International Health Informatics Symposium 

About: International Health Informatics Symposium is an academic conference. The conference publishes majorly in the area(s): Health care & Health informatics. Over the lifetime, 238 publications have been published by the conference receiving 4660 citations.

Deploying an interactive machine learning system in an evidence-based practice center: abstrackr

Abstract: Medical researchers looking for evidence pertinent to a specific clinical question must navigate an increasingly voluminous corpus of published literature. This data deluge has motivated the development of machine learning and data mining technologies to facilitate efficient biomedical research. Despite the obvious labor-saving potential of these technologies and the concomitant academic interest therein, however, adoption of machine learning techniques by medical researchers has been relatively sluggish. One explanation for this is that while many machine learning methods have been proposed and retrospectively evaluated, they are rarely (if ever) actually made accessible to the practitioners whom they would benefit. In this work, we describe the ongoing development of an end-to-end interactive machine learning system at the Tufts Evidence-based Practice Center. More specifically, we have developed abstrackr, an online tool for the task of citation screening for systematic reviews. This tool provides an interface to our machine learning methods. The main aim of this work is to provide a case study in deploying cutting-edge machine learning methods that will actually be used by experts in a clinical research setting.

Securing the e-health cloud

Abstract: Modern information technology is increasingly used in healthcare with the goal to improve and enhance medical services and to reduce costs. In this context, the outsourcing of computation and storage resources to general IT providers (cloud computing) has become very appealing. E-health clouds offer new possibilities, such as easy and ubiquitous access to medical data, and opportunities for new business models. However, they also bear new risks and raise challenges with respect to security and privacy aspects. In this paper, we point out several shortcomings of current e-health solutions and standards, particularly they do not address the client platform security, which is a crucial aspect for the overall security of e-health systems. To fill this gap, we present a security architecture for establishing privacy domains in e-health infrastructures. Our solution provides client platform security and appropriately combines this with network security concepts. Moreover, we discuss further open problems and research challenges on security, privacy and usability of e-health cloud systems.

Unsupervised pattern discovery in electronic health care data using probabilistic clustering models

Abstract: Bedside clinicians routinely identify temporal patterns in physiologic data in the process of choosing and administering treatments intended to alter the course of critical illness for individual patients. Our primary interest is the study of unsupervised learning techniques for automatically uncovering such patterns from the physiologic time series data contained in electronic health care records. This data is sparse, high-dimensional and often both uncertain and incomplete. In this paper, we develop and study a probabilistic clustering model designed to mitigate the effects of temporal sparsity inherent in electronic health care records data. We evaluate the model qualitatively by visualizing the learned cluster parameters and quantitatively in terms of its ability to predict mortality outcomes associated with patient episodes. Our results indicate that the model can discover distinct, recognizable physiologic patterns with prognostic significance.

Motion primitive-based human activity recognition using a bag-of-features approach

Abstract: Human activity modeling and recognition using wearable sensors is important in pervasive healthcare, with applications including quantitative assessment of motor function, rehabilitation, and elder care. Previous human activity recognition techniques use a "whole-motion" model in which continuous sensor streams are divided into windows with a fixed time duration whose length is chosen such that all the relevant information in each activity signal can be extracted from each window. In this paper, we present a statistical motion primitive-based framework for human activity representation and recognition. Our framework is based on Bag-of-Features (BoF), which builds activity models using histograms of primitive symbols. We experimentally validate the effectiveness the BoF-based framework for recognizing nine activity classes and evaluate six factors which impact the performance of the framework. The factors include window size, choices of features, methods to construct motion primitives, motion vocabulary size, weighting schemes of motion primitive assignments, and learning machine kernel functions. Finally, we demonstrate that our statistical BoF-based framework can achieve much better performance compared to a non-statistical string-matching-based approach.

The MONARCA self-assessment system: a persuasive personal monitoring system for bipolar patients

Abstract: An increasing number of persuasive personal healthcare monitoring systems are being researched, designed and tested. However, most of these systems have targeted somatic diseases and few have targeted mental illness. This paper describes the MONARCA system; a persuasive personal monitoring system for bipolar patients based on an Android mobile phone. The paper describes the user-centered design process behind the system, the user experience, and the technical implementation. This system is one of the first examples of the use of mobile monitoring to support the treatment of mental illness, and we discuss lessons learned and how others can use our experience in the design of such systems for the treatment of this important, yet challenging, patient group.