Nomogram predicts cancer-specific survival for patients with primary gastrointestinal melanoma
Nomogram predicts cancer-specific survival for patients with primary gastrointestinal melanoma
According to a recent study, it was validated that nomogram can predict cancer-specific survival and develop a risk stratification system for patients with primary gastrointestinal melanoma. The findings of the study were published in The Turkish Journal of Gastroenterology.
Results from a database of 433 patients with primary gastrointestinal melanoma were included in the study after randomly dividing the participants into training and validation cohorts (8:2). The nomogram was constructed based on the risk factors identified in the multivariate Cox regression analysis. Based on the nomogram, a risk stratification system was developed. Time-dependent receiver operating characteristic, calibration curve, and decision curve analysis were performed.
All cases were randomly divided into either the training (n = 347, 80%) or validation cohort (n = 86, 20%). For all patients, the median cancer-specific survival (CSS) time was 18.0 months (95% CI: 14.7-21.3). The median CSS was 18.0 months (95% CI: 14.5-21.5) and 18.0 months (95% CI: 10.7-25.3) in the training and validation cohorts, respectively (log-rank test, P = .241).
It was found that CSS under the curves of the nomogram for 6-, 12-, and 18-month were 0.789, 0.757, and 0.726 for internal validation, and 0.796, 0.763, and 0.795 for the external validation. Furthermore, the patients were divided into 2 risk sub-groups to study the risk stratification, low-risk (point: 0-182) and high-risk (point: 183-333). The median CSS was 31.0 months (95% CI: 24.5-37.5) in the low-risk subgroup and 8.0 months (95% CI: 6.2-9.8) in the high-risk subgroup. The Kaplan-Meier analysis and the log-rank test demonstrated that the risk stratification was well-differentiated in patients with varying risks of cancer-specific survival.
Thus, it can be concluded that the nomogram prediction model may be practical for validation of cancer-specific survival and development of a risk stratification system in patients with primary gastrointestinal melanoma.
Nomogram predicts cancer-specific survival for patients with primary gastrointestinal melanoma
Nomogram predicts cancer-specific survival for patients with primary gastrointestinal melanoma
According to a recent study, it was validated that nomogram can predict cancer-specific survival and develop a risk stratification system for patients with primary gastrointestinal melanoma. The findings of the study were published in The Turkish Journal of Gastroenterology.
Results from a database of 433 patients with primary gastrointestinal melanoma were included in the study after randomly dividing the participants into training and validation cohorts (8:2). The nomogram was constructed based on the risk factors identified in the multivariate Cox regression analysis. Based on the nomogram, a risk stratification system was developed. Time-dependent receiver operating characteristic, calibration curve, and decision curve analysis were performed.
All cases were randomly divided into either the training (n = 347, 80%) or validation cohort (n = 86, 20%). For all patients, the median cancer-specific survival (CSS) time was 18.0 months (95% CI: 14.7-21.3). The median CSS was 18.0 months (95% CI: 14.5-21.5) and 18.0 months (95% CI: 10.7-25.3) in the training and validation cohorts, respectively (log-rank test, P = .241).
It was found that CSS under the curves of the nomogram for 6-, 12-, and 18-month were 0.789, 0.757, and 0.726 for internal validation, and 0.796, 0.763, and 0.795 for the external validation. Furthermore, the patients were divided into 2 risk sub-groups to study the risk stratification, low-risk (point: 0-182) and high-risk (point: 183-333). The median CSS was 31.0 months (95% CI: 24.5-37.5) in the low-risk subgroup and 8.0 months (95% CI: 6.2-9.8) in the high-risk subgroup. The Kaplan-Meier analysis and the log-rank test demonstrated that the risk stratification was well-differentiated in patients with varying risks of cancer-specific survival.
Thus, it can be concluded that the nomogram prediction model may be practical for validation of cancer-specific survival and development of a risk stratification system in patients with primary gastrointestinal melanoma.