Development of a non-melanoma skin cancer detection model

Predicting keratinocyte carcinoma in patients with actinic keratosis: development and internal validation of a multivariable risk-prediction model

BACKGROUND

Patients with actinic keratosis (AK) are at increased risk for developing keratinocyte carcinoma (KC) but predictive factors and their risk rates are unknown.

OBJECTIVES

To develop and internally validate a prediction model to calculate the absolute risk of a first KC in patients with AK.

METHODS

The risk-prediction model was based on the prospective population-based Rotterdam Study cohort. We hereto analysed the data of participants with at least one AK lesion at cohort baseline using a multivariable Cox proportional hazards model and included 13 a priori defined candidate predictor variables considering phenotypic, genetic and lifestyle risk factors. KCs were identified by linkage of the data with the Dutch Pathology Registry.

RESULTS

Of the 1169 AK participants at baseline, 176 (15·1%) developed a KC after a median follow-up of 1·8 years. The final model with significant predictors was obtained after backward stepwise selection and comprised the presence of four to nine AKs [hazard ratio (HR) 1·68, 95% confidence interval (CI) 1·17-2·42], 10 or more AKs (HR 2·44, 95% CI 1·65-3·61), AK localization on the upper extremities (HR 0·75, 95% CI 0·52-1·08) or elsewhere except the head (HR 1·40, 95% CI 0·98-2·01) and coffee consumption (HR 0·92, 95% CI 0·84-1·01). Evaluation of the discriminative ability of the model showed a bootstrap validated concordance index (c-index) of 0·60.

CONCLUSIONS

We showed that the risk of KC in patients with AK can be calculated with the use of four easily assessable predictor variables. Given the c-index, extension of the model with additional, currently unknown predictor variables is desirable. Linked Comment: Kim et al. Br J Dermatol 2020; 183:415-416.

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

Importance

A prediction model for new-onset nonmelanoma skin cancer could enhance prevention measures, but few patient data-driven tools exist for more accurate prediction.

Objective

To use machine learning to develop a prediction model for incident nonmelanoma skin cancer based on large-scale, multidimensional, nonimaging medical information.

Design, Setting, and Participants

This study used a database comprising 2 million randomly sampled patients from the Taiwan National Health Insurance Research Database from January 1, 1999, to December 31, 2013. A total of 1829 patients with nonmelanoma skin cancer as their first diagnosed cancer and 7665 random controls without cancer were included in the analysis. A convolutional neural network, a deep learning approach, was used to develop a risk prediction model. This risk prediction model used 3-year clinical diagnostic information, medical records, and temporal-sequential information to predict the skin cancer risk of a given patient within the next year. Stepwise feature selection was also performed to investigate important and determining factors of the model. Statistical analysis was performed from November 1, 2016, to October 31, 2018.

Main Outcomes and Measures

Sensitivity, specificity, and area under the receiver operating characteristic (AUROC) curve were used to evaluate the performance of the models.

Results

A total of 1829 patients (923 women [50.5%] and 906 men [49.5%]; mean [SD] age, 65.3 [15.7] years) with nonmelanoma skin cancer and 7665 random controls without cancer (3951 women [51.5%] and 3714 men [48.4%]; mean [SD] age, 47.5 [17.3] years) were included in the analysis. The 1-year incident nonmelanoma skin cancer risk prediction model using sequential diagnostic information and drug prescription information as a time-incorporated feature matrix could attain an AUROC of 0.89 (95% CI, 0.87-0.91), with a mean (SD) sensitivity of 83.1% (3.5%) and mean (SD) specificity of 82.3% (4.1%). Carcinoma in situ of skin (AUROC, 0.867; -2.80% loss) and other chronic comorbidities (eg, degenerative osteopathy [AUROC, 0.872; -2.32% loss], hypertension [AUROC, 0.879; -1.53% loss], and chronic kidney insufficiency [AUROC, 0.879; -1.52% loss]) served as more discriminative factors for the prediction. Medications such as trazodone, acarbose, systemic antifungal agents, statins, nonsteroidal anti-inflammatory drugs, and thiazide diuretics were the top-ranking discriminative features in the model; each led to more than a 1% decrease of the AUROC when eliminated individually (eg, trazodone AUROC, 0.868; -2.67% reduction; acarbose AUROC, 0.870; -2.50 reduction; and systemic antifungal agents AUROC, 0.875; -1.99 reduction).

Conclusions and Relevance

The findings of this study suggest that a risk prediction model may have potential predictive factors for nonmelanoma skin cancer. This model may help health care professionals target high-risk populations for more intensive skin cancer preventive methods.

Multiclass classification for skin cancer profiling based on the integration of heterogeneous gene expression series

Most of the research studies developed applying microarray technology to the characterization of different pathological states of any disease may fail in reaching statistically significant results. This is largely due to the small repertoire of analysed samples, and to the limitation in the number of states or pathologies usually addressed. Moreover, the influence of potential deviations on the gene expression quantification is usually disregarded. In spite of the continuous changes in omic sciences, reflected for instance in the emergence of new Next-Generation Sequencing-related technologies, the existing availability of a vast amount of gene expression microarray datasets should be properly exploited. Therefore, this work proposes a novel methodological approach involving the integration of several heterogeneous skin cancer series, and a later multiclass classifier design. This approach is thus a way to provide the clinicians with an intelligent diagnosis support tool based on the use of a robust set of selected biomarkers, which simultaneously distinguishes among different cancer-related skin states. To achieve this, a multi-platform combination of microarray datasets from Affymetrix and Illumina manufacturers was carried out. This integration is expected to strengthen the statistical robustness of the study as well as the finding of highly-reliable skin cancer biomarkers. Specifically, the designed operation pipeline has allowed the identification of a small subset of 17 differentially expressed genes (DEGs) from which to distinguish among 7 involved skin states. These genes were obtained from the assessment of a number of potential batch effects on the gene expression data. The biological interpretation of these genes was inspected in the specific literature to understand their underlying information in relation to skin cancer. Finally, in order to assess their possible effectiveness in cancer diagnosis, a cross-validation Support Vector Machines (SVM)-based classification including feature ranking was performed. The accuracy attained exceeded the 92% in overall recognition of the 7 different cancer-related skin states. The proposed integration scheme is expected to allow the co-integration with other state-of-the-art technologies such as RNA-seq.

Predicting non-melanoma skin cancer via a multi-parameterized artificial neural network

Ultraviolet radiation (UVR) exposure and family history are major associated risk factors for the development of non-melanoma skin cancer (NMSC). The objective of this study was to develop and validate a multi-parameterized artificial neural network based on available personal health information for early detection of NMSC with high sensitivity and specificity, even in the absence of known UVR exposure and family history. The 1997-2015 NHIS adult survey data used to train and validate our neural network (NN) comprised of 2,056 NMSC and 460,574 non-cancer cases. We extracted 13 parameters for our NN: gender, age, BMI, diabetic status, smoking status, emphysema, asthma, race, Hispanic ethnicity, hypertension, heart diseases, vigorous exercise habits, and history of stroke. This study yielded an area under the ROC curve of 0.81 and 0.81 for training and validation, respectively. Our results (training sensitivity 88.5% and specificity 62.2%, validation sensitivity 86.2% and specificity 62.7%) were comparable to a previous study of basal and squamous cell carcinoma prediction that also included UVR exposure and family history information. These results indicate that our NN is robust enough to make predictions, suggesting that we have identified novel associations and potential predictive parameters of NMSC.

Patient-reported outcomes in topical field treatment of actinic keratosis in Swedish and Danish patients

Topical treatments in dermatology can be long, complex and lead to nonadherence and nonpersistence to prescribed treatment. Clinical efficacy observed in randomized clinical trials (RCT) may therefore be reduced in real-world clinical practice. The objective of this study was to analyze patient-reported treatment adherence, treatment satisfaction and health-related quality of life (HRQoL) with topical treatments of actinic keratosis (AK) in routine clinical practice in Denmark and Sweden. Adult patients prescribed field-directed topical AK treatments with diclofenac gel, imiquimod or ingenol mebutate per routine clinical practice were eligible for the observational RAPID-ACT study. Data were collected through physician and patient questionnaires that included validated instruments to measure treatment satisfaction (TSQM-9), treatment adherence (MMAS) and HRQoL (EQ-5D-5L, EQ-VAS, AKQoL). In total, 446 patients from Denmark and Sweden were included. Ingenol mebutate patients reported a higher satisfaction with treatment effectiveness compared to patients treated with diclofenac (p = .006) while no other differences in treatment satisfaction could be determined. Treatment adherence was generally high, but higher for ingenol mebutate compared to both diclofenac (p < .001) and imiquimod (p = .007), possibly due to shorter treatment duration. No differences in improved HRQoL were found. More research is needed about the link between treatment adherence and real-world effectiveness.