Skip to main content

Table 4 Discovering rules from a disease dictionary

From: Normalizing biomedical terms by minimizing ambiguity and variability

 

Dictionary

 

Lookup performance

Iter.

Ambiguity

Variability

Rule

Precision

Recall

0

1.001

2.794

(convert capital letters to lower case)

0.994

0.158

1

1.002

2.747

‘,’ → ‘’

0.989

0.184

2

1.002

2.667

‘ nos’ → ‘’

0.986

0.216

3

1.003

2.609

‘[x]’ → ‘’

0.985

0.263

4

1.003

2.580

‘o’ → ‘’

0.982

0.275

5

1.003

2.554

‘ies’ → ‘y’

0.983

0.291

6

1.003

2.529

‘ ’ → ‘-’

0.984

0.305

7

1.003

2.504

‘-’ → ‘;’

0.984

0.317

8

1.003

2.484

‘e’ → ‘i’

0.985

0.332

9

1.004

2.472

‘iasi’ → ‘rdir’

0.986

0.336

10

1.004

2.459

‘’s’ → ‘’

0.986

0.345

11

1.004

2.449

‘s’ → ‘z’

0.986

0.347

12

1.004

2.448

‘;(nz)’ → ‘’

0.986

0.347

13

1.004

2.447

‘kidniy’ → ‘rinal’

0.986

0.347

14

1.004

2.446

‘pulmnary’ → ‘lung’

0.986

0.347

15

1.004

2.443

‘ir’ → ‘ri’

0.986

0.348

16

1.004

2.441

‘aimia’ → ‘imiaz’

0.986

0.349

17

1.004

2.439

‘[d]’ → ‘’

0.986

0.349

18

1.004

2.436

‘aimlytic;animiaz’ → ‘imlytic;animia’

0.986

0.351

:

:

:

:

:

:

24

1.004

2.427

‘z;thi’ → ‘’

0.986

0.354

:

:

:

:

:

:

31

1.004

2.420

‘z;’ → ‘/’

0.986

0.355

32

1.004

2.348

‘/’ → ‘;’

0.987

0.377

33

1.004

2.348

‘dizrdri;liv’ → ‘livri;dizrd’

0.987

0.377

:

:

:

:

:

:

38

1.004

2.345

‘uding’ → ‘’

0.987

0.378

:

:

:

:

:

:

42

1.005

2.343

‘zufficiincy’ → ‘cmpitinci’

0.987

0.380

:

:

:

:

:

:

50

1.005

2.339

‘(in;zputum)’ → ‘in;zputum’

0.987

0.381

:

:

:

:

:

:

57

1.005

2.335

‘iincy’ → ‘’

0.987

0.382

:

:

:

:

:

:

70

1.005

2.333

‘[idta]’ → ‘’

0.987

0.385

:

:

:

:

:

:

89

1.005

2.327

‘ph’ → ‘f’

0.987

0.387

:

:

:

:

:

:

93

1.005

2.325

‘ci’ → ‘x’

0.987

0.388

:

:

:

:

:

: