DeltaMSI: artificial intelligence-based modeling of microsatellite instability scoring on next-generation sequencing data

Table 2 AUC of DeltaMSI models and mSINGS versus IHC outcome Table shows the AUC (95% CI) of models tested in DeltaMSI development (logistic regression, SVC and the combined voting) as compared to mSINGS on all 28 marker regions (mSINGS) and mSINGS on 10 top-performing regions (mSINGS10) in N = 215 samples confirmed by IHC (179 of the original model set plus 36 Gy zone result samples that were additionally tested by IHC)

Variable	AUC	95% CI	P	Cut-off	Sensitivity	95% CI	Specificity	95% CI	+LR	−LR
Logistic regression	0.949	0.909–0.975	0.0216	0.26	88	75.7–95.5	98.79	95.7–99.9	72.6	0.12
SVC	0.950	0.911–0.976	0.0198	0.26	90	78.2–96.7	98.79	95.7–99.9	74.25	0.1
Combined Voting	0.950	0.910–0.975	0.0224	0.26	88	75.7–95.5	100	97.8–100.0	∞	0.12
mSINGS10	0.931	0.887–0.962	0.0295	0.26	90	78.2–96.7	98.79	95.7–99.9	74.25	0.1
mSINGS_allregions	0.876	0.823 to 0.918		0.29	68	53.3–80.5	98.17	94.7–99.6	37.17	0.33

P value versus mSINGS_allregions. Table also indicates the proposed binary cut-off for clinical use and the associated sensitivity/specificity and positive (+LR) and negative (−LR) likelihood ratios to predict or rule out dMMR status

ISSN: 1471-2105