Skip to main content

Table 2 Metacharacteristics: misprints, terms, abbreviations according to dictionaries

From: Citywide quality of health information system through text mining of electronic health records

HIS Medical terms Russian words English words Proper name Abbreviations Medical Drugs Correct words Number of records
HIS #1 0.21 0.33 0.0001 0.20 0.17 0.03 0.42 37,772
HIS #5 0.32 0.47 0.0001 0.14 0.20 0.04 0.57 31,736
HIS #3 0.47 0.64 0.0014 0.09 0.54 0.10 0.77 170
HIS #10 0.63 0.78 0.0000 0.24 0.61 0.00 0.78 1371
HIS #9 0.47 0.69 0.0000 0.18 0.38 0.08 0.79 4868
HIS #12 0.55 0.72 0.0007 0.15 0.35 0.06 0.81 322
HIS #11 0.57 0.74 0.0000 0.17 0.36 0.06 0.81 48
HIS #2 0.51 0.72 0.0000 0.15 0.41 0.08 0.82 3196
HIS #6 0.48 0.72 0.0000 0.20 0.44 0.07 0.82 3
HIS #8 0.41 0.80 0.0000 0.30 0.48 0.04 0.86 80
HIS #7 0.66 0.85 0.0000 0.11 0.37 0.05 0.91 43
HIS #4 0.53 0.89 0.0000 0.00 0.21 0.00 0.95 19
HIS #13 0.67 0.87 0.0234 0.16 0.72 0.12 0.96 1