Identification of Lifestyle Behaviors Associated with Recurrence and Survival in Colorectal Cancer Patients Using Random Survival Forests

Zutphen, Moniek van; Duijnhoven, Fränzel J.B. van; Wesselink, Evertine; Schrauwen, Ruud; Kouwenhoven, Ewout A.; Halteren, Henk K. van; Wilt, Johannes H. W. de; Kok, Dieuwertje E.; Boshuizen, Hendriek C.

doi:10.3390/cancers13102442

Cited by 9 publications

(10 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Five publications [115][116][117][118] that were superseded by more recent publications and three [119][120][121] only reporting unadjusted results were excluded from any subsequent analyses. Therefore, a total of 20 publications (16 studies) on post-diagnosis physical activity, pre-to post and postdiagnosis change in physical activity levels, and post-diagnosis sedentary behaviour were included.…”

Section: Resultsmentioning

confidence: 99%

Post‐diagnosis physical activity and sedentary behaviour and colorectal cancer prognosis: A Global Cancer Update Programme (CUP Global) systematic literature review and meta‐analysis

Markozannes,

Becerra‐Tomás,

Cariolou

et al. 2024

Intl Journal of Cancer

View full text Add to dashboard Cite

Low physical activity and high sedentary behaviour have been clearly linked with colorectal cancer development, yet data on their potential role in colorectal cancer survival is limited. Better characterisation of these relationships is needed for the development of post‐diagnosis physical activity and sedentary behaviour guidance for colorectal cancer survivors. We searched PubMed and Embase through 28 February 2022 for studies assessing post‐diagnosis physical activity, and/or sedentary behaviour in relation to all‐cause and cause‐specific mortality and recurrence after colorectal cancer diagnosis. Total and recreational physical activity were assessed overall and by frequency, duration, intensity, and volume using categorical, linear, and non‐linear dose–response random‐effects meta‐analyses. The Global Cancer Update Programme (CUP Global) independent Expert Committee on Cancer Survivorship and Expert Panel interpreted and graded the likelihood of causality. We identified 16 observational studies on 82,220 non‐overlapping patients from six countries. Physical activity was consistently inversely associated with colorectal cancer morbidity and mortality outcomes, with 13%–60% estimated reductions in risk. Sedentary behaviour was positively associated with all‐cause mortality. The evidence had methodological limitations including potential confounding, selection bias and reverse causation, coupled with a limited number of studies for most associations. The CUP Global Expert panel concluded limited‐suggestive evidence for recreational physical activity with all‐cause mortality and cancer recurrence. Total physical activity and its specific domains and dimensions, and sedentary behaviour were all graded as limited‐no conclusion for all outcomes. Future research should focus on randomised trials, while observational studies should obtain objective and repeated physical activity measures and better adjustment for confounders.

show abstract

Section: Resultsmentioning

confidence: 99%

Post‐diagnosis physical activity and sedentary behaviour and colorectal cancer prognosis: A Global Cancer Update Programme (CUP Global) systematic literature review and meta‐analysis

Markozannes,

Becerra‐Tomás,

Cariolou

et al. 2024

Intl Journal of Cancer

View full text Add to dashboard Cite

show abstract

“…Although overall T&CM use was not associated with increased adherence to the recommended healthy lifestyles, differences in adherence were seen in individual T&CM modalities. The findings of low adherence to diet and BMI are of concern as non-adherence to these factors are associated with poor prognosis, recurrence, and reduced health-related quality of life [ 6 , 7 , 10 , 11 , 13 , 14 ]. Survivors with cancer previously were more likely to adhere to the diet recommendation.…”

Section: Discussionmentioning

confidence: 99%

“…Thus, cancer outcomes are associated with lifestyle factors such as diet, physical activity, smoking, and alcohol consumption [ 8 , 9 ]. Healthy lifestyles have been found to reduce the risk of recurrence of some cancers [ 10 , 11 ]. Concurrent adherence to several healthy lifestyle factors has more benefits than adherence to just one factor [ 12 ], like lowered mortality [ 13 ] and improved health-related quality of life [ 14 ].…”

Section: Introductionmentioning

confidence: 99%

Adherence to lifestyle recommendations among Norwegian cancer survivors and the impact of traditional and complementary medicine use: the Tromsø Study 2015–2016

Nakandi,

Benebo,

Hopstock

et al. 2023

BMC Complement Med Ther

View full text Add to dashboard Cite

Introduction Adherence to healthy lifestyle recommendations has positive effects on cancer outcomes yet adherence is low among cancer survivors. Differences in adherence between women and men, phase of survivorship, and other factors that might increase adherence, like the use of traditional and complementary medicine (T&CM), need to be explored. We aimed to study the adherence to national recommendations for a healthy diet (daily intake of ≥ 5 portions of fruit/vegetables), physical activity (150 min of moderate-intensity or 75 min of high-intensity/week), normal body mass index (BMI) (18.5–24.9 kg/m2), non-smoking, and low-risk alcohol consumption (women ≤ 10 g/day, men ≤ 20 g/day) among Norwegian cancer survivors and their associations with sex, the use of T&CM, and survivorship phase. Methods We used logistic regression, independent sample t-test, and chi-square test to study self-reported (diet, physical activity, smoking, alcohol consumption) and measured (BMI) adherence in 1530 cancer survivors (40 years and above, participating in the population-based Tromsø Study conducted in 2015–2016 (65% attendance). We dichotomized all assessed lifestyle recommendations (adherence = 1 point, non-adherence = 0 points), and created a score for every recommendation (0–5 points). Adherence to individual lifestyle recommendations and the use of T&CM as well as the phase of survivorship was adjusted for sex, age, income, and living with a partner. Results Adherence to recommendations was 7.5% for diet, 85.3% for physical activity, 30.5% for BMI, 89.3% for non-smoking, and 87.6% for alcohol consumption. In total 2.3% adhered to all five recommendations concurrently (mean score 2.96 [SD = 0.86]). Women adhered to more recommendations concurrently compared to men (3.03 [SD = 0.90] vs. 2.89 [SD = 0.80] points respectively, [p = .012]). In total, 31% reported the use of T&CM and there were no differences in adherence to individual lifestyle recommendations or concurrent adherence in overall T&CM use compared to non-use. Users of self-help techniques were more likely to adhere to the recommendations of diet (aOR 2.69, 95% CI 1.45–4.98) and physical activity (aOR 6.26, 95% CI 1.51–25.92). Users of traditional healers and users of more than one T&CM modality were less likely to adhere to the low-risk alcohol consumption recommendation, (aOR 0.32, 95% CI 0.13–0.77, and aOR 0.53, 95% CI 1.08–2.17, respectively) compared to T&CM non-users. Survivors with cancer previously (1162) had higher odds of adhering to the recommendation of diet (aOR 2.66, 95% CI 1.36–5.19) than survivors with cancer presently (n = 368), but not to other recommendations. Conclusion The health of cancer survivors can be improved through adherence to lifestyle recommendations, yet our study found partial adherence among survivors in Norway, in accordance with findings from other countries. Although overall T&CM use was not associated with higher adherence to lifestyle recommendations, differences in adherence were seen among individual modalities like the use of self-help techniques and traditional healers. Our results suggest the need for intensified follow-up of lifestyle with attention to male survivors and diet among all survivors throughout the cancer survivorship continuum.

show abstract

“…Early CRC recurrence and metastasis were defined as occurring within 16 months of surgery 24,25 , and included both local recurrence and distant metastases. Local recurrence is a recurrence at the original surgical site or around the anastomosis, while distant metastases refer to metastases in the liver, lungs, bones, brain, distant lymph nodes, and other organs.…”

Section: Outcome Variables and Predictorsmentioning

confidence: 99%

Predictive models based on machine learning for early recurrence and metastasis in postoperative patients with colorectal cancer

Dong,

Mo,

Huang

et al. 2024

Interdisciplinary Nursing Research

View full text Add to dashboard Cite

Objectives: To construct and validate a prediction model based on machine learning algorithms for early recurrence and metastasis in patients with colorectal cancer after surgery. Methods: This study employed a prospective cohort design. A total of 498 postoperative patients with colorectal cancer, treated at an affiliated hospital of Qingdao University, were recruited using convenience sampling from June to December 2021. Data were collected during outpatient visits and hospitalizations. The risk factors for early recurrence and metastasis of colorectal cancer were determined through multivariate logistic regression analysis in SPSS 26.0 software. Using Python 3.7.0 software, four machine learning algorithms (logistic regression, Support Vector Machine, XGBoost, and LightGBM) were used to develop and validate prediction models for early recurrence and metastasis of colorectal cancer after surgery. Results: Of the 498 patients, 51 (10.24%) had early recurrence and metastasis. Multivariate logistic regression analysis showed that personal traits (family history of cancer, histological type, degree of tumor differentiation, number of positive lymph nodes, and T stage), behaviour and/or lifestyle (intake of refined grains, whole grains, fish, shrimp, crab, and nuts, as well as resilience), and interpersonal networks (social support) were all associated with early recurrence and metastasis of colorectal cancer (P<0.05). The logistic regression prediction model showed the best prediction performance out of the four models, with an accuracy rate of 0.920, specificity of 0.982, F1 of 0.495, AUC of 0.867, Kappa of 0.056, and Brier score of 0.067. Conclusion: Our findings suggest that a prediction model based on logistic regression could accurately and scientifically predict which patients are likely to experience early recurrence and metastasis, helping to lessen the burden for both patients and the healthcare system.

show abstract

Identification of Lifestyle Behaviors Associated with Recurrence and Survival in Colorectal Cancer Patients Using Random Survival Forests

Cited by 9 publications

References 51 publications

Post‐diagnosis physical activity and sedentary behaviour and colorectal cancer prognosis: A Global Cancer Update Programme (CUP Global) systematic literature review and meta‐analysis

Post‐diagnosis physical activity and sedentary behaviour and colorectal cancer prognosis: A Global Cancer Update Programme (CUP Global) systematic literature review and meta‐analysis

Adherence to lifestyle recommendations among Norwegian cancer survivors and the impact of traditional and complementary medicine use: the Tromsø Study 2015–2016

Predictive models based on machine learning for early recurrence and metastasis in postoperative patients with colorectal cancer

Contact Info

Product

Resources

About