Aniello Minutolo

A Fuzzy Decision Support Language for Building Mobile DSSs for Healthcare Applications

Recently, Fuzzy Logic has been proposed as the most suitable approach for profitably tackling uncertainty and vagueness in clinical guidelines, and providing a new mobile generation of Decision Support Systems. This paper presents an intuitive XML-based language, named Fuzzy Decision Support Language, for both configuring a fuzzy inference system and encoding fuzzy medical knowledge to be embedded into a mobile DSS. Such a language enables the encoding of: i) fuzzy medical knowledge, in terms of groups of positive evidence rules and fuzzy ELSE rules assembling all the negative evidence for a specific situation; ii) input and output data, respectively elaborated or produced by the fuzzy DSS, in order to provide meaningful and semantically well-defined advices. As a proof of concept, the proposed language has been applied to encode, into a mobile DSS, the medical knowledge required to remotely detect suspicious situations of sleep apnea or heart failure in patients affected by cardiovascular diseases.

A natural pointing technique for semi-immersive virtual environments

Several interaction metaphors and techniques have been proposed to allow a natural interaction in virtual environments. Usually all these techniques are designed to be used with input devices such as wands, 3D mice or gloves. However, the availability of a new generation of auto-stereoscopic displays now makes it possible to exploit virtual experiences in new scenarios. In this paper we propose a variation of the ray-casting technique suitable for use with a standard mouse. With this proposed technique, users can move a 3D cursor in the virtual world without worrying about the third dimension and without losing the level of immersion provided by the 3D display.

A lazy evaluation approach for mobile reasoning in DSSs

Recently, a new mobile generation of decision support systems (DSSs) is appearing to face a set of new challenging scenarios, where information must be used anywhere for supporting the decision-making tasks seamlessly and ubiquitously. In this respect, this paper presents a lazy evaluation approach for reasoning in mobile knowledge-based DSSs in order to grant an efficient handling of memory and computational resources. The approach relies on knowledge representation and reasoning facilities to face and efficiently reason on the continuous and real-time flow of data. The core of the approach is a lazy pattern matching algorithm, specifically designed and implemented as a light-weight solution suitable for resource-limited mobile devices with the final aim of improving performance in real-time and intensive applications.

Fuzzy on FHIR: a Decision Support service for Healthcare Applications

In the last years, an explosion of interest has been seen with respect to clinical decision support systems based on guidelines, since they have promised to reduce inter-practice variation, to promote evidence-based medicine, and to contain the cost of health care. Despite this great promise, many obstacles lie in the way of their integration into routine clinical care. Indeed, first, the communication with information systems to collect health data is a very thorny task due to the heterogeneity of data sources. Secondly, the machine-readable representation of guidelines can generate an unrealistic oversimplification of reality, since not able to completely handle uncertainty and imprecision typically affecting guidelines. Finally, a large number of existing decision support systems have been implemented as standalone software solutions that cannot be well reused or transported to other medical scenarios. Starting from these considerations, this paper proposes a standards-based decision support service for facilitating the development of healthcare applications enabling: i) the encoding of uncertain and vague knowledge underpinning clinical guidelines by using Fuzzy Logic; ii) the representation of input and output health data by using the emerging standard FHIR (Fast Healthcare Interoperability Resources). As a proof of concept, a WSDL-based SOAP implementation of the service has been tested on a set of clinical guidelines pertaining the evaluation of blood pressure for a monitored patient.

An Ontology-Based Approach for Representing Medical Recommendations in mHealth Applications

Nowadays, mHealth applications have been evolving in the form of pervasive solutions for supporting healthy life-style and wellness self-management. In such a direction, the Italian project “Smart Health 2.0” realized innovative technological infrastructures, on which different mHealth applications and services were developed, aimed at remotely supporting individuals in diseases prevention and improving their welfare and life styles. In this paper, the ontology-based approach proposed in the project to represent, share, and reason on the knowledge characterizing a subject within mHealth applications is presented. The proposed approach uses a hybrid strategy integrating ontology models and deductive rules built on the top of them. In order to better describe the proposed approach, a case of application has been presented with respect to an mHealth application designed for managing diet according to given daily caloric needs.

A multi-level fuzzy inference system for developing DSS based on clinical guidelines

Clinical Decision Support Systems (CDSSs) are typically based on clinical guidelines explicitly formalized in the form of rules for reproducing the physicians decisionmaking process and, also, improving the efficiency of medical practices. With the aim of building CDSSs able to represent uncertainty existing in clinical guidelines and efficiently reason on a huge number of inter-connected rules, this paper presents a multi-level fuzzy inference system offering the following set of specifically-devised functionalities: (i) fuzzy rules can be organized in one or more groups of positive evidence rules, where each group is able to interact with other ones by properly chaining their conclusions; (ii) rules inside a group are independently processed and evaluated; (iii) each group of rules can be customized by means of a peculiar configuration for the inference; (iv) a fuzzy ELSE rule can be associated to a group for assembling all the negative evidence for a specific situation. A proof of concept scenario is finally given to describe how the proposed solution can be applied.

Query Expansion Based on WordNet and Word2vec for Italian Question Answering Systems

Recently, Question Answering (QA) systems have emerged as efficient solutions for helping users find proper answers to questions pertaining to a specific situation. One of the major modern paradigms for QA is based on Information Retrieval (IR) techniques, where the text of a user question is evaluated in order to extract a collection of relevant keywords, formulate queries on the top of them for a search engine and extract candidate answers from documents matching with the queries. Nevertheless, in the case of semantically complex and rich languages, like Italian, many concepts can be expressed in a variety of distinct linguistic forms. This problem particularly arises when QA is applied to smaller sets of documents pertaining to a closed domain, where an answer might appear only once, and its exact wording might differ partially or completely from the one used in the query. To solve this issue, this paper proposes a hybrid approach of Query Expansion (QE) where lexical resources and word embeddings (WEs) are combined to generate synonyms and hypernyms of relevant words extracted from the user question and contextualize this set with respect to the corpus of interest and with respect to the peculiar question. An experimental session has been arranged in order to compare the proposed QE approach with other different techniques and evaluate its impact of with respect to the accuracy of a QA system in extracting proper answers to factoid questions from documents pertaining to the Cultural Heritage domain. The experiments showed the effectiveness of the proposed solution with respect to three different evaluation metrics typically used in literature.

A Hypothetical Reasoning System for Mobile Health and Wellness Applications

In the last years, rule-based systems have been used in mobile health and wellness applications for embedding and reasoning over domain-specific knowledge and suggesting actions to perform. However, often, no sufficient information is available to infer definite indications about the action to perform and one or more hypothesis should be formulated and evaluated with respect to their possible impacts. In order to face this issue, this paper proposes a mobile hypothetical reasoning system able to evaluate set of hypotheses, infer their outcomes and support the user in choosing the best one. In particular, it offers facilities to: (i) build specific scenarios starting from different initial hypothesis formulated by the user; (ii) optimize them by eliminating common domain-specific elements and avoiding their processing more than once; (iii) efficiently evaluate a set of logic rules over the optimized scenarios directly on the mobile devices and infer the logical consequences by providing timely responses and limiting the consumption of their resources. A case study has been arranged in order to evaluate the system’s effectiveness within a mobile application for managing personal diets according to daily caloric needs.

Encoding Clinical Recommendations into Fuzzy DSSs: An Application to COPD Guidelines

Clinical Decision Support Systems (DSSs) have been applied to medical scenarios by computerizing a set of clinical guidelines of interest, with the final aim of simulating the process followed by the physicians. In this context, fuzzy logic has been profitably used for modeling clinical guidelines affected by uncertainty and improving the interpretability of clinical DSSs through its expressivity close to natural language. However, the task of computerizing clinical guidelines in terms of fuzzy if-then rules can be complex and, often, requires technical capabilities not owned by physicians. In order to face this issue, this paper introduces a fuzzy knowledge editing framework expressly devised and designed to simplify the procedures necessary to codify clinical guidelines in terms of fuzzy if-then rules and linguistic variables. This framework is described with respect to a specific real case regarding the formalization of clinical recommendations extracted from the GOLD guidelines, which contain the best evidence for diagnosing and managing the Chronic Obstructive Pulmonary Disease.

An Automatic Method for Deriving OWL Ontologies from XML Documents

In the last decade, the field of Big Data Analytics has become increasingly important in both the academic and the business communities. Typically, data are mostly structured, collected by different actors through various heterogeneous and distributed information sources, and stored and managed often directly in XML. In order to enable large volume of data to be described in such a way that their meaning can be exploited by machines and, thus, semantic queries and automatic inferential procedures can be enabled, this paper presents an automatic method to derive OWL ontologies from XML schemas. The main contribution of this method relies on the possibility of producing a target ontology starting from multiple XML schemas, by discriminating between domain and cross-domain entities and, contextually, simplifying the overall structure of the final ontology generated, i.e. By eliminating not-used cross-domain entities. This method has been applied to a concrete application case in the healthcare domain, with the goal of generating an ontological model from the XML schemas implementing the HL7 Version 3 Clinical Document Architecture Release 2.