Development and Narrow Validation of Computer Vision Approach to Facilitate Assessment of Change in Pigmented Cutaneous Lesions.

The documentation of the change in the number and appearance of pigmented cutaneous lesions over time is critical to the early detection of skin cancers and may provide preliminary signals of efficacy in early-phase therapeutic prevention trials for melanoma. Despite substantial progress in computer-aided diagnosis of melanoma, automated methods to assess the evolution of lesions are relatively undeveloped. This report describes the development and narrow validation of mathematical algorithms to register nevi between sequential digital photographs of large areas of skin and to align images for improved detection and quantification of changes. Serial posterior truncal photographs from a pre-existing database were processed and analyzed by the software, and the results were evaluated by a panel of clinicians using a separate Extensible Markup Language‒based application. The software had a high sensitivity for the detection of cutaneous lesions as small as 2 mm. The software registered lesions accurately, with occasional errors at the edges of the images. In one pilot study with 17 patients, the use of the software enabled clinicians to identify new and/or enlarged lesions in 3‒11 additional patients versus the unregistered images. Automated quantification of size change performed similarly to that of human raters. These results support the further development and broader validation of this technique.

Multiple primary melanoma in association with other personal and familial cancers.

BACKGROUND: Multiple primary melanoma (MPM) is known to be associated with familial melanoma. However, the association between MPM and other personal and familial cancers is not well documented. The objective of this study was to evaluate the association between MPM and personal history of other cancers or cancer history among first-degree relatives (FDRs). METHODS: We performed a retrospective case-control study including cases with gender-matched MPM and single primary melanoma (SPM) at a 1:2 ratio from the University of Pittsburgh Cancer Institute Melanoma Center Biological Sample and Nevus Bank. The associations between MPM and other cancers were evaluated using univariable and multivariable logistic regression models. RESULTS: In total, 378 patients (44.2% men; median age 52 years) were enrolled, including 252 with SPM and 126 with MPM. In comparison to patients with SPM, patients with MPM were more likely to have squamous cell carcinoma (odds ratio [OR] 1.95, 95% confidence interval [CI] 1.001-3.79, p = 0.047) and prostate cancer (OR 2.72, 95% CI 1.07-7.01, p = 0.034). FDRs of patients with MPM had higher prevalence of melanoma (OR 2.37, 95% CI 1.31-4.28, p = 0.004) and prostate cancer (OR 2.92, 95% CI 1.47-6.14, p = 0.002) but not other cancers. In multivariable analysis, the association remained significant between MPM and squamous cell carcinoma (OR 2.18, 95% CI 1.08-4.39, p = 0.028), prostate cancer (OR 2.85, 95% CI 1.09-7.54, p = 0.032), FDR history of melanoma (OR 2.37, 95% CI 1.31-4.29, p = 0.004), and FDR history of prostate cancer (OR 3.26, 95% CI 1.59-6.83, p = 0.001). CONCLUSIONS: Patients with MPM have a higher prevalence of personal and FDR histories of nonmelanoma skin cancers and prostate cancer.

Poorer survival outcomes in patients with multiple versus single primary melanoma.

BACKGROUND: Given equivocal results related to overall survival (OS) for patients with multiple primary melanomas (MPMs) compared with those with single primary melanomas (SPMs) in previous reports, the authors sought to determine whether OS differs between these 2 cohorts in their center using their UPCI-96-99 database. Secondary aims were to assess the differences in recurrence-free survival (RFS). In a subset of patients, transcriptomic profiling of peripheral blood mononuclear cells (PBMCs) was performed to assess disease-associated genes of interest. METHODS: This retrospective case-controlled study included patients with MPMs and age-, sex-, and stage-matched controls with SPMs at a 1:1 ratio. Cox regression models were used to evaluate the effect of the presence of MPMs on death and recurrence. NanoString PanCancer Immune Profiling was used to assess peripheral blood immune status in patients. RESULTS: In total, 320 patients were evaluated. The mean patient age was 47 years; 43.8% were male. Patients with MPMs had worse RFS and OS (P = .023 and P = .0019, respectively). The presence of MPMs was associated with an increased risk of death (hazard ratio [HR], 4.52, P = .0006), and increased risk of disease recurrence (HR, 2.17; P = .004) after adjusting for age, sex, and stage. The degree of tumor-infiltrating lymphocytes (TILs) was different between the first melanoma of MPMs and SPMs. Expression of CXCL6 and FOXJ1 was increased in PBMCs isolated from patients with MPMs. CONCLUSIONS: Patients with MPMs had worse RFS and OS compared with patients with SPMs. Immunologic differences were also observed, including TIL content and expression of CXCL6/FOXJ1 in PBMCs of patients with MPMs, which warrant further investigation.

Standardization of Inpatient CPR Status Discussions and Documentation Within the Division of Hematology-Oncology at UPMC Shadyside: Results From PDSA Cycles 1 and 2.

PURPOSE: In December 2016, 49% of patients admitted to inpatient oncology services at University of Pittsburgh Medical Center Shadyside Hospital had cardiopulmonary resuscitation (CPR) status discussion documentation before discharge. The aim of this project was to improve the rate of CPR status conversations. METHODS: During Plan-Do-Study-Act (PDSA) cycle 1, a stakeholder workgroup was formed in January 2017 by oncology faculty, fellows, nurses, advance practice providers (APPs), medicine housestaff, and palliative care faculty. All oncology clinicians and inpatient team members were reminded weekly to discuss and document CPR status preferences. APPs received training on efficient and effective CPR status assessment from palliative care faculty. Oncology leadership received monthly e-mail updates of CPR status documentation rates and endorsed CPR status best practice guidelines. For PDSA cycle 2, patient charts without CPR status documentation in March 2018 were reviewed, and themes were shared with oncology leadership and reviewed with APPs. RESULTS: After PDSA cycle 1, CPR status assessment rates increased from 49% to greater than 80%. In 2017, more than 1,500 more CPR status discussions were documented than in 2016. The percentage of patients discharged with "comfort measures only" or "do not resuscitate" orders increased from 14.2% (95% CI, 9.5% to 19.0%) to 19.8% (95% CI, 15.6% to 24.0%). For PDSA cycle 2, charts of 60 patients without CPR assessment were reviewed. Of these, 52% were admitted overnight by nocturnists and 48% by daytime APPs. Fifty-five percent of patients (n = 33 of 60) had metastatic disease. CPR status was documented on previous admissions for 53% of patients (n = 31 of 60) in the past 12 months. Fifteen percent (n = 11 of 60) were admitted for scheduled inpatient chemotherapy. CONCLUSION: A multipronged approach significantly increased CPR status assessments. More patients transitioned to comfort measures only or do not resuscitate when their preferences were clearly assessed and documented.