June 11, 2018
Room number NA1-140
Cleveland Clinic,9500 Euclid Avenue,Cleveland,Ohio

5:30-5:45 PM:BrainX Community live!
5:45-6:00 PM:Drivers Unplugged: Satish Viswanath, PhD.
6:00 -7:00PM:Machine learning applications in Oncology and Gastrointestinal diseases.Satish Viswanath, PhD.
7:00-7:30 PM:Networking session.

Predictive analytics for early recognition and intervention in sepsis

In medicine, time and again early intervention has improved morbidity and mortality.Early recognition is the first step in early intervention to improve quality of care.While many prediction models are in use,implementation has been challenging.

Many have used EHR(electronic health record) data to develop predictive models and implement them through EHR.Many are using state of the art dashboards and mobile platforms for effective and efficient communication of predictions.

We are proud to highlight the work being done by one of the founding members of Team BrainX,Dr.Jeremy Weiss, in development of predictive analytic tools for early recognition of sepsis.

Team BrainX is one of the only 62 teams in the 2nd round of IBM Watson Artificial Intelligence X-Prize.

New data and educational material!

Check out the new resources through data and learn links on main page.

We have added new links to data sources for open source data groups having significant amount of data for research and development.Landmark research articles are being added on a daily basis.

CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning

ChexNet is a 121 layer convolutional neural network developed at Stanford University which reads chest X-ray images to diagnose 14 different chest diseases including Pneumonia.In this study 112,120 chest X-ray images of 30,805 patients were analyzed to develop the algorithm.CheXNet achieved an F1 score of 0.435 (95% CI 0.387, 0.481), higher than the radiologist average of 0.387 (95% CI 0.330, 0.442).

Read this paper using the link below:

What is an F-1 score?

F1 score is harmonic mean of precision and recall used frequently in machine learning to measure accuracy of a test.

F1 = 2 x (Precision x Recall)/(Precision + Recall)

Best F1 score is 1 and worst is 0.



Why the world needs BRAINX COMMUNITY.

With the adoption of electronic health records in healthcare, access to digital data has created an opportunity that never existed before.While data which still resides in smaller protected  silos of various healthcare systems is growing,so are many other platforms which includes wearables, smart devices with IOT capabilities and connected care.These are only going to exponentially increase the amount of data we collect and store.

Are we ready to use this data?

Healthcare professionals need to work together with machine learning experts to create innovative solutions and advanced analytics platforms for data processing, meaningful use and ultimately impactful interventions which will advance patient care.

How will we intersect?

Currently,other than a few episodic meetings there is no venue for constant interaction between the healthcare community,machine learning experts and others with similar interests.

Hence,the need to create the BRAINX COMMUNITY which is the first online community providing a platform for connected exchange of information and development.

Piyush Mathur MD,FCCM