Table 1.
Baseline demographic and clinical characteristics of patient electrodiagnostic reports
| Features | Total (n = 200) | Intervention (AI–physician) (n = 100) | Control (Physician) (n = 100) | p value |
|---|---|---|---|---|
| Age [median, IQR] | 53.0 [40.0–65.0] | 55.0 [43.0–68.0] | 51.0 [38.0–62.0] | 0.072 |
| Male (n, %) | 102 (51.0%) | 56 (56.0%) | 46 (46.0%) | 0.157 |
| Abnormal tests | 146 (73.0%) | 75 (75.0%) | 71 (71.0%) | 0.522 |
| Normal tests | 54 (27.0%) | 25 (25.0%) | 29 (29.0%) | 0.522 |
| Correctness of AI model of detecting abnormality tests | – | 70 (93.3%) | – | – |
| Correctness of AI model of detecting normal tests | – | 23 (92.0%) | – | – |
| Diagnosis found in the reports | ||||
| Polyneuropathy diagnosis | 26 (13.0%) | 13 (13.0%) | 13 (13.0%) | 1.000 |
| Mononeuropathy diagnosis | 64 (32.0%) | 32 (32.0%) | 32 (32.0%) | 1.000 |
| Radiculopathy | 68 (34.0%) | 36 (36.0%) | 32 (32.0%) | 0.548 |
| Plexopathy | 2 (1.0%) | 1 (1.0%) | 1 (1.0%) | 1.000 |
| Myopathy | 2 (1.0%) | 1 (1.0%) | 1 (1.0%) | 1.000 |
| Motor neuron disease | 0 (0.0%) | 0 (0.0%) | 0 (0.0%) | – |
| Patient Comorbidities | ||||
| Diabetes mellitus | 4 (2.0%) | 2 (2.0%) | 2 (2.0%) | 1.000 |
| Dyslipidemia | 20 (10.0%) | 10 (10.0%) | 10 (10.0%) | 1.000 |
| Hypertension | 18 (9.0%) | 9 (9.0%) | 9 (9.0%) | 1.000 |
| Congestive heart failure | 0 (0.0%) | 0 (0.0%) | 0 (0.0%) | – |
| Ischemic heart disease | 4 (2.0%) | 2 (2.0%) | 2 (2.0%) | 1.000 |
| Cancer | 8 (4.0%) | 4 (4.0%) | 4 (4.0%) | 1.000 |