scholarly journals Evaluation of algorithms using administrative health and structured electronic medical record data to determine breast and colorectal cancer recurrence in a Canadian province

2020 ◽  
Author(s):  
Kathleen Decker ◽  
Pascal Lambert ◽  
Marshall Pitz ◽  
Harminder Singh
Keyword(s):  
Colorectal Cancer ◽  
Validation Cohort ◽  
Cancer Recurrence ◽  
Conditional Inference ◽  
Brier Score ◽  
Correct Classification ◽  
Canadian Province ◽  
Conditional Inference Tree ◽  
Colorectal Cancer Recurrence ◽  
Inference Tree

Abstract Background: Algorithms that use administrative health and electronic medical record (EMR) data to determine cancer recurrence have the potential to replace chart reviews. This study evaluated algorithms to determine breast and colorectal cancer recurrence in a Canadian province with a universal health care system.Methods: Individuals diagnosed with stage I-III breast or colorectal cancer diagnosed from 2004 to 2012 in Manitoba, Canada were included. Pre-specified and conditional inference tree algorithms using administrative health and structured EMR data were developed. Sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) correct classification, and scaled Brier scores were measured.Results: The weighted pre-specified variable algorithm for the breast cancer validation cohort (N=1181, 167 recurrences) demonstrated 81.1% sensitivity, 93.2% specificity, 61.4% PPV, 97.4% NPV, 91.8% correct classification, and scaled Brier score of 0.21. The weighted conditional inference tree algorithm demonstrated 68.5% sensitivity, 97.0% specificity, 75.4% PPV, 95.8% NPV, 93.6% correct classification, and scaled Brier score of 0.39. The weighted pre-specified variable algorithm for the colorectal validation cohort (N=693, 136 recurrences) demonstrated 77.7% sensitivity, 92.8% specificity, 70.7% PPV, 94.9% NPV, 90.1% correct classification, and scaled Brier score of 0.33. The conditional inference tree algorithm demonstrated 62.6% sensitivity, 97.8% specificity, 86.4% PPV, 92.2% NPV, 91.4% correct classification, and scaled Brier score of 0.42. Conclusions: Algorithms using administrative health and structured EMR data to determine breast and colorectal cancer recurrence had moderate sensitivity and PPV, high specificity, NPV, and correct classification, but low accuracy. Algorithms for determining cancer recurrence must improve before replacing chart reviews.

scholarly journals Evaluation of algorithms using administrative health and structured electronic medical record data to determine breast and colorectal cancer recurrence in a Canadian province

BMC Cancer ◽  
2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Pascal Lambert ◽  
Marshall Pitz ◽  
Harminder Singh ◽  
Kathleen Decker
Keyword(s):  
Colorectal Cancer ◽  
Validation Cohort ◽  
Cancer Recurrence ◽  
Conditional Inference ◽  
Brier Score ◽  
Correct Classification ◽  
Canadian Province ◽  
Conditional Inference Tree ◽  
Colorectal Cancer Recurrence ◽  
Inference Tree

Abstract Background Algorithms that use administrative health and electronic medical record (EMR) data to determine cancer recurrence have the potential to replace chart reviews. This study evaluated algorithms to determine breast and colorectal cancer recurrence in a Canadian province with a universal health care system. Methods Individuals diagnosed with stage I-III breast or colorectal cancer diagnosed from 2004 to 2012 in Manitoba, Canada were included. Pre-specified and conditional inference tree algorithms using administrative health and structured EMR data were developed. Sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) correct classification, and scaled Brier scores were measured. Results The weighted pre-specified variable algorithm for the breast cancer validation cohort (N = 1181, 167 recurrences) demonstrated 81.1% sensitivity, 93.2% specificity, 61.4% PPV, 97.4% NPV, 91.8% correct classification, and scaled Brier score of 0.21. The weighted conditional inference tree algorithm demonstrated 68.5% sensitivity, 97.0% specificity, 75.4% PPV, 95.8% NPV, 93.6% correct classification, and scaled Brier score of 0.39. The weighted pre-specified variable algorithm for the colorectal validation cohort (N = 693, 136 recurrences) demonstrated 77.7% sensitivity, 92.8% specificity, 70.7% PPV, 94.9% NPV, 90.1% correct classification, and scaled Brier score of 0.33. The conditional inference tree algorithm demonstrated 62.6% sensitivity, 97.8% specificity, 86.4% PPV, 92.2% NPV, 91.4% correct classification, and scaled Brier score of 0.42. Conclusions Algorithms developed in this study using administrative health and structured EMR data to determine breast and colorectal cancer recurrence had moderate sensitivity and PPV, high specificity, NPV, and correct classification, but low accuracy. The accuracy is similar to other algorithms developed to classify recurrence only (i.e., distinguished from second primary) and inferior to algorithms that do not make this distinction. The accuracy of algorithms for determining cancer recurrence only must improve before replacing chart reviews.

Rising Stars and Underdogs: The Role Race and Parental Education Play in Predicting Mentorship

2021 ◽  
pp. 0044118X2110046
Author(s):  
Veronica Fruiht ◽  
Jordan Boeder ◽  
Thomas Chan
Keyword(s):  
Critical Race Theory ◽  
Parental Education ◽  
Individual Characteristics ◽  
Conditional Inference ◽  
Youth Of Color ◽  
Social Success ◽  
Conditional Inference Tree ◽  
Tree Models ◽  
Nationally Representative ◽  
Inference Tree

Research suggests that youth with more financial and social resources are more likely to have access to mentorship. Conversely, the rising star hypothesis posits that youth who show promise through their individual successes are more likely to be mentored. Utilizing a nationally representative sample ( N = 4,882), we tested whether demographic characteristics (e.g., race, SES) or personal resources (e.g., academic/social success) are better predictors of receiving mentorship. Regression analyses suggested that demographic, contextual, and individual characteristics all significantly predicted access to mentorship, specifically by non-familial mentors. However, conditional inference tree models that explored the interaction of mentorship predictors by race showed that individual characteristics mattered less for Black and Latino/a youth. Therefore, the rising star hypothesis may hold true for White youth, but the story of mentoring is more complicated for youth of color. Findings highlight the implications of Critical Race Theory for mentoring research and practice.

scholarly journals The association between the adapted dietary inflammatory index and colorectal cancer recurrence and all-cause mortality

2021 ◽  
Author(s):  
Evertine Wesselink ◽  
Laura E. Staritsky ◽  
Moniek van Zutphen ◽  
Anne J.M.R. Geijsen ◽  
Dieuwertje E. Kok ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Cancer Recurrence ◽  
Dietary Inflammatory Index ◽  
Inflammatory Index ◽  
All Cause Mortality ◽  
Colorectal Cancer Recurrence

Prognostic Impact of Sarcopenia in Colorectal Cancer Recurrence

Nutrition ◽  
2021 ◽  
pp. 111362
Author(s):  
Koichi Takiguchi ◽  
Shinji Furuya ◽  
Makoto Sudo ◽  
Ryo Saito ◽  
Atsushi Yamamoto ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Cancer Recurrence ◽  
Prognostic Impact ◽  
Colorectal Cancer Recurrence

Local colorectal cancer recurrence: pelvic MRI evaluation

2012 ◽  
Vol 38 (1) ◽  
pp. 72-81 ◽  
Author(s):  
A. Colosio ◽  
P. Fornès ◽  
P. Soyer ◽  
M. Lewin ◽  
M. Loock ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Cancer Recurrence ◽  
Pelvic Mri ◽  
Colorectal Cancer Recurrence ◽  
Mri Evaluation

scholarly journals A Complicated Colorectal Cancer Recurrence

2020 ◽  
Vol 18 (1) ◽  
pp. 25-27
Author(s):  
Anna Marija Lescinska ◽  
Valerija Grakova ◽  
Aleksandrs Malasonoks ◽  
Armands Sivins
Keyword(s):  
Colorectal Cancer ◽  
Case Report ◽  
Cancer Recurrence ◽  
Cancer Death ◽  
Treatment Results ◽  
Western Countries ◽  
The Third ◽  
Common Cancer ◽  
One Step ◽  
Colorectal Cancer Recurrence

SummaryThe case report demonstrates painstaking, one step at a time multitherapy for the third most common cancer and the third cause of cancer death in western countries – colorectal cancer. Multitherapeutic approach at specialized centers for the treatment of colorectal cancer is the cornerstone for reaching favorable treatment results and prognosis.

Sign in / Sign up

Export Citation Format

Share Document