SOLICITATION NOTICE
Q -- Development of Machine-Learned Bayesian Belief Networks (BBNs) and Web Interface for Gastric Cancer and Pancreatic Cancer
- Notice Date
- 12/20/2011
- Notice Type
- Presolicitation
- NAICS
- 541990
— All Other Professional, Scientific, and Technical Services
- Contracting Office
- Department of Health and Human Services, National Institutes of Health, National Cancer Institute, Office of Acquisitions, 6120 Executive Blvd., EPS Suite 600, Rockville, Maryland, 20852
- ZIP Code
- 20852
- Solicitation Number
- NCI-120017-LG
- Archive Date
- 1/19/2012
- Point of Contact
- Laura Glockner, Phone: 3014968607
- E-Mail Address
-
laura.glockner@nih.gov
(laura.glockner@nih.gov)
- Small Business Set-Aside
- N/A
- Description
- Department of Health and Human Services, National Institutes of Health, National Cancer Institute, Office of Acquisitions, 6120 Executive Boulevard, EPS Suite 600, Room 6070, Rockville, MD 20852, UNITED STATES. Description The National Cancer Institute (NCI), Center for Cancer Research (CCR), Surgery Branch plans to procure on a sole source basis services from DecisionQ Corporation, 1010 Wisconsin Avenue, Suite 310, Washington, DC 20007 for the development of prognostic and predictive models for gastric cancer and pancreatic cancer using machine-learned Bayesian Belief Networks. This acquisition will be processed in accordance with simplified acquisition procedures in FAR Part 13.106 (b)(1). The North American Industry Classification System code is 541990 and the business size standard is $7.0 million. Only one award will be made as a result of this solicitation. This will be awarded as a firm fixed price type contract. It has been determined that there is no opportunity to acquire green products or services under this procurement. Period of Performance: Performance shall be for twelve (12) months from date of award. The Surgery Branch of the National Cancer Institute is involved in the conduct of laboratory and clinical research aimed at improving the care, management, and outcome of patients with cancer. As such, Surgery Branch investigators are developing prognostic and predictive models for gastric and pancreatic cancer outcomes using machine-learned Bayesian Belief Networks. A set of SEER Public Use data will be used to produce Bayesian Belief Network (BBN) classifiers that can estimate the probability of mortality of a given subject at 12, 24, 36, and 60 months for each of Gastric Cancer and Pancreatic Cancer. These models will be cross-validated for statistical significance and interpreted for clinical significance. The models will be enabled in a web- or mobile interface so that they can be used by clinicians to derive individual prognostic estimates. Following the identification and curation of the SEER data and the preparation of training and test sets, the data will be modeled using machine-learning to produce Bayesian Belief Networks. The machine-learning algorithm must use Bayesian Information Criterion scoring or equivalent (Minimum Description Length or Model Length scoring). The machine learning algorithm should be capable of handling 100+ features simultaneously, handling features with up to 100 unique text levels, and capable of incorporating text, numeric, and date values in the same training exercise and model. The Bayesian Belief Networks produced by the algorithm must be stored in a readily accessible format (XML, HTML, PMML, or equivalent) and be capable of display through a web interface that a user can use to interact with the algorithms. DecisionQ Corporation is the only known contractor that can perform the required services for this contract. DecisionQ sells the proprietary software, FasterAnalytics, and services that are the only known products capable of training machine-learned Bayesian models from these types of data sets. DecisionQ Corporation is the only certified provider with this software to the healthcare sector. FasterAnalytics is a proprietary product using a proprietary algorithm and is sold only by the contractor, DecisionQ Corporation. This is not a solicitation for competitive quotations. However, if any interested party believes they can meet the above requirement, they may submit a statement of capabilities. All information furnished must be in writing and must contain sufficient detail to allow the NCI to determine if it can meet the above unique specifications described herein. An original and one copy of the capability statement must be received in the NCI Office of Acquisition on or before 11:00 AM EST on January 4, 2012. No electronic capability statements will be accepted (i.e. email or fax) an original and one copy must be sent to the NCI Office of Acquisition to the address stated above. All questions must be in writing and can be faxed (301) 402-4513 or emailed to Laura Glockner, Contract Specialist at laura.glockner@nih.gov. A determination by the Government not to compete this proposed contract based upon responses to this notice is solely within the discretion of the Government. Information received will be considered solely for the purpose of determining whether to conduct a competitive procurement. In order to receive an award, contractors must have valid registration and certification in the Central Contractor Registration (CCR) www.ccr.gov and the Online Representations and Certifications Applications (ORCA), http://orca.bpn.gov. No collect calls will be accepted. Please reference solicitation number NCI-120017-LG on all correspondence.
- Web Link
-
FBO.gov Permalink
(https://www.fbo.gov/spg/HHS/NIH/RCB/NCI-120017-LG/listing.html)
- Record
- SN02642436-W 20111222/111220234306-2f9c865f7aa566bf3d786ffd546e6760 (fbodaily.com)
- Source
-
FedBizOpps Link to This Notice
(may not be valid after Archive Date)
| FSG Index | This Issue's Index | Today's FBO Daily Index Page |