Research Article

Diagnostic Accuracy of NICE Classification System for Optical Recognition of Predictive Morphology of Colorectal Polyps

Table 3

Diagnostic accuracy of the NICE classification system for optical recognition of colorectal polyps histology (n denotes number of polyps).

Share of accurate diagnosis
(%)95% CIOR

All polyps735564(76.7)(73.4–79.7)
Sex of the patient
 Male490368(75.1)(71.0–78.9)1
 Female245196(80.0)(74.4–84.8)1.330.139>0.999
Age of patients (years)
 ≤444034(85.0)(70.2–94.3)1
 45–548157(70.4)(59.2–80.0)0.420.085>0.999
 55–64291223(76.6)(71.3–81.3)0.580.238>0.999
 65–74220169(76.8)(70.7–82.2)0.590.254>0.999
 ≥7510381(78.6)(69.4–86.1)0.650.392>0.999
Number of examined polyps per physician
 Physician A388296(76.3)(71.7–80.4)1
 Physician B11496(84.2)(76.2–90.4)1.660.074>0.999
 Physician C9880(81.6)(72.5–88.7)1.380.260>0.999
 Physician D3722(59.5)(41.8–75.0)0.460.0270.567
 Physician E3826(68.4)(51.3–82.5)0.670.284>0.999
 Physician F3022(73.3)(54.1–87.7)0.860.715>0.999
 Physician G106(60.0)(26.2–87.8)0.470.245>0.999
 Other physicians2016(80.0)(56.3–94.3)1.240.703>0.999
Polyp location>0.999
 Rectum11586(74.8)(65.9–82.4)1>0.999
 Sigmoid colon320244(76.3)(71.3–80.9)1.080.752>0.999
 Descending colon6544(67.7)(55.0–78.8)0.710.309>0.999
 Splenic flexure76(85.7)(42.1–99.6)2.020.522>0.999
 Transverse colon3929(74.4)(57.9–87.0)0.980.9580.958
 Hepatic flexure3028(93.3)(77.9–99.2)4.720.0420.840
 Ascending colon5140(78.4)(64.6–88.7)1.230.612>0.999
 Cecum10887(80.6)(71.9–87.6)1.400.303>0.999
Polyp size (mm)
 Diminutive (1–5 mm)336211(62.8)(57.4–68.0)1
 Small (6–9 mm)140120(85.7)(78.9–91.0)3.56<0.001<0.001
 Large (10–20 mm)205185(90.2)(85.3–93.9)5.48<0.001<0.001
 Extra-large (>20 mm)4944(89.8)(77.8–96.6)5.210.0010.025
The Paris endoscopic classification
 Sessile polyps (Is)497368(74.0)(69.9–77.8)1
 Pedunculated polyps (Ip)137121(88.3)(81.7–93.2)2.650.0010.024
 Subpedunculated polyps (Is + Ip)4437(84.1)(69.9–93.4)1.850.146>0.999
 Flat elevation of mucosa (IIa)2714(51.9)(32.0–71.4)0.380.0150.345
 Flat elevation with central depression (IIa + IIc)55(100.0)(47.8–100)-
 IIa + Iib32(66.7)(9.4–99.2)-
 Is + Iia22(100.0)(15.8–100)-
The NICE classification
 110438(36.5)(27.3–46.5)1
 2612516(84.3)(81.2–87.1)0.34<0.001<0.001
 3198(42.1)(28.8–75.5)1.930.191>0.999
Lesions (NICE classification)
 Nonneoplastic10438(36.5)(27.3–46.5)1
 Neoplastic631526(83.4)(80.3–86.2)8.70<0.001<0.001
Histopathological diagnosis
 LGIEN375325(86.7)(82.8–90.0)1
 HGIEN209195(93.3)(89.9–96.3)2.140.0160.352
 Hyperplastic polyp10836(33.3)(24.5–43.0)0.08<0.001<0.001
 Normal tissue180(0.0)(0.0–18.5)0.00
 Invasive carcinoma168(50.0)(24.7–75.4)0.15<0.001<0.001
 Other90(0.0)(0.0–33.6)0.00
The risk of lesions
 Low (LGIEN, hyperplastic, normal tissue, and other)510361(70.8)(66.6–74.7)1
 High (HGEIN, invasive carcinoma)225203(90.2)(85.5–93.8)3.81<0.001<0.001

The data is presented as the number (percent), unless otherwise indicated. 1 = reference category; OR = odds ratio; 95% CI = 95% confidence interval;  = statistical significance of appearance for accurate diagnosis;  = statistical significance corrected by sequential Holm-Bonferroni correction; - = statistics have not been calculated because of the low polyp count.