Positive health-promoting behaviors, including lifestyle factors (e.g., physical activity) and appropriate health service utilization (e.g., screening for secondary cancers), can minimize the health risks and challenges facing cancer survivors. The goal of this article is to examine factors associated with positive health behaviors in 2,615 posttreatment cancer survivors who completed the 2010 LIVESTRONG survey. Multivariate logistic regression was used to model odds of reporting each of six positive health behaviors “as a result of your experience with cancer”: three “healthy lifestyle” behaviors and three “health care utilization” behaviors. In fully adjusted models, factors associated with greater likelihood of engaging in positive lifestyle behaviors (e.g., physical activity, changing diet) included sociodemographic factors, greater knowledge about how to reduce cancer risk; and reporting more psychological benefits due to cancer (ps <.01). Factors associated with greater likelihood of attending medical appointments and obtaining recommended cancer screenings included older age, better patient–provider communication, greater knowledge about how to reduce cancer risk, and more psychological benefits of cancer (ps <.01). Results suggest that knowledge about how to prevent cancer and benefit finding after cancer are related to positive health behaviors broadly, whereas better patient–provider communication is associated with positive cancer screening and health care utilization but not healthy lifestyle behaviors. Clinical interventions targeting these modifiable factors could maximize positive health behavior changes among cancer survivors, affecting risk for cancer recurrence as well as overall health and well-being.
Background and objective Smoking is the largest preventable cause of death and diseases in the developed world, and advances in modern electronics and machine learning can help us deliver real-time intervention to smokers in novel ways. In this paper, we examine different machine learning approaches to use situational features associated with having or not having urges to smoke during a quit attempt in order to accurately classify high-urge states. Methods To test our machine learning approaches, specifically, Bayes, discriminant analysis and decision tree learning methods, we used a dataset collected from over 300 participants who had initiated a quit attempt. The three classification approaches are evaluated observing sensitivity, specificity, accuracy and precision. Results The outcome of the analysis showed that algorithms based on feature selection make it possible to obtain high classification rates with only a few features selected from the entire dataset. The classification tree method outperformed the naive Bayes and discriminant analysis methods, with an accuracy of the classifications up to 86%. These numbers suggest that machine learning may be a suitable approach to deal with smoking cessation matters, and to predict smoking urges, outlining a potential use for mobile health applications. Conclusions In conclusion, machine learning classifiers can help identify smoking situations, and the search for the best features and classifier parameters significantly improves the algorithms’ performance. In addition, this study also supports the usefulness of new technologies in improving the effect of smoking cessation interventions, the management of time and patients by therapists, and thus the optimization of available health care resources. Future studies should focus on providing more adaptive and personalized support to people who really need it, in a minimum amount of time by developing novel expert systems capable of delivering real-time interventions.
Objective The Institute of Medicine recommends cancer survivors completing treatment be provided with a treatment summary to facilitate delivery of patient-centered survivorship care. However, the relationship between treatment summary receipt and patient-centered communication (PCC) and overall quality of care (QOC) are not well understood. Methods Cancer survivors responding to the Health Information National Trends Survey reported treatment summary receipt, QOC, and experiences of six core functions of PCC. Multivariable logistic regression assessed the relationship between treatment summary receipt and PCC. The prevalence of survivors’ treatment summary receipt and demographic/clinical characteristics predictive of treatment summary receipt were also assessed. Results Of 359 respondents with a cancer history, 34.5% reported receiving a treatment summary. Greater treatment burden was associated with increased treatment summary receipt. Treatment summary receipt was associated with higher QOC and more PCC, both overall and for five of the six PCC functions. Conclusion The receipt of cancer treatment summaries may improve PCC and QOC for survivors. Practice Implications The positive relationship between treatment summary receipt and survivors’ PCC experience substantiates continued efforts to provide treatment summaries to survivors transitioning from active treatment to survivorship care. Future research should characterize mechanisms by which treatment summary provision may enhance PCC.
The Healthy People (HP) initiative outlines a comprehensive set of goals aimed at improving the nation’s health and reducing health disparities. Health Communication has been included as an explicit goal since the launch of HP 2010. The Health Information National Trends Survey (HINTS) was established as a means of exploring how the changing information environment was affecting the public’s health, and is therefore an ideal tool for monitoring key health communication objectives included in Healthy People agenda. In this paper, we apply an integrative data analysis strategy to over 10 years of HINTS data to demonstrate how public health surveillance can be used to evaluate broad national health goals, like those set forth under the Healthy People initiative. We analyzed just one item from the HINTS survey regarding Internet access in order to illustrate what public health surveillance tools, like HINTS, can reveal about important indicators that are of interest to all those who work to improve the health of the public. The results of our analyses show that reported Internet penetration has exceeded the HP 2020 target of 75.4%. HINTS data also allowed us to model the effects of various socio-demographic factors, which revealed persistent differences based on age and education, with the oldest age groups and those with less than a college education falling short of the HP 2020 target as of 2013. Furthermore, although differences by race/ethnicity were observed, our analyses suggest that the race in itself accounts very little of the variance in Internet access.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.