PageRank for anomaly detection - Hadoop Summit

© Hortonworks Inc. 2015
PageRank for Anomaly Detection
Hadoop Summit Europe, 2015
Ofer Mendelevitch, Hortonworks

© Hortonworks Inc. 2015 Page 2
About Us
Ofer Mendelevitch
Director, Data Science @ Hortonworks
Previously: Nor1, Yahoo!, Risk Insight, Quiver
blog: http://hortonworks.com/blog/author/ofermend/
Joint work with Jiwon Seo
(could not make it last minute)
Ph.D Candidate @ Stanford
Software Engineer @ Pinterest
Designed SociaLite (w/ professor Monica Lam)

What is this talk about?
•Why is fraud detection important in healthcare?
•The Medicare-B dataset
•Our approach: Similarity and PageRank
•Implementation: Apache Pig and SociaLite
•Some Results

Fraud prevention is important in healthcare
Recovery rates are still low, e.g., 3-4%
Source: https://fullfact.org/wp-content/uploads/2014/03/The-Financial-Cost-of-Healthcare-Fraud-Report-2014-11.3.14a.pdf
$0
$500
$1,000
$1,500
$2,000
$2,500
US
EU
$2,270
$940
$171
$71
Healthcare Expenditures (Billions)
Fraud
Non fraud

Example fraud cases in healthcare…
•A doctor billing too often for most expensive office
visits
http://www.dallasnews.com/investigations/20140515-medicare-data-
reveals-unusual-billing-patterns-by-nearly-80-texas-doctors-medical-
practitioners.ece
•Medical supply stores paid off local doctors to
prescribe motorized wheelchairs worth $7500 but
instead provided scooters worth $1500
http://blog.operasolutions.com/bid/388511/Data-Science-As-the-
Panacea-for-Healthcare-Fraud-Waste-and-Abuse

What are some fraud patterns?
•Billing for services that were not actually
performed
•Performing unnecessary services
•Using stolen patient IDs to submit claims
•Unbundling: billing each stage of a procedure as
if it is performed separately
•Upcoding: billing for more expensive services
than were actually performed
•Billing cosmetic surgeries as necessary repairs
•Etc…

Most healthcare providers have some type
of system in place to identify such fraud
•Rules based:
–Business rules catch known fraud patterns
•Machine-learning based:
–Automated learning catches difficult to characterize
fraud patterns
•What are “good features” in the model that
increase the accuracy?
–Claim features, e.g. total amount
–Provider features, e.g., total payment last year
–Patient features, e.g., current set of diagnoses

Why PageRank for fraud detection?
•Most approaches apply supervised learning
–Graph algorithms not as widely-used
•The main idea:
–Produce new “features” for the existing model
–Specifically, a score per provider reflecting its degree of
anomaly relative to a medical specialty

Our Dataset
•Medicare-B – real world public healthcare dataset
–Released by CMS (US Centers for Medicare and
Medicaid Services) in 2014
–Includes provider payment information for 2012
–9.5M records; 880K+ providers; 5616 CPT (procedure)
codes
•We will only use 4 fields:
–NPI: provider ID
–Specialty: e.g. Internal Medicine, Dentist, etc
–CPT code: medical procedure code
–Count: # of procedures performed (normalized)

Example rows from the dataset
1003000126 ENKESHAFI ARDALAN M.D. M I 900 SETON DR CUMBERLAND 215021854 MD US Internal Medicine
Y F99222 Initial hospital care 115 112 115 135.25 0 199 0 108.11565217 0.9005883395
1003000126 ENKESHAFI ARDALAN M.D. M I 900 SETON DR CUMBERLAND 215021854 MD US Internal Medicine
Y F99223 Initial hospital care 93 88 93 198.59 0 291 9.5916630466 158.87 0
1003000134 CIBULL THOMAS L M.D. M I 2650 RIDGE AVE EVANSTON HOSPITAL EVANSTON 602011718 IL US
Pathology Y F88304 Tissue exam by pathologist 226 207 209 11.64 0 115 0 8.9804424779 1.7203407716
Pathology Y F88305 Tissue exam by pathologist 6070 3624 4416 37.729960461 0.0012569747 170 0 28.984504119
5.6268316462
Pathology Y F88311 Decalcify tissue 13 13 13 12.7 0 39 0 7.8153846154 4.2806624494
We use only 4 fields: NPI, specialty, CPT code and count:
1003000126, Internal Medicine, Initial hospital care (F99222), 115
1003000126, Internal Medicine, Initial hospital care (F99223), 88
1003000134, Pathology, Tissue exam by pathologist (F88304), 209
1003000134, Pathology, Tissue exam by pathologist (F88305), 4416
1003000134, Pathology, Decalcify tissue (F88311), 13

Our approach – the steps
•Step 1: Data Preparation/cleansing
•Step 2: Compute similarities, build graph
•Step 3: Compute PageRank, identify anomalies

Step 1: Data cleansing
1003000126ENKESHAFIARDALANM.D.MI900SETONDRCUMBERLAND215021854MDUSInternalMedicineYF99222Initialhospitalcare115112115135.2501990108.115652170.9005883395
1003000126ENKESHAFIARDALANM.D.MI900SETONDRCUMBERLAND215021854MDUSInternalMedicineYF99223Initialhospitalcare938893198.5902919.5916630466158.870
1003000134CIBULLTHOMASLM.D.MI2650RIDGEAVEEVANSTONHOSPITALEVANSTON602011718ILUSPathologyYF88304Tissueexambypathologist22620720911.64011508.98044247791.7203407716
10030126InternalMedicineInitialcare(F99222)115
10030134PathologyTissueexam(F88304)209Filter columns, data
cleansing
•Extract needed data fields from dataset
–NPI (National Provider ID), Specialty, CPT (procedure)
code, count
–For count, we chose: “bene_day_srvc_cnt” (number of
distinct Medicare beneficiary per day services)
•Re-compute “specialty” due to data quality issues

Specialty Lookup: NPI and NUCC datasets
•Problem:
–Some “specialty” values are inaccurate or not specific
enough
•Solution: pre-processing step
–NPI data: maps NPI to specialty code
–NUCC data: maps specialty code to taxonomy

Step 2: build graph by similarities
10030134PathologyTissueexam(F88304)209
•Two providers are “similar” if they have the same
“procedure code patterns”
•We use “Cosine Similarity”
–Each provider represented as vector of 5949 CPT codes

Example: similar providers
•NPI1
•NPI2
CPT 93042 99283 99284 99285 99291
Count 280 29 265 410 28
CPT 99283 99284 99285 99291
Count 118 151 270 37
CPT Description
93042 Rhythm Ecg report
99283 Emergency dept visit (1)
99291 Critical care first hour

Computing similarity at large scale…
• Number of providers: ~880,000
• 880K * 880K = 77,440,000,000 similarity computations
• Each one a “dot product” between vectors of length 5949
(but sparse)

How do we address scalability?
•Our Implementation:
–Heuristics:
–Only compute similarity between NPI1 and NPI2 if they
share their most important CPT codes
–Filter out NPIs with less than 3 CPT codes
–Use Apache PIG on a Hadoop cluster (with UDFs) to
compute in parallal
•Alternatives:
–DIM-SUM (map-reduce or Spark)
–Locality Sensitive Hashing (DataFu)

PIG code: compute similarity
GRP = group DATA by npi parallel 10;
PTS = foreach GRP generate group as npi, DATA.(cpt_inx, count) as cpt_vec;
PTS_TOP = foreach PTS generate npi, cpt_vec, FLATTEN(udfs.top_cpt(cpt_vec)) as (cpt_inx: int, count: int);
PTS_TOP_CPT = foreach PTS_TOP generate npi, cpt_vec, cpt_inx;
CPT_CLUST = foreach (group PTS_TOP_CPT by cpt_inx parallel 10) generate PTS_TOP_CPT.(npi, cpt_vec) as clust_bag;
RANKED = RANK CPT_CLUST;
ID_WITH_CLUST = foreach RANKED generate $0 as clust_id, clust_bag;
ID_WITH_SMALL_CLUST = foreach ID_WITH_CLUST generate clust_id, FLATTEN(udfs.breakLargeBag(clust_bag, 2000)) as clust_bag;
ID_WITH_SMALL_CLUST_RAND = foreach ID_WITH_SMALL_CLUST generate clust_id, clust_bag, RANDOM() as r;
ID_WITH_SMALL_CLUST_SHUF = foreach (GROUP ID_WITH_SMALL_CLUST_RAND by r parallel 240)
generate FLATTEN($1) as (clust_id, clust_bag, r);
NPI_AND_CLUST_ID = foreach ID_WITH_CLUST generate FLATTEN(clust_bag) as (npi: int, cpt_vec), clust_id;
CLUST_JOINED = join ID_WITH_SMALL_CLUST_SHUF by clust_id, NPI_AND_CLUST_ID by clust_id using 'replicated';
PAIRS = foreach CLUST_JOINED generate npi as npi1, FLATTEN(udfs.similarNpi(npi, cpt_vec, clust_bag, 0.85)) as npi2;
OUT = distinct PAIRS parallel 20;
Things to highlight:
• Using “replicated” joins (map-side joins) where possible
• Handling Data Skew
• Using Python UDFs to compute similarity, break large
bags, etc

Step 3: Personalized PageRank
Run Personalized
PageRank with SociaLite
•Compute specialty-centric “Personalized
PageRank” for each node (provider)
•Anomaly candidate: high score but wrong
specialty
0.025
0.3 0.092
0.095
0.15
0.2
0.002
0.005
0.02
0.01
0.012
0.2

PageRank – a quick overview
• Random walk over the graph
• Start from any (randomly selected)
node
• At each step, walker can:
– Move to an adjacent node
(probability d = 80%)
– Randomly jump (or “teleport”) to any
node in the graph
(probability 1-d = 20%)
All doctor names are fictitious

Personalized PageRank – focused on a
given specialty (Ng, Miller, Jones)
• Random walk over the graph
• Start from any random node IN THE
SPECIALTY GROUP
• At each step, walker can:
– Move to an adjacent node
(probability d = 80%)
– Randomly jump (or “teleport”) to any
node OF THE GIVEN SPECIALTY GROUP
(probability 1-d = 20%)
All doctor names are fictitious

Personalized PageRank with SociaLite
`Rank(int npi:0..$MAX_NPI_ID, int i:iter, float rank).`
`Rank(source_npi, 0, pr) :- Source(source_npi), pr=1.0f/$N.`
for i in range(10):
`Rank(node, $i+1, $sum(pr)) :- Source(node), pr = 0.2f*1.0f/$N ;
:- Rank(src, $i, pr1), pr1>1e-8, EdgeCnt(src, cnt),
pr = 0.8f*pr1/cnt, Graph(src, node).`
Initialize PageRank value of source providers to be 1/N
In each iteration:
• Teleport to source providers (w/ probability 0.2) ;
• Random walk to one of neighbors (w/ probability 0.8)

What’s so cool about SociaLite?
•PageRank in 3 lines of code
•Python integration
•You don’t have to “think like a node”. Declarative
language – “looks like” the formula

Using the PageRank scores?
Rules
Fraud
Model
Claim
Generate
Features
PageRank Scores
Decision
Provider
Patient
Amount
Date, time
Etc…
Patient
information
Provider
Information
Etc…
Feature 1
Feature 2
…
Feature N
PR Feature 1
PR Feature 2
…
PR feature M

Example result #1: Ophthalmology
Found internist with high score, but these CPT codes:
• Internal eye photography
• Cmptr ophth img optic nerve
• Echo exam of eye thickness
• Cptr ophth dx img post segmt
• Revise eyelashes
• Ophthalmic biometry
• Eye exam new patient
• Eye exam established pat
• After cataract laser surgery
• Eye exam & treatment
• Eye exam with photos
• Cataract surg w/iol 1 stage
• Visual field examination(s)

Example result #2: Plastic Surgery
Found Otolaryngologist with high score, but these CPT codes:
• Skin tissue rearrangement (multiple variants)
• Biopsy skin lesion

Thank you!
Any Questions?
Ofer Mendelevitch, ofer@hortonworks.com, @ofermend
Code available here:
https://github.com/ofermend/medicare-demo/
Blog post series: http://hortonworks.com/blog/using-pagerank-
detect-anomalies-fraud-healthcare/

PageRank for anomaly detection - Hadoop Summit

More Related Content

Viewers also liked (6)

Similar to PageRank for anomaly detection - Hadoop Summit (20)

Recently uploaded (20)

PageRank for anomaly detection - Hadoop Summit

Editor's Notes