140.SAS CLINICAL ANALYSIS USING DATA, PROC MEANS, PROC FREQ, PROC UNIVARIATE, PROC CORR, PROC REPORT, PROC SQL, PROC SGPLOT, AND PROC EXPORT

SAS CLINICAL ANALYSIS USING DATA, PROC MEANS, PROC FREQ, PROC UNIVARIATE, PROC CORR, PROC REPORT, PROC SQL, PROC SGPLOT, AND PROC EXPORT

 /* Step 1: Creating the Clinical Trial Dataset */

DATA Clinical_Trials;

    LENGTH Trial_ID $10 Patient_ID $10 Gender $6 Drug_Name $15 Side_Effects $20 Outcome $10;

    FORMAT Age 8. Dosage_mg 8.2 Efficacy 8.2 BP_Change 8.2 Recovery_Time 8.2 Weight_Change 8.2 Heart_Rate 8.2 Cholesterol_Level 8.2;

    DO Trial_Index = 1001 TO 1005;

        Trial_ID = CATS("T", Trial_Index);

        DO Patient_Index = 2001 TO 2005; 

            Patient_ID = CATS("P", Patient_Index);

            Age = ROUND(18 + RANUNI(1234) * 62, 1); /* Age between 18 and 80 */

            Gender_Val = INT(RANUNI(1234) * 2) + 1;

            SELECT (Gender_Val);

                WHEN (1) Gender = "Male";

                WHEN (2) Gender = "Female";

                OTHERWISE Gender = "Unknown";

            END;

            /* Assigning Drug Name */

            Drug_Num = INT(RANUNI(1234) * 5) + 1;

            SELECT (Drug_Num);

                WHEN (1) Drug_Name = "DrugA";

                WHEN (2) Drug_Name = "DrugB";

                WHEN (3) Drug_Name = "DrugC";

                WHEN (4) Drug_Name = "DrugD";

                WHEN (5) Drug_Name = "DrugE";

                OTHERWISE Drug_Name = "Unknown";

            END;

            Dosage_mg = ROUND(50 + RANUNI(1234) * 250, 1); /* Dosage between 50 and 300mg */

            Efficacy = ROUND(RANUNI(1234) * 100, 1); /* Efficacy between 0-100% */

\

            Side_Num = INT(RANUNI(1234) * 6) + 1;

            SELECT (Side_Num);

                WHEN (1) Side_Effects = "None";

                WHEN (2) Side_Effects = "Nausea";

                WHEN (3) Side_Effects = "Dizziness";

                WHEN (4) Side_Effects = "Headache";

                WHEN (5) Side_Effects = "Fatigue";

                WHEN (6) Side_Effects = "Insomnia";

                OTHERWISE Side_Effects = "Unknown";

            END;

            BP_Change = ROUND(-15 + RANUNI(1234) * 30, 1); /* BP change between -15 and 15 */

            Recovery_Time = ROUND(5 + RANUNI(1234) * 30, 1); /* Recovery time between 5 and 35 days */

            Weight_Change = ROUND(-10 + RANUNI(1234) * 20, 1); /* Weight change between -10 and 10 kg */

            Heart_Rate = ROUND(60 + RANUNI(1234) * 40, 1); /* Heart rate between 60 and 100 bpm */

            Cholesterol_Level = ROUND(150 + RANUNI(1234) * 100, 1); /* Cholesterol level between 150 and 250 */

            IF Efficacy > 50 THEN Outcome = "Success";

            ELSE Outcome = "Failure";

            OUTPUT;

        END;

    END;

RUN;

PROC PRINT;RUN;

OUTPUT:

Obs	Trial_ID	Patient_ID	Gender	Drug_Name	Side_Effects	Outcome	Age	Dosage_mg	Efficacy	BP_Change	Recovery_Time	Weight_Change	Heart_Rate	Cholesterol_Level	Trial_Index	Patient_Index	Gender_Val	Drug_Num	Side_Num
1	T1001	P2001	Male	DrugB	None	Failure	33	74.00	26.00	-14.00	8.00	-1.00	66.00	154.00	1001	2001	1	2	1
2	T1001	P2002	Male	DrugE	Dizziness	Success	46	292.00	74.00	-4.00	15.00	0.00	71.00	185.00	1001	2002	1	5	3
3	T1001	P2003	Male	DrugA	Headache	Failure	34	228.00	0.00	12.00	12.00	6.00	66.00	162.00	1001	2003	1	1	4
4	T1001	P2004	Female	DrugD	Headache	Success	51	187.00	98.00	-2.00	20.00	9.00	88.00	185.00	1001	2004	2	4	4
5	T1001	P2005	Female	DrugA	Headache	Success	29	129.00	97.00	-6.00	25.00	1.00	88.00	210.00	1001	2005	2	1	4
6	T1002	P2001	Male	DrugB	Headache	Success	33	232.00	92.00	6.00	6.00	4.00	74.00	186.00	1002	2001	1	2	4
7	T1002	P2002	Female	DrugC	Fatigue	Success	50	91.00	83.00	-10.00	21.00	-2.00	96.00	177.00	1002	2002	2	3	5
8	T1002	P2003	Male	DrugB	Headache	Failure	55	124.00	37.00	15.00	8.00	8.00	62.00	155.00	1002	2003	1	2	4
9	T1002	P2004	Female	DrugE	Insomnia	Failure	67	153.00	1.00	14.00	7.00	9.00	95.00	167.00	1002	2004	2	5	6
10	T1002	P2005	Male	DrugE	Headache	Success	69	77.00	75.00	14.00	27.00	-7.00	82.00	242.00	1002	2005	1	5	4
11	T1003	P2001	Male	DrugE	Fatigue	Success	36	232.00	56.00	12.00	31.00	-7.00	76.00	195.00	1003	2001	1	5	5
12	T1003	P2002	Male	DrugA	None	Success	33	240.00	61.00	1.00	10.00	-5.00	92.00	220.00	1003	2002	1	1	1
13	T1003	P2003	Female	DrugE	Insomnia	Failure	78	162.00	48.00	-10.00	29.00	1.00	63.00	216.00	1003	2003	2	5	6
14	T1003	P2004	Male	DrugD	None	Failure	64	266.00	6.00	-9.00	28.00	-8.00	79.00	158.00	1003	2004	1	4	1
15	T1003	P2005	Female	DrugC	Dizziness	Failure	77	163.00	8.00	-8.00	20.00	5.00	90.00	239.00	1003	2005	2	3	3
16	T1004	P2001	Female	DrugD	Dizziness	Success	23	147.00	84.00	8.00	19.00	4.00	87.00	228.00	1004	2001	2	4	3
17	T1004	P2002	Female	DrugE	Nausea	Success	47	215.00	55.00	-4.00	9.00	0.00	61.00	214.00	1004	2002	2	5	2
18	T1004	P2003	Female	DrugC	Dizziness	Failure	72	83.00	33.00	13.00	6.00	-2.00	68.00	155.00	1004	2003	2	3	3
19	T1004	P2004	Female	DrugD	Dizziness	Success	56	175.00	53.00	4.00	32.00	5.00	72.00	203.00	1004	2004	2	4	3
20	T1004	P2005	Male	DrugE	Headache	Failure	33	226.00	33.00	2.00	31.00	0.00	86.00	232.00	1004	2005	1	5	4
21	T1005	P2001	Male	DrugB	Insomnia	Success	62	170.00	54.00	-13.00	20.00	-7.00	61.00	158.00	1005	2001	1	2	6
22	T1005	P2002	Male	DrugA	None	Success	50	201.00	94.00	9.00	13.00	6.00	72.00	163.00	1005	2002	1	1	1
23	T1005	P2003	Male	DrugA	Nausea	Failure	21	200.00	42.00	-6.00	14.00	1.00	65.00	243.00	1005	2003	1	1	2
24	T1005	P2004	Male	DrugA	Headache	Success	25	244.00	96.00	11.00	22.00	-5.00	92.00	216.00	1005	2004	1	1	4
25	T1005	P2005	Male	DrugE	None	Failure	68	274.00	22.00	1.00	8.00	-4.00	88.00	222.00	1005	2005	1	5	1

/* Step 2: Descriptive Statistics */

PROC MEANS DATA=Clinical_Trials N MEAN STD MIN MAX;

    VAR Age Dosage_mg Efficacy BP_Change Recovery_Time Weight_Change Heart_Rate Cholesterol_Level;

RUN;

OUTPUT:

                                                           The MEANS Procedure

Variable	N	Mean	Std Dev	Minimum	Maximum
Age Dosage_mg Efficacy BP_Change Recovery_Time Weight_Change Heart_Rate Cholesterol_Level	25 25 25 25 25 25 25 25	48.4800000 183.4000000 53.1200000 1.4400000 17.6400000 0.4400000 77.6000000 195.4000000	17.7766701 63.1116735 31.9600271 9.4959641 8.8028405 5.2605450 11.8392004 30.8963320	21.0000000 74.0000000 0 -14.0000000 6.0000000 -8.0000000 61.0000000 154.0000000	78.0000000 292.0000000 98.0000000 15.0000000 32.0000000 9.0000000 96.0000000 243.0000000

/* Step 3: Additional Summary Statistics */

PROC MEANS DATA=Clinical_Trials N MEDIAN Q1 Q3;

    VAR Age Dosage_mg Efficacy BP_Change Recovery_Time;

RUN;

OUTPUT:

                                                          The MEANS Procedure

Variable	N	Median	Lower Quartile	Upper Quartile
Age Dosage_mg Efficacy BP_Change Recovery_Time	25 25 25 25 25	50.0000000 187.0000000 54.0000000 1.0000000 19.0000000	33.0000000 147.0000000 33.0000000 -6.0000000 9.0000000	64.0000000 232.0000000 83.0000000 11.0000000 25.0000000

/* Step 4: Frequency Analysis */

PROC FREQ DATA=Clinical_Trials;

    TABLES Gender Drug_Name Side_Effects Outcome / NOROW NOCOL NOPERCENT;

RUN;

OUTPUT:

                                                                    The FREQ Procedure

Gender	Frequency	Cumulative Frequency
Female	10	10
Male	15	25

Drug_Name	Frequency	Cumulative Frequency
DrugA	6	6
DrugB	4	10
DrugC	3	13
DrugD	4	17
DrugE	8	25

Side_Effects	Frequency	Cumulative Frequency
Dizziness	5	5
Fatigue	2	7
Headache	8	15
Insomnia	3	18
Nausea	2	20
None	5	25

Outcome	Frequency	Cumulative Frequency
Failure	11	11
Success	14	25

/* Step 5: Univariate Analysis with Outlier Detection */

PROC UNIVARIATE DATA=Clinical_Trials;

    VAR Age Dosage_mg Efficacy BP_Change Recovery_Time Weight_Change Heart_Rate Cholesterol_Level;

    HISTOGRAM / NORMAL;

    QQPLOT;

RUN;

OUTPUT:

                                                  The UNIVARIATE Procedure

                                                          Variable: Age

Moments
N	25	Sum Weights	25
Mean	48.48	Sum Observations	1212
Std Deviation	17.7766701	Variance	316.01
Skewness	0.11151479	Kurtosis	-1.2704097
Uncorrected SS	66342	Corrected SS	7584.24
Coeff Variation	36.6680489	Std Error Mean	3.55533402

Basic Statistical Measures
Location		Variability
Mean	48.48000	Std Deviation	17.77667
Median	50.00000	Variance	316.01000
Mode	33.00000	Range	57.00000
		Interquartile Range	31.00000

NOTE: ONLY AGE VARIABLE OUTPUT PLACED HERE TRY TO SEE ALL VARIABLES IN SAS...

/* Step 6: Correlation Analysis */

PROC CORR DATA=Clinical_Trials;

    VAR Age Dosage_mg Efficacy BP_Change Recovery_Time Heart_Rate Cholesterol_Level;

RUN;

OUTPUT:

Pearson Correlation Coefficients, N = 25 Prob > |r| under H0: Rho=0
	Age	Dosage_mg	Efficacy	BP_Change	Recovery_Time	Heart_Rate	Cholesterol_Level
Age	1.00000	-0.22513 0.2793	-0.38843 0.0550	-0.06326 0.7639	0.04588 0.8276	-0.06161 0.7699	-0.16127 0.4412
Dosage_mg	-0.22513 0.2793	1.00000	-0.03909 0.8528	-0.00323 0.9878	0.03312 0.8751	0.03931 0.8520	0.14770 0.4811
Efficacy	-0.38843 0.0550	-0.03909 0.8528	1.00000	0.03497 0.8682	0.17062 0.4148	0.17610 0.3998	0.17966 0.3901
BP_Change	-0.06326 0.7639	-0.00323 0.9878	0.03497 0.8682	1.00000	-0.17149 0.4124	0.10466 0.6186	-0.04848 0.8180
Recovery_Time	0.04588 0.8276	0.03312 0.8751	0.17062 0.4148	-0.17149 0.4124	1.00000	0.17887 0.3923	0.35291 0.0836
Heart_Rate	-0.06161 0.7699	0.03931 0.8520	0.17610 0.3998	0.10466 0.6186	0.17887 0.3923	1.00000	0.34002 0.0963
Cholesterol_Level	-0.16127 0.4412	0.14770 0.4811	0.17966 0.3901	-0.04848 0.8180	0.35291 0.0836	0.34002 0.0963	1.00000

/* Step 7: Report Generation */

PROC REPORT DATA=Clinical_Trials NOWD;

    COLUMN Trial_ID Patient_ID Gender Drug_Name Dosage_mg Efficacy Recovery_Time Outcome Heart_Rate Cholesterol_Level;

    DEFINE Trial_ID / GROUP;

    DEFINE Patient_ID / DISPLAY;

    DEFINE Gender / GROUP;

    DEFINE Drug_Name / GROUP;

    DEFINE Dosage_mg / ANALYSIS MEAN;

    DEFINE Efficacy / ANALYSIS MEAN;

    DEFINE Recovery_Time / ANALYSIS MEAN;

    DEFINE Outcome / GROUP;

    DEFINE Heart_Rate / ANALYSIS MEAN;

    DEFINE Cholesterol_Level / ANALYSIS MEAN;

RUN;

OUTPUT:

Trial_ID	Patient_ID	Gender	Drug_Name	Dosage_mg	Efficacy	Recovery_Time	Outcome	Heart_Rate	Cholesterol_Level
T1001	P2005	Female	DrugA	129.00	97.00	25.00	Success	88.00	210.00
	P2004		DrugD	187.00	98.00	20.00	Success	88.00	185.00
	P2003	Male	DrugA	228.00	0.00	12.00	Failure	66.00	162.00
	P2001		DrugB	74.00	26.00	8.00	Failure	66.00	154.00
	P2002		DrugE	292.00	74.00	15.00	Success	71.00	185.00
T1002	P2002	Female	DrugC	91.00	83.00	21.00	Success	96.00	177.00
	P2004		DrugE	153.00	1.00	7.00	Failure	95.00	167.00
	P2003	Male	DrugB	124.00	37.00	8.00	Failure	62.00	155.00
	P2001			232.00	92.00	6.00	Success	74.00	186.00
	P2005		DrugE	77.00	75.00	27.00	Success	82.00	242.00
T1003	P2005	Female	DrugC	163.00	8.00	20.00	Failure	90.00	239.00
	P2003		DrugE	162.00	48.00	29.00	Failure	63.00	216.00
	P2002	Male	DrugA	240.00	61.00	10.00	Success	92.00	220.00
	P2004		DrugD	266.00	6.00	28.00	Failure	79.00	158.00
	P2001		DrugE	232.00	56.00	31.00	Success	76.00	195.00
T1004	P2003	Female	DrugC	83.00	33.00	6.00	Failure	68.00	155.00
	P2001		DrugD	147.00	84.00	19.00	Success	87.00	228.00
	P2004			175.00	53.00	32.00		72.00	203.00
	P2002		DrugE	215.00	55.00	9.00	Success	61.00	214.00
	P2005	Male	DrugE	226.00	33.00	31.00	Failure	86.00	232.00
T1005	P2003	Male	DrugA	200.00	42.00	14.00	Failure	65.00	243.00
	P2002			201.00	94.00	13.00	Success	72.00	163.00
	P2004			244.00	96.00	22.00		92.00	216.00
	P2001		DrugB	170.00	54.00	20.00	Success	61.00	158.00
	P2005		DrugE	274.00	22.00	8.00	Failure	88.00	222.00

/* Step 8: Advanced SQL Queries */

PROC SQL;

    SELECT Drug_Name, AVG(Efficacy) AS Avg_Efficacy, COUNT(*) AS Total_Patients

    FROM Clinical_Trials

    GROUP BY Drug_Name

    ORDER BY Avg_Efficacy DESC;

QUIT;

OUTPUT:

Drug_Name	Avg_Efficacy	Total_Patients
DrugA	65	6
DrugD	60.25	4
DrugB	52.25	4
DrugE	45.5	8
DrugC	41.33333	3

PROC SQL;

    SELECT Gender, AVG(Age) AS Avg_Age, COUNT(*) AS Total_Patients

    FROM Clinical_Trials

    GROUP BY Gender;

QUIT;

OUTPUT:

Gender	Avg_Age	Total_Patients
Female	55	10
Male	44.13333	15

PROC SQL;

    SELECT Side_Effects, COUNT(*) AS Frequency

    FROM Clinical_Trials

    GROUP BY Side_Effects

    ORDER BY Frequency DESC;

QUIT;

OUTPUT:

Side_Effects	Frequency
Headache	8
None	5
Dizziness	5
Insomnia	3
Fatigue	2
Nausea	2

PROC SQL;

    SELECT AVG(Heart_Rate) AS Avg_Heart_Rate, AVG(Cholesterol_Level) AS Avg_Cholesterol

    FROM Clinical_Trials;

QUIT;

OUTPUT:

Avg_Heart_Rate	Avg_Cholesterol
77.6	195.4

/* Step 9: Data Visualization */

PROC SGPLOT DATA=Clinical_Trials;

    VBOX Efficacy / CATEGORY=Drug_Name;

    TITLE "Drug Efficacy Comparison";

RUN;

PROC SGPLOT DATA=Clinical_Trials;

    VBAR Side_Effects / RESPONSE=BP_Change GROUP=Drug_Name;

    TITLE "Side Effects vs BP Change";

RUN;

PROC SGPLOT DATA=Clinical_Trials;

    SCATTER X=Age Y=Efficacy / GROUP=Drug_Name;

    TITLE "Age vs Efficacy by Drug";

RUN;

PROC SGPLOT DATA=Clinical_Trials;

    HISTOGRAM Recovery_Time / NORMAL;

    TITLE "Recovery Time Distribution";

RUN;

PROC SGPLOT DATA=Clinical_Trials;

    SERIES X=Age Y=Heart_Rate / GROUP=Gender;

    TITLE "Heart Rate vs Age";

RUN;

PROC SGPLOT DATA=Clinical_Trials;

    VBOX Cholesterol_Level / CATEGORY=Gender;

    TITLE "Cholesterol Levels by Gender";

RUN;

/* Step 10: Data Export */

PROC EXPORT DATA=Clinical_Trials

    OUTFILE="clinical_trials_output.csv"

    DBMS=CSV

    REPLACE;

RUN;

PRACTICE AND COMMENT YOUR CODE: 

-->PLEASE FOLLOW OUR BLOG FOR MORE UPDATES.

TO FOLLOW OUR TELEGRAM CHANNEL CLICK HERE