Sara Romano

A semantic approach for fine-grain access control of e-health documents

Fine-grain access control is now possible to enforce thanks to the adoption of available standard de facto and access control models; they allow to protect data and resources as long as they are properly structured. Furthermore, in many critical domains of the e-government (as the e-health, for example) the introduction of access control mechanisms is needed to respect laws in force on security and privacy. The main problem to face in such contexts is related to the coexistence of both structured and unstructured data; this, indeed, represents a huge limitation for documents management in public and private contexts. In particular, the adoption of unstructured documents, even if stored on digital media, make fine-grain access control mechanisms useless. In this article, we have exploited the adoption of different techniques aiming at analysing texts and automatically extracting relevant information to structure and manage them. We propose a semantic-based framework for data transformation that is able to locate and identify critical sections of medical records to be protected and then enable a protection system to enforce proper security policies.

A semantic based methodology to classify and protect sensitive data in medical records

The e-Health is going to change the way how patients and healthcare providers interact. The exchange of confidential and integer information is one of the major open issues for the health care sector. While it is quite easy to enforce fine grain access control policies to new well structured medical records managed by newly designed information systems, many eHealth systems are based on “document management systems”. In the practice the system provides a digital version of the whole medical record and it is impossible to enforce fine grain access rules. In this paper we propose the adoption of a semantic based methodology that is able to automatically retrieve the security level associated to a portion of a medical record and use this information to classify resources and locate the proper security rules to apply.

A Semantic-based Document Processing Framework: A Security Perspective

The coexistence of different formats and physical supports to store data is one of the main open issues in document management systems, in particular, the presence of unstructured data represents a huge limitation for the elaboration and analysis of many documents and processes. At this aim we are exploiting the adoption of different techniques to analyze texts and automatically extract relevant information, concepts or complex relations, in this paper we proposed a general framework for data transformation and implemented such model trough an architecture based on semantic analysis. The analysis that can be performed on data has many different applications, in this paper we illustrate an interesting perspective related on how to enforce a fine grained access control on sensitive data that are in capsulated in unstructured, monolithic files. We also presented a case study for the formalization and protection of e-health medical records.

Supporting temporal analytics for health-related events in microblogs

Microblogging services, such as Twitter, are gaining interests as a means of sharing information in social networks. Numerous works have shown the potential of using Twitter posts (or tweets) in order to infer the existence and magnitude of real-world events. In the medical domain, there has been a surge in detecting public health related tweets for early warning so that a rapid response from health authorities can take place. In this paper, we present a temporal analytics tool for supporting a comparative, temporal analysis of disease outbreaks between Twitter and official sources, such as, World Health Organization (WHO) and ProMED-mail. We automatically extract and aggregate outbreak events from official outbreak reports, producing time series data. Our tool can support a correlation analysis and an understanding of the temporal developments of outbreak mentions in Twitter, based on comparisons with official sources.

Detecting anomalies in Twitter stream for public security issues

Social networking services gain more often interest for research goals in several fields and applications thanks to the big amount of data that users daily post on them. Knowledge that has accumulated in the social sites enables to catch the reflection of real world events. In this work we present a general framework for event detection from Twitter. The framework aims to collect tweets related to a particular social event, in order to filter and classify those which can be relevant to detect malicious actions in Twitter communities. Relevant tweets are processed to raise an alert in case of anomaly within the collected set.

Challenges in Detecting Epidemic Outbreaks from Social Networks

Many studies have indicated the potential of using Social Networks for the early detection of public health events, such as epidemic outbreaks, so that a faster response can take place. Anyhow, the most of these studies are focused on one or two diseases, and consequently to date it is not clear if and how different outbreaks give rise to different temporal dynamics of the messages. Furthermore, it is not clear if it is possible to define a single generic Data Mining solution for the detection of epidemic outbreaks from this Big Data, or if specifically tailored approaches should be implemented for each disease. To get an insight on this issue, we collected a massive dataset of Twitter messages to extract relevant information regarding different outbreaks from different countries in 2011. The manual analysis we conducted allowed us to define some macro-classes of diseases. Results show that there is a considerable variability in the temporal dynamics of Twitter messages from different diseases, and that the identification of a suitable source of information, to define a ground truth suitable for the assessment of time series analysis algorithms, is a challenging task. Finally we also report on a special case we found, highlighting that a lot of research has still to be done in this field.

A Cloud Based Architecture for Massive Sensor Data Analysis in Health Monitoring Systems

In recent analysis conducted by the European Commission it is estimated that within the EU population the number of the elderly (65≥) is growing from 17.4% of the total in 2010 up to 30.0% in 2060. At the same time, the EU population within the working age (15-64 years old) is expected to dramatically decrease from 61% to 51% of the total. These demographic changes impact on the public budgets, a decreasing number of health personnel, higher incidence of chronic diseases and growing demands and expectations from citizens for higher quality services and social care. In this scenario, ICT-solutions are necessary in order to reduce the cost of formal health care, to allow disease prevention and related lifestyle changes. Several research efforts are devoted to provide innovative and not-intrusive systems to continuously monitor in real-time the state and behavior of patients. Those health monitoring systems rely on heterogeneous data acquisition from sensors, video, historical and simulated data, performing inferences and data elaboration in order to provide alternatives to the traditional management of patients, e.g. allowing them to manage their health conditions at home. Depending on the functionalities to implement, the amount of data that has to be elaborated could represent the bottleneck of a monitoring system and it is critical in real-time applications. To achieve an increment on computational power, cloud computing in combination of hardware solutions should be adopted. In this work we present a layered architecture infrastructure for data analysis, based on two Decision Tree predictor hardware implementations. The first one is a high performance architecture, able to compute a massive analysis. The second one is a lightweight architecture suitable to execute prediction with few hardware resources.

An innovative framework for securing unstructured documents

The coexistence of both structured and unstructured data represents a huge limitation for documents management in public and private contexts. In order to identify and protect specific resources within monolithic documents we have exploited the adoption of different techniques aiming to analyze texts and automatically extract relevant information. In this paper we propose an innovative framework for data transformation that is based on a semantic approach and can be adapted in many different contexts; in particular, we will illustrate the applicability of such a framework for the formalization and protection of e-health medical records.

Approaching Hardware Solutions for Massive E-Health Sensor Data Analysis

The increase of life expectation and low birth rates have deeply impacted on the worldwide demographic structure. These changes impact on the public budgets and growing demands and expectations from citizens for higher quality services and social care. Several research efforts are devoted to provide alternatives to the traditional management of patients with innovative and not-intrusive systems to monitor in real-time the state and behavior of patients. Remote health monitoring systems can be used to monitor several vital parameters within a variety of ranges. These systems rely on heterogeneous data acquisition from sensors, video, historical and simulated data, performing inferences, and data elaboration in order to provide alternatives to the traditional management of patients. Depending on the functionalities to implement, the amount of data that has to be elaborated could represent the bottleneck of a monitoring system and it is critical in real-time applications. In this chapter we present a layered architecture infrastructure, based on two Decision Tree predictor hardware implementations, suitable for medical data analysis in real-time and aimed at dealing with a wide data volume and preserving a good hardware resources efficiency. We show how we improved the classification components and feature selection in order to achieve high-level throughput and high-level accuracy for the classification task of big data.

A Semantic System for Diagnoses Suggestion and Clinical Record Management

The increasing life expectations together with the low birth rates lead to radically change the demographic structure in European Union. The increasing average life expectancy is increasing the number of healthy elderly people and consequently the incidence of chronic diseases with a dramatic increase of healthcare costs. The demographic changes heavily impact on the public budgets, a decreasing number of health personnel, higher incidence of chronic diseases and growing demands and expectations from citizens for higher quality services and social care. The main outcome is that e-Health applied to the existing healthcare systems can increase their efficiency, improve quality of life and reduce costs providing alternatives to the traditional disease management and allowing disease prevention. Several research efforts are devoted to provide innovative and not-intrusive e-Health systems. In this work we present a methodology for diagnosis decision supporting based on big data analysis of available medical data. This methodology is aimed to assist medical personnel in the patients diagnosis making.