Prospective evaluation of a new machine learning model for the minimally invasive diagnosis of CNS lymphomas using ultrasensitive analysis of circulating tumour DNA from cerebrospinal fluid and blood plasma

Prospective evaluation of a new machine learning model for the minimally invasive diagnosis of CNS lymphomas using ultrasensitive analysis of circulating tumour DNA from cerebrospinal fluid and blood plasma - DETECT_CNSL

Status

Recruiting

Phases

Unknown

Study type

Interventional

Source

DRKS

Registry ID

DRKS00033402

Enrollment

120

Registered

2024-04-25

Start date

2024-09-25

Completion date

Unknown

Last updated

2026-03-02

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

CNS lymphomas C85.9

Interventions

Group 1: There is an indication for a neurosurgical stereotactic biopsy due to a radiologically proven brain lesion and CNS lymphoma can be considered as a differential diagnosis. Before the biopsy, c

Eligibility

Sex/Gender

All

Age

18 Years to 99 Years

Inclusion criteria

Inclusion criteria: Adult patients of any gender. Patients for whom a neurosurgical stereotactic biopsy is indicated and one of the differential diagnoses is CNS lymphoma. Patients who are capable of giving consent and who have given their informed consent.

Exclusion criteria

Exclusion criteria: Age under 18 years. Pregnancy. Presence of a condition or abnormality which, in the opinion of the assessor, jeopardises patient safety. This specifically includes conditions or abnormalities that jeopardise the safety of a CSF puncture, i.e. signs of entrapment. Imaging (usually an MRI) must be available to rule these out. An additional imaging examination (e.g. cranial CT), which may involve radiation exposure, is not performed. Patients who lack legal capacity and are unable to understand the nature, significance and consequences of the study. Patients who are in a dependent or employment relationship with the sponsor or the investigators

Design outcomes

Primary

Measure	Time frame
Sensitivity of the machine learning method for the correct identification of CNS lymphomas from CSF compared to the gold standard (histopathology)	—

Secondary

Measure	Time frame
Sensitivity of the machine learning method after steroid administration compared to the sensitivity before stereotactic biopsy. Sensitivity of the machine learning method for the correct identification of CNS lymphomas from blood plasma compared to the gold standard (histopathology).	—

Countries

Germany

Contacts

Public ContactMatthias Weiß

Universitätsklinikum Freiburg

matthias.weiss@uniklinik-freiburg.de+49 761 270 32902

Outcome results

None listed

Source: DRKS (via WHO ICTRP) · Data processed: Mar 14, 2026