This article is more than 5 years old. Information may no longer be current.
Melanoma risk prediction model may be useful in prevention interventions
Click Here to Manage Email Alerts
A melanoma risk prediction model performed well on external validation and may be useful in informing patients of their risk for melanoma, according to study results recently published in JAMA Dermatology.
Researchers in Australia developed the multivariable risk prediction model by using unconditional logistic regression.
“Relative risk estimates from the model were combined with Australian melanoma incidence and competing mortality rates to obtain absolute risk rates,” the researchers wrote.
The Australian Melanoma Family study, which included 829 cases of primary cutaneous melanoma and 535 controls, was used to develop the risk prediction model. The model was externally validated using four population-based studies, including the Western Australia Melanoma Study (511 case-control pairs), Leeds Melanoma Case-Control study (960 cases, 513 controls in Yorkshire, United Kingdom), Epigene-QSkin Study (766 melanoma cases and 43,778 participants without melanoma in Australia), and the Swedish Women’s Lifestyle and Health Cohort study (49,259 women, including 273 women with incident first-primary melanoma).
Hair color, nevus density, first-degree family history of melanoma, previous nonmelanoma skin cancer and lifetime sunbed use were included in the risk prediction model.
The area under the receiver operating curve (AUC) was 0.7 (95% CI, 0.67-0.73) on internal validation.
The AUC was 0.66 (95% CI, 0.63-0.69) in the Western Australia Melanoma Study, 0.67 (95% CI, 0.65-0.7) in the Leeds Melanoma Case-Control Study, 0.64 (95% CI, 0.62-0.66) in the Epigene-QSkin study, and 0.63 (95% Ci, 0.6-0.67) in the Swedish Women’s Lifestyle and Health Cohort Study in external validation of the AUC.
“Model calibration showed close agreement between predicted and observed numbers of incident melanomas across all deciles of predicted risk,” the researchers wrote.
When the risk prediction model was used to classify individuals as high risk compared with classifying all individuals as high risk, there was a higher net benefit in the external validations.
“The model was well calibrated and had higher net benefit compared with classifying all individuals as high risk across all 20-year absolute risk thresholds,” the researchers reported.
“This risk prediction model developed using self-assessed risk factors demonstrated good discrimination and calibration, and performed satisfactorily on external validation,” the researchers concluded. “It could be used to inform individuals of their risk of developing melanoma and to stratify them into risk categories using 20-year absolute risk thresholds of 1% or less for targeted and primary secondary primary interventions.” – by Bruce Thiel
Disclosure: The researchers report no relevant financial disclosures.
Click Here to Manage Email Alerts