Polidocanol: A Review of Off-Label Dermatologic Uses.

BACKGROUND: Polidocanol is an FDA-approved treatment of incompetent great saphenous veins, accessory saphenous veins, and visible varicosities of the great saphenous vein system, but numerous other off-label dermatological applications have been reported. OBJECTIVE: To describe the various off-label dermatological clinical uses of polidocanol, as well as efficacy and adverse effects. METHODS: The review of studies searchable on PubMed from 2004 to 2021 describing clinical uses of polidocanol to determine efficacy and adverse effects associated with various dermatologic applications. RESULTS: Polidocanol has shown efficacy in the treatment of mucocele of minor salivary gland, hemangioma, upper extremity veins, reticular veins of the chest, facial veins, pyogenic granuloma, lymphangioma circumscriptum, digital mucous cyst, mixed skin ulcers, cutaneous focal mucinosis, seromas, glomuvenous malformations, acne cysts, lymphocele, and dissecting cellulitis. Commonly reported side effects include pain, erythema, swelling, ecchymosis, and ulceration. Most sources were case reports and small prospective studies, as such the strength of data supporting many uses is limited by small sample sizes and lack of controls. CONCLUSION: Although polidocanol is currently only FDA approved for incompetent great saphenous veins, accessory saphenous veins, and visible varicosities of the great saphenous vein system, the use of polidocanol has been selected for a variety of off-label clinical applications.

Closing the loop: automatically identifying abnormal imaging results in scanned documents.

OBJECTIVES: Scanned documents (SDs), while common in electronic health records and potentially rich in clinically relevant information, rarely fit well with clinician workflow. Here, we identify scanned imaging reports requiring follow-up with high recall and practically useful precision. MATERIALS AND METHODS: We focused on identifying imaging findings for 3 common causes of malpractice claims: (1) potentially malignant breast (mammography) and (2) lung (chest computed tomography [CT]) lesions and (3) long-bone fracture (X-ray) reports. We train our ClinicalBERT-based pipeline on existing typed/dictated reports classified manually or using ICD-10 codes, evaluate using a test set of manually classified SDs, and compare against string-matching (baseline approach). RESULTS: A total of 393 mammograms, 305 chest CT, and 683 bone X-ray reports were manually reviewed. The string-matching approach had an F1 of 0.667. For mammograms, chest CTs, and bone X-rays, respectively: models trained on manually classified training data and optimized for F1 reached an F1 of 0.900, 0.905, and 0.817, while separate models optimized for recall achieved a recall of 1.000 with precisions of 0.727, 0.518, and 0.275. Models trained on ICD-10-labelled data and optimized for F1 achieved F1 scores of 0.647, 0.830, and 0.643, while those optimized for recall achieved a recall of 1.0 with precisions of 0.407, 0.683, and 0.358. DISCUSSION: Our pipeline can identify abnormal reports with potentially useful performance and so decrease the manual effort required to screen for abnormal findings that require follow-up. CONCLUSION: It is possible to automatically identify clinically significant abnormalities in SDs with high recall and practically useful precision in a generalizable and minimally laborious way.

Issues in Melanoma Detection: Semisupervised Deep Learning Algorithm Development via a Combination of Human and Artificial Intelligence.

BACKGROUND: Automatic skin lesion recognition has shown to be effective in increasing access to reliable dermatology evaluation; however, most existing algorithms rely solely on images. Many diagnostic rules, including the 3-point checklist, are not considered by artificial intelligence algorithms, which comprise human knowledge and reflect the diagnosis process of human experts. OBJECTIVE: In this paper, we aimed to develop a semisupervised model that can not only integrate the dermoscopic features and scoring rule from the 3-point checklist but also automate the feature-annotation process. METHODS: We first trained the semisupervised model on a small, annotated data set with disease and dermoscopic feature labels and tried to improve the classification accuracy by integrating the 3-point checklist using ranking loss function. We then used a large, unlabeled data set with only disease label to learn from the trained algorithm to automatically classify skin lesions and features. RESULTS: After adding the 3-point checklist to our model, its performance for melanoma classification improved from a mean of 0.8867 (SD 0.0191) to 0.8943 (SD 0.0115) under 5-fold cross-validation. The trained semisupervised model can automatically detect 3 dermoscopic features from the 3-point checklist, with best performances of 0.80 (area under the curve [AUC] 0.8380), 0.89 (AUC 0.9036), and 0.76 (AUC 0.8444), in some cases outperforming human annotators. CONCLUSIONS: Our proposed semisupervised learning framework can help with the automatic diagnosis of skin disease based on its ability to detect dermoscopic features and automate the label-annotation process. The framework can also help combine semantic knowledge with a computer algorithm to arrive at a more accurate and more interpretable diagnostic result, which can be applied to broader use cases.

Heterogeneity and mutation in KRAS and associated oncogenes: evaluating the potential for the evolution of resistance to targeting of KRAS G12C.

Activating mutations in RAS genes are associated with approximately 20% of all human cancers. New targeted therapies show preclinical promise in inhibiting the KRAS G12C variant. However, concerns exist regarding the effectiveness of such therapies in vivo given the possibilities of existing intratumor heterogeneity or de novo mutation leading to treatment resistance. We performed deep sequencing of 27 KRAS G12-positive lung tumors to determine the prevalence of other oncogenic mutations within KRAS or within commonly mutated downstream genes that could confer resistance at the time of treatment. We also passaged patient-derived xenografts to assess the potential for novel KRAS mutation to arise during subsequent tumor evolution. Furthermore, we estimate the de novo mutation rate in KRAS position 12 and in genes downstream of KRAS. Finally, we present an approach for estimation of the selection intensity for these point mutations that explains their high prevalence in tumors. We find no evidence of heterogeneity that may compromise KRAS G12C targeted therapy within sequenced lung tumors or passaged xenografts. We find that mutations that confer resistance are even less likely to occur downstream of KRAS than to occur within KRAS. Our approach predicts that BRAF V600E would provide the highest fitness advantage for de novo-resistant subclones. Overall, our findings suggest that resistance to targeted therapy of KRAS G12C-positive tumors is unlikely to be present at the time of treatment and, among the de novo mutations likely to confer resistance, mutations in BRAF, a gene with targeted inhibitors presently available, result in subclones with the highest fitness advantage.