Current patterns of care and outcomes for dermatofibrosarcoma protuberans: An international multi-institutional collaborative.

BACKGROUND: Dermatofibrosarcoma protuberans (DFSP) is a cutaneous sarcoma with an infiltrative growth pattern that makes it challenging to clear margins. High quality data regarding DFSP natural history, management, and outcomes are limited. METHODS: Data were retrospectively collected for adult DFSP patients who underwent resection at 10 institutions in eight countries. Demographics, tumor characteristics, treatment strategies, and outcomes were analyzed. RESULTS: Analysis included 347 patients consisting of young (median, 42 years), White (76.2%), males (54.2%) with truncal lesions (57.3%). The majority (76.8%) were symptomatic at presentation. Preoperative imaging was used in 55.9% of cases. Diagnosis was established with excisional biopsy in 50.9% versus incisional biopsy in 25.0% of cases. Despite planned margins of >1.0 cm in 67.4% of cases, only 69.0% of patients achieved R0 resection. Twenty-two percent of patients underwent at least one re-excision. R0 resection was achieved at a second procedure in 80.2% and a third procedure in 86.2%. Ultimately, R0 resection was feasible in 89.5% of all patients. Fibrosarcomatous transformation (FST) was observed in 12.6%. In total, 6.6% (N = 23) recurred (17 local, six distant). Of the six distant recurrences, 50.0% had FST. With a median follow-up of 47.0 months, disease-specific survival rate was 98.8%. In multivariable analysis, R0 margins at index resection were associated with wider circumferential margins and non-FST histology. CONCLUSIONS: In this international, multicenter collaborative, DFSP practice patterns were heterogeneous but achieved favorable recurrence rates and survival. Multiple excisions to clear margins remain commonplace and can inform future efforts to optimize margin selection.

National survey of patient perspectives on cost discussions among recipients of copay assistance.

BACKGROUND: Individuals with cancer and other medical conditions often experience financial concerns from high costs-of-care and may utilize copay assistance programs (CAP). We sought to describe CAP recipients' experiences/preferences for cost discussions with clinicians. METHODS: We conducted a national, cross-sectional electronic-survey from 10/2022 to 11/2022 of CAP recipients with cancer or autoimmune conditions to assess patient perspectives on cost discussions. We used multivariable logistic regression models to explore associations of patient perspectives on cost discussions with patient characteristics and patient-reported outcomes (eg, financial toxicity, depression/anxiety, and health literacy). RESULTS: Among 1,566 participants, 71% had cancer and 29% had autoimmune conditions. Although 62% of respondents desired cost discussions, only 32% reported discussions took place. Additionally, 52% of respondents wanted their doctor to consider out-of-pocket costs when deciding the best treatment, and 61% of respondents felt doctors should ensure patients can afford treatment prescribed. Participants with depression symptoms were more likely to want doctors to consider out-of-pocket costs (OR = 1.54, P = .005) and to believe doctors should ensure patients can afford treatment (OR = 1.60, P = .005). Those with severe financial toxicity were more likely to desire cost discussions (OR = 1.65, P < .001) and want doctors to consider out-of-pocket costs (OR = 1.52, P = .001). Participants with marginal/inadequate health literacy were more likely to desire cost discussions (OR = 1.37, P = .01) and believe doctors should ensure patients can afford treatment (OR = 1.30, P = .036). CONCLUSIONS: In this large sample of CAP recipients with cancer and autoimmune conditions, most reported a desire for cost discussions, but under one-third reported such discussions took place.

Development of a Multilevel Model to Identify Patients at Risk for Delay in Starting Cancer Treatment.

Importance: Delays in starting cancer treatment disproportionately affect vulnerable populations and can influence patients' experience and outcomes. Machine learning algorithms incorporating electronic health record (EHR) data and neighborhood-level social determinants of health (SDOH) measures may identify at-risk patients. Objective: To develop and validate a machine learning model for estimating the probability of a treatment delay using multilevel data sources. Design, Setting, and Participants: This cohort study evaluated 4 different machine learning approaches for estimating the likelihood of a treatment delay greater than 60 days (group least absolute shrinkage and selection operator [LASSO], bayesian additive regression tree, gradient boosting, and random forest). Criteria for selecting between approaches were discrimination, calibration, and interpretability/simplicity. The multilevel data set included clinical, demographic, and neighborhood-level census data derived from the EHR, cancer registry, and American Community Survey. Patients with invasive breast, lung, colorectal, bladder, or kidney cancer diagnosed from 2013 to 2019 and treated at a comprehensive cancer center were included. Data analysis was performed from January 2022 to June 2023. Exposures: Variables included demographics, cancer characteristics, comorbidities, laboratory values, imaging orders, and neighborhood variables. Main Outcomes and Measures: The outcome estimated by machine learning models was likelihood of a delay greater than 60 days between cancer diagnosis and treatment initiation. The primary metric used to evaluate model performance was area under the receiver operating characteristic curve (AUC-ROC). Results: A total of 6409 patients were included (mean [SD] age, 62.8 [12.5] years; 4321 [67.4%] female; 2576 [40.2%] with breast cancer, 1738 [27.1%] with lung cancer, and 1059 [16.5%] with kidney cancer). A total of 1621 (25.3%) experienced a delay greater than 60 days. The selected group LASSO model had an AUC-ROC of 0.713 (95% CI, 0.679-0.745). Lower likelihood of delay was seen with diagnosis at the treating institution; first malignant neoplasm; Asian or Pacific Islander or White race; private insurance; and lacking comorbidities. Greater likelihood of delay was seen at the extremes of neighborhood deprivation. Model performance (AUC-ROC) was lower in Black patients, patients with race and ethnicity other than non-Hispanic White, and those living in the most disadvantaged neighborhoods. Though the model selected neighborhood SDOH variables as contributing variables, performance was similar when fit with and without these variables. Conclusions and Relevance: In this cohort study, a machine learning model incorporating EHR and SDOH data was able to estimate the likelihood of delays in starting cancer therapy. Future work should focus on additional ways to incorporate SDOH data to improve model performance, particularly in vulnerable populations.

Development of Machine Learning Algorithms Incorporating Electronic Health Record Data, Patient-Reported Outcomes, or Both to Predict Mortality for Outpatients With Cancer.

PURPOSE: Machine learning (ML) algorithms that incorporate routinely collected patient-reported outcomes (PROs) alongside electronic health record (EHR) variables may improve prediction of short-term mortality and facilitate earlier supportive and palliative care for patients with cancer. METHODS: We trained and validated two-phase ML algorithms that incorporated standard PRO assessments alongside approximately 200 routinely collected EHR variables, among patients with medical oncology encounters at a tertiary academic oncology and a community oncology practice. RESULTS: Among 12,350 patients, 5,870 (47.5%) completed PRO assessments. Compared with EHR- and PRO-only algorithms, the EHR + PRO model improved predictive performance in both tertiary oncology (EHR + PRO v EHR v PRO: area under the curve [AUC] 0.86 [0.85-0.87] v 0.82 [0.81-0.83] v 0.74 [0.74-0.74]) and community oncology (area under the curve 0.89 [0.88-0.90] v 0.86 [0.85-0.88] v 0.77 [0.76-0.79]) practices. CONCLUSION: Routinely collected PROs contain added prognostic information not captured by an EHR-based ML mortality risk algorithm. Augmenting an EHR-based algorithm with PROs resulted in a more accurate and clinically relevant model, which can facilitate earlier and targeted supportive care for patients with cancer.