Category : Informatics & Analysis

Learning analytics for better learning content | Ed Tech Now

We thought you needed: large quantities of data (volume); varied sources of data (variety); semantically meaningful data (which is a similar to validity), the latter being  about accuracy and the former being about having a meaningful standard in the first place, against which that accuracy can be measured. This is a complex topic

RESOURCE: MOOCs and other ed-tech bubbles | Ed Tech Now

"analytics is predicated on “big data” but in education, big data will not exist until we sort out the current failure of interoperability" By spotting patterns in the data produced by students’ online learning activity, learning analytics systems should be able to help: predict student progress; inform adaptive learning strategies (sequencing digital learning activities

MANUSCRIPT: Automated Detection of Adverse Events Using Natural Language Processing of Discharge Summaries

A b s t r a c t Objective:  To determine whether natural language processing (NLP) can effectively detect adverse events defined in the New York Patient Occurrence Reporting and Tracking System (NYPORTS) using discharge summaries. http://www.ncbi.nlm.nih.gov/pmc/articles/PMC1174890/pdf/448.pdf

MANUSCRIPT: Large-scale evaluation of automated clinical note de-identification and its impact on information extraction

ABSTRACT Objective (1) To evaluate a state-of-the-art natural language processing (NLP)-based approach to automatically de-identify a large set of diverse clinical notes. (2) To measure the impact of de-identification on the performance of information extraction algorithms on the de-identified documents. http://jamia.bmj.com/content/20/1/84.full.pdf html

MANUSCRIPT: eQuality for All: Extending Automated Quality Measurement of Free Text Clinical Narratives

Introduction: Electronic quality monitoring (eQuality) from clinical narratives may advance current manual quality measurement techniques. We evaluated automated eQuality measurement tools on clinical narratives of veterans’ disability examinations. http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2656015/pdf/amia-0071-s2008.pdf

MANUSCRIPT: Mapping Physician Networks with Self- Reported and Administrative Data

Objective: To assess whether connections between physicians based on shared patients in administrative data correspond with professional relationships between physicians. Data Sources/Study Setting: Survey of physicians affiliated with a large academic and community physicians’ organization and 2006 Medicare data from a 100 percent sample of patients in the Boston Hospital referral region. http://humannaturelab.net/wp-content/themes/human-nature-lab/media/pdf/publications/articles/122.pdf

MANUSCRIPT: Physician Patient-sharing Networks and the Cost and Intensity of Care in US Hospitals

Background: There is substantial variation in the cost and intensity of care delivered by US hospitals. We assessed how the structure of patient-sharing networks of physicians affiliated with hospitals might contribute to this variation. http://humannaturelab.net/wp-content/themes/human-nature-lab/media/pdf/publications/articles/128.pdf

MANUSCRIPT: Reasons for Choice of Referral Physician Among Primary Care and Specialist Physicians

BACKGROUND: Specialty referral patterns can affect health care costs as well as clinical outcomes. For a given clinical problem, referring physicians usually have a choice of several physicians to whom they can refer. Once the decision to refer is made, the choice of individual physician may have important downstream effects. OBJECTIVE: To examine the reasons why

MANUSCRIPT: Variation in Patient-Sharing Networks of Physicians Across the United States

Context: Physicians are embedded in informal networks that result from their sharing of patients, information, and behaviors. Objectives: To identify professional networks among physicians, examine how such networks vary across geographic regions, and determine factors associated with physician connections. http://humannaturelab.net/wp-content/themes/human-nature-lab/media/pdf/publications/articles/134.pdf

MANUSCRIPT: Automated Assessment of Medical Training Evaluation Text

    Abstract Medical post-graduate residency training and medical student training increasingly utilize electronic systems to evaluate trainee performance based on defined training competencies with quantitative and qualitative data, the later of which typically consists of text comments. Medical education is concomitantly becoming a growing area of clinical research. While electronic systems have proliferated in number,