OpenML
Diabetes130US

Diabetes130US

active ARFF Publicly available Visibility: public Uploaded 27-01-2023 by Young Lee
0 likes downloaded by 0 people , 0 total downloads 0 issues 0 downvotes
Issue #Downvotes for this reason By


Loading wiki
Help us complete this description Edit
The dataset represents 10 years (1999-2008) of clinical care at 130 US hospitals and integrated delivery networks. It includes over 50 features representing patient and hospital outcomes. Information was extracted from the database for encounters that satisfied the following criteria:(1) It is an inpatient encounter (a hospital admission).(2) It is a diabetic encounter, that is, one during which any kind of diabetes was entered to the system as a diagnosis.(3) The length of stay was at least 1 day and at most 14 days.(4) Laboratory tests were performed during the encounter.(5) Medications were administered during the encounter.The data contains such attributes as patient number, race, gender, age, admission type, time in hospital, medical specialty of admitting physician, number of lab test performed, HbA1c test result, diagnosis, number of medication, diabetic medications, number of outpatient, inpatient, and emergency visits in the year before the hospitalization, etc.

48 features

class (target)string3 unique values
0 missing
admission_type_idnumeric8 unique values
0 missing
discharge_disposition_idnumeric26 unique values
0 missing
admission_source_idnumeric17 unique values
0 missing
time_in_hospitalnumeric14 unique values
0 missing
num_lab_proceduresnumeric118 unique values
0 missing
num_proceduresnumeric7 unique values
0 missing
num_medicationsnumeric75 unique values
0 missing
number_outpatientnumeric39 unique values
0 missing
number_emergencynumeric33 unique values
0 missing
number_inpatientnumeric21 unique values
0 missing
number_diagnosesnumeric16 unique values
0 missing
racenominal5 unique values
2273 missing
gendernominal3 unique values
0 missing
agenominal10 unique values
0 missing
weightnominal9 unique values
98569 missing
payer_codenominal17 unique values
40256 missing
medical_specialtynominal72 unique values
49949 missing
diag_1nominal716 unique values
21 missing
diag_2nominal748 unique values
358 missing
diag_3nominal789 unique values
1423 missing
max_glu_serumnominal4 unique values
0 missing
A1Cresultnominal4 unique values
0 missing
metforminnominal4 unique values
0 missing
repaglinidenominal4 unique values
0 missing
nateglinidenominal4 unique values
0 missing
chlorpropamidenominal4 unique values
0 missing
glimepiridenominal4 unique values
0 missing
acetohexamidenominal2 unique values
0 missing
glipizidenominal4 unique values
0 missing
glyburidenominal4 unique values
0 missing
tolbutamidenominal2 unique values
0 missing
pioglitazonenominal4 unique values
0 missing
rosiglitazonenominal4 unique values
0 missing
acarbosenominal4 unique values
0 missing
miglitolnominal4 unique values
0 missing
troglitazonenominal2 unique values
0 missing
tolazamidenominal3 unique values
0 missing
examidenominal1 unique values
0 missing
citogliptonnominal1 unique values
0 missing
insulinnominal4 unique values
0 missing
glyburide.metforminnominal4 unique values
0 missing
glipizide.metforminnominal2 unique values
0 missing
glimepiride.pioglitazonenominal2 unique values
0 missing
metformin.rosiglitazonenominal2 unique values
0 missing
metformin.pioglitazonenominal2 unique values
0 missing
changenominal2 unique values
0 missing
diabetesMednominal2 unique values
0 missing

19 properties

101766
Number of instances (rows) of the dataset.
48
Number of attributes (columns) of the dataset.
3
Number of distinct values of the target attribute (if it is nominal).
192849
Number of missing values in the dataset.
100723
Number of instances with at least one value missing.
11
Number of numeric attributes.
36
Number of nominal attributes.
54864
Number of instances belonging to the most frequent class.
11.16
Percentage of instances belonging to the least frequent class.
11357
Number of instances belonging to the least frequent class.
9
Number of binary attributes.
18.75
Percentage of binary attributes.
98.98
Percentage of instances having missing values.
1
Average class difference between consecutive instances.
3.95
Percentage of missing values.
0
Number of attributes divided by the number of instances.
22.92
Percentage of numeric attributes.
53.91
Percentage of instances belonging to the most frequent class.
75
Percentage of nominal attributes.

2 tasks

0 runs - estimation_procedure: 10-fold Crossvalidation - evaluation_measure: predictive_accuracy - target_feature: class
0 runs - estimation_procedure: 4-fold Crossvalidation - target_feature: class
Define a new task