Introduction to Ranking Models - Text Mining Techniques for Healthcare Provider Quality Determination - page 26

Table 7. Translated codes

Patient Concatenated Diagnoses

1 Pneumonia, organism unspecified, Chronic obstructive asthma, Hemoptysis, Overweight and obesity, Asthma, Symptoms

involving respiratory system and other chest symptoms, Overweight, obesity and other hyperalimentation

2 Pneumonia, organism unspecified, Acute bronchiolitis, Acute upper respiratory infections of multiple or unspecified sites

3 Pneumonia, organism unspecified, Chronic obstructive asthma, Pure hypercholesterolemia

4 Pneumonia, organism unspecified

5 Other musculoskeletal symptoms referable to limbs, Atrial fibrillation and flutter, Venous embolism and thrombosis of deep

vessels of lower extremity, Other specified disorders of circulatory system, Essential hypertension, Old myocardial infarction

6 Syncope and collapse, Hemorrhagic disorder due to intrinsic circulating anticoagulants, Moyamoya disease, Convulsions, Es-

sential hypertension, Viral exanthem, unspecified, Fever

7 Pneumonia, organism unspecified, Hypertensive kidney disease, benign, Anemia in chronic illness, Pure hypercholesterolemia,

Méniére's disease, Other diseases of respiratory system, not elsewhere classified, Sleep disturbances

8 Other cellulitis and abscess, ankle, not foot, Pneumonia, organism unspecified, Venous embolism and thrombosis of deep vessels

of lower extremity, Asthma, unspecified, Staphylococcus, Diabetes mellitus without mention of complication, Other hemolytic
anemias due to enzyme deficiency

9 Essential hypertension, malignant, Diabetes mellitus without mention of complication, Overweight and obesity, Edema, Es-

sential hypertension, Diabetes mellitus

10 Pneumonia, organism unspecified, Volume depletion, Asthma, unspecified, Pleurisy without mention of effusion or current

tuberculosis, Essential hypertension, Old myocardial infarction

11 Volume depletion, Aortic valve disorders, Congestive heart failure, unspecified, Candidiasis, Hypotension, unspecified, Diabetes

mellitus without mention of complication, liver donor

12 Alzheimer's disease, Volume depletion, Dementia in conditions classified elsewhere, Diseases of white blood cells, Other

cholecystitis, Essential hypertension, Coronary atherosclerosis

13 Other physical therapy, Pneumonia, organism unspecified, Acute renal failure, unspecified, Congestive heart failure, unspecified,

Long-term (current) drug use, Essential hypertension, Coronary atherosclerosis

14 Displacement of thoracic or lumbar intervertebral disc without myelopathy, Spina bifida, Multiple sclerosis, Kyphoscoliosis

and scoliosis

15 Congestive heart failure, unspecified, Acute renal failure, unspecified, Hypertensive kidney disease, Diabetes with renal mani-

festations, Long-term (current) drug use, Coronary atherosclerosis, Anemia, unspecified

data work.concat(keep= dupersid icd9codx) ;
length icd9codx $ 32767 ;
set work.tran ;
array chconcat {*} med_: ;
icd9codx = left(trim(med_1)) ;
do i = 2 to dim(chconcat) ;
icd9codx = left(trim(icd9codx)) || ' ' || left(trim(chconcat[i])) ;
end ;
run ;

Because it is unknown just how many variables need to be concatenated, the maximum possible
length was used. Proc SQL is used to reduce the length of the text string to its minimum possible.

proc sql ;

select max(length(icd9codx)) into:icd9codx_LEN from work.concat ;