Digital Health Innovation and Informatics

PV QA 2 - Poster Viewing Q&A 2

MO_18_2748 - Risk-Index of Colorectal Cancer to Triage for Screening

Monday, October 22
10:45 AM - 12:15 PM
Location: Innovation Hub, Exhibit Hall 3

Risk-Index of Colorectal Cancer to Triage for Screening
B. Nartowt1, G. R. Hart1, I. Ali1, W. Muhammad2, Y. Liang1, D. A. Roffman3, and J. Deng1; 1Department of Therapeutic Radiology, Yale School of Medicine, Yale University, New Haven, CT, 2Yale Therapeutic Radiology, New Haven, CT, 3Yale University, New Haven, CT

   Purpose/Objective(s): Colorectal cancer (CRC) is the unregulated growth of one or more adenomatous polyps (most frequently adenocarcinomas) occurring in the colon and/or the rectum. Of all new cancer cases in the US, 8.0% are colorectal. Colorectal cancer claims 8.4% of all cancer-deaths and thus has above-average mortality vs. other cancers. To detect CRC at early stages, the United States Preventative Services Task Force (USPSTF) recommends screening by colonoscopy or sigmoidoscopy for ages 50-75. However, the high false positive rates of these procedures lead to a lot of unnecessary screening. The goal of this study is to develop an artificial neural network (ANN) for colorectal cancer risk prediction usable for triaging people for screening based on their personal health data. Materials/Methods: The data to train and validate the ANN is the set of 1997-2016 responses (excepting 2004) to the National Health Interview Survey (NHIS) personal health questionnaire, in which colon and/or rectal cancer occurring 4 years or less from the survey date is counted as one instance of CRC. Respondents with 1 or more null entries were discarded. Using 70% of the NHIS data, training uses gradient descent in parameter space to adjust the parameters of a softmax-function and minimize a logistic cost function (regression). The extent to which the parameters are adjusted is calculated using the chain rule of calculus (backpropagation). The validation tests the regression-fitted function upon the remaining 30% of the data. As a binary test, sensitivity (TPR), specificity (SPC), and positive/negative predictive values (PPV/NPV) are calculated and compared with the USPSTF. As a trinary test, three levels of risk-stratification are defined by requiring that no more than 1% of CRC/non-CRC cases be misclassified as low/high-risk. If a person of medium risk having/not having CRC is counted as half of a false negative/positive (e.g., annual/biennial screenings for those of high/medium risk), the trinary test of risk-stratification also has an associated TPR, SPC, PPV, and NPV.

Results: As a binary test, the ANN has sensitivity of 0.7, specificity of 0.7, PPV of 0.09, and NPV of 0., all (except for NPV) exceeding the USPSTF guidelines and independent of tumorous advancement. As a trinary test, lowered SPC and PPV are exchanged for higher TPR and NPV. Table 1: Performance of USPSTF (entire data set) compared to the ANN (validation-portion of data set, only).

CRC, # screened

CRC, # not screened

No CRC, # screened

No CRC, # not screened

ANN (bi.)





ANN (tri.)














ANN (bi.)





ANN (tri.)










Conclusion:   CRC risk calculated by ANN from personal health data is noninvasive, insensitive to tumorous advancement, & outperforms USPSTF screening guidelines as a binary and trinary test. In addition, the ANN offers the prospect of CRC risk assessment in real time and on the world map.

Author Disclosure: B. Nartowt: None. G.R. Hart: None. I. Ali: None. W. Muhammad: None. Y. Liang: None. D.A. Roffman: None. J. Deng: Research Grant; NIH. Board member; Physics in Medicine and Biology.

Bradley Nartowt, PhD

Bradley Joseph Nartowt was born in Worcester, MA, and grew up in Oxford, MA. He attended St. Peter-Marian Jr./Sr. High School in Worcester, MA, where he participated in football, track-and-field, and cross country. He was awarded the Gilrein Family Memorial Scholarship on graduation.

During his undergraduate program at Franciscan University of Steubenville, in Steubenville, OH, Bradley earned repeated placement on the Dean’s List, and in June of 2006 received his Bachelor of Science with honors in Mathematical Science, with minors in chemistry and engineering science. After working in a metallography lab and operating furnaces while taking graduate classes for a year, he was then invited into the graduate program in materials science and engineering at the University of Florida, where he received his Master of Science in December of 2008. He then became a graduate researcher and teacher at the University of Minnesota, Duluth, from 2009 to 2011, earning a Master of Science in physics in May of 2011.

Bradley returned to the University of Florida in August of 2011 to begin a PhD in physics. During this program, he researched the thermoelectric effect, and invented a method at the proof-of-concept level to access the nonlinear regime of a thermoelectric device.

Bradley currently is a postdoctoral associate for Yale University using machine-learning methods to predict risk of and determine factors causing colorectal cancer, as well as simulating delivery of therapeutic radiation to tumors.


Send Email for Bradley Nartowt


MO_18_2748 - Risk-Index of Colorectal Cancer to Triage for Screening

Attendees who have favorited this

Please enter your access key

The asset you are trying to access is locked. Please enter your access key to unlock.

Send Email for Risk-Index of Colorectal Cancer to Triage for Screening