Patrick Philipp

Toward cognitive pipelines of medical assistance algorithms

PurposeAssistance algorithms for medical tasks have great potential to support physicians with their daily work. However, medicine is also one of the most demanding domains for computer-based support systems, since medical assistance tasks are complex and the practical experience of the physician is crucial. Recent developments in the area of cognitive computing appear to be well suited to tackle medicine as an application domain.MethodsWe propose a system based on the idea of cognitive computing and consisting of auto-configurable medical assistance algorithms and their self-adapting combination. The system enables automatic execution of new algorithms, given they are made available as Medical Cognitive Apps and are registered in a central semantic repository. Learning components can be added to the system to optimize the results in the cases when numerous Medical Cognitive Apps are available for the same task. Our prototypical implementation is applied to the areas of surgical phase recognition based on sensor data and image progressing for tumor progression mappings.ResultsOur results suggest that such assistance algorithms can be automatically configured in execution pipelines, candidate results can be automatically scored and combined, and the system can learn from experience. Furthermore, our evaluation shows that the Medical Cognitive Apps are providing the correct results as they did for local execution and run in a reasonable amount of time.ConclusionThe proposed solution is applicable to a variety of medical use cases and effectively supports the automated and self-adaptive configuration of cognitive pipelines based on medical interpretation algorithms.

Context-Aware Entity Disambiguation in Text Using Markov Chains

In recent years, the amount of entities in large knowledge bases has been increasing rapidly. Such entities can help to bridge unstructured text with structured knowledge and thus be beneficial for many entity-centric applications. The key issue is to link entity mentions in text with entities in knowledge bases, where the main challenge lies in mention ambiguity. Many methods have been proposed to tackle this problem. However, most of the methods assume certain characteristics of the input mentions and documents, e.g., only named entities are considered. In this paper, we propose a context-aware approach to collective entity disambiguation of the input mentions in text with different characteristics in a consistent manner. We extensively evaluate the performance of our approach over 9 datasets and compare it with 14 state-of-the-art methods. Experimental results show that our approach outperforms the existing methods in most cases.

Towards an open-source semantic data infrastructure for integrating clinical and scientific data in cognition-guided surgery

In the surgical domain, individual clinical experience, which is derived in large part from past clinical cases, plays an important role in the treatment decision process. Simultaneously the surgeon has to keep track of a large amount of clinical data, emerging from a number of heterogeneous systems during all phases of surgical treatment. This is complemented with the constantly growing knowledge derived from clinical studies and literature. To recall this vast amount of information at the right moment poses a growing challenge that should be supported by adequate technology. While many tools and projects aim at sharing or integrating data from various sources or even provide knowledge-based decision support - to our knowledge - no concept has been proposed that addresses the entire surgical pathway by accessing the entire information in order to provide context-aware cognitive assistance. Therefore a semantic representation and central storage of data and knowledge is a fundamental requirement. We present a semantic data infrastructure for integrating heterogeneous surgical data sources based on a common knowledge representation. A combination of the Extensible Neuroimaging Archive Toolkit (XNAT) with semantic web technologies, standardized interfaces and a common application platform enables applications to access and semantically annotate data, perform semantic reasoning and eventually create individual context-aware surgical assistance. The infrastructure meets the requirements of a cognitive surgical assistant system and has been successfully applied in various use cases. The system is based completely on free technologies and is available to the community as an open-source package.

Automatisierung von Vorverarbeitungsschritten für medizinische Bilddaten mit semantischen Technologien

Medizinische Interpretationsverfahren konnen Arzte in ihrem taglichen Arbeitsablauf unterstutzen, indem Arbeitsschritte im Bereich der Bildvorverarbeitung oder -analyse automatisiert werden. Um dies zu ermoglichen, werden Systeme benotigt, die eigenstandig Arbeitsprozesse erstellen und ausfuhren konnen. Wir stellen in dieser Arbeit unser Framework anhand des Tumor Progression Mapping (TPM) vor. Es erm oglicht Algorithmen semantisch zu beschreiben und sie automatisch datengetrieben ausfuhren zu lassen. Wir verwenden dazu Konzepte aus dem Semantic Web: Das Resource Description Framework (RDF) erm oglicht uns Algorithmen mit Semantik anzureichern. Anschliesend benutzen wir Linked Data Prinzipien, um eine semantische Architektur zu entwickeln. Wir stellen die Algorithmen als selbstbeschreibende semantische Web Services bereit und fuhren sie automatisch datengetrieben aus. Wir zeigen anhand dem Tumor Progression Mapping, dass diese deklarative Architektur automatisch verschiedene Arbeitsprozesse erstellen und ausfuhren kann.

On Automating Decentralized Multi-Step Service Combination

Information on the Web is heterogeneous and available in constantly increasing quantities. Consequently, there are numerous, partly redundant data analytics services, each optimized for data with certain characteristics. Often, analytics tasks require multiple services to be pipelined to find a solution, where combinations of exchangeable services for single steps might outperform one-service-predictions. This work proposes a Multi-Agent System (MAS) perception of prior setting, where decentralized agents are considered to manage services, having to coordinate their decisions to find a consensus. We, first, propose a supervised method for service accuracy estimation and, therefore, exploit locality-sensitive features of training data. Given a committee of services managed by agents, we develop coordination strategies to handle conflicting confidences and reduce erroneous predictions due to service correlation. We evaluate our approach with Named Entity Recognition (NER)- and Named Entity Disambiguation (NED) services on text corpora with heterogeneous characteristics (i.e. news articles and tweets). Our empirical results improve the out-of-the-box performance of the original services.

Expert-based probabilistic modeling of workflows in context of surgical interventions

To provide assistance functions in context of surgical interventions, the use of medical workflows plays an important role. Workflow models can be used to assess the progress of an on-going surgery, enabling tailored (i.e., context sensitive) support for the medical practitioner. Subsequently, this provides opportunities to prevent malpractices, to enhance the patients outcome and to preserve a high level of satisfaction. In this work, we propose a framework which enables a formalization of medical workflows. It is driven by a dialog of medical as well as technical experts and is based on the Unified Modeling Language (UML). An easy comprehensible UML activity serves as a starting point for the automatic generation of more complex models that can be used for the actual estimation of the progress of a surgical intervention. In this work, we present translation rules, which allow to transfer a given UML activity into a Dynamic Bayesian Network (DBN). The methods are presented for the application example of a cholecystectomy (surgical removal of the gallbladder).

A Semantic Framework for Sequential Decision Making

Current developments in the medical domain, not unlike many other sectors, are marked by the growing digitalisation of data, including patient records, study results, clinical guidelines or imagery. This trend creates the opportunity for the development of innovative decision support systems to assist physicians in making a diagnosis or preparing a treatment plan. To this end, complex tasks need to be solved, requiring one or more interpretation algorithms e.g. image processors or classifiers to be chosen and executed based on heterogeneous data. We, therefore, propose a semantic framework for sequential decision making and develop the foundations of a Linked agent who executes interpretation algorithms available as Linked APIs [9] on a data-driven, declarative basis [10] by integrating structured knowledge formalized in RDF and OWL, and having access to meta components for optimization. We evaluate our framework based on image processing of brain images and ad-hoc selection of surgical phase recognition algorithms.

Sequential Decision Making with Medical Interpretation Algorithms in the Semantic Web

Supporting physicians in their daily work with state-of-the art technology is an important ongoing undertaking. If a radiologist wants to see the tumour region of a headscan of a new patient, a system needs to build a workflow of several interpretation algorithms all processing the image in one or the other way. If a lot of such interpretation algorithms are available, the system needs to select viable candidates, choose the optimal interpretation algorithms for the current patient and finally execute them correctly on the right data. We work towards developing such a system by using RDF and OWL to annotate interpretation algorithms and data, executing interpretation algorithms on a data-driven and declarative basis and integrating so-called meta components. These let us flexibly decide which interpretation algorithms to execute in order to optimally solve the current task.