SlideShare a Scribd company logo
© Hortonworks Inc. 2015
PageRank for Anomaly Detection
Hadoop Summit
San Jose, 2015
Ofer Mendelevitch, Hortonworks
Jiwon Seo, Stanford University
© 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
Ph.D Candidate @ Stanford
Software Engineer @ Pinterest
Designed SociaLite (w/ professor Monica Lam)
© Hortonworks Inc. 2015 Page 3
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
© Hortonworks Inc. 2015 Page 4
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
© Hortonworks Inc. 2015 Page 5
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
© Hortonworks Inc. 2015 Page 6
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…
© Hortonworks Inc. 2015 Page 7
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
© Hortonworks Inc. 2015 Page 8
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
© Hortonworks Inc. 2015 Page 9
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)
© Hortonworks Inc. 2015 Page 10
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
1003000134 CIBULL THOMAS L M.D. M I 2650 RIDGE AVE EVANSTON HOSPITAL EVANSTON 602011718 IL US
Pathology Y F88305 Tissue exam by pathologist 6070 3624 4416 37.729960461 0.0012569747 170 0 28.984504119
5.6268316462
1003000134 CIBULL THOMAS L M.D. M I 2650 RIDGE AVE EVANSTON HOSPITAL EVANSTON 602011718 IL US
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
© Hortonworks Inc. 2015 Page 11
Our approach – the steps
•Step 1: Data Preparation/cleansing
•Step 2: Compute similarities, build graph
•Step 3: Compute PageRank, identify anomalies
© Hortonworks Inc. 2015 Page 12
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
10030126InternalMedicineInitialcare(F99223)88
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
© Hortonworks Inc. 2015 Page 13
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
© Hortonworks Inc. 2015 Page 14
Step 2: build graph by similarities
10030126InternalMedicineInitialcare(F99222)115
10030126InternalMedicineInitialcare(F99223)88
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
© Hortonworks Inc. 2015 Page 15
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)
99284 Emergency dept visit (2)
99285 Emergency dept visit (3)
99291 Critical care first hour
© Hortonworks Inc. 2015 Page 16
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)
© Hortonworks Inc. 2015 Page 17
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)
© Hortonworks Inc. 2015 Page 18
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
© Hortonworks Inc. 2015 Page 19
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
© Hortonworks Inc. 2015 Page 20
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
Dr.Miller
9.6%
Dr.Jones
9.6%
Dr.Lam
9.6%
Dr.Ng
12.5%
Dr.Cheng
6.7%
Dr.Das
12.0%
Dr.Seo
9.2%
Dr.Page
6.6%
Dr.Ortega
12.0%
Dr.Padian
12.1%
© Hortonworks Inc. 2015 Page 21
Personalized PageRank
Focused on a given specialty
• 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
Dr.Miller
1.6%
Dr.Jones
1.6%
Dr. Lam
1.6%
Dr.Ng
3.3%
Dr.Cheng
4.6%
Dr. Das
20.7%
Dr. Seo
15.7%
Dr. Page
11.8%
Dr. Ortega
20.7%
Dr.Padian
18.2%
© Hortonworks Inc. 2015 Page 22
Personalized PageRank
Focused on a given specialty
• 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
Dr. Miller
20.1%
Dr. Jones
20.1 %
Dr.Lam
20.1%
Dr.Ng
23.2 %
Dr.Cheng
5.8%
Dr.Das
2.2%
Dr.Seo
1.7%
Dr.Page
0.9%
Dr.Ortega
2.2%
Dr.Padian
3.9%
© Hortonworks Inc. 2015 Page 23
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)
© Hortonworks Inc. 2015 Page 24
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
© Hortonworks Inc. 2015 Page 25
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
© Hortonworks Inc. 2015 Page 26
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)
© Hortonworks Inc. 2015 Page 27
Example result #2: Plastic Surgery
Found Otolaryngologist with high score, but these CPT codes:
• Skin tissue rearrangement (multiple variants)
• Biopsy skin lesion
© Hortonworks Inc. 2015 Page 28
Thank you!
Any Questions?
Ofer Mendelevitch, ofer@hortonworks.com, @ofermend
Jiwon Seo, jiwon@stanford.edu, @jiwon
Code available here:
https://github.com/ofermend/medicare-demo/
Blog post series: http://hortonworks.com/blog/using-pagerank-
detect-anomalies-fraud-healthcare/

More Related Content

Viewers also liked

Advertising and sales management
Advertising and sales managementAdvertising and sales management
Advertising and sales managementPrafulla Tekriwal
 
5024 Final Presentation
5024 Final Presentation5024 Final Presentation
5024 Final PresentationLinjun Li
 
Topic Modeling via Tensor Factorization Use Case for Apache REEF Framework
Topic Modeling via Tensor Factorization Use Case for Apache REEF FrameworkTopic Modeling via Tensor Factorization Use Case for Apache REEF Framework
Topic Modeling via Tensor Factorization Use Case for Apache REEF Framework
DataWorks Summit
 
Hadoop and R Go to the Movies
Hadoop and R Go to the MoviesHadoop and R Go to the Movies
Hadoop and R Go to the MoviesDataWorks Summit
 
Visualising your Big Data: Eye Vegetables and Eye Candy
Visualising your Big Data: Eye Vegetables and Eye CandyVisualising your Big Data: Eye Vegetables and Eye Candy
Visualising your Big Data: Eye Vegetables and Eye Candy
DataWorks Summit
 
Keys to the Kingdom: SQL in Hadoop
Keys to the Kingdom: SQL in HadoopKeys to the Kingdom: SQL in Hadoop
Keys to the Kingdom: SQL in Hadoop
DataWorks Summit
 
Journey Mapping & Experience Mapping - Real Word Example
Journey Mapping & Experience Mapping - Real Word ExampleJourney Mapping & Experience Mapping - Real Word Example
Journey Mapping & Experience Mapping - Real Word Example
Nigel Hudson
 
Hadoop Boosts Profits in Media and Telecom Industry
Hadoop Boosts Profits in Media and Telecom IndustryHadoop Boosts Profits in Media and Telecom Industry
Hadoop Boosts Profits in Media and Telecom IndustryDataWorks Summit
 
Profesionales web
Profesionales webProfesionales web
Profesionales web
Mike Nieva
 
Scaling Ancestry DNA with the Hadoop Ecosystem
Scaling Ancestry DNA with the Hadoop EcosystemScaling Ancestry DNA with the Hadoop Ecosystem
Scaling Ancestry DNA with the Hadoop EcosystemDataWorks Summit
 
10stepstowritingaresearchapaper 110925164756-phpapp01 3
10stepstowritingaresearchapaper 110925164756-phpapp01 310stepstowritingaresearchapaper 110925164756-phpapp01 3
10stepstowritingaresearchapaper 110925164756-phpapp01 3
Lorraine Martin
 
Dean Jansen: Community-Driven Video Accessibility | Content in Motion
Dean Jansen: Community-Driven Video Accessibility | Content in MotionDean Jansen: Community-Driven Video Accessibility | Content in Motion
Dean Jansen: Community-Driven Video Accessibility | Content in Motion
EUscreen
 
Kids and alcohol
Kids and alcohol Kids and alcohol
Kids and alcohol
Shannon Gilliland
 
Presentación Jk Rowling
Presentación Jk RowlingPresentación Jk Rowling
Presentación Jk Rowling
Marion Sayado
 
Hadoop in Validated Environment - Data Governance Initiative
Hadoop in Validated Environment - Data Governance InitiativeHadoop in Validated Environment - Data Governance Initiative
Hadoop in Validated Environment - Data Governance Initiative
DataWorks Summit
 

Viewers also liked (20)

CV (2)
CV (2)CV (2)
CV (2)
 
Advertising and sales management
Advertising and sales managementAdvertising and sales management
Advertising and sales management
 
5024 Final Presentation
5024 Final Presentation5024 Final Presentation
5024 Final Presentation
 
SOCIAL IRAN
SOCIAL IRANSOCIAL IRAN
SOCIAL IRAN
 
MELODY CV
MELODY CVMELODY CV
MELODY CV
 
Topic Modeling via Tensor Factorization Use Case for Apache REEF Framework
Topic Modeling via Tensor Factorization Use Case for Apache REEF FrameworkTopic Modeling via Tensor Factorization Use Case for Apache REEF Framework
Topic Modeling via Tensor Factorization Use Case for Apache REEF Framework
 
Hadoop and R Go to the Movies
Hadoop and R Go to the MoviesHadoop and R Go to the Movies
Hadoop and R Go to the Movies
 
Visualising your Big Data: Eye Vegetables and Eye Candy
Visualising your Big Data: Eye Vegetables and Eye CandyVisualising your Big Data: Eye Vegetables and Eye Candy
Visualising your Big Data: Eye Vegetables and Eye Candy
 
Why save & invest
Why save & investWhy save & invest
Why save & invest
 
Keys to the Kingdom: SQL in Hadoop
Keys to the Kingdom: SQL in HadoopKeys to the Kingdom: SQL in Hadoop
Keys to the Kingdom: SQL in Hadoop
 
Journey Mapping & Experience Mapping - Real Word Example
Journey Mapping & Experience Mapping - Real Word ExampleJourney Mapping & Experience Mapping - Real Word Example
Journey Mapping & Experience Mapping - Real Word Example
 
Hadoop Boosts Profits in Media and Telecom Industry
Hadoop Boosts Profits in Media and Telecom IndustryHadoop Boosts Profits in Media and Telecom Industry
Hadoop Boosts Profits in Media and Telecom Industry
 
Profesionales web
Profesionales webProfesionales web
Profesionales web
 
SM
SMSM
SM
 
Scaling Ancestry DNA with the Hadoop Ecosystem
Scaling Ancestry DNA with the Hadoop EcosystemScaling Ancestry DNA with the Hadoop Ecosystem
Scaling Ancestry DNA with the Hadoop Ecosystem
 
10stepstowritingaresearchapaper 110925164756-phpapp01 3
10stepstowritingaresearchapaper 110925164756-phpapp01 310stepstowritingaresearchapaper 110925164756-phpapp01 3
10stepstowritingaresearchapaper 110925164756-phpapp01 3
 
Dean Jansen: Community-Driven Video Accessibility | Content in Motion
Dean Jansen: Community-Driven Video Accessibility | Content in MotionDean Jansen: Community-Driven Video Accessibility | Content in Motion
Dean Jansen: Community-Driven Video Accessibility | Content in Motion
 
Kids and alcohol
Kids and alcohol Kids and alcohol
Kids and alcohol
 
Presentación Jk Rowling
Presentación Jk RowlingPresentación Jk Rowling
Presentación Jk Rowling
 
Hadoop in Validated Environment - Data Governance Initiative
Hadoop in Validated Environment - Data Governance InitiativeHadoop in Validated Environment - Data Governance Initiative
Hadoop in Validated Environment - Data Governance Initiative
 

Similar to PageRank for Anomaly Detection

PageRank for anomaly detection - Hadoop Summit
PageRank for anomaly detection - Hadoop SummitPageRank for anomaly detection - Hadoop Summit
PageRank for anomaly detection - Hadoop Summit
Ofer Mendelevitch
 
Page rank for anomaly detection
Page rank for anomaly detectionPage rank for anomaly detection
Page rank for anomaly detection
gpano
 
Tgi hospital planning
Tgi hospital planningTgi hospital planning
Tgi hospital planning
Pankaj Gupta
 
The Wearable to Consumer Translation: Giving your Dog a Voyce
The Wearable to Consumer Translation: Giving your Dog a VoyceThe Wearable to Consumer Translation: Giving your Dog a Voyce
The Wearable to Consumer Translation: Giving your Dog a Voyce
MuleSoft
 
ICD-10 Impact Presentation
ICD-10 Impact PresentationICD-10 Impact Presentation
ICD-10 Impact Presentation
Phoenix Health Systems
 
Using the Right Metrics to Improve Physician Practice Management
Using the Right Metrics to Improve Physician Practice ManagementUsing the Right Metrics to Improve Physician Practice Management
Using the Right Metrics to Improve Physician Practice ManagementWarren E. Corprew, Jr. MBA CMA CHFP
 
Erequesting and the Electronic Healthcare Record
Erequesting and the Electronic Healthcare RecordErequesting and the Electronic Healthcare Record
Erequesting and the Electronic Healthcare RecordAnant Patel
 
Patstat indicators step by step
Patstat indicators step by stepPatstat indicators step by step
Patstat indicators step by step
Gianluca Tarasconi
 
Impact Assessment for ICD10 Implementation
Impact Assessment for ICD10 ImplementationImpact Assessment for ICD10 Implementation
Impact Assessment for ICD10 ImplementationMichael Bearnson
 
HealthTech Heartbeat - 2014 Market Review
HealthTech Heartbeat - 2014 Market ReviewHealthTech Heartbeat - 2014 Market Review
HealthTech Heartbeat - 2014 Market Review
resultsig
 
Healthcare deserts: How accessible is US healthcare?
Healthcare deserts: How accessible is US healthcare?Healthcare deserts: How accessible is US healthcare?
Healthcare deserts: How accessible is US healthcare?
Data Con LA
 
Fault Detection in Mobile Communication Networks Using Data Mining Techniques...
Fault Detection in Mobile Communication Networks Using Data Mining Techniques...Fault Detection in Mobile Communication Networks Using Data Mining Techniques...
Fault Detection in Mobile Communication Networks Using Data Mining Techniques...
ijcisjournal
 
Health language siemens presentation
Health language siemens presentationHealth language siemens presentation
Health language siemens presentation
Chris Cummins
 
ICD-10 Testing
ICD-10 TestingICD-10 Testing
ICD-10 Testing
Qualitest
 
BSA (Graham Mitchell) Polypharmacy Prescribing Comparators Overview March 17
 BSA (Graham Mitchell) Polypharmacy Prescribing Comparators Overview March 17 BSA (Graham Mitchell) Polypharmacy Prescribing Comparators Overview March 17
BSA (Graham Mitchell) Polypharmacy Prescribing Comparators Overview March 17
Health Innovation Wessex
 
HealthTech Heartbeat - Q2 2015 Market Review
HealthTech Heartbeat - Q2 2015 Market ReviewHealthTech Heartbeat - Q2 2015 Market Review
HealthTech Heartbeat - Q2 2015 Market Review
resultsig
 
Ogilvie - Beyond the statistical average
Ogilvie  - Beyond the statistical averageOgilvie  - Beyond the statistical average
Ogilvie - Beyond the statistical average
International Software Benchmarking Standards Group (ISBSG)
 
Nexus project showcase - HealthOne
Nexus project showcase - HealthOneNexus project showcase - HealthOne
Nexus project showcase - HealthOne
Health Informatics New Zealand
 
2012 to 2013 Australian Hospital Digital Scanning Survey
2012 to 2013 Australian Hospital Digital Scanning Survey2012 to 2013 Australian Hospital Digital Scanning Survey
2012 to 2013 Australian Hospital Digital Scanning Survey
squareearth
 

Similar to PageRank for Anomaly Detection (20)

PageRank for anomaly detection - Hadoop Summit
PageRank for anomaly detection - Hadoop SummitPageRank for anomaly detection - Hadoop Summit
PageRank for anomaly detection - Hadoop Summit
 
Page rank for anomaly detection
Page rank for anomaly detectionPage rank for anomaly detection
Page rank for anomaly detection
 
Tgi hospital planning
Tgi hospital planningTgi hospital planning
Tgi hospital planning
 
The Wearable to Consumer Translation: Giving your Dog a Voyce
The Wearable to Consumer Translation: Giving your Dog a VoyceThe Wearable to Consumer Translation: Giving your Dog a Voyce
The Wearable to Consumer Translation: Giving your Dog a Voyce
 
ICD-10 Impact Presentation
ICD-10 Impact PresentationICD-10 Impact Presentation
ICD-10 Impact Presentation
 
Using the Right Metrics to Improve Physician Practice Management
Using the Right Metrics to Improve Physician Practice ManagementUsing the Right Metrics to Improve Physician Practice Management
Using the Right Metrics to Improve Physician Practice Management
 
Erequesting and the Electronic Healthcare Record
Erequesting and the Electronic Healthcare RecordErequesting and the Electronic Healthcare Record
Erequesting and the Electronic Healthcare Record
 
DC_OC15_mo
DC_OC15_moDC_OC15_mo
DC_OC15_mo
 
Patstat indicators step by step
Patstat indicators step by stepPatstat indicators step by step
Patstat indicators step by step
 
Impact Assessment for ICD10 Implementation
Impact Assessment for ICD10 ImplementationImpact Assessment for ICD10 Implementation
Impact Assessment for ICD10 Implementation
 
HealthTech Heartbeat - 2014 Market Review
HealthTech Heartbeat - 2014 Market ReviewHealthTech Heartbeat - 2014 Market Review
HealthTech Heartbeat - 2014 Market Review
 
Healthcare deserts: How accessible is US healthcare?
Healthcare deserts: How accessible is US healthcare?Healthcare deserts: How accessible is US healthcare?
Healthcare deserts: How accessible is US healthcare?
 
Fault Detection in Mobile Communication Networks Using Data Mining Techniques...
Fault Detection in Mobile Communication Networks Using Data Mining Techniques...Fault Detection in Mobile Communication Networks Using Data Mining Techniques...
Fault Detection in Mobile Communication Networks Using Data Mining Techniques...
 
Health language siemens presentation
Health language siemens presentationHealth language siemens presentation
Health language siemens presentation
 
ICD-10 Testing
ICD-10 TestingICD-10 Testing
ICD-10 Testing
 
BSA (Graham Mitchell) Polypharmacy Prescribing Comparators Overview March 17
 BSA (Graham Mitchell) Polypharmacy Prescribing Comparators Overview March 17 BSA (Graham Mitchell) Polypharmacy Prescribing Comparators Overview March 17
BSA (Graham Mitchell) Polypharmacy Prescribing Comparators Overview March 17
 
HealthTech Heartbeat - Q2 2015 Market Review
HealthTech Heartbeat - Q2 2015 Market ReviewHealthTech Heartbeat - Q2 2015 Market Review
HealthTech Heartbeat - Q2 2015 Market Review
 
Ogilvie - Beyond the statistical average
Ogilvie  - Beyond the statistical averageOgilvie  - Beyond the statistical average
Ogilvie - Beyond the statistical average
 
Nexus project showcase - HealthOne
Nexus project showcase - HealthOneNexus project showcase - HealthOne
Nexus project showcase - HealthOne
 
2012 to 2013 Australian Hospital Digital Scanning Survey
2012 to 2013 Australian Hospital Digital Scanning Survey2012 to 2013 Australian Hospital Digital Scanning Survey
2012 to 2013 Australian Hospital Digital Scanning Survey
 

More from DataWorks Summit

Data Science Crash Course
Data Science Crash CourseData Science Crash Course
Data Science Crash Course
DataWorks Summit
 
Floating on a RAFT: HBase Durability with Apache Ratis
Floating on a RAFT: HBase Durability with Apache RatisFloating on a RAFT: HBase Durability with Apache Ratis
Floating on a RAFT: HBase Durability with Apache Ratis
DataWorks Summit
 
Tracking Crime as It Occurs with Apache Phoenix, Apache HBase and Apache NiFi
Tracking Crime as It Occurs with Apache Phoenix, Apache HBase and Apache NiFiTracking Crime as It Occurs with Apache Phoenix, Apache HBase and Apache NiFi
Tracking Crime as It Occurs with Apache Phoenix, Apache HBase and Apache NiFi
DataWorks Summit
 
HBase Tales From the Trenches - Short stories about most common HBase operati...
HBase Tales From the Trenches - Short stories about most common HBase operati...HBase Tales From the Trenches - Short stories about most common HBase operati...
HBase Tales From the Trenches - Short stories about most common HBase operati...
DataWorks Summit
 
Optimizing Geospatial Operations with Server-side Programming in HBase and Ac...
Optimizing Geospatial Operations with Server-side Programming in HBase and Ac...Optimizing Geospatial Operations with Server-side Programming in HBase and Ac...
Optimizing Geospatial Operations with Server-side Programming in HBase and Ac...
DataWorks Summit
 
Managing the Dewey Decimal System
Managing the Dewey Decimal SystemManaging the Dewey Decimal System
Managing the Dewey Decimal System
DataWorks Summit
 
Practical NoSQL: Accumulo's dirlist Example
Practical NoSQL: Accumulo's dirlist ExamplePractical NoSQL: Accumulo's dirlist Example
Practical NoSQL: Accumulo's dirlist Example
DataWorks Summit
 
HBase Global Indexing to support large-scale data ingestion at Uber
HBase Global Indexing to support large-scale data ingestion at UberHBase Global Indexing to support large-scale data ingestion at Uber
HBase Global Indexing to support large-scale data ingestion at Uber
DataWorks Summit
 
Scaling Cloud-Scale Translytics Workloads with Omid and Phoenix
Scaling Cloud-Scale Translytics Workloads with Omid and PhoenixScaling Cloud-Scale Translytics Workloads with Omid and Phoenix
Scaling Cloud-Scale Translytics Workloads with Omid and Phoenix
DataWorks Summit
 
Building the High Speed Cybersecurity Data Pipeline Using Apache NiFi
Building the High Speed Cybersecurity Data Pipeline Using Apache NiFiBuilding the High Speed Cybersecurity Data Pipeline Using Apache NiFi
Building the High Speed Cybersecurity Data Pipeline Using Apache NiFi
DataWorks Summit
 
Supporting Apache HBase : Troubleshooting and Supportability Improvements
Supporting Apache HBase : Troubleshooting and Supportability ImprovementsSupporting Apache HBase : Troubleshooting and Supportability Improvements
Supporting Apache HBase : Troubleshooting and Supportability Improvements
DataWorks Summit
 
Security Framework for Multitenant Architecture
Security Framework for Multitenant ArchitectureSecurity Framework for Multitenant Architecture
Security Framework for Multitenant Architecture
DataWorks Summit
 
Presto: Optimizing Performance of SQL-on-Anything Engine
Presto: Optimizing Performance of SQL-on-Anything EnginePresto: Optimizing Performance of SQL-on-Anything Engine
Presto: Optimizing Performance of SQL-on-Anything Engine
DataWorks Summit
 
Introducing MlFlow: An Open Source Platform for the Machine Learning Lifecycl...
Introducing MlFlow: An Open Source Platform for the Machine Learning Lifecycl...Introducing MlFlow: An Open Source Platform for the Machine Learning Lifecycl...
Introducing MlFlow: An Open Source Platform for the Machine Learning Lifecycl...
DataWorks Summit
 
Extending Twitter's Data Platform to Google Cloud
Extending Twitter's Data Platform to Google CloudExtending Twitter's Data Platform to Google Cloud
Extending Twitter's Data Platform to Google Cloud
DataWorks Summit
 
Event-Driven Messaging and Actions using Apache Flink and Apache NiFi
Event-Driven Messaging and Actions using Apache Flink and Apache NiFiEvent-Driven Messaging and Actions using Apache Flink and Apache NiFi
Event-Driven Messaging and Actions using Apache Flink and Apache NiFi
DataWorks Summit
 
Securing Data in Hybrid on-premise and Cloud Environments using Apache Ranger
Securing Data in Hybrid on-premise and Cloud Environments using Apache RangerSecuring Data in Hybrid on-premise and Cloud Environments using Apache Ranger
Securing Data in Hybrid on-premise and Cloud Environments using Apache Ranger
DataWorks Summit
 
Big Data Meets NVM: Accelerating Big Data Processing with Non-Volatile Memory...
Big Data Meets NVM: Accelerating Big Data Processing with Non-Volatile Memory...Big Data Meets NVM: Accelerating Big Data Processing with Non-Volatile Memory...
Big Data Meets NVM: Accelerating Big Data Processing with Non-Volatile Memory...
DataWorks Summit
 
Computer Vision: Coming to a Store Near You
Computer Vision: Coming to a Store Near YouComputer Vision: Coming to a Store Near You
Computer Vision: Coming to a Store Near You
DataWorks Summit
 
Big Data Genomics: Clustering Billions of DNA Sequences with Apache Spark
Big Data Genomics: Clustering Billions of DNA Sequences with Apache SparkBig Data Genomics: Clustering Billions of DNA Sequences with Apache Spark
Big Data Genomics: Clustering Billions of DNA Sequences with Apache Spark
DataWorks Summit
 

More from DataWorks Summit (20)

Data Science Crash Course
Data Science Crash CourseData Science Crash Course
Data Science Crash Course
 
Floating on a RAFT: HBase Durability with Apache Ratis
Floating on a RAFT: HBase Durability with Apache RatisFloating on a RAFT: HBase Durability with Apache Ratis
Floating on a RAFT: HBase Durability with Apache Ratis
 
Tracking Crime as It Occurs with Apache Phoenix, Apache HBase and Apache NiFi
Tracking Crime as It Occurs with Apache Phoenix, Apache HBase and Apache NiFiTracking Crime as It Occurs with Apache Phoenix, Apache HBase and Apache NiFi
Tracking Crime as It Occurs with Apache Phoenix, Apache HBase and Apache NiFi
 
HBase Tales From the Trenches - Short stories about most common HBase operati...
HBase Tales From the Trenches - Short stories about most common HBase operati...HBase Tales From the Trenches - Short stories about most common HBase operati...
HBase Tales From the Trenches - Short stories about most common HBase operati...
 
Optimizing Geospatial Operations with Server-side Programming in HBase and Ac...
Optimizing Geospatial Operations with Server-side Programming in HBase and Ac...Optimizing Geospatial Operations with Server-side Programming in HBase and Ac...
Optimizing Geospatial Operations with Server-side Programming in HBase and Ac...
 
Managing the Dewey Decimal System
Managing the Dewey Decimal SystemManaging the Dewey Decimal System
Managing the Dewey Decimal System
 
Practical NoSQL: Accumulo's dirlist Example
Practical NoSQL: Accumulo's dirlist ExamplePractical NoSQL: Accumulo's dirlist Example
Practical NoSQL: Accumulo's dirlist Example
 
HBase Global Indexing to support large-scale data ingestion at Uber
HBase Global Indexing to support large-scale data ingestion at UberHBase Global Indexing to support large-scale data ingestion at Uber
HBase Global Indexing to support large-scale data ingestion at Uber
 
Scaling Cloud-Scale Translytics Workloads with Omid and Phoenix
Scaling Cloud-Scale Translytics Workloads with Omid and PhoenixScaling Cloud-Scale Translytics Workloads with Omid and Phoenix
Scaling Cloud-Scale Translytics Workloads with Omid and Phoenix
 
Building the High Speed Cybersecurity Data Pipeline Using Apache NiFi
Building the High Speed Cybersecurity Data Pipeline Using Apache NiFiBuilding the High Speed Cybersecurity Data Pipeline Using Apache NiFi
Building the High Speed Cybersecurity Data Pipeline Using Apache NiFi
 
Supporting Apache HBase : Troubleshooting and Supportability Improvements
Supporting Apache HBase : Troubleshooting and Supportability ImprovementsSupporting Apache HBase : Troubleshooting and Supportability Improvements
Supporting Apache HBase : Troubleshooting and Supportability Improvements
 
Security Framework for Multitenant Architecture
Security Framework for Multitenant ArchitectureSecurity Framework for Multitenant Architecture
Security Framework for Multitenant Architecture
 
Presto: Optimizing Performance of SQL-on-Anything Engine
Presto: Optimizing Performance of SQL-on-Anything EnginePresto: Optimizing Performance of SQL-on-Anything Engine
Presto: Optimizing Performance of SQL-on-Anything Engine
 
Introducing MlFlow: An Open Source Platform for the Machine Learning Lifecycl...
Introducing MlFlow: An Open Source Platform for the Machine Learning Lifecycl...Introducing MlFlow: An Open Source Platform for the Machine Learning Lifecycl...
Introducing MlFlow: An Open Source Platform for the Machine Learning Lifecycl...
 
Extending Twitter's Data Platform to Google Cloud
Extending Twitter's Data Platform to Google CloudExtending Twitter's Data Platform to Google Cloud
Extending Twitter's Data Platform to Google Cloud
 
Event-Driven Messaging and Actions using Apache Flink and Apache NiFi
Event-Driven Messaging and Actions using Apache Flink and Apache NiFiEvent-Driven Messaging and Actions using Apache Flink and Apache NiFi
Event-Driven Messaging and Actions using Apache Flink and Apache NiFi
 
Securing Data in Hybrid on-premise and Cloud Environments using Apache Ranger
Securing Data in Hybrid on-premise and Cloud Environments using Apache RangerSecuring Data in Hybrid on-premise and Cloud Environments using Apache Ranger
Securing Data in Hybrid on-premise and Cloud Environments using Apache Ranger
 
Big Data Meets NVM: Accelerating Big Data Processing with Non-Volatile Memory...
Big Data Meets NVM: Accelerating Big Data Processing with Non-Volatile Memory...Big Data Meets NVM: Accelerating Big Data Processing with Non-Volatile Memory...
Big Data Meets NVM: Accelerating Big Data Processing with Non-Volatile Memory...
 
Computer Vision: Coming to a Store Near You
Computer Vision: Coming to a Store Near YouComputer Vision: Coming to a Store Near You
Computer Vision: Coming to a Store Near You
 
Big Data Genomics: Clustering Billions of DNA Sequences with Apache Spark
Big Data Genomics: Clustering Billions of DNA Sequences with Apache SparkBig Data Genomics: Clustering Billions of DNA Sequences with Apache Spark
Big Data Genomics: Clustering Billions of DNA Sequences with Apache Spark
 

Recently uploaded

Artificial Intelligence for XMLDevelopment
Artificial Intelligence for XMLDevelopmentArtificial Intelligence for XMLDevelopment
Artificial Intelligence for XMLDevelopment
Octavian Nadolu
 
GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...
GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...
GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...
Neo4j
 
20240605 QFM017 Machine Intelligence Reading List May 2024
20240605 QFM017 Machine Intelligence Reading List May 202420240605 QFM017 Machine Intelligence Reading List May 2024
20240605 QFM017 Machine Intelligence Reading List May 2024
Matthew Sinclair
 
Building RAG with self-deployed Milvus vector database and Snowpark Container...
Building RAG with self-deployed Milvus vector database and Snowpark Container...Building RAG with self-deployed Milvus vector database and Snowpark Container...
Building RAG with self-deployed Milvus vector database and Snowpark Container...
Zilliz
 
Epistemic Interaction - tuning interfaces to provide information for AI support
Epistemic Interaction - tuning interfaces to provide information for AI supportEpistemic Interaction - tuning interfaces to provide information for AI support
Epistemic Interaction - tuning interfaces to provide information for AI support
Alan Dix
 
Video Streaming: Then, Now, and in the Future
Video Streaming: Then, Now, and in the FutureVideo Streaming: Then, Now, and in the Future
Video Streaming: Then, Now, and in the Future
Alpen-Adria-Universität
 
Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !
KatiaHIMEUR1
 
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdfObservability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Paige Cruz
 
Microsoft - Power Platform_G.Aspiotis.pdf
Microsoft - Power Platform_G.Aspiotis.pdfMicrosoft - Power Platform_G.Aspiotis.pdf
Microsoft - Power Platform_G.Aspiotis.pdf
Uni Systems S.M.S.A.
 
Essentials of Automations: The Art of Triggers and Actions in FME
Essentials of Automations: The Art of Triggers and Actions in FMEEssentials of Automations: The Art of Triggers and Actions in FME
Essentials of Automations: The Art of Triggers and Actions in FME
Safe Software
 
Enchancing adoption of Open Source Libraries. A case study on Albumentations.AI
Enchancing adoption of Open Source Libraries. A case study on Albumentations.AIEnchancing adoption of Open Source Libraries. A case study on Albumentations.AI
Enchancing adoption of Open Source Libraries. A case study on Albumentations.AI
Vladimir Iglovikov, Ph.D.
 
Removing Uninteresting Bytes in Software Fuzzing
Removing Uninteresting Bytes in Software FuzzingRemoving Uninteresting Bytes in Software Fuzzing
Removing Uninteresting Bytes in Software Fuzzing
Aftab Hussain
 
Uni Systems Copilot event_05062024_C.Vlachos.pdf
Uni Systems Copilot event_05062024_C.Vlachos.pdfUni Systems Copilot event_05062024_C.Vlachos.pdf
Uni Systems Copilot event_05062024_C.Vlachos.pdf
Uni Systems S.M.S.A.
 
GraphSummit Singapore | Neo4j Product Vision & Roadmap - Q2 2024
GraphSummit Singapore | Neo4j Product Vision & Roadmap - Q2 2024GraphSummit Singapore | Neo4j Product Vision & Roadmap - Q2 2024
GraphSummit Singapore | Neo4j Product Vision & Roadmap - Q2 2024
Neo4j
 
GraphSummit Singapore | The Art of the Possible with Graph - Q2 2024
GraphSummit Singapore | The Art of the  Possible with Graph - Q2 2024GraphSummit Singapore | The Art of the  Possible with Graph - Q2 2024
GraphSummit Singapore | The Art of the Possible with Graph - Q2 2024
Neo4j
 
Communications Mining Series - Zero to Hero - Session 1
Communications Mining Series - Zero to Hero - Session 1Communications Mining Series - Zero to Hero - Session 1
Communications Mining Series - Zero to Hero - Session 1
DianaGray10
 
みなさんこんにちはこれ何文字まで入るの?40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの?えこ...
みなさんこんにちはこれ何文字まで入るの?40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの?えこ...みなさんこんにちはこれ何文字まで入るの?40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの?えこ...
みなさんこんにちはこれ何文字まで入るの?40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの?えこ...
名前 です男
 
How to Get CNIC Information System with Paksim Ga.pptx
How to Get CNIC Information System with Paksim Ga.pptxHow to Get CNIC Information System with Paksim Ga.pptx
How to Get CNIC Information System with Paksim Ga.pptx
danishmna97
 
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdf
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdfUnlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdf
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdf
Malak Abu Hammad
 
20 Comprehensive Checklist of Designing and Developing a Website
20 Comprehensive Checklist of Designing and Developing a Website20 Comprehensive Checklist of Designing and Developing a Website
20 Comprehensive Checklist of Designing and Developing a Website
Pixlogix Infotech
 

Recently uploaded (20)

Artificial Intelligence for XMLDevelopment
Artificial Intelligence for XMLDevelopmentArtificial Intelligence for XMLDevelopment
Artificial Intelligence for XMLDevelopment
 
GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...
GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...
GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...
 
20240605 QFM017 Machine Intelligence Reading List May 2024
20240605 QFM017 Machine Intelligence Reading List May 202420240605 QFM017 Machine Intelligence Reading List May 2024
20240605 QFM017 Machine Intelligence Reading List May 2024
 
Building RAG with self-deployed Milvus vector database and Snowpark Container...
Building RAG with self-deployed Milvus vector database and Snowpark Container...Building RAG with self-deployed Milvus vector database and Snowpark Container...
Building RAG with self-deployed Milvus vector database and Snowpark Container...
 
Epistemic Interaction - tuning interfaces to provide information for AI support
Epistemic Interaction - tuning interfaces to provide information for AI supportEpistemic Interaction - tuning interfaces to provide information for AI support
Epistemic Interaction - tuning interfaces to provide information for AI support
 
Video Streaming: Then, Now, and in the Future
Video Streaming: Then, Now, and in the FutureVideo Streaming: Then, Now, and in the Future
Video Streaming: Then, Now, and in the Future
 
Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !
 
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdfObservability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
 
Microsoft - Power Platform_G.Aspiotis.pdf
Microsoft - Power Platform_G.Aspiotis.pdfMicrosoft - Power Platform_G.Aspiotis.pdf
Microsoft - Power Platform_G.Aspiotis.pdf
 
Essentials of Automations: The Art of Triggers and Actions in FME
Essentials of Automations: The Art of Triggers and Actions in FMEEssentials of Automations: The Art of Triggers and Actions in FME
Essentials of Automations: The Art of Triggers and Actions in FME
 
Enchancing adoption of Open Source Libraries. A case study on Albumentations.AI
Enchancing adoption of Open Source Libraries. A case study on Albumentations.AIEnchancing adoption of Open Source Libraries. A case study on Albumentations.AI
Enchancing adoption of Open Source Libraries. A case study on Albumentations.AI
 
Removing Uninteresting Bytes in Software Fuzzing
Removing Uninteresting Bytes in Software FuzzingRemoving Uninteresting Bytes in Software Fuzzing
Removing Uninteresting Bytes in Software Fuzzing
 
Uni Systems Copilot event_05062024_C.Vlachos.pdf
Uni Systems Copilot event_05062024_C.Vlachos.pdfUni Systems Copilot event_05062024_C.Vlachos.pdf
Uni Systems Copilot event_05062024_C.Vlachos.pdf
 
GraphSummit Singapore | Neo4j Product Vision & Roadmap - Q2 2024
GraphSummit Singapore | Neo4j Product Vision & Roadmap - Q2 2024GraphSummit Singapore | Neo4j Product Vision & Roadmap - Q2 2024
GraphSummit Singapore | Neo4j Product Vision & Roadmap - Q2 2024
 
GraphSummit Singapore | The Art of the Possible with Graph - Q2 2024
GraphSummit Singapore | The Art of the  Possible with Graph - Q2 2024GraphSummit Singapore | The Art of the  Possible with Graph - Q2 2024
GraphSummit Singapore | The Art of the Possible with Graph - Q2 2024
 
Communications Mining Series - Zero to Hero - Session 1
Communications Mining Series - Zero to Hero - Session 1Communications Mining Series - Zero to Hero - Session 1
Communications Mining Series - Zero to Hero - Session 1
 
みなさんこんにちはこれ何文字まで入るの?40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの?えこ...
みなさんこんにちはこれ何文字まで入るの?40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの?えこ...みなさんこんにちはこれ何文字まで入るの?40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの?えこ...
みなさんこんにちはこれ何文字まで入るの?40文字以下不可とか本当に意味わからないけどこれ限界文字数書いてないからマジでやばい文字数いけるんじゃないの?えこ...
 
How to Get CNIC Information System with Paksim Ga.pptx
How to Get CNIC Information System with Paksim Ga.pptxHow to Get CNIC Information System with Paksim Ga.pptx
How to Get CNIC Information System with Paksim Ga.pptx
 
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdf
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdfUnlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdf
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdf
 
20 Comprehensive Checklist of Designing and Developing a Website
20 Comprehensive Checklist of Designing and Developing a Website20 Comprehensive Checklist of Designing and Developing a Website
20 Comprehensive Checklist of Designing and Developing a Website
 

PageRank for Anomaly Detection

  • 1. © Hortonworks Inc. 2015 PageRank for Anomaly Detection Hadoop Summit San Jose, 2015 Ofer Mendelevitch, Hortonworks Jiwon Seo, Stanford University
  • 2. © 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 Ph.D Candidate @ Stanford Software Engineer @ Pinterest Designed SociaLite (w/ professor Monica Lam)
  • 3. © Hortonworks Inc. 2015 Page 3 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
  • 4. © Hortonworks Inc. 2015 Page 4 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
  • 5. © Hortonworks Inc. 2015 Page 5 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
  • 6. © Hortonworks Inc. 2015 Page 6 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…
  • 7. © Hortonworks Inc. 2015 Page 7 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
  • 8. © Hortonworks Inc. 2015 Page 8 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
  • 9. © Hortonworks Inc. 2015 Page 9 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)
  • 10. © Hortonworks Inc. 2015 Page 10 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 1003000134 CIBULL THOMAS L M.D. M I 2650 RIDGE AVE EVANSTON HOSPITAL EVANSTON 602011718 IL US Pathology Y F88305 Tissue exam by pathologist 6070 3624 4416 37.729960461 0.0012569747 170 0 28.984504119 5.6268316462 1003000134 CIBULL THOMAS L M.D. M I 2650 RIDGE AVE EVANSTON HOSPITAL EVANSTON 602011718 IL US 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
  • 11. © Hortonworks Inc. 2015 Page 11 Our approach – the steps •Step 1: Data Preparation/cleansing •Step 2: Compute similarities, build graph •Step 3: Compute PageRank, identify anomalies
  • 12. © Hortonworks Inc. 2015 Page 12 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 10030126InternalMedicineInitialcare(F99223)88 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
  • 13. © Hortonworks Inc. 2015 Page 13 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
  • 14. © Hortonworks Inc. 2015 Page 14 Step 2: build graph by similarities 10030126InternalMedicineInitialcare(F99222)115 10030126InternalMedicineInitialcare(F99223)88 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
  • 15. © Hortonworks Inc. 2015 Page 15 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) 99284 Emergency dept visit (2) 99285 Emergency dept visit (3) 99291 Critical care first hour
  • 16. © Hortonworks Inc. 2015 Page 16 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)
  • 17. © Hortonworks Inc. 2015 Page 17 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)
  • 18. © Hortonworks Inc. 2015 Page 18 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
  • 19. © Hortonworks Inc. 2015 Page 19 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
  • 20. © Hortonworks Inc. 2015 Page 20 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 Dr.Miller 9.6% Dr.Jones 9.6% Dr.Lam 9.6% Dr.Ng 12.5% Dr.Cheng 6.7% Dr.Das 12.0% Dr.Seo 9.2% Dr.Page 6.6% Dr.Ortega 12.0% Dr.Padian 12.1%
  • 21. © Hortonworks Inc. 2015 Page 21 Personalized PageRank Focused on a given specialty • 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 Dr.Miller 1.6% Dr.Jones 1.6% Dr. Lam 1.6% Dr.Ng 3.3% Dr.Cheng 4.6% Dr. Das 20.7% Dr. Seo 15.7% Dr. Page 11.8% Dr. Ortega 20.7% Dr.Padian 18.2%
  • 22. © Hortonworks Inc. 2015 Page 22 Personalized PageRank Focused on a given specialty • 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 Dr. Miller 20.1% Dr. Jones 20.1 % Dr.Lam 20.1% Dr.Ng 23.2 % Dr.Cheng 5.8% Dr.Das 2.2% Dr.Seo 1.7% Dr.Page 0.9% Dr.Ortega 2.2% Dr.Padian 3.9%
  • 23. © Hortonworks Inc. 2015 Page 23 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)
  • 24. © Hortonworks Inc. 2015 Page 24 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
  • 25. © Hortonworks Inc. 2015 Page 25 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
  • 26. © Hortonworks Inc. 2015 Page 26 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)
  • 27. © Hortonworks Inc. 2015 Page 27 Example result #2: Plastic Surgery Found Otolaryngologist with high score, but these CPT codes: • Skin tissue rearrangement (multiple variants) • Biopsy skin lesion
  • 28. © Hortonworks Inc. 2015 Page 28 Thank you! Any Questions? Ofer Mendelevitch, ofer@hortonworks.com, @ofermend Jiwon Seo, jiwon@stanford.edu, @jiwon Code available here: https://github.com/ofermend/medicare-demo/ Blog post series: http://hortonworks.com/blog/using-pagerank- detect-anomalies-fraud-healthcare/

Editor's Notes

  1. We use bene_day_srvc_cnt – # of distinct services provided per day to a patient (some services are provided more than once a day for the same procedure)
  2. Note: using other fields instead of bene_day_srvc_cnt is also possible. E.g., payment amounts; or a combination
  3. PR score = likelihood of random surfer to end up on this node
  4. Ophthalmology = eye doctor This internist was scored high in Ophthalmology group
  5. Otolaryngology = ENT doctor Clearly these CPT codes are for plastic surgery. This provider was scored high in plastic surgery