Abstract

Abstract
Bipolar Disorder (BD) is a chronic and disabling disease that usually appears around 20 to 30 years old. Patients who suffer with BD may struggle for years to achieve a correct diagnosis, and only 50% of them generally receive adequate treatment. In this work we apply a machine learning technique called Inductive Logic Programming (ILP) in order to model relapse and no-relapse patients in a first attempt in this area to improve diagnosis and optimize psychiatrists' time spent with patients. We use ILP because it is well suited for our multi-relational dataset and because a human can easily interpret the logical rules produced. Our classifiers can predict relapse cases with 92% Recall and no-relapse cases with 73% Recall. The rules and variable theories generated by ILP reproduce some findings from the scientific literature. The generated multi-relational models can be directly interpreted by clinicians and researchers, and also open space to research biological mechanisms and interventions. © 2015 IMIA and IOS Press.

Abstract

Abstract
The development and use of computerized decision-support systems in the domain of breast cancer has the potential to facilitate the early detection of disease as well as spare healthy women unnecessary interventions. Despite encouraging trends, there is much room for improvement in the capabilities of such systems to further alleviate the burden of breast cancer. One of the main challenges that current systems face is integrating and translating multi-scale variables like patient risk factors and imaging features into complex management recommendations that would supplement and/or generalize similar activities provided by subspecialty-trained clinicians currently. In this chapter, we discuss the main types of knowledge-objectattribute, spatial, temporal and hierarchical-present in the domain of breast image analysis and their formal representation using two popular techniques from artificial intelligence-Bayesian networks and first-order logic. In particular, we demonstrate (i) the explicit representation of uncertain relationships between low-level image features and high-level image findings (e.g., mass, microcalcifications) by probability distributions in Bayesian networks, and (ii) the expressive power of logic to generally represent the dynamic number of objects in the domain. By concrete examples with patient data we show the practical application of both formalisms and their potential for use in decision-support systems.

Abstract
Handwritten signature recognition is still the most widely accepted method to validate paper based documents. However, in the digital world, there is no readymade way to distinguish a real handwritten signature on a scanned document from a forged copy of another signature made by the same person on another document that is simply "pasted" into the forged document. In this paper we describe how we are using the touch screen of smartphones or tablets to collect handwritten signature images and associated biometric markers derived from the motion direction of handwritten signatures that are made directly into the device touchscreen. These time base biometric markers can then be converted into signaling time waves, by using the dragging or lifting movements the user makes with a touch screen omnidirectional tip stylus, when he handwrites is signature at the device touchscreen. These time/space signaling time waves can then be converted into a biometric bit stream that can be matched with previously enrolled biometric markers of the user's handwritten signature. In this paper we contend that the collection of these simple biometric features is sufficient to achieve a level of user recognition and authentication that is sufficient for the majority of online user authentication and digital documents authenticity.

Abstract
Introduction: The improvements made to healthcare IT systems made over the past years led to the creation of a multitude of different applications essential to the institutions daily operations. Aim: We aim to create and install a system capable of displaying production metrics for healthcare management with little requirements, efforts and software providers involved. Methods: We propose a system capable of displaying production metrics for healthcare facilities, by extracting HL7 messages and other eHealth relevant protocols directly from the institution's network infrastructure. Our system is then able to populate a knowledge database with meaningful information derived from the gathered data. Results: Our system is currently being tested on a large healthcare facility where it extracts and analyses a daily average of 44,000 HL7 messages. The system is currently capable of inferring and displaying the daily distribution of healthcare related activities such as laboratory orders or even relevant billing information. Conclusion: HL7 messages moving over the network contain valuable information that can then be used to assess many relevant production metrics for the entire facility and from otherwise non-interoperable production systems that, in most cases, can only be seen as black boxes by other system integrators.