Table 5.
The auxiliary performance of Interpretable Eye Diseases Screening System (IEDSS) in identifying multimorbidity.
| Accuracy (95% CI) | P value(vs IEDSS) | P value(with IEDSS vs without IEDSS) | Correct diagnosis | Misidenti-fication | Undetected lesions | Misdetected lesions | |
|---|---|---|---|---|---|---|---|
| Junior ophthalmologist without IEDSS | 78·40 (74·79-82·01) |
0·003⁎⁎ | 0·009⁎⁎ | 392 | 61 | 29 | 22 |
| Junior ophthalmologist with IEDSS | 84·80 (81·65-87·95) |
0·722 | 424 | 51 | 15 | 14 | |
| Senior ophthalmologist without IEDSS | 85·00 (81·87-88·13) |
0·789 | 0·271 | 425 | 32 | 18 | 27 |
| Senior ophthalmologist with IEDSS | 87·40 (84·49-90·31) |
0·405 | 437 | 30 | 10 | 23 | |
| IEDSS | 85·60 (82·52-88·68) |
428 | 53 | 9 | 16 |
Correct diagnosis was defined as successfully identifying all types of diseases. The wrong samples were summarized into: (1) misidentification, which was defined as the lesion was correctly detected but the disease was misdiagnosed; (2) undetected lesions, which was defined as the missed detection of lesions; (3) misdetected lesions, including false positives and wrongly categorized lesions. *p < 0·05,
⁎⁎
p < 0·01.