Redundancy-aware topic modeling for patient record notes

R Cohen, I Aviram, M Elhadad, N Elhadad - PloS one, 2014‏ - journals.plos.org
The clinical notes in a given patient record contain much redundancy, in large part due to
clinicians' documentation habit of copying from previous notes in the record and pasting into …

Utilizing uncoded consultation notes from electronic medical records for predictive modeling of colorectal cancer

M Hoogendoorn, P Szolovits, LMG Moons… - Artificial intelligence in …, 2016‏ - Elsevier
Objective Machine learning techniques can be used to extract predictive models for
diseases from electronic medical records (EMRs). However, the nature of EMRs makes it …

Mining the clinical narrative: All text are not equal

K Feldman, N Hazekamp… - 2016 IEEE international …, 2016‏ - ieeexplore.ieee.org
Over the past decade, the application of data science techniques to clinical data has allowed
practitioners and researchers to develop a sundry of analytical models. These models have …

[PDF][PDF] A comparison of dimensionality reduction techniques for unstructured clinical text

Y Halpern, S Horng, LA Nathanson… - Icml 2012 workshop …, 2012‏ - people.csail.mit.edu
Much of clinical data is free text, which is challenging to use together with machine learning,
visualization tools, and clinical decision rules. In this paper, we compare supervised and …

Modeling clinical context: rediscovering the social history and evaluating language from the clinic to the wards

C Walsh, N Elhadad - AMIA Summits on Translational Science …, 2014‏ - pmc.ncbi.nlm.nih.gov
Social, behavioral, and cultural factors are clearly linked to health and disease outcomes.
The medical social history is a critical evaluation of these factors performed by healthcare …

[ספר][B] Machine learning for disease prediction

AJ Frandsen - 2016‏ - search.proquest.com
Millions of people in the United States alone suffer from undiagnosed or late-diagnosed
chronic diseases such as Chronic Kidney Disease and Type II Diabetes. Catching these …

Supervised embedding of textual predictors with applications in clinical diagnostics for pediatric cardiology

TE Perry, H Zha, K Zhou, P Frias, D Zeng… - Journal of the …, 2014‏ - academic.oup.com
Objective Electronic health records possess critical predictive information for machine-
learning-based diagnostic aids. However, many traditional machine learning methods fail to …

Leveraging structural characteristics of interdependent networks to model non-linear cascading risks

A Raja, MR Hasan, S Rajanna, A Salleb-Aoussi - 2013‏ - dair.nps.edu
This paper describes our continuing efforts to forge new ground in identifying the effects of
interdependency on acquisition and, if needed, uncovering early indicators of …

[PDF][PDF] Exploring temporal patterns in emergency department triage notes with topic models

S Kocbek, K Verspoor, W Buntine - Proceedings of the …, 2014‏ - aclanthology.org
Topic modeling is an unsupervised machine-learning task of discovering topics, the
underlying thematic structure in a text corpus. Dynamic topic models are capable of …

Beyond Modeling: The Emergent Role of Informatics in Advancing Healthcare Knowledge

KJ Feldman - 2018‏ - curate.nd.edu
Throughout the history of modern medicine the observation of patient characteristics, health,
and treatment has been driven by a desire to advance knowledge around human health and …