Predictors of the Healthy Eating Index and Glycemic Index in Multi-Ethnic Colorectal Cancer Families

Abstract

For personalized nutrition in preparation for precision healthcare, we examined the predictors of healthy eating, using the healthy eating index (HEI) and glycemic index (GI), in family-based multi-ethnic colorectal cancer (CRC) families. A total of 106 participants, 53 CRC cases and 53 family members from multi-ethnic families participated in the study. Machine learning validation procedures, including the ensemble method and generalized regression prediction, Elastic Net with Akaike’s Information Criterion with correction and Leave-One-Out cross validation methods, were applied to validate the results for enhanced prediction and reproducibility. Models were compared based on HEI scales for the scores of 77 versus 80 as the status of healthy eating, predicted from individual dietary parameters and health outcomes. Gender and CRC status were interactive as additional predictors of HEI based on the HEI score of 77. Predictors of HEI 80 as the criterion score of a good diet included five significant dietary parameters (with intake amount): whole fruit (1 cup), milk or milk alternative such as soy drinks (6 oz), whole grain (1 oz), saturated fat (15 g), and oil and nuts (1 oz). Compared to the GI models, HEI models presented more accurate and fitted models. Milk or a milk alternative such as soy drink (6 oz) is the common significant parameter across HEI and GI predictive models. These results point to the importance of healthy eating, with the appropriate amount of healthy foods, as modifiable factors for cancer prevention.

Gene-Metabolite Interaction in the One Carbon Metabolism Pathway: Predictors of Colorectal Cancer in Multi-Ethnic Families

“…The study methods were reported before [ 43 , 52 ] and are summarized in the following. We included 30 participants, 15 CRC cases and 15 matched family/friend controls by accessing the California Cancer Registry (CCR) database and other cases through referrals from the community where the study was conducted.…”

“…We included 30 participants, 15 CRC cases and 15 matched family/friend controls by accessing the California Cancer Registry (CCR) database and other cases through referrals from the community where the study was conducted. The designated Human Subjects Institutional Review Boards (IRB) from the local educational institutions and the California State Committee for the Protection of Human Subjects (CPHS 12-12-1007) approved the project [ 43 , 52 ]. With the approved study procedures, the qualified participants were recruited.…”

“…Demographic data included lifestyle and dietary status [ 43 , 52 , 53 ], family history, functional capacities using the items included in the 1999–2012 National Health Interview Survey [ 54 ] and the family pedigrees from the Coalition for Health Professional Education in Genetics [ 55 ].…”

“…In this study we employed supervised machine learning because the target variable is specified. The analytics and rationales have been reported earlier [ 43 , 52 ] and are summarized in the following. We used bootstrap forest, also known as bagging (i.e., bootstrap aggregating), which is one of the most popular ensemble methods [ 44 , 45 , 46 , 47 ].…”

A case–control study on dietary quality indices and glioma

“…These indices consider the whole diet rather than its individual components. DDS along with AHEI have been shown as a measure of healthy diet rich in fruits, vegetables and photochemicals (13)(14)(15) . Although different measures of diet have been linked with cancers, no study examined these indicators in relation to glioma.…”