Perceived Threat and Internet Use Predict Intentions to Get Bowel Cancer Screening (Colonoscopy): Longitudinal Questionnaire Study

Large-data contextualizations of social determinant associations in pediatric head and neck cancers

PURPOSE OF REVIEW

Prior investigations in social determinants of health (SDoH) and their impact on pediatric head and neck cancers are limited by the narrow scope of cancer types and SDoH being studied while lacking inquiry on the interrelational contribution of varied SDoH in real-world contexts. The purpose of this review is to discuss the current research tackling these shortcomings of SDoH-based studies in head and neck cancer and to discuss means of applying these findings in prospective initiatives and implementations.

RECENT FINDINGS

Through leveraging contemporary, large-data analyses measuring diverse social vulnerabilities, several studies have identified comprehensive delineations of which social disparities contribute the largest quantifiable impact on the care of head and neck cancer patients. Progressing from prior SDoH-based research of the decade, these studies contextualize the effect of social vulnerabilities and have laid the foundations to begin addressing these issues in the complex, modern-day environment of interrelatedsocial factors.

SUMMARY

Social determinants of health markedly affect pediatric head and neck cancer care and prognosis in complex and surprising ways. Modern-day tools and analyses derived from large-data techniques have unveiled the quantifiable underpinnings of how SDoH impact these pathologies.

Assessing eHealth Literacy and Identifying Factors Influencing Its Adoption Among Cancer Inpatients: A Cross-Sectional Study in Guangdong Population

Purpose

The purpose of this study was to investigate the current state of eHealth literacy among cancer patients in a grade A tertiary hospital in Guangzhou, Guangdong Province, and to identify the factors that influence it, in order to provide a basis for improving the eHealth literacy of cancer patients.

Patients and Methods

From September to November 2021, a convenience sampling method was employed to survey cancer patients in the oncology department of a grade A tertiary hospital in Guangzhou, using a self-administered general information questionnaire and the eHealth literacy scale (eHEALS). A total of 130 questionnaires were distributed, and 117 valid questionnaires were returned.

Results

The mean total score of eHealth literacy among cancer patients was 21.32±8.35. Multiple linear regression analysis revealed that the frequency of searching for health information and education level were significant factors influencing eHealth literacy (p<0.05). Specifically, the education level (junior high school vs primary school or below) was found to have a significant association with eHealth literacy (beta=0.26, p=0.039).

Conclusion

The results of this study suggest that the eHealth literacy of cancer patients is relatively low, with low scores on the dimensions of judgment and decision-making ability. The government and relevant regulatory authorities should focus on strengthening the reliability of online health information and implementing targeted e-interventions to enhance the eHealth literacy of cancer patients.

Factors influencing the e-health literacy in cancer patients: a systematic review

PURPOSE

As Internet technology evolves, electronic health (e-health) literacy gradually becomes a key factor in healthy behaviors and health-related decision-making. However, little is known about the influencing factors of e-health literacy among cancer survivors. Thus, the objective of this study was to systematically review the status quo, assessment tools, and influencing factors of e-health literacy in cancer patients.

METHODS

We conducted a comprehensive search in several databases, including PubMed, MEDLINE, Embase, CINAHL, PsycInfo, Cochrane Library, China National Knowledge Infrastructure, Wanfang Database, Chinese BioMedical Literature Database, and Chinese Science and Technology Journal Database between January 2000 and December 2021.

RESULTS

A total of nine articles were included in this review, all of which were cross-sectional studies. Following the JBI critical appraisal tool, seven of them were rated as high quality. The e-Health Literacy Scale (eHEALS) was the most commonly used measurement for e-health literacy in cancer patients. The level of e-health literacy in cancer survivors was not high, which was associated with a variable of factors. The behavioral model of health services use was adopted to summarize related influencing factors. From an individual's perspective, predisposing characteristics and enabling resources were the most significant factors, without factors related to needs characteristics.

CONCLUSION

The study has identified the influencing factors of e-health literacy among cancer survivors, including age, gender, domicile place, education level, information-seeking behavior, and social support. In the future, e-health literacy lectures need to be carried out for elderly cancer patients, especially those who live in rural areas and have no access to the Internet. Families and friends of cancer survivors should also be encouraged to offer them more support.

IMPLICATIONS FOR CANCER SURVIVORS

These findings of this review provide novel insights for both family members and medical workers to improve e-health literacy in cancer patients. Further research is required to develop easy-to-use electronic health information acquisition devices and establish propagable e-health literacy intervention programs for cancer survivors.

Blood Biomarkers Panels for Screening of Colorectal Cancer and Adenoma on a Machine Learning-Assisted Detection Platform

OBJECTIVE

A mini-invasive and good-compliance program is critical to broaden colorectal cancer (CRC) screening and reduce CRC-related mortality. Blood testing combined with imaging examination has been proved to be feasible on screen for multicancer and guide intervention. The study aims to construct a machine learning-assisted detection platform with available multi-targets for CRC and colorectal adenoma (CRA) screening.

METHODS

This was a retrospective study that the blood test data from 204 CRCs, 384 CRAs, and 229 healthy controls was extracted. The classified models were constructed with 4 machine learning (ML) algorithms including support vector machine (SVM), random forest (RF), decision tree (DT), and eXtreme Gradient Boosting (XGB) based on the candidate biomarkers. The importance index was used by SHapely Adaptive exPlanations (SHAP) analysis to identify the dominant characteristics. The performance of classified models was evaluated. The most dominating features from the proposed panel were developed by logistic regression (LR) for identification CRC from control.

RESULTS

The candidate biomarkers consisted of 26 multi-targets panel including CEA, AFP, and so on. Among the 4 models, the SVM classifier for CRA yields the best predictive performance (the area under the receiver operating curve, AUC: .925, sensitivity: .904, and specificity: .771). As for CRC classification, the RF model with 26 candidate biomarkers provided the best predictive parameters (AUC: .941, sensitivity: .902, and specificity: .912). Compared with CEA and CA199, the predictive performance was significantly improved. The streamlined model with 6 biomarkers for CRC also obtained a good performance (AUC: .946, sensitivity: .885, and specificity: .913).

CONCLUSIONS

The predictive models consisting of 26 multi-targets panel would be used as a non-invasive, economical, and effective risk stratification platform, which was expected to be applied for auxiliary screening of CRA and CRC in clinical practice.

Colorectal Cancer Detected by Machine Learning Models Using Conventional Laboratory Test Data

Background: Current diagnostic methods for colorectal cancer (CRC) are colonoscopy and sigmoidoscopy, which are invasive and complex procedures with possible complications. This study aimed to determine models for CRC identification that involve minimally invasive, affordable, portable, and accurate screening variables. Methods: This was a retrospective study that used data from electronic medical records of patients with CRC and healthy individuals between July 2017 and June 2018. Laboratory data, including liver enzymes, lipid profiles, complete blood counts, and tumor biomarkers, were extracted from the electronic medical records. Five machine learning models (logistic regression, random forest, k-nearest neighbors, support vector machine [SVM], and naïve Bayes) were used to identify CRC. The performances were evaluated using the areas under the curve (AUCs), sensitivity, specificity, positive predictive values (PPV), and negative predictive values (NPV). Results: A total of 1164 electronic medical records (CRC patients: 582; healthy controls: 582) were included. The logistic regression model achieved the highest performance in identifying CRC (AUC: 0.865, sensitivity: 89.5%, specificity: 83.5%, PPV: 84.4%, NPV: 88.9%). The first four weighted features in the model were carcinoembryonic antigen (CEA), hemoglobin (HGB), lipoprotein (a) (Lp(a)), and high-density lipoprotein (HDL). A diagnostic model for CRC was established based on the four indicators, with an AUC of 0.849 (0.840-0.860) for identifying all CRC patients, and it performed best in discriminating patients with late colon cancer from healthy individuals with an AUC of 0.905 (0.889-0.929). Conclusions: The logistic regression model based on CEA, HGB, Lp(a), and HDL might be a powerful, noninvasive, and cost-effective method to identify CRC.

Using Decision Tree Aggregation with Random Forest Model to Identify Gut Microbes Associated with Colorectal Cancer

The imbalance of human gut microbiota has been associated with colorectal cancer. In recent years, metagenomics research has provided a large amount of scientific data enabling us to study the dedicated roles of gut microbes in the onset and progression of cancer. We removed unrelated and redundant features during feature selection by mutual information. We then trained a random forest classifier on a large metagenomics dataset of colorectal cancer patients and healthy people assembled from published reports and extracted and analysed the information from the learned decision trees. We identified key microbial species associated with colorectal cancers. These microbes included Porphyromonas asaccharolytica, Peptostreptococcus stomatis, Fusobacterium,Parvimonas sp., Streptococcus vestibularis and Flavonifractor plautii. We obtained the optimal splitting abundance thresholds for these species to distinguish between healthy and colorectal cancer samples. This extracted consensus decision tree may be applied to the diagnosis of colorectal cancers.