ABSTRACT--- The project has been developed during the second semester of the 2013/2014 academic year. This Project has been done inside EURECA and INTEGRATE European biomedical research projects, where the GIB (Biomedical Informatics Group) of the UPM works as a partner. Both projects aim is to develop platforms and services with the main goal of storing clinical information (e.g. information from hospital electronic health records (EHRs), clinical trials or research articles) in a common way and easy to access and query, in order to support medical research. The whole software environment of these projects is based on the idea of semantic interoperability, which means the ability of computer systems to exchange data with unambiguous and shared meaning. This idea allows knowledge inference, which fits perfectly in medical research context. The tool to develop in this project is also "semantic operability-oriented". Its purpose is to store standardized clinical information in a common data model, implemented in relational databases. The project has been performed during the period between February 3rd and June 6th, of 2014. It has followed a "Waterfall model" of software development, in which progress is seen as flowing steadily downwards through its phases. Each phase starts when its previous phase has been completed and reviewed. The task of documenting the project‟s work is an exception; it has been performed in a parallel way to the rest of the tasks.

Desarrollo de un proceso de normalización semántica de bases de datos en ensayos clínicos

El trabajo se enmarca dentro de los proyecto INTEGRATE y EURECA, cuyo objetivo es el desarrollo de una capa de interoperabilidad semántica que permita la integración de datos e investigación clínica, proporcionando una plataforma común que pueda ser integrada en diferentes instituciones clínicas y que facilite el intercambio de información entre las mismas. De esta manera se promueve la mejora de la práctica clínica a través de la cooperación entre instituciones de investigación con objetivos comunes. En los proyectos se hace uso de estándares y vocabularios clínicos ya existentes, como pueden ser HL7 o SNOMED, adaptándolos a las necesidades particulares de los datos con los que se trabaja en INTEGRATE y EURECA. Los datos clínicos se representan de manera que cada concepto utilizado sea único, evitando ambigüedades y apoyando la idea de plataforma común. El alumno ha formado parte de un equipo de trabajo perteneciente al Grupo de Informática de la UPM, que a su vez trabaja como uno de los socios de los proyectos europeos nombrados anteriormente. La herramienta desarrollada, tiene como objetivo realizar tareas de homogenización de la información almacenada en las bases de datos de los proyectos haciendo uso de los mecanismos de normalización proporcionados por el vocabulario médico SNOMED-CT. Las bases de datos normalizadas serán las utilizadas para llevar a cabo consultas por medio de servicios proporcionados en la capa de interoperabilidad, ya que contendrán información más precisa y completa que las bases de datos sin normalizar. El trabajo ha sido realizado entre el día 12 de Septiembre del año 2014, donde comienza la etapa de formación y recopilación de información, y el día 5 de Enero del año 2015, en el cuál se termina la redacción de la memoria. El ciclo de vida utilizado ha sido el de desarrollo en cascada, en el que las tareas no comienzan hasta que la etapa inmediatamente anterior haya sido finalizada y validada. Sin embargo, no todas las tareas han seguido este modelo, ya que la realización de la memoria del trabajo se ha llevado a cabo de manera paralela con el resto de tareas. El número total de horas dedicadas al Trabajo de Fin de Grado es 324. Las tareas realizadas y el tiempo de dedicación de cada una de ellas se detallan a continuación:  Formación. Etapa de recopilación de información necesaria para implementar la herramienta y estudio de la misma [30 horas.  Especificación de requisitos. Se documentan los diferentes requisitos que ha de cumplir la herramienta [20 horas].  Diseño. En esta etapa se toman las decisiones de diseño de la herramienta [35 horas].  Implementación. Desarrollo del código de la herramienta [80 horas].  Pruebas. Etapa de validación de la herramienta, tanto de manera independiente como integrada en los proyectos INTEGRATE y EURECA [70 horas].  Depuración. Corrección de errores e introducción de mejoras de la herramienta [45 horas].  Realización de la memoria. Redacción de la memoria final del trabajo [44 horas].---ABSTRACT---This project belongs to the semantic interoperability layer developed in the European projects INTEGRATE and EURECA, which aims to provide a platform to promote interchange of medical information from clinical trials to clinical institutions. Thus, research institutions may cooperate to enhance clinical practice. Different health standards and clinical terminologies has been used in both INTEGRATE and EURECA projects, e.g. HL7 or SNOMED-CT. These tools have been adapted to the projects data requirements. Clinical data are represented by unique concepts, avoiding ambiguity problems. The student has been working in the Biomedical Informatics Group from UPM, partner of the INTEGRATE and EURECA projects. The tool developed aims to perform homogenization tasks over information stored in databases of the project, through normalized representation provided by the SNOMED-CT terminology. The data query is executed against the normalized version of the databases, since the information retrieved will be more informative than non-normalized databases. The project has been performed from September 12th of 2014, when initiation stage began, to January 5th of 2015, when the final report was finished. The waterfall model for software development was followed during the working process. Therefore, a phase may not start before the previous one finishes and has been validated, except from the final report redaction, which has been carried out in parallel with the others phases. The tasks that have been developed and time for each one are detailed as follows:  Training. Gathering the necessary information to develop the tool [30 hours].  Software requirement specification. Requirements the tool must accomplish [20 hours].  Design. Decisions on the design of the tool [35 hours].  Implementation. Tool development [80 hours].  Testing. Tool evaluation within the framework of the INTEGRATE and EURECA projects [70 hours].  Debugging. Improve efficiency and correct errors [45 hours].  Documenting. Final report elaboration [44 hours].