ArticleJCO clinical cancer informatics2026
Machine Learning Algorithm for the Detection of Tumor Microsatellite Instability Based on Multiomics Biomarkers.
Article in JCO clinical cancer informatics, 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 1 paper.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
1 citing paper in PubMed.
- Review
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
15 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
purposeAccurate classification of microsatellite instability (MSI) in advanced cancers is critical for identifying patients who may benefit from immune checkpoint inhibitors. However, variability in MSI detection workflows can lead to missed MSI-high cases, indicating need for complementary screening approaches. Using next-generation sequencing (NGS) data from colorectal tumors, we developed a machine learning (ML) model to predict MSI status using immune-related gene expression profiles and pathogenic single-nucleotide variants (SNVs) and copy-number variants (CNVs). MATERIALS AND
methodsWe analyzed NGS data from 2,756 patients with colorectal cancer (CRC), including DNA panel results for SNVs and CNVs, RNA sequencing of immune-related genes, and tumor mutation burden (TMB). ML algorithms were trained on 70% of the CRC cohort using TMB and selected features by Boruta algorithm. Trained models were tested on the remainder of the CRC cohort and The Cancer Genome Atlas (TCGA) colorectal (COAD) and rectal (READ) adenocarcinoma data sets. To assess the translatability to other cancer types, uterine and gastric cancer cases were tested.
resultsFeature selection identified 107 features for model training, including SNVs and CNVs. The CART model with the highest mean accuracy, precision, and recall showed strong performance across the CRC, TCGA COAD/READ, uterine, and gastric cancer cohorts, ranging from 78% sensitivity in uterine cancer to 99%-100% specificity and negative predictive value in CRC. Of the 53 indeterminate CRC and uterine cases, 15% were classified as likely MSI-high. Of these, 75% had mismatch repair immunohistochemistry results available, with 83% showing MLH1 and PMS2 loss.
conclusionOur ML approach accurately predicted MSI status in colorectal and uterine cancers using multiomics data derived from NGS, without relying on direct microsatellite sequencing. The ability to identify MSI-high tumors among indeterminate cases demonstrates potential to improve diagnostic precision and ensures timely access to immunotherapy for patients with MSI-high disease.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.