© 2016© 2016
A Practical Approach to Analyzing
Healthcare Data
Chapter 8 – Exploratory Data
Applications
© 2016
Exploratory Data Analysis
• AKA Data Mining
• Using statistical techniques to find patterns in data
• Typically a mixture of graphical displays and
descriptive statistics
• Many practical applications in improving
healthcare operations
• HIM professionals are uniquely positioned to
perform this analysis because they understand the
data and the underlying operational and
reimbursement implications of patterns
© 2016
Case Mix Analysis
• Case Mix Index (CMI) – average MS-DRG weight for
all patients
– May be calculated for subsets of patients such as
Medicare/Medicaid/selected MS-DRGs
– May exclude portions such as transplants (very high
weight MS-DRGs) or transfers (reduced payment and
short stays)
– Single number that may be used as a proxy for measuring
the resource intensity of a hospital’s patients
– Medicare CMI is the primary driver of the inpatient
Medicare revenue
– Frequently a key performance indicator for a hospital and
a key driver of the revenue budget
© 2016
Case Mix Index
Example1. Multiply the number of cases in each MS-DRG by the relative
weight
2. Sum the values from #1
3. Sum the number of discharges
4. Divide total relative weights by the number of discharges
Note: This is the weighted average of the relative weights for each
MS-DRG.
© 2016
MS-DRG Families
• MS-DRGs may be broken into families with two or three
members:
– No CC
– CC (not present in all families)
– MCC
• The MS-DRG weight system is designed to assign higher
weights to MS-DRGs that require a higher resource
intensity
• MCC MS-DRGs are assigned higher weights than no CC
MS-DRGs in the same family
MS-
DRG MS-DRG Title Weights
190 CHRONIC OBSTRUCTIVE PULMONARY DISEASE W MCC 1.1860
191 CHRONIC OBSTRUCTIVE PULMONARY DISEASE W CC 0.9521
192 CHRONIC OBSTRUCTIVE PULMONARY DISEASE W/O CC/MCC 0.7072
258 CARDIAC PACEMAKER DEVICE REPLACEMENT W MCC 2.6945
259 CARDIAC PACEMAKER DEVICE REPLACEMENT W/O MCC 1.8590
COPD
Pacemaker
Replacement
© 2016
CC/MCC Capture Rates
• Example:
• 𝐶𝐶 𝑀𝐶𝐶 𝐶𝑎𝑝𝑡𝑢𝑟𝑒 𝑅𝑎𝑡𝑒 =
87+51
87+51+33
= 80.7%
• This value can be compared to HCUP data using a z-test for
proportions to determine if the sample rate is higher/lower than
the national rate
• In general, hospitals with higher CC/MCC capture rates have
higher CMI
• A unusually high CC/MCC capture rate may be indicative of a
compliance issue (over-coding) and should also be investigated
MS-DRG Description Volume Relative Wt
280 AMI, Alive w MCC 87 1.7999
281 AMI, Alive w CC 51 1.0961
282 AMI, Alive w no CC/MCC 33 0.7736
© 2016
CMI Shifts
• Significant shifts in CMI should be investigated to
determine the root cause
• Potential causes:
– New service lines
– Surgeon vacation schedules
– Holidays
– Natural disasters (hurricanes, tornados, etc.)
© 2016
Present on Admission (POA)
indicator
If diagnosis that might be a hospital acquired
condition (HAC) was not present on admission,
claim is paid as if diagnosis was not on claim
© 2016
Other DRGs Systems
• AP-DRGs
– All-patient DRGs
– AKA “New York Grouper”
– Three character, numeric
– Weights are calibrated for all patients and not only
Medicare
• APR-DRGs
– All patient refined DRGs
– 3M proprietary grouping system
– 3 character, numeric followed by digit (1-4) for
severity and (1-4) for risk of mortality
© 2016
Ambulatory Patient Classifications
(APC)
• CMS uses APCs to pay for services in the hospital
outpatient and ambulatory surgery settings.
• Challenges of APCs
– Claim may have more than one payable APC
– Assignment of CPT/HCPCS codes to APCs may change
each year
– More of a fee schedule than a true prospective payment
system
• Can use APC weights to calculate a service mix index
(SMI)
– Note that this measures the average resource intensity for
the services provided and not for the typical case
© 2016
Other Analysis Tools/Reports
• Outpatient Code Editor (OCE)
– Used to find missed procedures
– Identify potential compliance issues (NCCI edit
violations)
• Examining levels of code subsets that are ordered
– Clinic visits (99201 to 99205)
– Emergency visits (99281 to 99285)
© 2016
Methods of Analysis
• Validation of utilization patterns
– Specialty specific codes
– Comparison to hospitals with like service mix
(trauma center, transplants, etc.)
• RVU Analysis
– Work RVUs may be used to benchmark
physician productivity
– Part of the CMS Physician Fee Schedule
© 2016
RVU – Physician Productivity
© 2016
RVU – Other Uses
• Average cost per RVU
• Physician compensation per work
RVU (wRVU)
• Malpractice expense per Malpractice
RVU (mRVU)
• Overhead or practice expense per
Practice Expense RVU (peRVU)
• Break-Even Conversion Factor
(BECF)

Hm306 week 7

  • 1.
    © 2016© 2016 APractical Approach to Analyzing Healthcare Data Chapter 8 – Exploratory Data Applications
  • 2.
    © 2016 Exploratory DataAnalysis • AKA Data Mining • Using statistical techniques to find patterns in data • Typically a mixture of graphical displays and descriptive statistics • Many practical applications in improving healthcare operations • HIM professionals are uniquely positioned to perform this analysis because they understand the data and the underlying operational and reimbursement implications of patterns
  • 3.
    © 2016 Case MixAnalysis • Case Mix Index (CMI) – average MS-DRG weight for all patients – May be calculated for subsets of patients such as Medicare/Medicaid/selected MS-DRGs – May exclude portions such as transplants (very high weight MS-DRGs) or transfers (reduced payment and short stays) – Single number that may be used as a proxy for measuring the resource intensity of a hospital’s patients – Medicare CMI is the primary driver of the inpatient Medicare revenue – Frequently a key performance indicator for a hospital and a key driver of the revenue budget
  • 4.
    © 2016 Case MixIndex Example1. Multiply the number of cases in each MS-DRG by the relative weight 2. Sum the values from #1 3. Sum the number of discharges 4. Divide total relative weights by the number of discharges Note: This is the weighted average of the relative weights for each MS-DRG.
  • 5.
    © 2016 MS-DRG Families •MS-DRGs may be broken into families with two or three members: – No CC – CC (not present in all families) – MCC • The MS-DRG weight system is designed to assign higher weights to MS-DRGs that require a higher resource intensity • MCC MS-DRGs are assigned higher weights than no CC MS-DRGs in the same family MS- DRG MS-DRG Title Weights 190 CHRONIC OBSTRUCTIVE PULMONARY DISEASE W MCC 1.1860 191 CHRONIC OBSTRUCTIVE PULMONARY DISEASE W CC 0.9521 192 CHRONIC OBSTRUCTIVE PULMONARY DISEASE W/O CC/MCC 0.7072 258 CARDIAC PACEMAKER DEVICE REPLACEMENT W MCC 2.6945 259 CARDIAC PACEMAKER DEVICE REPLACEMENT W/O MCC 1.8590 COPD Pacemaker Replacement
  • 6.
    © 2016 CC/MCC CaptureRates • Example: • 𝐶𝐶 𝑀𝐶𝐶 𝐶𝑎𝑝𝑡𝑢𝑟𝑒 𝑅𝑎𝑡𝑒 = 87+51 87+51+33 = 80.7% • This value can be compared to HCUP data using a z-test for proportions to determine if the sample rate is higher/lower than the national rate • In general, hospitals with higher CC/MCC capture rates have higher CMI • A unusually high CC/MCC capture rate may be indicative of a compliance issue (over-coding) and should also be investigated MS-DRG Description Volume Relative Wt 280 AMI, Alive w MCC 87 1.7999 281 AMI, Alive w CC 51 1.0961 282 AMI, Alive w no CC/MCC 33 0.7736
  • 7.
    © 2016 CMI Shifts •Significant shifts in CMI should be investigated to determine the root cause • Potential causes: – New service lines – Surgeon vacation schedules – Holidays – Natural disasters (hurricanes, tornados, etc.)
  • 8.
    © 2016 Present onAdmission (POA) indicator If diagnosis that might be a hospital acquired condition (HAC) was not present on admission, claim is paid as if diagnosis was not on claim
  • 9.
    © 2016 Other DRGsSystems • AP-DRGs – All-patient DRGs – AKA “New York Grouper” – Three character, numeric – Weights are calibrated for all patients and not only Medicare • APR-DRGs – All patient refined DRGs – 3M proprietary grouping system – 3 character, numeric followed by digit (1-4) for severity and (1-4) for risk of mortality
  • 10.
    © 2016 Ambulatory PatientClassifications (APC) • CMS uses APCs to pay for services in the hospital outpatient and ambulatory surgery settings. • Challenges of APCs – Claim may have more than one payable APC – Assignment of CPT/HCPCS codes to APCs may change each year – More of a fee schedule than a true prospective payment system • Can use APC weights to calculate a service mix index (SMI) – Note that this measures the average resource intensity for the services provided and not for the typical case
  • 11.
    © 2016 Other AnalysisTools/Reports • Outpatient Code Editor (OCE) – Used to find missed procedures – Identify potential compliance issues (NCCI edit violations) • Examining levels of code subsets that are ordered – Clinic visits (99201 to 99205) – Emergency visits (99281 to 99285)
  • 12.
    © 2016 Methods ofAnalysis • Validation of utilization patterns – Specialty specific codes – Comparison to hospitals with like service mix (trauma center, transplants, etc.) • RVU Analysis – Work RVUs may be used to benchmark physician productivity – Part of the CMS Physician Fee Schedule
  • 13.
    © 2016 RVU –Physician Productivity
  • 14.
    © 2016 RVU –Other Uses • Average cost per RVU • Physician compensation per work RVU (wRVU) • Malpractice expense per Malpractice RVU (mRVU) • Overhead or practice expense per Practice Expense RVU (peRVU) • Break-Even Conversion Factor (BECF)