Showing posts with label Riff. Show all posts
Showing posts with label Riff. Show all posts

Friday, November 26, 2010

Diseases and Disasters (Dis2): Riff’s Performance

A couple of years ago, I introduced Riff; a hybrid (event-based and indicator-based) disease surveillance platform, at the International Society for Disease Surveillance (ISDS) [the original concept is fully described here - more up-to-date information can be found on InSTEDD's website here].  Riff was designed to streamline the collaboration between human experts dealing with diverse streams of information and enabling them with machine learning algorithms that can learn quickly and accurately classify the information for detection, prediction and response to health-related events (such as disease outbreaks or pandemics).  On Jan 17th 2010, the Thomson Reuters Foundation used Riff [after prior adoption in their EIS system; an Emergency Information Service for survivors of natural disasters (early work can be found in Nico’s Blog here)] to launch a first-of-its kind, free disaster-information service for the people of Port Au Prince, Haiti. This allowed survivors of Haiti's earthquake to receive critical information by text message directly to their phones, free of charge.

Earlier this year; April 2010, I setup a Riff space; Diseases and Disasters (or Dis2), for providing timely situation awareness from credible and reliable [gold standard of a sort] online reports on diseases and disasters in the world provided primarily by BioCaster and HealthMap. This already tagged and verified information provided Riff’s classifier with a great training opportunity that I had to monitor closely and correct at the beginning for both features (e.g., condition, type of disease transmission, severity, etc.) and geo-location of where the event actually occurred as shown here:

Conditions Tracked in Dis2 Proportional to their Coverage since April 19, 2010
%Conditions Tracked in Dis2 since April 19, 2010
Location of Conditions Tracked in Dis2 Proportional to their Coverage since April 19, 2010
Location (Heatmap) of Conditions Tracked in Dis2 since April 19, 2010


In collaboration with the Humanitarian FOSS Project; supported by a group of computing faculty and open source proponents at Trinity College, Wesleyan University, and Connecticut College (Open Source ALPACA Light Parsing And Classifying Application (ALPACA) and Open Source e-dop for Disease Ontology Prediction for Riff), we developed a Support Vector Machines (or SVM) for automatic feature extraction, data classification and tagging. Riff’s classifier performed incredibly well in the Dis2collaborative space with very little training at the outset; 83% (95% CI: 81-85%) True Positive rate as shown here:

Riff's Performance in the Dis2 Collaborative Space (True Positive and False Negative Ratios)
Riff's Performance in the Dis2 Collaborative Space (True Positive and False Negative Ratios)


Riff is an Open Source Project, you can download its source code here and help further enhance its performance. 

Acknowledgment


Monday, June 21, 2010

Dengue Fever in Florida (in the US?)

An outbreak in Key West, Fla., has re-emerged in April 2010. Historically, dengue was in Florida in the early 1900, but locally-acquired cases had not been confirmed since then until August 2009.  The recent Florida outbreak might have gone unnoticed if it hadn't been for an astute physician in upstate New York who identified the first case in Rochester, N.Y., involving a patient who had just returned from a week-long visit to Key West.

In the US, dengue fever has rarely been an issue outside of the Texas-Mexico border region, but currently it is estimated that more than half of the US population live in places which contain one or both of mosquito species capable of transmitting the dengue fever virus creating conditions more favorable for an outbreak.  Dengue is now [starting last year] a reportable disease in the US due to its increasing threat.

Dengue fever is characterized by agonizing aching in the bones, joints and muscles, a pounding headache, pain behind the eyes, a high fever and a classic rash. There is no cure or vaccine, only preventative and supportive care. 

Sunday, March 1, 2009

Open Collaboration Experiment around Emergency Alerts, Disasters, Market Recalls, and More...

We set up two open collaboration spaces around up-to-date notifications and alerts on the following:

- Emergency Preparedness & Response alerts, Recent Outbreaks and Incidents, Clinician Outreach and Communication Activity (COCA), and Public Service Announcements for Hurricanes from US CDC

- Recalls, market withdrawals and safety alerts from the the U.S. Food and Drug Administration (FDA)

These spaces offer a suite of collaborative features, including: commenting, tagging (adding your own keywords), mapping (user generated and automated), relating multiple alerts, searching and filtering, specifying a time window, adding attachments, subscribing (currently in the form of a web-friendly format also known as RSS, but in the very near future we will support email subscription), and more. The two spaces are also equipped with an intelligent process (referred to as machine-learning algorithm) that "learns" from inputs provided by the users (e.g., adding a keyword (tag), or correcting the mapping of an item). This intelligent process quickly and accurately learns from users inputs (with 95% confidence based on previous tests) and starts suggesting tags as well as correcting itself and offering even better results over time (by simply accepting or rejecting a suggested tag or an automatically mapped location).

Have you an alert or item you like to share with the community? You can easily contribute that alert by clicking the "Add Item" feature.

We invite you to try it and help us spread the good word by inviting others as well. We look forward to your feedback and comments in order to make this tool as useful as it can possibly be. If you have thoughts or questions you can contact us at info@instedd.org or email me directly at: kasshout@instedd.org.

Tuesday, December 9, 2008

2nd International Conference on Global Health Applications of Handheld Computing Devices Conference

On November 24th, Eric and I presented at the 2nd International Conference on Global Health Applications of Handheld Computing Devices, at US CDC in Atlanta, GA.


Several opening talks reflected on our presence and our tools, including:

1) Leslie (Les) Lenert, Director, National Center for Public Health Informatics, US CDC:


2) Sally Stansfield, Executive Director, Health Metrics Network, WHO, Geneva:


3) Mark Landry, Health Informatics, Office of Global AIDS Coordinator, Department of State, who described InSTEDD as “the best out of the box thinking

Related Links:

Sunday, October 26, 2008

1st PHI Workshop at Mahidol: Collaborations in Public Health Informatics among MBDS and SEAMEO Countries

Nico and I were invited to present at the 1st Workshop on Public Health Informatics organized by Center for Excellence for Biomedical and Public Health Informatics (BIOPHICS), Faculty of Tropical Medicine at Mahidol University in Bangkok, Thailand (Sep 29-Oct 10, 2008). The workshop was co-organized by University of Washington and the Rockefeller Foundation. This two-week workshop introduced the discipline of public health informatics to an elite group of public health and information technology experts from the MBDS and SEAMEO countries (Vietnam, Yunnan, Cambodia, Lao PDR, Myanmar, Indonesia, Philippines, Thailand, etc.) The course included topics on the application of latest advancements in information science and technology in supporting public health practice, education and research.


On the morning of Thursday October 9, 2008, Nico and I gave 3 lectures on the application of machine learning for early detection and response, Open Source movement and licensing, and discussed various Open Source applications for public health. We introduced biosurveillance, its current challenges and limitations, and proposed a practical “collaborative approach” for effective early disease detection and response from local, national, and global perspectives.

We then had a lunch break with Assoc. Prof. Pratap Singhasivanon, Dean of Faculty of Tropical Medicine who also supervises BIOPHICS. We discussed with Dr. Pratap InSTEDD’s role in the region and the MBDS, the various projects and technology tools currently underway, the innovation lab model, and our gratitude for extending his invitation to us to present at the 1st PHI course.

We spent the majority of the afternoon in the computer lab where we offered hands-on training on various Open Source tools and projects, their implication to public health, and their role in the MBDS region. We also used this opportunity to introduce InSTEDD’s tools including: Mesh4X, Geochat (Overview, Details and source), Riff and RNA.

At the end of day, we had a quick tour of BIOPHICS and its various state-of-the art projects. We were briefed of BIOPHICS multi-clinical trials center (several million patients), observational studies and disease registry, and had a tour of the BIOPHICS data center. The clinical trials ranged from PK study, Phase I to Phase III studies, and Phase IV monitoring adverse drug reaction (ADR). We were also offered a demonstration of a versatile and mobile patient tracking system. Other services include computerized system development for disease surveillance and medical/laboratory data. BIOPHICS has experts in basic science, health science, public health, medical and information sciences and they offer various consulting services related to applications of genetics statistics, bioinformatics and clinical informatics.

On Friday October 10, 2008, each country had a representative speaker from their group who presented on their country's current challenges in disease surveillance and response, what they learned from the workshop, and how best to apply that to address the current system's limitations and challenges.

We were pleased to see how InSTEDD's tools and “collaborative” approach was mentioned in various discussions and considered to be part of the solution (Picture: The Cambodian team presented on their future solution and suggested using various InSTEDD tools and technologies as part of this solution.)

Afterwards, Nico and I sat on a final panel discussion that addressed participants’ questions with regards to the material presented during the workshop. We received various questions on the role of Geochat and SMS in enhancing and augmenting current surveillance and response activities in the MBDS and SEAMEO countries. Given the fact that text-messaging solutions can be cost-prohibitive for many localities, we discussed how Geochat’s “Gateway” offers an affordable alternative—requiring coordination between mobile providers and government agencies—and more features than regular text-messaging provided by local mobile companies.


We then concluded the session with graduation ceremony where participants received their certificate in PHI, the first for the region! Congrats!

After graduation, Dr. Moe Ko Oo, (Regional Coordinator for the MBDS project), Dr. Yin Myo Aye (Data Analyst & Manager for the MBDS project) and I had a meeting to further discuss the project and InSTEDD's contribution to the region. During the workshop we introduced various open source efforts projects; in particular we discussed two efforts which aggregate news media and ProMed reports, HealthMap and BioCaster. Dr. Moe and I discussed the importance of providing situation awareness capacity for the MBDS region by extending these efforts from detection into response. We discussed in details; as I mentioned in a previous blog, how the majority of current systems have been geared towards specific data sources and detection algorithms but much less effort has been focused on how these systems will "interact" with humans. Dr. Moe was very keen towards our “collaborative” approach, and I quote: “HealthMap, the data they are presenting in their web is good for us to know, but we would like to see more on it” and that efforts as such should offer a “…better analytical way for future planning and advocacy purpose.” We also discussed how our approach could further refine and enhance classification of health events especially at the earliest stages of an infectious disease outbreak. I had a follow-up discussion with Dr. John Browntein and his team is working with ProMed (recent grant from Google (healthMap/ProMed) through the Google Predict and Prevent initiative) on extending the current HealthMap platform to incorporate collaborative tools.