Refine
Has Fulltext
- yes (4)
Document Type
- Article (4)
Language
- English (4)
Keywords
- Cancer Research (2)
- Oncology (2)
- General Medicine (1)
Institute
Artificial intelligence (AI) systems have been shown to help dermatologists diagnose melanoma more accurately, however they lack transparency, hindering user acceptance. Explainable AI (XAI) methods can help to increase transparency, yet often lack precise, domain-specific explanations. Moreover, the impact of XAI methods on dermatologists’ decisions has not yet been evaluated. Building upon previous research, we introduce an XAI system that provides precise and domain-specific explanations alongside its differential diagnoses of melanomas and nevi. Through a three-phase study, we assess its impact on dermatologists’ diagnostic accuracy, diagnostic confidence, and trust in the XAI-support. Our results show strong alignment between XAI and dermatologist explanations. We also show that dermatologists’ confidence in their diagnoses, and their trust in the support system significantly increase with XAI compared to conventional AI. This study highlights dermatologists’ willingness to adopt such XAI systems, promoting future use in the clinic.
Background
Cancer immunotherapy has revolutionized melanoma treatment, but the high number of non-responders still emphasizes the need for improvement of therapy. One potential avenue for enhancing anti-tumor treatment is through the modulation of coagulation and platelet activity. Both have been found to play an important role in the tumor microenvironment, tumor growth and metastasis. Preclinical studies indicate a beneficial effect, clinical data has been inconsistent.
Methods
We examined a cohort of advanced, non-resectable melanoma patients (n = 2419) derived from the German prospective multicenter skin cancer registry ADOReg, who were treated with immune checkpoint inhibitors (ICI). The patients were classified based on whether it was documented that they received platelet aggregation inhibition (PAI) (n = 137) (acetylsalicylic acid (ASA) or clopidogrel), anticoagulation (AC) (n = 185) (direct oral anticoagulation (DOAC), phenprocoumon, heparins) at the start of ICI or no antithrombotic medication (n = 2097) at any point during ICI treatment. The study endpoints were best overall response (BOR), progression-free survival (PFS) and overall survival (OS).
Results
A significantly improved PFS was observed in patients documented to receive ASA (15.1 vs 6.4 months, HR 0.67, 95 % CI: 0.5 to 0.88, p = 0.0047) as well as in patients to receive AC (15.1 vs. 6.4 months, HR 0.7, 95 % CI: 0.53 to 0.91, p = 0.01) compared to patients for whom no antithrombotic medication was documented. Multivariate analysis of OS showed significant risk reduction in patients who received DOAC (HR 0.68, 95 % CI: 0.49 to 0.92, p = 0.0170) or phenprocoumon (HR: 0.44, 95 % CI: 0.19 to 0.85, p = 0.0301).
Conclusion
Our study indicates a positive prognostic effect of anticoagulant and antiplatelet concomitant medication in melanoma patients receiving ICI. Further studies are needed to confrim the cancer-related benefit of adding anticoagulation or platelet inhibition to ICI treatment.
