Construction and validation of nomograms combined with novel machine learning algorithms to predict early death of patients with metastatic colorectal cancer

Zhang, Yalong; Zhang, Zunni; Wei, Liuxiang; Wei, Shujing

doi:10.3389/fpubh.2022.1008137

Cited by 9 publications

(6 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All eligible patients were randomly divided into a training set and a validation set at a ratio of 7:3, with 1718 patients in the training set and 735 in the validation set. Such a dataset partitioning is consistent with the approach Yalong Zhang et al adopted in their study of ML prediction models ( 33 ). Meanwhile, Jianping Lv et al, in their research, used a ML model designed to predict the risk of bullying victimization among adolescents in the same way that our dataset was partitioned ( 34 ).…”

Section: Resultssupporting

confidence: 82%

A machine learning model to predict the risk of depression in US adults with obstructive sleep apnea hypopnea syndrome: a cross-sectional study

Li,

Ai,

Liang

2024

Front. Public Health

View full text Add to dashboard Cite

ObjectiveDepression is very common and harmful in patients with obstructive sleep apnea hypopnea syndrome (OSAHS). It is necessary to screen OSAHS patients for depression early. However, there are no validated tools to assess the likelihood of depression in patients with OSAHS. This study used data from the National Health and Nutrition Examination Survey (NHANES) database and machine learning (ML) methods to construct a risk prediction model for depression, aiming to predict the probability of depression in the OSAHS population. Relevant features were analyzed and a nomogram was drawn to visually predict and easily estimate the risk of depression according to the best performing model.Study designThis is a cross-sectional study.MethodsData from three cycles (2005–2006, 2007–2008, and 2015–2016) were selected from the NHANES database, and 16 influencing factors were screened and included. Three prediction models were established by the logistic regression algorithm, least absolute shrinkage and selection operator (LASSO) algorithm, and random forest algorithm, respectively. The receiver operating characteristic (ROC) area under the curve (AUC), specificity, sensitivity, and decision curve analysis (DCA) were used to assess evaluate and compare the different ML models.ResultsThe logistic regression model had lower sensitivity than the lasso model, while the specificity and AUC area were higher than the random forest and lasso models. Moreover, when the threshold probability range was 0.19–0.25 and 0.45–0.82, the net benefit of the logistic regression model was the largest. The logistic regression model clarified the factors contributing to depression, including gender, general health condition, body mass index (BMI), smoking, OSAHS severity, age, education level, ratio of family income to poverty (PIR), and asthma.ConclusionThis study developed three machine learning (ML) models (logistic regression model, lasso model, and random forest model) using the NHANES database to predict depression and identify influencing factors among OSAHS patients. Among them, the logistic regression model was superior to the lasso and random forest models in overall prediction performance. By drawing the nomogram and applying it to the sleep testing center or sleep clinic, sleep technicians and medical staff can quickly and easily identify whether OSAHS patients have depression to carry out the necessary referral and psychological treatment.

show abstract

Section: Resultssupporting

confidence: 82%

A machine learning model to predict the risk of depression in US adults with obstructive sleep apnea hypopnea syndrome: a cross-sectional study

Li,

Ai,

Liang

2024

Front. Public Health

View full text Add to dashboard Cite

show abstract

“…[23,26] Thus, there is a necessity to identify prognostic factors associated with early death in elderly SCLC patients, which will facilitate the identification of patients at higher risk of early death and give them access to more individualized treatment plans. Previous studies have investigated early mortality in malignancies such as gastric, colorectal and ovarian cancers [27][28][29][30][31][32] and identified relevant risk factors. Prognostic factors in patients with metastatic SCLC have also been explored, [33][34][35] but fewer studies have been conducted on early death in elderly SCLC patients.…”

Section: Discussionmentioning

confidence: 99%

A practical nomogram for predicting early death in elderly small cell lung cancer patients: A SEER-based study

Chen,

Liu,

Tou

et al. 2024

Medicine

View full text Add to dashboard Cite

This study aimed to identify risk factors for early death in elderly small cell lung cancer (SCLC) patients and develop nomogram prediction models for all-cause and cancer-specific early death to improve patient management. Data of elderly patients diagnosed with SCLC were extracted from the SEER database, then randomly divided into training and validation cohorts. Univariate and stepwise multivariable Logistic regression analyses were performed on the training cohort to identify independent risk factors for early death in these patients. Nomograms were developed based on these factors to predict the overall risk of early death. The efficacy of the nomograms was validated using various methods, including ROC analysis, calibration curves, DCA, NRI, and IDI. Among 2077 elderly SCLC patients, 773 died within 3 months, 713 due to cancer-specific causes. Older age, higher AJCC staging, brain metastases, and lack of surgery, chemotherapy, or radiotherapy increase the risk of all-cause early death, while higher AJCC staging, brain metastases, lung metastases, and lack of surgery, chemotherapy, or radiotherapy increase the risk of cancer-specific death (P < .05). These identified factors were used to construct 2 nomograms to predict the risk of early death. The ROC indicated that the nomograms performed well in predicting both all-cause early death (AUC = 0.823 in the training cohort and AUC = 0.843 in the validation cohort) and cancer-specific early death (AUC = 0.814 in the training cohort and AUC = 0.841 in the validation cohort). The results of calibration curves, DCAs, NRI and IDI also showed that the 2 sets of nomograms had good predictive power and clinical utility and were superior to the commonly used TNM staging system. The nomogram prediction models constructed in this study can effectively assist clinicians in predicting the risk of early death in elderly SCLC patients, and can also help physicians screen patients at higher risk and develop personalized treatment plans for them.

show abstract

“…Some radiation therapy-related symptoms, such as long-term intestinal dysfunction and even fecal incontinence, might, nevertheless, considerably affect patient treatment adherence and quality of life ( 48 , 49 ). Previous research has indicated that radiotherapy is an independent risk factor for early death of metastatic CRC ( 50 ). Our research discovered that getting radiotherapy can lessen the risk of early death of patients with ECRC.…”

Section: Discussionmentioning

confidence: 99%

A predictive model for early death in elderly colorectal cancer patients: a population-based study

Wang,

Shen,

Fei

et al. 2023

Front. Oncol.

View full text Add to dashboard Cite

PurposeThe purpose of this study is to determine what variables contribute to the early death of elderly colorectal cancer patients (ECRC) and to generate predictive nomograms for this population.MethodsThis retrospective cohort analysis included elderly individuals (≥75 years old) diagnosed with colorectal cancer (CRC) from 2010-2015 in the Surveillance, Epidemiology, and End Result databases (SEER) databases. The external validation was conducted using a sample of the Chinese population obtained from the China-Japan Union Hospital of Jilin University. Logistic regression analyses were used to ascertain variables associated with early death and to develop nomograms. The nomograms were internally and externally validated with the help of the receiver operating characteristic curve (ROC), calibration curve, and decision curve analysis (DCA).ResultsThe SEER cohort consisted of 28,111 individuals, while the Chinese cohort contained 315 cases. Logistic regression analyses shown that race, marital status, tumor size, Grade, T stage, N stage, M stage, brain metastasis, liver metastasis, bone metastasis, surgery, chemotherapy, and radiotherapy were independent prognostic factors for all-cause and cancer-specific early death in ECRC patients; The variable of sex was only related to an increased risk of all-cause early death, whereas the factor of insurance status was solely associated with an increased risk of cancer-specific early death. Subsequently, two nomograms were devised to estimate the likelihood of all-cause and cancer-specific early death among individuals with ECRC. The nomograms exhibited robust predictive accuracy for predicting early death of ECRC patients, as evidenced by both internal and external validation.ConclusionWe developed two easy-to-use nomograms to predicting the likelihood of early death in ECRC patients, which would contribute significantly to the improvement of clinical decision-making and the formulation of personalized treatment approaches for this particular population.

show abstract

Construction and validation of nomograms combined with novel machine learning algorithms to predict early death of patients with metastatic colorectal cancer

Cited by 9 publications

References 36 publications

A machine learning model to predict the risk of depression in US adults with obstructive sleep apnea hypopnea syndrome: a cross-sectional study

A machine learning model to predict the risk of depression in US adults with obstructive sleep apnea hypopnea syndrome: a cross-sectional study

A practical nomogram for predicting early death in elderly small cell lung cancer patients: A SEER-based study

A predictive model for early death in elderly colorectal cancer patients: a population-based study

Contact Info

Product

Resources

About