What happened
Dxcover Ltd is developing a blood test that reads the infrared spectrum of a serum sample and uses machine learning to spot the pattern of brain cancer. At the developers' request, the Scottish Health Technologies Group (SHTG) assessed the evidence and published its overview in October 2021. The published study tested 385 people at a single center in Edinburgh. They were 321 patients referred from primary care for CT scans and 64 patients with known brain tumors. Sensitivity was 81% and specificity 80%, for a negative predictive value of 95% and a positive predictive value of 45%. SHTG notes that the cohort was enriched with known tumors and did not match the primary care patients for whom the test is meant. The referred group held only three tumors. In an exploratory model, the test was likely to be cost-effective at £100 if 1% of tested patients had brain cancer. Directors and an employee of ClinSpec Diagnostics, the spinout company whose staff developed the test, co-wrote the study. SHTG states that firm conclusions cannot be drawn without evaluation in general practice.
Sources
-
Peer-reviewed study, by the makers.
Brennan PM, Butler HJ, Christie L, et al. Early diagnosis of brain tumours using a novel spectroscopic liquid biopsy. Brain Communications 2021, 3(2):fcab056. doi:10.1093/braincomms/fcab056. Four authors were directors and one an employee of ClinSpec Diagnostics, the spinout company behind the test.
Our test predicted the presence of glioblastoma, the most common and aggressive brain tumour, with 91% sensitivity, and all brain tumours with 81% sensitivity, and 80% specificity.
-
Assessment report, by authors with no tie to the system.
Scottish Health Technologies Group, Healthcare Improvement Scotland. Dxcover™ brain cancer liquid biopsy test for early brain cancer detection in primary care. Innovative Medical Technology Overview IMTO 03-21, October 2021. Executive summary.
In a published diagnostic accuracy cohort study (n=385) undertaken in secondary care that included 64 patients with known brain tumours, the DxcoverTM test was able to distinguish between patients with and without brain cancer.
Details
AI system
- Workflow
-
Serum samples were analyzed by infrared spectroscopy and a machine-learning algorithm, blind to the imaging results. The cohort combined patients referred for direct-access CT with patients already diagnosed with brain tumors.
Follow-up
- Conditions for replication
-
Accuracy is confirmed in the primary care population for whom the test is meant. About 1% or more of tested patients have brain cancer, the level at which the test was likely to be cost-effective at £100 in the exploratory model.
Entry details
- Sector
-
Healthcare (cancer diagnostics).
- Purpose
-
Dxcover Ltd built the Dxcover brain cancer liquid biopsy test to help general practitioners decide which patients with vague symptoms to send urgently for brain imaging.
31 more questions not yet checked
model, release, provider, role, configuration, inputs and outputs, autonomy, human oversight, AI contribution, beneficiaries, reach, distribution and access, duration, every measurement question, every money question, ownership and control, dependencies, cross-border connections, geopolitical implications, replication attempts, availability, institutional decision, grounds, action and result, success criterion, every evidence question, observed or intended, alternative assessments, related entries, other identifiers, category mappings.
Cite this record
Peter H. Vartanian. (2026). Dxcover blood test separated patients with and without brain cancer (AIBD-0930). Artificial Intelligence Benefits Database, edition of 1 November 2026. https://petervartanian.xyz/aibd/records/AIBD-0930.html (archived at https://doi.org/10.7910/DVN/AADSII, version 7.0)