Prem Timsina

A systematic review of IT for diabetes self-management: are we there yet?

BACKGROUND Recent advances in information technology (IT) coupled with the increased ubiquitous nature of information technology (IT) present unique opportunities for improving diabetes self-management. The objective of this paper is to determine, in a systematic review, how IT has been used to improve self-management for adults with Type 1 and Type 2 diabetes. METHODS The review covers articles extracted from relevant databases using search terms related information technology and diabetes self-management published after 1970 until August 2012. Additional articles were extracted using the citation map in Web of Science. Articles representing original research describing the use of IT as an enabler for self-management tasks performed by the patient are included in the final analysis. RESULTS Overall, 74% of studies showed some form of added benefit, 13% articles showed no-significant value provided by IT, and 13% of articles did not clearly define the added benefit due to IT. Information technologies used included the Internet (47%), cellular phones (32%), telemedicine (12%), and decision support techniques (9%). Limitations and research gaps identified include usability, real-time feedback, integration with provider electronic medical record (EMR), as well as analytics and decision support capabilities. CONCLUSION There is a distinct need for more comprehensive interventions, in which several technologies are integrated in order to be able to manage chronic conditions such as diabetes. Such IT interventions should be theoretically founded and should rely on principles of user-centered and socio-technical design in its planning, design and implementation. Moreover, the effectiveness of self-management systems should be assessed along multiple dimensions: motivation for self-management, long-term adherence, cost, adoption, satisfaction and outcomes as a final result.

Opportunities for Business Intelligence and Big Data Analytics in Evidence Based Medicine

Evidence based medicine (EBM) is the conscientious, explicit, and judicious use of current best evidence in making decisions about the care of individual patients. Each year, a significant number of research studies (potentially serving as evidence) are reported in the literature at an ever-increasing rate outpacing the translation of research findings into practice. Coupled with the proliferation of electronic health records, and consumer health information, researchers and practitioners are challenged to leverage the full potential of EBM. In this paper we present a research agenda for leveraging business intelligence and big data analytics in evidence based medicine, and illustrate how analytics can be used to support EBM.

Advanced analytics for the automation of medical systematic reviews

While systematic reviews (SRs) are positioned as an essential element of modern evidence-based medical practice, the creation and update of these reviews is resource intensive. In this research, we propose to leverage advanced analytics techniques for automatically classifying articles for inclusion and exclusion for systematic reviews. Specifically, we used soft-margin polynomial Support Vector Machine (SVM) as a classifier, exploited Unified Medical Language Systems (UMLS) for medical terms extraction, and examined various techniques to resolve the class imbalance issue. Through an empirical study, we demonstrated that soft-margin polynomial SVM achieves better classification performance than the existing algorithms used in current research, and the performance of the classifier can be further improved by using UMLS to identify medical terms in articles and applying re-sampling methods to resolve the class imbalance issue.

A comparative analysis of semi-supervised learning: The case of article selection for medical systematic reviews

While systematic reviews are positioned as an essential element of modern evidence-based medical practice, the creation of these reviews is resource intensive. To mitigate this problem, there have been some attempts to leverage supervised machine learning to automate the article triage procedure. This approach has been proved to be helpful for updating existing systematic reviews. However, this technique holds very little promise for creating new reviews because training data is rarely available when it comes to systematic creation. In this research we assess and compare the applicability of semi-supervised learning to overcome this labeling bottleneck and support the creation of systematic reviews. The results indicated that semi-supervised learning could significantly reduce the human effort and is a viable technique for automating medical systematic review creation with a small-sized training dataset.

Using Semi-Supervised Learning for the Creation of Medical Systematic Review: An Exploratory Analysis

In this research, we explore semi-supervised learning based classifiers to identify articles that can be included when creating medical systematic reviews (SRs). Specifically, we perform comparative study of various semi-supervised learning algorithm, and identify the best technique that is suited for SRs creation. We also aim to identify whether semisupervised learning technique with few labeled samples produce meaningful work saving for SRs creation. Through an empirical study, we demonstrate that semi-supervised classifiers are viable for selecting articles for systematic reviews and situations when only a few numbers of training samples are available.

Leveraging Advanced Analytics Techniques for Medical Systematic Review Update

While systematic reviews (SRs) are positioned as an essential element of modern evidence-based medical practice, the creation and update of these reviews is resource intensive. In this research, we propose to leverage advanced analytics techniques for automatically classifying articles for inclusion and exclusion for systematic review update. Specifically, we used the soft-margin Support Vector Machine (SVM) as a classifier and examined various techniques to resolve class imbalance issues. Through an empirical study, we demonstrated that the soft-margin SVM works better than the perceptron algorithm used in current research and the performance of the classifier can be further improved by exploiting different sampling methods to resolve class imbalance issues.