<img height="1" width="1" alt="" style="display:none" src="https://www.facebook.com/tr?id=648880075207035&amp;ev=NoScript">
BayesiaLab

"Managing the Decision Supply Chain"?

Sometimes, it appears, the analytics industry is getting carried away with creating new jargon. Today, there was a post about managing the "decision supply chain." 

Read More...

BayesiaLab in Boston

This week, nine scientists successfully completed our introductory BayesiaLab course in Boston. Congratulations! Next week, the BayesiaLab training program will continue with a 3-day advanced course

Read More...

BayesiaLab, from Rome to Boston.

Our team is racking up frequent flyer miles again. Last week's training in Rome was a success (see photo below), and now we're off to Boston for two BayesiaLab courses starting next Wednesday. The 3-Day Introductory Course is pretty much sold out, but we still have space in the 3-Day Advanced BayesiaLab Course starting on March 9.

Read More...

The BayesiaLab Digest - February 9, 2015
Asymmetric Threat Detection with Bayesian Networks

Here is today's citation of new and interesting applied research with Bayesian networks:

Dragos, Valentina, Juergen Ziegler, and Paulo C. Costa.
Description and Assessment of a User Oriented Approach for Asymmetric Threat Detection.
Technical Report. George Mason University, 2013. 
http://oai.dtic.mil/oai/oai?verb=getRecord&metadataPrefix=html&identifier=ADA606212.

Read More...

The BayesiaLab Digest - February 7, 2015
Motion Intent Detection with Bayesian Networks

Here is today's citation of new and interesting applied research with Bayesian networks:

Wang, Zuoguan, Aysegul Gunduz, Peter Brunner, Anthony L. Ritaccio, Qiang Ji, and Gerwin Schalk.
Decoding Onset and Direction of Movements Using Electrocorticographic (ECoG) Signals in Humans.
Frontiers in Neuroengineering 5 (2012): 15. doi:10.3389/fneng.2012.00015.
http://www.ecse.rpi.edu/~qji/Papers/decoding_finger.pdf

Read More...

Advanced BayesiaLab Course in Paris

This week, we hosted the 3-Day Advanced BayesiaLab Course in Paris, and, for the first time, this program was conducted entirely in French. Even though we came up with all the new methodologies that are taught in this course, it's actually not so easy to find the right nomenclature in multiple languages. Hopefully, language scholars will forgive us for all the neologisms that we created along the way.

Read More...

The BayesiaLab Digest - January 26, 2015:
Modeling Aircraft Encounters with Bayesian Networks

Here is today's citation of new and interesting applied research with Bayesian networks:

Griffith, J. D., Matthew W. Edwards, Raymond M. Miraflor, and Andrew Weinert.
Due Regard Encounter Model Version 1.0.
Project Report. Lexington, Massachusetts: Massachusetts Institute of Technology Lincoln Laboratory, August 19, 2013.
Read More...

The BayesiaLab Digest - January 23, 2015:
Modelling crime linkage with Bayesian networks.

Here is today's citation of new and interesting applied research with Bayesian networks:

Jacob de Zoete, M.S., 2014.
Modelling crime linkage with Bayesian networks.

Read More...

The BayesiaLab Digest - January 22, 2015:
Evaluating and Ranking Threats to the Long-Term Persistence of Polar Bears.

Here is today's citation of new and interesting applied research with Bayesian networks:

Atwood, T., Marcot, B., Douglas, D., Amstrup, S., Rode, K., Durner, G., Bromaghin, J., 2015.
Evaluating and Ranking Threats to the Long-Term Persistence of Polar Bears.

Read More...

The BayesiaLab Digest - January 15, 2015

Here is this week's selection of interesting new journal articles on applied research with Bayesian networks. 


Benndorf, M., Kotter, E., Langer, M., Herda, C., Wu, Y., Burnside, E.S., 2015.
Development of an online, publicly accessible naive Bayesian decision support tool for mammographic mass lesions based on the American College of Radiology (ACR) BI-RADS lexicon.
Eur Radiol 1–8.
doi:10.1007/s00330-014-3570-6
http://link.springer.com/article/10.1007/s00330-014-3570-6

Purpose
To develop and validate a decision support tool for mammographic mass lesions based on a standardized descriptor terminology (BI-RADS lexicon) to reduce variability of practice.

Materials and methods
We used separate training data (1,276 lesions, 138 malignant) and validation data (1,177 lesions, 175 malignant). We created naïve Bayes (NB) classifiers from the training data with tenfold cross-validation. Our “inclusive model” comprised BI-RADS categories, BI-RADS descriptors, and age as predictive variables; our “descriptor model” comprised BI-RADS descriptors and age. The resulting NB classifiers were applied to the validation data. We evaluated and compared classifier performance with ROC-analysis.

Results
In the training data, the inclusive model yields an AUC of 0.959; the descriptor model yields an AUC of 0.910 (P < 0.001). The inclusive model is superior to the clinical performance (BI-RADS categories alone, P < 0.001); the descriptor model performs similarly. When applied to the validation data, the inclusive model yields an AUC of 0.935; the descriptor model yields an AUC of 0.876 (P < 0.001). Again, the inclusive model is superior to the clinical performance (P < 0.001); the descriptor model performs similarly.

Conclusion
We consider our classifier a step towards a more uniform interpretation of combinations of BI-RADS descriptors. We provide our classifier at www.ebm-radiology.com/nbmm/index.html.

Read More...
2017 BayesiaLab Conference