Prevention of Post-Mastectomy Pain Syndrome: A Review of Recent Literature on Perioperative Interventions.

PURPOSE OF REVIEW: Up to 60% of breast cancer patients continue to experience pain three months or more after surgery, with 15 to 25% reporting moderate to severe pain. Post-mastectomy pain syndrome (PMPS) places a high burden on patients. We reviewed recent studies on perioperative interventions to prevent PMPS incidence and severity. RECENT FINDINGS: Recent studies on pharmacologic and regional anesthetic interventions were reviewed. Only nine of the twenty-three studies included reported a significant improvement in PMPS incidence and/or severity, sometimes with mixed results for similar interventions. Evidence for prevention of PMPS is mixed. Further investigation of impact of variations in dosing is warranted. In addition, promising newer interventions for prevention of PMPS such as cryoneurolysis of intercostal nerves and stellate ganglion block need confirmatory studies.

Stress testing reveals gaps in clinic readiness of image-based diagnostic artificial intelligence models.

Artificial intelligence models match or exceed dermatologists in melanoma image classification. Less is known about their robustness against real-world variations, and clinicians may incorrectly assume that a model with an acceptable area under the receiver operating characteristic curve or related performance metric is ready for clinical use. Here, we systematically assessed the performance of dermatologist-level convolutional neural networks (CNNs) on real-world non-curated images by applying computational "stress tests". Our goal was to create a proxy environment in which to comprehensively test the generalizability of off-the-shelf CNNs developed without training or evaluation protocols specific to individual clinics. We found inconsistent predictions on images captured repeatedly in the same setting or subjected to simple transformations (e.g., rotation). Such transformations resulted in false positive or negative predictions for 6.5-22% of skin lesions across test datasets. Our findings indicate that models meeting conventionally reported metrics need further validation with computational stress tests to assess clinic readiness.

Outcomes of Melanoma In Situ Treated With Mohs Micrographic Surgery Compared With Wide Local Excision.

Importance: Melanoma in situ (MIS) is increasing in incidence, and expert consensus opinion recommends surgical excision for therapeutic management. Currently, wide local excision (WLE) is the standard of care. However, Mohs micrographic surgery (MMS) is now used to treat a growing subset of individuals with MIS. During MMS, unlike WLE, the entire cutaneous surgical margin is evaluated intraoperatively for tumor cells. Objective: To assess the outcomes of patients with MIS treated with MMS compared with those treated with WLE. Design, Setting, and Participants: Retrospective review of a prospective database. The study cohort consisted of 662 patients with MIS treated with MMS or WLE per standard of care in dermatology and surgery (general surgery, otolaryngology, plastics, oculoplastics, surgical oncology) at an academic tertiary care referral center from January 1, 1978, to December 31, 2013, with follow-up through 2015. Exposure: Mohs micrographic surgery or WLE. Main Outcomes and Measures: Recurrence, overall survival, and melanoma-specific survival. Results: There were 277 patients treated with MMS (mean [SD] age, 64.0 [13.1] years; 62.1% male) and 385 treated with WLE (mean [SD] age, 58.5 [15.6] years; P < .001 for age; 54.8% male). Median follow-up was 8.6 (range, 0.2-37) years. Compared with WLE, MMS was used more frequently on the face (222 [80.2%] vs 141 [36.7%]) and scalp and neck (23 [8.3%] vs 26 [6.8%]; P < .001). The median (range) year of diagnosis was 2008 (1986-2013) for the MMS group vs 2003 (1978-2013) for the WLE group (P < .001). Overall recurrence rates were 5 (1.8%) in the MMS group and 22 (5.7%) in the WLE group (P = .07). Mean (SD) time to recurrence after MMS was 3.91 (4.4) years, and after WLE, 4.45 (2.7) years (P = .73). The 5-year recurrence rate was 1.1% in the MMS group and 4.1% in the WLE group (P = .07). For WLE-treated tumors, the surgical margin taken was greater for tumors that recurred compared with tumors that did not recur (P = .003). Five-year overall survival for MMS was 92% and for WLE was 94% (P = .28). Melanoma-specific mortality for the MMS group was 2 vs 13 patients for the WLE group, with mean (SD) survival of 6.5 (4.8) and 6.1 (0.8) years, respectively (P = .77). Conclusions and Relevance: No significant differences were found in the recurrence rate, overall survival, or melanoma-specific survival of patients with MIS treated with MMS compared with WLE.