Machine learning algorithm to predict response to immunotherapy in real-life settings for patients with advanced melanoma.

BACKGROUND: Melanoma is one of the most fatal forms of skin cancer. Defining relevant biomarkers to predict treatment outcome based on immune checkpoint inhibitors (ICIs) is needed in order to increase overall survival of metastatic melanoma patients (MM). OBJECTIVES: This study compared different machine learning models in terms of performance to identify biomarkers from clinical diagnosis and follow-up of MM patients, to predict treatment response to ICIs under real-life conditions. MATERIALS & METHODS: Clinical data from melanoma patients with an AJCC status of III C/D or IV, having received ICIs, were extracted from the RIC-MEL database for this pilot study. Light Gradient Boosting Machine, linear regression, Random Forest (RF), Support Vector Machine and Extreme Gradient Boosting were compared in terms of performance. The SHAP (SHapley Additive exPlanations) method was used to assess the link between the different clinical features investigated and the prediction of response to ICIs. RESULTS: RF showed the highest scores for accuracy (0.63) and sensitivity (0.64) and high scores for precision (0.61) and specificity (0.63). AJCC stage (0.076) showed the highest SHAP mean value, thus being the most suitable feature to predict response to treatment. The number of metastatic sites per year (0.049), number of months since first treatment initiation and the Breslow index (both 0.032) were less predictive, but still showed relatively high predictive power. CONCLUSION: This machine learning approach confirms that a certain number of biomarkers may enable prediction of treatment success with ICIs.

[Successful completion of an ISO 9001 v 2015 certification process in clinical investigation research]. / Réussir une démarche de certification ISO 9001 v 2015 en investigation clinique.

Clinical investigation at the University Hospital of Nantes is carried out within the investigation department, which consists of coordination and 24 clinical research teams gathered at four different hospital sites. The Clinical Investigation Units are all equipped with a Quality Management System. This has been in place for more than 12 years and was initially created for the Clinical Investigation Units of the Clinical Investigation Centre (CIC 1413) in Nantes and then transposed in 2013, to the emerging Clinical Investigation Units. OBJECTIVE: In order to evaluate the performance of this quality approach applied to all UHC investigations, the Investigation Department is committed to obtaining an ISO 9001:2015 certification. METHODS: The quality division of the investigation department conducted the project according to a methodology, based on internal and external evaluations to determine an inventory and the retro-planning of the certification approach. RESULTS: The scope of the certification involved the investigation department of the University Hospital: 24 clinical investigation units, over 500 medical staff, 150 non-medical staff. In our certification approach, the client was the promoter of the clinical study. The process lasted 18 months and included phases of training and awareness-raising for all the staff involved. The quality management system of the investigation department has been revised and improved in accordance with current regulations. The Investigation Department obtained the ISO 9001:2015 certification for all clinical investigations at the Nantes University Hospital in June 2017 without any non-compliance. CONCLUSION: Our work shows that the investigation department has successfully adapted the ISO 9001:2015 standard to institutional clinical research. The certification for specific activities in clinical investigation is the guarantee of an optimized and relevant organization for the safety of volunteers, participating in clinical research as well as the scientific quality of the research and contributes to the satisfaction of sponsors.