Histological interpretation of spitzoid tumours: an extensive machine learning-based concordance analysis for improving decision making.

The histopathological classification of melanocytic tumours with spitzoid features remains a challenging task. We confront the complexities involved in the histological classification of these tumours by proposing machine learning (ML) algorithms that objectively categorise the most relevant features in order of importance. The data set comprises 122 tumours (39 benign, 44 atypical and 39 malignant) from four different countries. BRAF and NRAS mutation status was evaluated in 51. Analysis of variance score was performed to rank 22 clinicopathological variables. The Gaussian naive Bayes algorithm achieved in distinguishing Spitz naevus from malignant spitzoid tumours with an accuracy of 0.95 and kappa score of 0.87, utilising the 12 most important variables. For benign versus non-benign Spitz tumours, the test reached a kappa score of 0.88 using the 13 highest-scored features. Furthermore, for the atypical Spitz tumours (AST) versus Spitz melanoma comparison, the logistic regression algorithm achieved a kappa value of 0.66 and an accuracy rate of 0.85. When the three categories were compared most AST were classified as melanoma, because of the similarities on histological features between the two groups. Our results show promise in supporting the histological classification of these tumours in clinical practice, and provide valuable insight into the use of ML to improve the accuracy and objectivity of this process while minimising interobserver variability. These proposed algorithms represent a potential solution to the lack of a clear threshold for the Spitz/spitzoid tumour classification, and its high accuracy supports its usefulness as a helpful tool to improve diagnostic decision-making.

Triaging HPV-Positive Cervical Samples with p16 and Ki-67 Dual Stained Cytology within an Organized Screening Program-A Prospective Observational Study from Western Norway.

The implementation of high-risk human papillomavirus testing (hrHPV testing) as a screening method in substitute for cytology has evoked the need for more sensitive and less objective tests for the triage of HPV-positive women. In a cohort of 1763 HPV-positive women, the potential of immunocytochemical p16 and Ki-67 dual staining as compared to cytology, alone or in combination with HPV partial genotyping, was tested for triage of women attending a cervical cancer screening program. Performance was measured using sensitivity, specificity, and positive and negative predictive values. Comparisons were assessed using logistic regression models and the McNemar test. Dual staining was evaluated in a prospectively collected study cohort of 1763 HPV-screened women. For triage of CIN2+ and CIN3+, NPV and sensitivity, 91.8% and 94.2% versus 87.9% and 89.7%, respectively, were significantly higher using dual staining together with HPV 16/18 positive, as compared to cytology (p < 0.001). The specificities, however, were lower for dual staining as compared to cytology. Conclusions: Dual staining is safer for decision-making regarding HPV-positive women's need for follow-up with colposcopy and biopsy, as compared to cytology.

CYP2C19*2 and CYP2C19*17 variants and effect of tamoxifen on breast cancer recurrence: Analysis of the International Tamoxifen Pharmacogenomics Consortium dataset.

The role of cytochrome P450 drug metabolizing enzymes in the efficacy of tamoxifen treatment of breast cancer is subject to substantial interest and controversy. CYP2D6 have been intensively studied, but the role of CYP2C19 is less elucidated, and we studied the association of CYPC19 genotype and recurrence of breast cancer. We used outcome and genotyping data from the large publicly available International Tamoxifen Pharmacogenomics Consortium (ITPC) dataset. Cox regression was used to compute the hazard ratios (HRs) for recurrence. CYP2C19 genotype data was available for 2 423 patients and the final sample cohort comprised 2 102 patients. CYP2C19*2 or *19 alleles did not influence DFS. For the CYP2C19*2 allele, the HR was 1.05 (CI 0.78-1.42) and 0.79 (CI 0.32-1.94) for hetero- and homozygote carriers, respectively. The corresponding HR for hetero- and homozygote carriers of the CYP2C19*17 allele were 1.02 (CI 0.71-1.46) and 0.57 (CI 0.26-1.24), respectively. Accounting for CYP2D6 genotype status did not change these estimates. We found no evidence to support a clinically meaningful role of CYP2C19 polymorphisms and response to tamoxifen in breast cancer patients and, consequently, CYP2C19 genotype status should not be included in clinical decisions on tamoxifen treatment.