Breast cancer (BC) is the most common cancer in women in Europe and worldwide, with a high prevalence in middle-aged and older women. The last years, the evolution in the existing treatment approaches have contributed to improved clinical outcomes and survival rates. Nevertheless, BC therapy-related cardiotoxicity, poses a severe impact in the short- and long-term Quality of Life (QoL) and associated survival of the BC patients. This study demonstrates how the CARDIOCARE platform and the developed risk stratification models provides healthcare professionals with a valuable tool for effectively managing BC patients, preventing treatment induced cardiotoxicity and improving their QoL. This is accomplished through the integration of multi-source patient-specific data from patient-oriented mobile applications and wearable sensors, and by the employment of beyond the state-of-the-art data mining and machine learning approaches.

The papers in this special section examine current advances on various fronts, focusing on reporting bioinformatics, analysis of molecular, genetic and/or clinical data pertaining to human cancer risk, prevention, outcomes or treatment response.

Cancer research has led to more cancer patients being cured, and many more enabled to live with their cancer. As such, some cancers are now considered a chronic disease, where patients and their families face the challenge to take an active role in their own care and in some cases in their treatment. To this direction the iManageCancer project aims to provide a cancer specific self-management platform designed according to the needs of patient groups while focusing, in parallel, on the wellbeing of the cancer patient. In this paper, we present the use-case requirements collected using a survey, a workshop and the analysis of three white papers and then we explain the corresponding system architecture. We describe in detail the main technological components of the designed platform, show the current status of development and we discuss further directions of research.

Successful implementation of meaningful Clinical Decision Support (CDS) solutions in healthcare has the potential to reduce the knowledge gap between clinical research and practice, especially in a complex genetic disease such as cancer. While significant effort has been invested in the implementation of tools for CDS in the last few decades, their uptake in the clinic has been limited. The barriers to adoption have been extensively discussed in the literature. In oncology, current CDS solutions are not able to support the complex decisions required for stratification and personalized treatment of patients and to keep up with the high rate of change in therapeutic options and knowledge. We propose a CDS framework that facilitates the implementation of decision support that flexibly integrates a large variety of clinical models and can bring to the clinic comprehensive solutions leveraging the latest available knowledge. We include both literature-based models and models built within the p-medicine research project using the available comprehensive datasets from clinical trials and care. The solution is open to the biomedical community, enabling the reuse of existing models for third-party CDS implementations and for the development of new models, and supporting collaboration among modelers, CDS implementers, biomedical researchers and clinicians. To increase adoption and support the complexity of patient management along the care continuum, we also propose to support and leverage the clinical processes defined and adhered to by healthcare organizations. We design an architecture that extends the CDS framework with workflow modeling and execution functionality to leverage the existing clinical processes. The knowledge models are embedded in the workflow models and executed at the right time, when and where the recommendation is needed in the clinical process. Next to supporting the decisions, this solution supports by default the decision processes as well and exploits the knowledge embedded in those processes.

As the volume of medical literature is growing rapidly, search engines implementing the basic information retrieval model often fail to address the information needs of the medical professionals. In this paper we propose a search tool that aims to capture the information need of the clinical user by including concepts from the context in the searching process. Three different approaches were implemented and evaluated, the pre-filtering, the query expansion and the reranking. The system also supports Collaborative Information Seeking (CIS) through algorithmic and User Interface (UI) interventions. The returned citations on a given query are reranked based on the ratings that team members have assigned for similar cases making use of the scoring proposed by the ISpy system. The results from the evaluation of the proposed tool show that pre-filtering performed better than the alternative contextualization search approaches in terms of precision.

Advances in the use of omic data and other biomarkers are increasing the number of variables in clinical research. Additional data have stratified the population of patients and require that current studies be performed among multiple institutions. Semantic interoperability and standardized data representation are a crucial task in the management of modern clinical trials. In the past few years, different efforts have focused on integrating biomedical information. Due to the complexity of this domain and the specific requirements of clinical research, the majority of data integration tasks are still performed manually. This paper presents a semantic normalization process and a query abstraction mechanism to facilitate data integration and retrieval. A process based on well-established standards from the biomedical domain and the latest semantic web technologies has been developed. Methods proposed in this paper have been tested within the EURECA EU research project, where clinical scenarios require the extraction of semantic knowledge from biomedical vocabularies. The aim of this paper is to provide a novel method to abstract from the data model and query syntax. The proposed approach has been compared with other initiatives in the field by storing the same dataset with each of those solutions. Results show an extended functionality and query capabilities at the cost of slightly worse performance in query execution. Implementations in real settings have shown that following this approach, usable interfaces can be developed to exploit clinical trial data outcomes.

Semantic interoperability is essential to facilitate efficient collaboration in heterogeneous multi-site healthcare environments. The deployment of a semantic interoperability solution has the potential to enable a wide range of informatics supported applications in clinical care and research both within as ingle healthcare organization and in a network of organizations. At the same time, building and deploying a semantic interoperability solution may require significant effort to carryout data transformation and to harmonize the semantics of the information in the different systems. Our approach to semantic interoperability leverages existing healthcare standards and ontologies, focusing first on specific clinical domains and key applications, and gradually expanding the solution when needed. An important objective of this work is to create a semantic link between clinical research and care environments to enable applications such as streamlining the execution of multi-centric clinical trials, including the identification of eligible patients for the trials. This paper presents an analysis of the suitability of several widely-used medical ontologies in the clinical domain: SNOMED-CT, LOINC, MedDRA, to capture the semantics of the clinical trial eligibility criteria, of the clinical trial data (e.g., Clinical Report Forms), and of the corresponding patient record data that would enable the automatic identification of eligible patients. Next to the coverage provided by the ontologies we evaluate and compare the sizes of the sets of relevant concepts and their relative frequency to estimate the cost of data transformation, of building the necessary semantic mappings, and of extending the solution to new domains. This analysis shows that our approach is both feasible and scalable.

The implementation of Clinical Decision Support (CDS) solutions is an important prerequisite for reducing the knowledge gap between clinical research and practice, especially in a complex genetic disease such as cancer. However, current CDS solutions are unable to support all the complex decisions required for personalized treatment of cancer patients and become quickly obsolete due to the high rate of change in therapeutic options and knowledge. Our CDS framework enables the development of decision support tools that flexibly integrate a large variety of multiscale models and can leverage the efforts of a large community of modellers. In our implementation, we combine community-developed models described in the literature (e.g. the St. Gallen stratification for early breast cancer) and models derived by mining the comprehensive datasets from clinical trials and care brought together in the p_Medicine collaborative research project. This framework and its underlying solution for models storage, management and execution will also constitute a platform for continuous validation of existing models on new data. Our goal is to enable the reuse of existing models for CDS and for the development of new models, and to support collaboration among modellers, CDS implementers, biomedical researchers and clinicians. We initially develop and deploy our solution in the context of the p-Medicine project in the oncology domain, but we aim to expand our scope and to reach out to a wide community of users in the biomedical area.

A substantial amount of clinical trials are subject to failure because they cannot recruit sufficient patients within the foreseen time and budget. Computer assisted evaluation of eligibility criteria is envisaged to improve the recruitment process by increasing coverage (i.e. making sure no eligible patients are `missed') and speeding up the eligibility scanning process; and thus eventually reduce the overall failure rate of clinical trials. In this paper a new recruitment application is presented which assists in evaluating eligibility criteria based on available clinical patient data (e.g. Electronic Health Record data). The application leverages for the querying of clinical data on a generic semantic integration platform and a new Domain Specific Language (DSL) based on the Groovy programming language.

Current research in oncology, require the involvement of several institutions participating in clinical trials. Heterogeneities of data formats and models require advanced methods to achieve semantic interoperability and provide sustainable solutions. In this field, the EU funded INTEGRATE project aims to develop the basic knowledge to allow data sharing of data from post-genomic clinical trials on breast cancer. In this paper, we describe the procedure implemented in this project and the required binding between relevant terminologies such as SNOMED CT and an HL7 v3 Reference Information Model (RIM)-based data model. After following the HL7 recommendations, we also describe the main issues of this process and the proposed solution, such as concept overlapping and coverage of the domain terminology. Despite the fact that the data from this domain presents a high level of heterogeneity, the methods and solutions introduced in this paper have been successfully applied within the INTEGRATE project context. Results suggest that the level of semantic interoperability required to manage patient data in modern clinical trials on breast cancer can be achieved with the proposed methodology.

An important objective of the INTEGRATE project1is 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 (machine-processable) 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.

The semi-automatic evaluation of eligibility criteria can facilitate the recruitment for clinical trials, timely completion of studies and generation of clinical evidence about new approaches to treatment, prevention and diagnosis. Because eligibility criteria are represented as free text, automatically extracting their meaning and evaluating them for a particular patient is challenging. This paper presents our approach to the problem of automatic interpretation of criteria meaning. It is based on detecting in text semantic entities (diseases, treatment, measurements etc.) using ontology annotators and semantic taggers, and detecting predefined patterns providing the contextual information in which these entities occur. Evaluation of the approach is the main subject of the paper. It covers several aspects: precision and recall of the pattern detection algorithm and the assessment of the implications of using the identified patterns to find potential candidates. It was performed manually using a subset of patterns and randomly selected 33 trials from ClinicalTrials.gov. The average precision and recall of pattern detection algorithm calculated for selected patterns is 0.9 and 0.91, meaning that in most cases using the patterns can lead to correct interpretation of criteria and can support patient recruitment.

DNA spectrograms express the periodicities of each of the four nucleotides A, T, C, and G in one or several genomic sequences to be analyzed. DNA spectral analysis can be applied to systematically investigate DNA patterns, which may correspond to relevant biological features. As opposed to looking at nucleotide sequences, spectrogram analysis may detect structural characteristics in very long sequences that are not identifiable by sequence alignment. Alignment of DNA spectrograms can be used to facilitate analysis of very long sequences or entire genomes at different resolutions. Standard clustering algorithms have been used in spectral analysis to find strong patterns in spectra. However, as they use a global distance metric, these algorithms can only detect strong patterns coexisting in several frequencies. In this paper, we propose a new method and several algorithms for aligning spectra suitable for efficient spectral analysis and allowing for the easy detection of strong patterns in both single frequencies and multiple frequencies.

DNA spectral analysis can be applied to systematically investigate DNA patterns, which may correspond to relevant biological features. As opposed to looking at nucleotide sequences, spectrogram analysis may detect structural characteristics in very long sequences that are not identifiable by sequence alignment. Clustering of DNA spectrograms can be used to perform spectral analysis of very large sequences or entire genomes, at different resolutions. Standard clustering algorithms have been used in spectral analysis to find strong patterns in spectra. However, as they use a global distance metric, those algorithms can only detect strong patterns coexisting in several frequencies. In this paper we propose a new method and several algorithms for aligning spectra suitable for efficient spectral analysis and allowing for the easy detection of strong patterns in both single frequencies and multiple frequencies.

Building multicluster systems out of multiple, geographically distributed clusters interconnected by high-speed wide-area networks can provide access to a larger computational power and to a wider range of resources. Jobs running on multiclusters and, more generally, in grids, may require (processor) coallocation, i.e., the simultaneous allocation of resources (processors) in different clusters or subsystems of a grid. In this paper, we propose four scheduling policies for processor coallocation in multiclusters, and we assess with simulations their performance under a wide variety of parameter settings. In particular, in our simulations we use synthetic workloads and workloads derived from the logs of actual systems and from runtime measurements. We conclude that although coallocation makes scheduling more difficult and the wide-area communication critically impacts the performance, there is a wide range of realistic applications that may benefit from coallocation. However, unrestricted coallocation is not recommended: Limiting the total job size or the number or the sizes of their components improves performance.

In systems consisting of multiple clusters of processors which are interconnected by relatively slow communication links and which employ space sharing for scheduling jobs, such as our Distributed ASCI Supercomputer (DAS), co-allocation, i.e., the simultaneous allocation of processors to single jobs in different clusters, may be required. We study the performance of co-allocation by means of simulations for the mean response time of jobs depending on the structure and sizes of jobs, the scheduling policy, and the communication speed ratio. Our main conclusion is that for current communication speed ratios in multiclusters, coallocation is a viable option.

In systems consisting of multiple clusters of processors which employ space sharing for scheduling jobs, such as our Distributed ASCI (Advanced School for Computing Imaging) Supercomputer (DAS), co-allocation, i.e., the simultaneous allocation of processors to single jobs in multiple clusters, may be required. In this paper we study the performance of several scheduling policies for co-allocating unordered requests in multiclusters with a workload derived from the DAS. We find that beside the policy, limiting the total job size significantly improves the performance, and that for a slowdown of jobs due to global communication bounded by 1.25, co-allocation is a viable choice.

In systems consisting of multiple clusters of processors interconnected by relatively slow communication links, co-allocation may be required. We study its performance by means of simulations, depending on the structure and sizes of jobs, and the communication speed ratio. We model a multicluster with C clusters of identical processors. The workload consists of rigid jobs that require fixed numbers of processors, possibly in multiple clusters simultaneously. A job is represented by a tuple of C values, each generated from a same distribution D. In an ordered request the positions of the components in the tuple specify the clusters from which the processors must be allocated. For an unordered request, by the components of the tuple the job only specifies the numbers of processors needed in the separate clusters. A flexible request specifies the total number of processors, obtained as the sum of the values in the tuple. For total requests, there is a single cluster and a request only specifies the total number of processors needed. All intracluster communication links have the same speed, as do all intercluster links. The communication speed ratio is the ratio between the time needed to complete a send operation between processors in different clusters and in the same cluster.

In systems consisting of multiple clusters of processors such as our Distributed ASCI Supercomputer (DAS), jobs may request co-allocation, i.e., the simultaneous allocation of processors in different clusters. We simulate such systems ignoring communication among the tasks of jobs, and determine the response times for different types and sizes of job requests, and for different numbers and sizes of clusters. In many cases we also compute or approximate the maximum utilization. We find that the numbers and sizes of the clusters and of the job components have a strong impact on performance, and that in many cases co-allocation is a viable choice.