The Westgard rules provide a statistical framework for evaluating the quality of analytical runs in medical laboratories. Developed by Dr. James Westgard in the 1980s, the rules are based on statistical process control and can be used individually or together to detect random and systematic errors. Key rules include 1:2s for warning of potential errors, 1:3s and 2:2s for rejecting runs with errors, and 10x for identifying systematic biases over multiple runs. Laboratories should aim to maximize error detection while minimizing false rejections when applying these rules.

1. WESTGARD RULES

2. • In 1981 Dr.James Westgard Of The University Of Wisconsin Published An Article
On Laboratory Quality Control That Set The Basis For Evaluating Analytical Run
Quality For Medical Laboratories.
• The Elements Of The Westgard Systems Are Based On Principles Of Statistical
Process Control Used In Industry Nation Wide Since The 1950’s
• These Rules Are Used Individually Or In Combination To Evaluate The Quality
Of Analytical Runs.

3. • The rules of how to use LJ correctly has been described by James
westgard and these are called Westgard rules.
• These rules are used for detecting changes in the analytical system.

4. Rules for what ?
• To decide whether an analytical run is in-control or out –of –control
• These rules can be applied as single rules and as a group of
rules(multi-rules)
• Westgard rules can be applied only if your qc are plotted with the
range of ±3 SD

5. Two key factors to keep in mind while selecting / using rules :
Maximize error detection:
Per cent error detection ( P ed ) >90%
Minimize false rejection :
Percent false rejection ( P fr ) < 5 %

6. 2 sets of QC rule nomenclatures
1. N and L
2. Within / across (run / material)

7. Nomenclature 1:

8. Nomenclature 2 :
Within-run / across material
DATE QC LEVELS
DAY I Level 1 Level 2
DAY 2 Level 1 Level 2
Across run / same material
DATE QC LEVELS
DAY 1 LEVEL 1 LEVEL2
DAY 2 LEVEL 1 LEVEL 2
2/3 LEVEL OF QC IN THE SAME RUN
SAME LEVEL (MATERIAL) OF QC BUT IN 2 OR MORE
CONSECUTIVE RUNS

9. Gaussian curve

10. 1:2S RULE

11. 1:2S RULE
• One control exceeding the ± 2 SD limit.
• Denotes a random error / beginning of a systematic error
• Warning rule
• It can be both in plus and in minus direction
• Even In absence of any analytical errors 4.5 % of data points in the
region of 1:2S region
If only one level of QC is being run in the lab 1:2S has to be a
rejection rule

13. 1:3S RULE

14. • one control result has exceeded the established mean +/- 3SD range.
• Rejection rule
• a run is rejected when a single control measurement exceeds the mean
3SD control limit
 This rule identifies unacceptable
Random error
Beginning of a large systematic error.

15. 2:2s RULE
• two consecutive control results have exceeded the same mean +/- 2SD
limit.
• Rejection rule.
• Identifies only systematic errors only
There are two applications to this rule
• With-in-run ( in the 2 levels of QC in the same run)
• Across runs ( in the same QC in 2 consecutive runs )

16. 2:2s RULE

17. If a normal (level 1) and abnormal (level 2) control are
>2s On the same side of mean:
• This run violates the within-run application for systematic error
If level 1 is accepatable and level 2 is 1:2s, the level 2 result from
previous run is examined:
• If level 2 in previous run was
• At +2.0s or greater
• Then the across run application for systematic error is violated

19. 2 of 32s RULE:
• When 2 out of 3 control measurements exceed the same ±2SD control
limit.
• Denotes systematic error.

21. R4S RULE :
• When 2 control measurements in a group exceeds the mean ±2SD on
either side or if the sum of SD of two material >4 SD
• Only be interpreted within-run, not across-run
• Identifies random error only
• Applied only within the current run.

22. R4S RULE:

24. 31S RULE :
• 3 consecutive control meaurements exceed the same mean plus 1s or
mean minus 1s control limit.
• Denotes systematic error
• 3 consecutive results
• Greater than 1s
• On the same side of mean
• Applied for within control material or across control material

25. 31S RULE :

26. • Within control material violations indicate systematic bias in a single
area of the method curve.
• While violation across control materials indicates systematic error
over a broader concentration.

27. 4 1S RULE :

30. 10 x RULE
• The 10-x Control Rule indicates ten consecutive control results have
fallen on the same side of the mean.
• rejection rule

31. 10 x RULE

32. • When 6 or 8 or 9 or 10 or 12 control results on the same side of mean
regardless of the specific SD in which they are located.
• Within control material violations indicate systematic bias in a single
area of the method curve
• While violation across control materials indicates systematic error
over a broader concentration.

35. 7 T RULE :

36. 7 T RULE :

37. RULE VIOLATION SYSTEMATIC ERROR RANDOM ERROR
1 : 2s
2 : 2s
1 : 3s
4: 1s
2 of 3:2s
3 : 1s
10x
7T
R : 4s

38. Within run errors
(The power of daily monitoring)
• Stop and take corrective action if a single point exceeds, 1 : 3s limit
• Stop and take corrective action if two levels of control exceed, 2:2s
• Stop and take corrective action, R4s limit. meant only to be applied
within run.

39. Across run errors :
( the power of periodic review)

42. What do you do now ?

43. Corrective actions
Things that can go wrong
• Instrument malfunction
• Reagents preparations,contamination,
volume
• Tech error
• Control specimen is old or prepared
improperly
Corrective action
• Identify malfunction
• New reagents
• Identify error and repeat test
• Use new control

44. THANK YOU