Skip to main content

Table 3 Prediction of Parkinson disease status, logistic regression, n = 56 (14 controls and 42 PD), Mean ± SD

From: Antemortem detection of Parkinson’s disease pathology in peripheral biopsies using artificial intelligence

 

Sensitivity/recall

Specificity

Precision

F1 score*

Accuracy

13 AI features altogether

0.71 ± 0.16

0.65 ± 0.30

0.86 ± 0.13

0.76 ± 0.12

0.69 ± 0.13

Expert score and its derivatives

0.59 ± 0.16

0.88 ± 0.24

0.94 ± 0.13

0.71 ± 0.13

0.66 ± 0.13

Expert score

0.54 ± 0.16

0.93** ± 0.17

0.96 ± 0.10

0.68 ± 0.14

0.64 ± 0.13

Expert score derivatives

0.60 ± 0.16

0.89 ± 0.23

0.94 ± 0.11

0.72 ± 0.13

0.67 ± 0.13

  1. *F1 score, harmonic mean is calculated as 2 * Precision * Recall/(Precision + Recall)
  2. **Expert score specificity is the same as reported previously [6]
Back to article page

Acta Neuropathologica Communications

ISSN: 2051-5960

Contact us