Posterous theme by Cory Watilo

nocx

medical informatics, neurogenetics, epigenetics, bipolar disorder, depression, suicide

Segagni et al. An ICT infrastructure to integrate clinical and molecular data / via @BioMedCentral @i2b2

-Open Source
-Integrates Clinical and Research data to support translational research

"Onco-i2b2 manages data of more than 6,500 patients with breast cancer diagnosis collected between 2001 and 2011 (over 390 of them have at least one biological sample in the cancer biobank), more than 47,000 visits and 96,000 observations over 960 medical concepts.
.
.
.
Onco-i2b2 is a concrete example of how integrated Information and Communication Technology architecture can be implemented to support translational research. The next steps of our project will involve the extension of its capabilities by implementing new plug-in devoted to bioinformatics data analysis as well as a temporal query module."

Symptom dimension as phenotype to address genetic heterogeneity in schizophrenia and bipolar disorder

Labbe et al.
Eur J Hum Genet 2012

"In a two-step approach, we proposed: (i) to form homogeneous clusters of subjects based on the symptom dimensions and (ii) to use the information from these homogeneous clusters in linkage analysis. This framework was applied to a unique SZ and BP sample composed of 1278 subjects from 48 large kindreds from the Eastern Quebec population. The results suggest that our strategy has the power to increase linkage signals previously obtained using the diagnosis as phenotype and allows for a better characterization of the linkage signals. This is the case for a linkage signal, which we formerly obtained in chromosome 13q and enhanced using the dimension mania. The analysis also suggests that the methods may detect new linkage signals not previously uncovered by using diagnosis alone, as in chromosomes 2q (delusion), 15q (bizarre behavior), 7p (anhedonia) and 9q (delusion). In the case of the 15q and 2q region, the results coincide with linkage signals detected in other studies"

"a reduction of 62.5% in manual annotation effort" Active learning for assertion classification in #NLP

Chen et al. Journal of Biomedical Informatics (April 2012), 45 (2), pg. 265-272 

Applying active learning to assertion classification of concepts in clinical text
"

< One of the first attempts to apply active learning to clinical text classification. 

< Active learning algorithms generally outperformed random sampling method. 

< Active learning reduced over 50% samples to achieve similar performance.

"

​