A noninvasive machine learning model using a complete blood count for screening of primary vitreoretinal lymphoma.
Blood-count based model detects primary vitreoretinal lymphoma with high sensitivity in screening.
A noninvasive machine learning model using a complete blood count for screening of primary vitreoretinal lymphoma.
Primary vitreoretinal lymphoma (primary vitreoretinal lymphoma) is a rare and aggressive intraocular malignancy that is frequently misdiagnosed because of its nonspecific early manifestations and the lack of effective screening tools.
This study presents the noninvasive and scalable blood-based screening strategy for detection of primary vitreoretinal lymphoma, with a web application enabling timely triage and population-level risk stratification.
In the community cohort (n = 515,326), 22 individuals are flagged as high risk, 13 of whom are confirmed as having primary vitreoretinal lymphoma (positive predictive value = 59.1%).
of true lymphoma cases, the blood test correctly flagged 95
We conduct a multicentre case-control study including 255 primary vitreoretinal lymphoma patients and 292 controls to develop a machine learning-based screening model using complete blood count data.
A six-feature random forest model demonstrates high diagnostic accuracy in the discovery cohort (area under the curve [AUC] = 0.85) and validates across all cohorts (AUC = 0.80-0.83), outperforming intraocular biomarkers such as the interleukin-10/interleukin-6 ratio (AUC = 0.65-0.78).
This study presents the noninvasive and scalable blood-based screening strategy for detection of primary vitreoretinal lymphoma, with a web application enabling timely triage and population-level risk stratification.