Claudio Eccher

Modeling Clinical Protocols Using Semantic MediaWiki: The Case of the Oncocure Project

A computerized Decision Support Systems (DSS) can improve the adherence of the clinicians to clinical guidelines and protocols. The building of a prescriptive DSS based on breast cancer treatment protocols and its integration with a legacy Electronic Patient Record is the aim of the Oncocure project. An important task of this project is the encoding of the protocols in computer-executable form -- a task that requires the collaboration of physicians and computer scientists in a distributed environment. In this paper, we describe our project and how semantic wiki technology was used for the encoding task. Semantic wiki technology features great flexibility, allowing to mix unstructured information and semantic annotations, and to automatically generate the final model with minimal adaptation cost. These features render semantic wikis natural candidates for small to medium scale modeling tasks, where the adaptation and training effort of bigger systems cannot be justified. This approach is not constrained to a specific protocol modeling language, but can be used as a collaborative tool for other languages. When implemented, our DSS is expected to reduce the cost of care while improving the adherence to the guideline and the quality of the documentation.

Logical Analysis of Mappings between Medical Classification Systems

Medical classification systems provide an essential instrument for unambiguously labeling clinical concepts in processes and services in healthcare and for improving the accessibility and elaboration of the medical content in clinical information systems. Over the last two decades the standardization efforts have established a number of classification systems as well as conversion mappings between them. Although these mappings represent the agreement reached between human specialists who devised them, there is no explicit formal reference establishing the precise meaning of the mappings. In this work we close this semantic gap by applying the results that have been recently reached in the area of AI and the Semantic Web on the formalization and analysis of mappings between heterogeneous conceptualizations. Practically, we focus on two classification systems which have received great widespread and preference within the European Union, namely ICPC-2 (International Classification of Primary Care) and ICD-10 (International Classification of Diseases). The particular contributions of this work are: the logical encoding in OWL of ICPC-2 and ICD-10 classifications; the formalization of the existing ICPC-ICD conversion mappings in terms of OWL axioms and further verification of its coherence using the logical reasoning; and finally, the outline of the other semantic techniques for automated analysis of implications of future mapping changes between ICPC and ICD classifications.

PerKApp: A context aware motivational system for healthier lifestyles

In this paper we present PerKApp, a context-aware system for inducing the user to adopt healthier lifestyles, based on a novel combination of persuasion technologies, natural language generation techniques, and deep knowledge representation tools. In our view, personalized and tailored messages generated according to the characteristic of user, user preferences and the context are extremely useful to increase the effectiveness of persuasion efforts in terms of user acceptance of the proposed behaviors. The architecture of PerKApp is designed with the goal of ease scalability and extendibility to other domains by redefinition of the knowledge and linguistic content.

Bridging an asbru protocol to an existing electronic patient record

Clinical protocols can improve the quality of care if implemented in Decision Support Systems (DSS) that are used in clinical practice. For optimal user acceptance, they must use data from the existing Electronic Patient Records (EPR) and enforce only small changes in the care process and minimal extra effort for data entry. In this paper we describe how we handle the challenge of mapping a breast cancer treatment protocol encoded in Asbru to a legacy EPR which has been used by oncologists at the point of care for years. We identified different levels of integration effort ranging from readily available data in the EPR to abstractions which can only be performed by domain experts. By involving the author of the protocol in the implementation process, we were able to design a system which promises to improve the daily routine at the places of application.

A semantic-enabled platform for supporting healthy lifestyles

Healthy lifestyle is not only a today trend fostered by the availability of low-cost monitoring devices, but may significantly contribute to the prevention of chronic diseases as consequence of a combination of incorrect diet and lack of physical activity. In this paper, we present the use of semantic web technologies to build an architecture for supporting the monitoring of people and for persuading them to follow healthy lifestyles. Semantic technologies are used for modeling all relevant information and for fostering reasoning activities by combining user-generated data and domain knowledge. Here, we give an overview of the whole platform and highlight the structure and the role of the ontology, how it is exploited for supporting the activities of domain experts for designing monitoring rules and how the reasoning task is performed. Finally, we provide some insights about how the reasoners output can be used for generating persuasive messages. The scenario of promoting healthy diets has been chosen for demonstrating how the platform works in a real-world environment.

Process Fragment Recognition in Clinical Documents

We describe a first experiment on automated activity and relation identification, and more in general, on the automated identification and extraction of computer-interpretable guideline fragments from clinical documents. We rely on clinical entity and relation (activities, actors, artifacts and their relations) recognition techniques and use MetaMap and the UMLS Metathesaurus to provide lexical information. In particular, we study the impact of clinical document syntax and semantics on the precision of activity and temporal relation recognition.

Collaborative Encoding of Asbru Clinical Protocols

Encoding guidelines and treatment protocols in formal and computer-executable form is not a trivial task and requires the collaboration between clinicians and knowledge engineers. In this paper, we describe CliP-MoKi, a Semantic Media Wiki (SMW)-based tool for the collaborative encoding in a distributed environment of cancer treatment protocols in Asbru. CliP-MoKi exploits the great flexibility of SMW technology to mix unstructured information and semantic annotations, allowing to automatically generate the final formal model with minimal adaptation cost. CliP-MoKi uses forms and a graphical representation of the resulting plan hierarchy to help the encoding and the representation of the model. All these features render CliP-MoKi a natural candidate for small to medium scale modeling tasks, since the use of bigger systems may require a big adaptation and training effort. Moreover, our approach is not constrained to Asbru, but CliP-MoKi can be adapted to support other modeling languages.

Optimisation and validation of a remote monitoring system (Onco-TreC) for home-based management of oral anticancer therapies: an Italian multicentre feasibility study

Introduction Despite the growing number of oral agents available for cancer treatment, their efficacy may be reduced due to the lack of adherence, inappropriate adverse event self-management and arbitrary dose adjustment. The management of anticancer therapies could exponentially benefit from the introduction of mobile health technologies in a highly integrated electronic oncology system. Methods and analysis We plan to customise and fine-tune an existing monitoring TreC platform used in different chronic diseases in the oncology setting. This project follows a multistep approach with two major purposes: 1. participatory design techniques driven by Health Literacy and Patient Reported Outcomes principles in order to adapt the system to the oncology setting involving patients and healthcare providers; 2. a prospective training-validation, interventional, non-pharmacological, multicentre study on a series of consecutive patients with cancer (20 and 60 patients in the training and validation steps, respectively) in order to assess system capability, usability and acceptability. The novel Onco-TreC 2.0 is expected to contribute to improving the adherence and safety of cancer care, promoting patient empowerment and patient–doctor communication. Ethics and dissemination Ethical approval was obtained from the Independent Ethics Committees of the participating institutions (CEIIAV protocol Number 2549/2015; reference Number 1315-PU). Informed consent will be obtained from all study participants. Findings will be disseminated through peer-reviewed journals, conferences and event presentations. Trial registration number ClinicalTrials.gov (NCT02921724); (Pre-results). Other study ID Number: IRST100.18.

Using a Mobile App to Manage Type 1 Diabetes: The Case of TreC Diabetes

Type 1 diabetes is chronic condition due to the autoimmune destruction of the insulin-producing beta cells in the pancreas. We present TreC Diabetes, a system consisting of a mobile diary and a web dashboard allowing patients to record disease-related information, which can be visualized by diabetologists through a dedicated dashboard. We also present the results of an observational study to assess the user acceptance of the system.

Distributed laboratory for remote image analysis in immunohistochemistry

Theaimof thepresent studywas toexplore thepotential for the Internet toprovide the communications mediumfor a distributedlaboratoryof quantitativepathologyinwhich diagnostic images are transmittedbetweenlaboratories for quantitative analysis of histological or cytological features. Twentycasesofbreastcarcinomaweretransmittedfromthe DepartmentofAnatomicPathologyattheUniversityofUdine totheInstituteof AnatomicPathologyat SChiaraHospital of Trento, 250kmaway. Histological images weresavedinJPEG format (at acompressionratioof about 15:1) andtransmitted throughthe Internet, using the MIME-compliant mail protocol. The morphometric labelling indexLI (ratiobetween positiveandtotal nuclear area) was evaluatedremotelybyan imageanalyser andwas thencomparedwiththe humanLI (percentageof positive nuclei against the total number of nuclei), evaluatedlocallybyanexperiencedpathologist. Remote morphometric quantificationof LI showedexcellent agreement withevaluationby pathologists (Spearman’s rank correlation, r=0.92, P=0.002). Because themorphometric evaluationof the LI was based ontheanalysisofthechromaticfeaturesofthecolourimages, it didnot needinteractive thresholdcontrol. This alloweda quantificationof the LI andthe Hscorewithout the interventionof thepathologist, whichincreasedthe speedof analysis of eachcase (average 35min, n=20). Our preliminaryresults showedthat Internet email represents a valuable tool for a distributedlaboratoryfor quantitative pathology. This offers newopportunities for multicentre studies andthus expands the ways that pathologists caninteract withtheir colleagues.