226.GLOBAL EPILEPSY TREATMENT DATA ANALYSIS USING PROC OPTIONS | PROC FORMAT | PROC PRINT | PROC CONTENTS | PROC FREQ | PROC MEANS | PROC SGPLOT | PROC SQL | PROC EXPORT | PROC COMPARE

GLOBAL EPILEPSY TREATMENT DATA ANALYSIS USING PROC OPTIONS | PROC FORMAT | PROC PRINT | PROC CONTENTS | PROC FREQ | PROC MEANS | PROC SGPLOT | PROC SQL | PROC EXPORT | PROC COMPARE

 /*Worldwide epilepsy‑treatment dataset*/

1.Global program‑level OPTIONS (good style)

options nocenter nodate nonumber ls=132 ps=60

        varlenchk=NOWARN         /* ignore length “shrinking” */

        fmtsearch=(work);        /* look‑up custom formats    */


2.Creating the 25‑row dataset

data work.epil_world;

   length PatientID $8  Country $20 Region $15  EpilepsyType $25

          Sex $1 PrimaryDrug $15 SeizureControl $12 TreatmentRegimen $10 ;

   format DiagnosisDate TreatmentStart TreatmentEnd date9. ;


   infile datalines dsd truncover;

   input PatientID Country Region EpilepsyType $

         Age Sex $

         DiagnosisDate :date9.

         TreatmentStart :date9.

         TreatmentEnd   :date9.

         PrimaryDrug $ SeizureControl $ ;


   /*—— DERIVE LENGTH‑OF‑TREATMENT ——*/

   DurationMonths = intck('month', TreatmentStart, TreatmentEnd );


   /*—— DERIVE REGIMEN TYPE ——*/

   TreatmentRegimen = ifc(DurationMonths>24, 'Poly', 'Mono');


   label DurationMonths = 'Treatment Duration (Months)';

datalines;

P001,India,Asia,Focal,24,M,05JAN2022,15JAN2022,15JUL2024,Levetiracetam,Controlled

P002,USA,NorthAmerica,Generalized,32,F,20MAR2021,10APR2021,10JUN2023,Valproate,Partial

P003,Brazil,SouthAmerica,Focal_to_Bilateral,45,M,12DEC2019,01JAN2020,01JAN2024,Carbamazepine,Controlled

P004,UK,Europe,Generalized,29,F,15FEB2020,20FEB2020,20FEB2022,Topiramate,Controlled

P005,Japan,Asia,Focal,38,M,01AUG2018,15AUG2018,15FEB2025,Lacosamide,Uncontrolled

P006,Nigeria,Africa,Unknown,27,F,10OCT2022,20OCT2022,20APR2024,Phenytoin,Partial

P007,Germany,Europe,Focal,51,M,05MAY2017,20MAY2017,20MAY2020,Carbamazepine,Controlled

P008,Canada,NorthAmerica,Generalized,33,F,02JAN2023,05JAN2023,05JUL2024,Valproate,Partial

P009,Australia,Oceania,Focal,41,M,22JUL2020,01AUG2020,01FEB2023,Levetiracetam,Controlled

P010,India,Asia,Focal_to_Bilateral,16,F,12SEP2023,15SEP2023,15MAR2025,Oxcarbazepine,Uncontrolled

P011,France,Europe,Generalized,60,M,20APR2016,01MAY2016,01MAY2024,Valproate,Controlled

P012,Brazil,SouthAmerica,Focal,34,F,15NOV2020,20NOV2020,20NOV2023,Lacosamide,Partial

P013,USA,NorthAmerica,Unknown,22,M,01JAN2024,15JAN2024,15JUN2024,Levetiracetam,Uncontrolled

P014,Japan,Asia,Generalized,57,F,10JUN2019,20JUN2019,20DEC2023,Topiramate,Controlled

P015,India,Asia,Focal,30,M,05JUL2021,10JUL2021,10JAN2025,Carbamazepine,Partial

P016,Kenya,Africa,Focal,28,F,22FEB2022,01MAR2022,01MAR2024,Lacosamide,Controlled

P017,UK,Europe,Unknown,46,M,11NOV2020,20NOV2020,20NOV2023,Phenytoin,Partial

P018,USA,NorthAmerica,Focal_to_Bilateral,37,F,01APR2022,10APR2022,10OCT2024,Valproate,Controlled

P019,Australia,Oceania,Generalized,19,M,01JAN2023,05JAN2023,05JAN2025,Levetiracetam,Controlled

P020,India,Asia,Focal,52,F,15DEC2018,01JAN2019,01JAN2024,Carbamazepine,Uncontrolled

P021,Germany,Europe,Focal,48,M,20MAY2020,25MAY2020,25NOV2023,Lacosamide,Partial

P022,Canada,NorthAmerica,Generalized,31,F,02FEB2021,10FEB2021,10AUG2023,Topiramate,Controlled

P023,Nigeria,Africa,Focal_to_Bilateral,43,M,08AUG2019,15AUG2019,15FEB2023,Valproate,Partial

P024,Brazil,SouthAmerica,Generalized,26,F,10DEC2022,20DEC2022,20JUN2024,Phenytoin,Controlled

P025,Japan,Asia,Unknown,55,M,01SEP2020,10SEP2020,10MAR2023,Levetiracetam,Uncontrolled

;

run;

proc print;run;

Output:

Obs PatientID Country Region EpilepsyType Sex PrimaryDrug SeizureControl TreatmentRegimen DiagnosisDate TreatmentStart TreatmentEnd Age DurationMonths
1 P001 India Asia Focal M Levetiracetam Controlled Poly 05JAN2022 15JAN2022 15JUL2024 24 30
2 P002 USA NorthAmerica Generalized F Valproate Partial Poly 20MAR2021 10APR2021 10JUN2023 32 26
3 P003 Brazil SouthAmerica Focal_to_Bilateral M Carbamazepine Controlled Poly 12DEC2019 01JAN2020 01JAN2024 45 48
4 P004 UK Europe Generalized F Topiramate Controlled Mono 15FEB2020 20FEB2020 20FEB2022 29 24
5 P005 Japan Asia Focal M Lacosamide Uncontrolled Poly 01AUG2018 15AUG2018 15FEB2025 38 78
6 P006 Nigeria Africa Unknown F Phenytoin Partial Mono 10OCT2022 20OCT2022 20APR2024 27 18
7 P007 Germany Europe Focal M Carbamazepine Controlled Poly 05MAY2017 20MAY2017 20MAY2020 51 36
8 P008 Canada NorthAmerica Generalized F Valproate Partial Mono 02JAN2023 05JAN2023 05JUL2024 33 18
9 P009 Australia Oceania Focal M Levetiracetam Controlled Poly 22JUL2020 01AUG2020 01FEB2023 41 30
10 P010 India Asia Focal_to_Bilateral F Oxcarbazepine Uncontrolled Mono 12SEP2023 15SEP2023 15MAR2025 16 18
11 P011 France Europe Generalized M Valproate Controlled Poly 20APR2016 01MAY2016 01MAY2024 60 96
12 P012 Brazil SouthAmerica Focal F Lacosamide Partial Poly 15NOV2020 20NOV2020 20NOV2023 34 36
13 P013 USA NorthAmerica Unknown M Levetiracetam Uncontrolled Mono 01JAN2024 15JAN2024 15JUN2024 22 5
14 P014 Japan Asia Generalized F Topiramate Controlled Poly 10JUN2019 20JUN2019 20DEC2023 57 54
15 P015 India Asia Focal M Carbamazepine Partial Poly 05JUL2021 10JUL2021 10JAN2025 30 42
16 P016 Kenya Africa Focal F Lacosamide Controlled Mono 22FEB2022 01MAR2022 01MAR2024 28 24
17 P017 UK Europe Unknown M Phenytoin Partial Poly 11NOV2020 20NOV2020 20NOV2023 46 36
18 P018 USA NorthAmerica Focal_to_Bilateral F Valproate Controlled Poly 01APR2022 10APR2022 10OCT2024 37 30
19 P019 Australia Oceania Generalized M Levetiracetam Controlled Mono 01JAN2023 05JAN2023 05JAN2025 19 24
20 P020 India Asia Focal F Carbamazepine Uncontrolled Poly 15DEC2018 01JAN2019 01JAN2024 52 60
21 P021 Germany Europe Focal M Lacosamide Partial Poly 20MAY2020 25MAY2020 25NOV2023 48 42
22 P022 Canada NorthAmerica Generalized F Topiramate Controlled Poly 02FEB2021 10FEB2021 10AUG2023 31 30
23 P023 Nigeria Africa Focal_to_Bilateral M Valproate Partial Poly 08AUG2019 15AUG2019 15FEB2023 43 42
24 P024 Brazil SouthAmerica Generalized F Phenytoin Controlled Mono 10DEC2022 20DEC2022 20JUN2024 26 18
25 P025 Japan Asia Unknown M Levetiracetam Uncontrolled Poly 01SEP2020 10SEP2020 10MAR2023 55 30

3.First‑look exploration

3.1 What’s inside? (PROC CONTENTS)

proc contents data=work.epil_world varnum;

   title "Structure of EPIL_W (Worldwide Epilepsy Study)";

run;

Output:

Structure of EPIL_WORLD (Worldwide Epilepsy Study)

The CONTENTS Procedure

Data Set Name WORK.EPIL_WORLD Observations 25
Member Type DATA Variables 13
Engine V9 Indexes 0
Created 14/09/2015 00:06:14 Observation Length 152
Last Modified 14/09/2015 00:06:14 Deleted Observations 0
Protection   Compressed NO
Data Set Type   Sorted NO
Label      
Data Representation WINDOWS_64    
Encoding wlatin1 Western (Windows)    


Engine/Host Dependent Information
Data Set Page Size 65536
Number of Data Set Pages 1
First Data Page 1
Max Obs per Page 430
Obs in First Data Page 25
Number of Data Set Repairs 0
ExtendObsCounter YES
Filename C:\Users\Lenovo\AppData\Local\Temp\SAS Temporary Files\_TD10416_DESKTOP-QFAA4KV_\epil_world.sas7bdat
Release Created 9.0401M2
Host Created X64_8HOME


Variables in Creation Order
# Variable Type Len Format Label
1 PatientID Char 8    
2 Country Char 20    
3 Region Char 15    
4 EpilepsyType Char 25    
5 Sex Char 1    
6 PrimaryDrug Char 15    
7 SeizureControl Char 12    
8 TreatmentRegimen Char 10    
9 DiagnosisDate Num 8 DATE9.  
10 TreatmentStart Num 8 DATE9.  
11 TreatmentEnd Num 8 DATE9.  
12 Age Num 8    
13 DurationMonths Num 8   Treatment Duration (Months)


3.2 Raw peek (PROC PRINT with WHERE)

proc print data=work.epil_world(obs=10);

   title "First 10 Records – Sanity Check";

   where Country in ('India','USA');

run;

Output:

First 10 Records – Sanity Check

Obs PatientID Country Region EpilepsyType Sex PrimaryDrug SeizureControl TreatmentRegimen DiagnosisDate TreatmentStart TreatmentEnd Age DurationMonths
1 P001 India Asia Focal M Levetiracetam Controlled Poly 05JAN2022 15JAN2022 15JUL2024 24 30
2 P002 USA NorthAmerica Generalized F Valproate Partial Poly 20MAR2021 10APR2021 10JUN2023 32 26
10 P010 India Asia Focal_to_Bilateral F Oxcarbazepine Uncontrolled Mono 12SEP2023 15SEP2023 15MAR2025 16 18
13 P013 USA NorthAmerica Unknown M Levetiracetam Uncontrolled Mono 01JAN2024 15JAN2024 15JUN2024 22 5
15 P015 India Asia Focal M Carbamazepine Partial Poly 05JUL2021 10JUL2021 10JAN2025 30 42
18 P018 USA NorthAmerica Focal_to_Bilateral F Valproate Controlled Poly 01APR2022 10APR2022 10OCT2024 37 30
20 P020 India Asia Focal F Carbamazepine Uncontrolled Poly 15DEC2018 01JAN2019 01JAN2024 52 60

4.Descriptive statistics

4.1 Demographics by epilepsy type (PROC FREQ)

proc freq data=work.epil_world order=freq;

   table EpilepsyType*Sex / nocol nopercent nocum;

   title "Sex Distribution by Epilepsy Classification";

run;

Output:

Sex Distribution by Epilepsy Classification

The FREQ Procedure

Frequency
Row Pct
Table of EpilepsyType by Sex
EpilepsyType Sex
M F Total
Focal
6
66.67
3
33.33
9
 
Generalized
2
25.00
6
75.00
8
 
Focal_to_Bilateral
2
50.00
2
50.00
4
 
Unknown
3
75.00
1
25.00
4
 
Total
13
12
25


4.2 Treatment length distribution (PROC MEANS)

proc means data=work.epil_world n mean median min max maxdec=1;

   class EpilepsyType;

   var DurationMonths Age;

   title "Duration & Age, Broken Down by Epilepsy Class";

run;

Output:

Duration & Age, Broken Down by Epilepsy Class

The MEANS Procedure

EpilepsyType N Obs Variable Label N Mean Median Minimum Maximum
Focal 9
DurationMonths
Age
Treatment Duration (Months)
 
9
9
42.0
38.4
36.0
38.0
24.0
24.0
78.0
52.0
Focal_to_Bilateral 4
DurationMonths
Age
Treatment Duration (Months)
 
4
4
34.5
35.3
36.0
40.0
18.0
16.0
48.0
45.0
Generalized 8
DurationMonths
Age
Treatment Duration (Months)
 
8
8
36.3
35.9
25.0
31.5
18.0
19.0
96.0
60.0
Unknown 4
DurationMonths
Age
Treatment Duration (Months)
 
4
4
22.3
37.5
24.0
36.5
5.0
22.0
36.0
55.0

4.3 Quick plot (PROC SGPLOT with summary function)

proc sgplot data=work.epil_world;

   vbox DurationMonths / category=Region;

   title "Boxplot: Months on Treatment by Global Region";

run;

Log:

NOTE: PROCEDURE SGPLOT used (Total process time):

      real time           3.32 seconds

      cpu time            0.56 seconds


NOTE: Listing image output written to SGPlot1.png.

NOTE: There were 25 observations read from the data set WORK.EPIL_WORLD.


5.Custom formats to declutter outputs

proc format;

   value $reg 'NorthAmerica' = 'N. America'

              'SouthAmerica' = 'S. America'

              'Oceania'      = 'Oce'

              other          = 'OTHER';

run;


proc freq data=work.epil_world;

   format Region $reg.;

   tables Region*SeizureControl / norow nocol nopercent;

   title "Outcome vs Region Using User Format";

run;

Output:

Outcome vs Region Using User Format

The FREQ Procedure

Frequency
Table of Region by SeizureControl
Region SeizureControl
Controlled Partial Uncontrolled Total
OTHER
6
5
4
15
N. America
2
2
1
5
Oce
2
0
0
2
S. America
2
1
0
3
Total
12
8
5
25

6.Analytic SQL snippets

proc sql;

   title "Mean Treatment Duration by Country & Control Status";

   select Country,

          SeizureControl,

          count(*)               as N_Patients,

          mean(DurationMonths)   as Avg_Months format=5.1

   from   work.epil_world

   group  by Country, SeizureControl

   having calculated Avg_Months > 18

   order  by Avg_Months desc;

quit;

Output:

Mean Treatment Duration by Country & Control Status

Country SeizureControl N_Patients Avg_Months
France Controlled 1 96.0
Japan Uncontrolled 2 54.0
Japan Controlled 1 54.0
Germany Partial 1 42.0
India Partial 1 42.0
India Uncontrolled 2 39.0
UK Partial 1 36.0
Germany Controlled 1 36.0
Brazil Partial 1 36.0
Brazil Controlled 2 33.0
Nigeria Partial 2 30.0
Canada Controlled 1 30.0
India Controlled 1 30.0
USA Controlled 1 30.0
Australia Controlled 2 27.0
USA Partial 1 26.0
UK Controlled 1 24.0
Kenya Controlled 1 24.0


7.Reusable macro: %SummaryBy

%macro SummaryBy(data=, class=, statvar=, outfile=);

   %local i n var;

   %let n=%sysfunc(countw(&class));


   %do i=1 %to &n;

      %let var=%scan(&class,&i);


      title "===&var Summary===";

      proc means data=&data n mean median maxdec=1;

         class &var;

         var &statvar;

      run;


      proc freq data=&data;

         tables &var / nocum nopercent;

      run;


      /*—— optional export ——*/

      %if %length(&outfile) %then %do;

         proc export data=&data(keep=&var &statvar)

             outfile="&outfile._&var..csv"

             dbms=csv replace;

         run;

      %end;

   %end;

%mend SummaryBy;


%SummaryBy(data=work.epil_world,

           class=Region EpilepsyType TreatmentRegimen,

           statvar=DurationMonths,

           outfile=%sysfunc(pathname(work))/epil_out);

Output:

===Region Summary===

The MEANS Procedure

Analysis Variable : DurationMonths Treatment Duration (Months)
Region N Obs N Mean Median
Africa 3 3 28.0 24.0
Asia 7 7 44.6 42.0
Europe 5 5 46.8 36.0
NorthAmerica 5 5 21.8 26.0
Oceania 2 2 27.0 27.0
SouthAmerica 3 3 34.0 36.0


===Region Summary===

The FREQ Procedure

Region Frequency
Africa 3
Asia 7
Europe 5
NorthAmerica 5
Oceania 2
SouthAmerica 3

===EpilepsyType Summary===

The MEANS Procedure

Analysis Variable : DurationMonths Treatment Duration (Months)
EpilepsyType N Obs N Mean Median
Focal 9 9 42.0 36.0
Focal_to_Bilateral 4 4 34.5 36.0
Generalized 8 8 36.3 25.0
Unknown 4 4 22.3 24.0

===EpilepsyType Summary===

The FREQ Procedure

EpilepsyType Frequency
Focal 9
Focal_to_Bilateral 4
Generalized 8
Unknown 4

===TreatmentRegimen Summary===

The MEANS Procedure

Analysis Variable : DurationMonths Treatment Duration (Months)
TreatmentRegimen N Obs N Mean Median
Mono 8 8 18.6 18.0
Poly 17 17 43.9 36.0

===TreatmentRegimen Summary===

The FREQ Procedure

TreatmentRegimen Frequency
Mono 8
Poly 17

8.Quality‑control snapshot

Compare derived vs re‑computed (PROC COMPARE)

data qc;

   set work.epil_world;

   RecalcMonths = intck('month', TreatmentStart, TreatmentEnd);

run;

proc print;run;

Obs PatientID Country Region EpilepsyType Sex PrimaryDrug SeizureControl TreatmentRegimen DiagnosisDate TreatmentStart TreatmentEnd Age DurationMonths RecalcMonths
1 P001 India Asia Focal M Levetiracetam Controlled Poly 05JAN2022 15JAN2022 15JUL2024 24 30 30
2 P002 USA NorthAmerica Generalized F Valproate Partial Poly 20MAR2021 10APR2021 10JUN2023 32 26 26
3 P003 Brazil SouthAmerica Focal_to_Bilateral M Carbamazepine Controlled Poly 12DEC2019 01JAN2020 01JAN2024 45 48 48
4 P004 UK Europe Generalized F Topiramate Controlled Mono 15FEB2020 20FEB2020 20FEB2022 29 24 24
5 P005 Japan Asia Focal M Lacosamide Uncontrolled Poly 01AUG2018 15AUG2018 15FEB2025 38 78 78
6 P006 Nigeria Africa Unknown F Phenytoin Partial Mono 10OCT2022 20OCT2022 20APR2024 27 18 18
7 P007 Germany Europe Focal M Carbamazepine Controlled Poly 05MAY2017 20MAY2017 20MAY2020 51 36 36
8 P008 Canada NorthAmerica Generalized F Valproate Partial Mono 02JAN2023 05JAN2023 05JUL2024 33 18 18
9 P009 Australia Oceania Focal M Levetiracetam Controlled Poly 22JUL2020 01AUG2020 01FEB2023 41 30 30
10 P010 India Asia Focal_to_Bilateral F Oxcarbazepine Uncontrolled Mono 12SEP2023 15SEP2023 15MAR2025 16 18 18
11 P011 France Europe Generalized M Valproate Controlled Poly 20APR2016 01MAY2016 01MAY2024 60 96 96
12 P012 Brazil SouthAmerica Focal F Lacosamide Partial Poly 15NOV2020 20NOV2020 20NOV2023 34 36 36
13 P013 USA NorthAmerica Unknown M Levetiracetam Uncontrolled Mono 01JAN2024 15JAN2024 15JUN2024 22 5 5
14 P014 Japan Asia Generalized F Topiramate Controlled Poly 10JUN2019 20JUN2019 20DEC2023 57 54 54
15 P015 India Asia Focal M Carbamazepine Partial Poly 05JUL2021 10JUL2021 10JAN2025 30 42 42
16 P016 Kenya Africa Focal F Lacosamide Controlled Mono 22FEB2022 01MAR2022 01MAR2024 28 24 24
17 P017 UK Europe Unknown M Phenytoin Partial Poly 11NOV2020 20NOV2020 20NOV2023 46 36 36
18 P018 USA NorthAmerica Focal_to_Bilateral F Valproate Controlled Poly 01APR2022 10APR2022 10OCT2024 37 30 30
19 P019 Australia Oceania Generalized M Levetiracetam Controlled Mono 01JAN2023 05JAN2023 05JAN2025 19 24 24
20 P020 India Asia Focal F Carbamazepine Uncontrolled Poly 15DEC2018 01JAN2019 01JAN2024 52 60 60
21 P021 Germany Europe Focal M Lacosamide Partial Poly 20MAY2020 25MAY2020 25NOV2023 48 42 42
22 P022 Canada NorthAmerica Generalized F Topiramate Controlled Poly 02FEB2021 10FEB2021 10AUG2023 31 30 30
23 P023 Nigeria Africa Focal_to_Bilateral M Valproate Partial Poly 08AUG2019 15AUG2019 15FEB2023 43 42 42
24 P024 Brazil SouthAmerica Generalized F Phenytoin Controlled Mono 10DEC2022 20DEC2022 20JUN2024 26 18 18
25 P025 Japan Asia Unknown M Levetiracetam Uncontrolled Poly 01SEP2020 10SEP2020 10MAR2023 55 30 30

proc compare base=qc(rename=(DurationMonths=Dur1))

             compare=qc(rename=(RecalcMonths=Dur2))

             criterion=0.0001 /* tolerance */

             out=diff(where=(difference ne 0));

   id PatientID;

   var Dur1;

   with Dur2;

   title "QC: Derived Duration vs Recalc";

run;

Output:

QC: Derived Duration vs Recalc

The COMPARE Procedure                                                                                                               
Comparison of WORK.QC with WORK.QC                                                                                                  
(Method=RELATIVE(2.22E-10), Criterion=0.0001)                                                                                       
                                                                                                                                    
Data Set Summary                                                                                                                    
                                                                                                                                    
Dataset           Created          Modified  NVar    NObs                                                                           
                                                                                                                                    
WORK.QC  14SEP15:00:35:14  14SEP15:00:35:14    14      25                                                                           
WORK.QC  14SEP15:00:35:14  14SEP15:00:35:14    14      25                                                                           
                                                                                                                                    
                                                                                                                                    
Variables Summary                                                                                                                   
                                                                                                                                    
Number of Variables in Common: 12.                                                                                                  
Number of Variables in WORK.QC but not in WORK.QC: 2.                                                                               
Number of Variables in WORK.QC but not in WORK.QC: 2.                                                                               
Number of ID Variables: 1.                                                                                                          
Number of VAR Statement Variables: 1.                                                                                               
Number of WITH Statement Variables: 1.

To Visit My Previous Sas Questions Datasets:Click Here
To Visit My Previous Home Energy Consumption Dataset:Click Here
To Visit My Previous Wildlife Migration Dataset:Click Here
To Visit My Previous Endangered Species Dataset:Click Here


-->PRACTICE AND COMMENT YOUR OUTPUT: 
--->PLEASE FOLLOW OUR BLOG FOR MORE UPDATES.

PLEASE FOLLOW OUR TELEGRAM CHANNEL CLICK HERE

PLEASE FOLLOW OUR FACEBOOK PAGE  CLICK HERE

PLEASE FOLLOW OUR INSTAGRAM PAGE CLICK HERE

Comments

Popular posts from this blog

409.Can We Build a Reliable Emergency Services Analytics & Fraud Detection System in SAS While Identifying and Fixing Intentional Errors?

397.If a satellite has excellent signal strength but very high latency, can it still deliver good quality communication? Why or why not?A Sas Study

401.How Efficient Are Global Data Centers? A Complete SAS Analytics Study