A Prediction Tool to Facilitate Risk-Stratified Screening for Squamous Cell Skin Cancer

Abstract

Cutaneous squamous cell cancers (cSCCs) present an under-recognized health issue among non-Hispanic whites, one that is likely to increase as populations age. cSCC risks vary considerably among non-Hispanic whites, and this heterogeneity indicates the need for risk-stratified screening strategies that are guided by patients' personal characteristics and clinical histories. Here we describe cSCCscore, a prediction tool that uses patients' covariates and clinical histories to assign them personal probabilities of developing cSCCs within 3 years after risk assessment. cSCCscore uses a statistical model for the occurrence and timing of a patient's cSCCs, whose parameters we estimated using cohort data from 66,995 patients in the Kaiser Permanente Northern California healthcare system. We found that patients' covariates and histories explained approximately 75% of their interpersonal cSCC risk variation. Using cross-validated performance measures, we also found cSCCscore's predictions to be moderately well calibrated to the patients' observed cSCC incidence. Moreover, cSCCscore discriminated well between patients who subsequently did and did not develop a new primary cSCC within 3 years after risk assignment, with area under the receiver operating characteristic curve of approximately 85%. Thus, cSCCscore can facilitate more informed management of non-Hispanic white patients at cSCC risk. cSCCscore's predictions are available at https://researchapps.github.io/cSCCscore/.

Genome‐wide association studies and polygenic risk scores for skin cancer: clinically useful yet?

“…A recently developed risk‐prediction tool, ‘cSCCscore’, assigns the probability of developing one or more cSCCs within 3 years, and includes age, tendency to sunburn, history of actinic keratosis and cSCC, and inherited predisposition, based on the total count of risk alleles at 16 GWAS‐identified loci . This model resulted in an AUC of 0·84 (95% CI 0·83–0·85) for women and 0·86 (95% CI 0·85–0·86) for men, indicating strong discriminatory ability between those who do and do not develop a new cSCC within 3 years.…”

Assessment of Deep Learning Using Nonimaging Information and Sequential Medical Records to Develop a Prediction Model for Nonmelanoma Skin Cancer

“…However, among those without a history of skin cancer, the result for the prediction was an AUC of 0.72. 18 Wang et al 19 had developed a prediction tool to provide a probability of developing cutaneous squamous cell carcinoma within the next 3 years for non-Hispanic white individuals, with an AUROC of 85%. The prediction tool also used history of skin cancer and inherited covariates.…”

“…Only demographics, UV-related covariates, skin cancer history, and lesionoriented parameters had been used for prediction. [18][19][20][21] In the era of data-driven health care, effective use of machine learning and big medical data could provide better and more personalized health care. [22][23][24][25] Machine learning is an extension of traditional statistical approaches and manages high-dimensional data (including images and large-scale electronic medical records [EMRs]), contributing to disease diagnosis, 26,27 prediction of disease development, 21,28,29 and prognosis prediction.…”

Cells to Surgery Quiz: March 2019

“…a. All of the patient covariates contributed significantly to the variation of cutaneous squamous cell carcinoma (cSCC) rates in both males and females: This is false, because all of the covariates contribute significantly to variation in cSCC rates in both sexes except sun sensitivity (as shown in Table 2 of the article by Wang et al [2018]), with P-values of 0.20 and 0.13 for females and males, respectively. b.…”

“…c. cSCC score was a poor discriminatory tool for determining those who did and did not develop a new cSCC in 3 years: This is false, because cSCCscore shows good discrimination between patients who did and did not develop a new cSCC within 3 years, as illustrated by the areas under the curve of approximately 85% for both males and females in Figure 3 of the article by Wang et al (2018). The authors also evaluated cSCCscore's performance separately in patients with and without histories of AK and cSCC, which resulted in respective areas under the curves of 70% and 75%, respectively, showing a fair discriminatory test.…”