Optimization of CSF biological investigations for CNS lymphoma diagnosis. Issue 10 (13th August 2019)

• Record Type: Journal Article
• Authors: Armand, Marine; Costopoulos, Myrto; Osman, Jennifer; Tarfi, Sihem; Houillier, Caroline; Choquet, Sylvain; Agnelo, Hervé; Bonnemye, Patrick; Ronez, Emily; Settegrana, Catherine; Soussain, Carole; Hoang‐Xuan, Khê; Le Garff‐Tavernier, Magali; Davi, Frédéric
• Is Part Of: American journal of hematology. Volume 94:Issue 10(2019:Oct.)
• Page Start: 1123
• Page End: 1131
• Publication Date: 2019-08-13
• Subjects: Hematology -- Periodicals; 616.15
• DOI: 10.1002/ajh.25578
• Languages: English
• ISSNs: 0361-8609

Abstract

Abstract: Diagnosis of lymphoma leptomeningeal dissemination is challenging and relies on a wide array of methods. So far, no consensus biological guidelines are available. This increases the chance of intra‐ and interpractice variations, despite the shared concern to perform the minimum amount of tests while preserving clinically relevant results.We evaluated a training cohort of 371 cerebrospinal fluid (CSF) samples from patients with putative lymphomatous central nervous system (CNS) localization using conventional cytology (CC), flow cytometry (FCM), molecular clonality assesment by PCR and cytokine quantification (CQ). This led us to propose a biological algorithm, which was then verified on a validation cohort of 197 samples. The samples were classified according to the clinical context and the results of each technique were compared. Using all four techniques was not useful for exclusion diagnosis of CNS lymphoma (CNSL), but they proved complementary for cases with suspected CNSL. This was particularly true for CQ in primary CNSL. Overall, diagnosis can be obtained with a two‐step approach. The first step comprises CC and FCM, as results are available quickly and FCM is a sensitive method. Both PCR and CQ can be postponed and performed in a second step, depending on the results from the first step and the clinical context.The proposed algorithm missed none of the CNSL samples of the validation cohort. Moreover, applying this algorithm would have spared 30% of PCR tests and 20% of CQ over a one‐year period, without compromising clinical management.