RESUMO
Pancreatic neuroendocrine neoplasms (pNENs) diagnosed in childhood are very rare, with few data available. The aim was to describe the clinical presentation and behavior of children with pNENs at a national level. METHODS: National multicenter retrospective study of all patients, aged from 0 to 17 years at diagnosis, treated from 2011 to 2020 for a pNEN and registered in the French National Registry of Childhood Cancers or FRACTURE database. RESULTS: Fifteen patients, 13 well-differentiated pancreatic neuroendocrine tumors (pNETs) and two neuroendocrine carcinomas (pNECs), were selected. Median age at diagnosis was 14 years (range, 7-17). Eight patients, all with localized disease, had a cancer predisposition syndrome (CPS), including five cases diagnosed during systematic screening. Five (31%) had metastatic disease at diagnosis: three grade 2 pNETs and two pNECs. First line therapy included exclusive pancreatectomy (seven cases, all M0), active surveillance (three cases, all M0), medical therapies (somatostatin analogues, chemotherapy; four cases, all M1), and surgery with medical therapy (one M1 case). Three-year progression-free survival was 57% (confidence interval [CI] 95%: 27-78) and was significantly better for patients with low-grade well differentiated (73 vs. 0%; p < 10-4) and localized (76 vs. 20%; p = .02) tumors. The two patients with pNECs died. Three-year overall survival was 92% (CI95%: 59-99) and was significantly better in patients with low-grade tumor (100 vs. 50%; p = 10-4). CONCLUSION: Childhood pNENs occur more frequently in adolescents with CPS. Localized low-grade pNETs in children have a very good prognosis, whereas the treatment of high-grade and metastatic pNETs/pNECs should be better defined.
RESUMO
INTRODUCTION: The recruitment step of all clinical trials is time consuming, harsh and generate extra costs. Artificial intelligence tools could improve recruitment in order to shorten inclusion phase. The objective was to assess the performance of an artificial intelligence driven tool (text mining, machine learning, classification ) for the screening and detection of patients, potentially eligible for recruitment in one of the clinical trials open at the "Institut de Cancérologie de Lorraine". METHODS: Computerized clinical data during the first medical consultation among patients managed in an anticancer center over the 2019-2023 period were used to study the performances of an artificial intelligence tool (SAS® Viya). Recall, precision and F1-score were used to determine the artificial intelligence algorithm effectiveness. Time saved on screening was determined by the difference between the time taken using the artificial intelligence-assisted method and that taken using the standard method in clinical trial participant screening. RESULTS: Out of 9876 patients included in the study, the artificial intelligence algorithm obtained the following scores: precision of 96 %, recall of 94 % and a 0.95 F1-score to detect patients with breast cancer (n=2039) and potentially eligible for inclusion in a clinical trial. The screening of 258 potentially eligible patient's files took 20s per file vs. 5min and 6s with standard method. DISCUSSION: This study suggests that artificial intelligence could yield sizable improvements over standard practices in several aspects of the patient screening process, as well as in approaches to feasibility, site selection, and trial selection.
Assuntos
Algoritmos , Inteligência Artificial , Ensaios Clínicos como Assunto , Seleção de Pacientes , Humanos , Feminino , Neoplasias da Mama/diagnóstico , Mineração de Dados/métodos , Pessoa de Meia-Idade , Definição da Elegibilidade/métodos , Aprendizado de Máquina , Idoso , Masculino , Fatores de Tempo , Neoplasias/diagnósticoRESUMO
BACKGROUND: Real-world data (RWD) related to the health status and care of cancer patients reflect the ongoing medical practice, and their analysis yields essential real-world evidence. Advanced information technologies are vital for their collection, qualification, and reuse in research projects. METHODS: UNICANCER, the French federation of comprehensive cancer centres, has innovated a unique research network: Consore. This potent federated tool enables the analysis of data from millions of cancer patients across eleven French hospitals. RESULTS: Currently operational within eleven French cancer centres, Consore employs natural language processing to structure the therapeutic management data of approximately 1.3 million cancer patients. These data originate from their electronic medical records, encompassing about 65 million medical records. Thanks to the structured data, which are harmonized within a common data model, and its federated search tool, Consore can create patient cohorts based on patient or tumor characteristics, and treatment modalities. This ability to derive larger cohorts is particularly attractive when studying rare cancers. CONCLUSIONS: Consore serves as a tremendous data mining instrument that propels French cancer centres into the big data era. With its federated technical architecture and unique shared data model, Consore facilitates compliance with regulations and acceleration of cancer research projects.