Experience That Delivers Business Results
Complex business problems often have something in common: the information needed to solve them exists, but it is scattered across systems that were never designed to work together.
Throughout a career spanning healthcare, medical devices, consulting, and enterprise analytics, the principal consultant behind JMC Analytics has developed solutions that connect disconnected information, uncover previously hidden relationships, and turn those discoveries into meaningful business results.
The following three initiatives illustrate this approach.
They span physician identity management, commercial market intelligence, and healthcare reimbursement recovery. Each required a deep understanding of the business problem, sophisticated data matching and integration, carefully designed business rules, and practical implementation.
These are not theoretical consulting methodologies. They are examples of solutions designed, developed, and implemented to address significant business challenges.
The common thread is turning difficult data problems into opportunities for better decisions, stronger operations, and improved financial performance.
Healthcare Provider Identity Resolution & Master Data Management
Transforming Fragmented Physician Data Into a Trusted Enterprise Asset
One of the most persistent challenges facing pharmaceutical and medical device companies is maintaining accurate, consistent information about the healthcare professionals with whom they do business.
Physician information originates from numerous sources, including customer relationship management (CRM) platforms, medical education systems, sales applications, clinical systems, enterprise databases, and third-party data providers.
These systems frequently operate independently, using different identifiers, naming conventions, addresses, and data management rules.
The result can be thousands of duplicate records, conflicting physician identities, inaccurate affiliations, and incomplete information.
These are not simply data quality problems. They can undermine sales productivity, physician engagement, reporting accuracy, and confidence in major enterprise technology investments.
The Business Challenge
At one of the world’s leading medical device companies, a major Salesforce implementation faced a serious data quality problem.
The system contained approximately 10,000 duplicate physician and contact records, creating confusion and threatening the sales organization’s willingness to adopt the platform.
Sales representatives needed accurate, trustworthy physician information. Multiple records representing the same physician made it difficult to identify the correct contact, understand existing relationships, and conduct business efficiently.
Without a solution, the company risked undermining adoption of a significant enterprise technology investment.
The challenge was not simply to remove duplicates. It was to establish a reliable method for identifying, reconciling, consolidating, and maintaining physician information across multiple business systems.
The Solution: A Complete Physician Data Mastering Capability
The principal consultant behind JMC Analytics personally conceived, designed, developed, implemented, documented, and operated a comprehensive physician identity resolution and master data management solution.
The work encompassed the entire solution lifecycle—from gathering business requirements and analyzing source data through algorithm development, data survivorship, statistical reporting, production implementation, and ongoing operations.
Unlike conventional duplicate detection approaches that rely primarily on names and addresses, the solution incorporated multiple layers of matching logic, scoring, precedence, and detailed business rules.
Its principal capabilities included:
Advanced Physician Identity Resolution
Developed sophisticated matching algorithms to identify physicians and other contacts represented by multiple records across disconnected systems.
Matching incorporated combinations of identifying attributes, phonetic comparisons, contact information, and available enterprise master data identifiers.
Matching Scores and Precedence
Designed a scoring and precedence framework to evaluate competing matches, distinguish stronger evidence from weaker evidence, and determine which records should be considered legitimate candidates for consolidation.
This was essential in an environment where similar names did not necessarily represent the same individual and where the same physician could appear under different names, addresses, or identifiers.
Data Survivorship and Golden Record Creation
Developed and implemented a sophisticated set of field-level business rules governing how information from multiple source records would be consolidated into a trusted master record.
When conflicting information existed, survivorship rules determined which source or value should take precedence for each individual data element.
Importantly, the solution did not simply discard information that lost a precedence comparison.
Where the business required multiple valid values to be retained—such as different telephone numbers—the rules could preserve those values as additional data elements in the consolidated record.
This approach balanced the need for a single, authoritative physician identity with the need to retain useful information accumulated across different systems.
Enterprise Master Data Reconciliation
Developed processes to validate existing master data identifiers, identify incorrect assignments, and establish reliable connections between CRM contacts and enterprise master data.
These capabilities improved the accuracy of record matching and created a stronger foundation for integrating additional information from other systems.
Statistical Reporting and Quality Monitoring
Designed and developed detailed statistical reports to measure matching results, evaluate the effectiveness of individual matching methods, identify remaining duplicates, and monitor data quality improvements.
These reports provided visibility into how the matching process was performing and supported continuous refinement of the algorithms and business rules.
Production Implementation and Ongoing Operations
Implemented the complete solution in a production environment and personally operated the matching and consolidation processes on a weekly basis for several years.
The system operated with very few defects, demonstrating that the matching algorithms, survivorship rules, and production procedures were not merely theoretical or experimental.
They were reliable enough to support an important enterprise business application over an extended period.
Measurable Business Results
The initiative delivered substantial, documented improvements in physician and contact data quality.
Key accomplishments included:
- 32% to 71%: Increased the percentage of CRM contacts successfully matched to enterprise master data—a 39-percentage-point improvement.
- 17,045: Identified valid replacement master data identifiers for records previously associated with invalid identifiers.
- 1,869: Identified additional duplicate contacts through improved enterprise master data matching.
- 1,919: Detected duplicate contacts across two reported processing runs.
- 977: Eliminated incorrect or confusing contact records during those two merge runs.
The solution also addressed the underlying processes responsible for introducing duplicate records, including integrations between medical education systems, CRM applications, and enterprise master data.
Beyond the measurable improvements, the initiative played an important role in building sales-representative confidence in the company’s Salesforce implementation.
By transforming unreliable physician information into a more consistent and usable resource, the solution helped support adoption of a major enterprise technology investment.
Why Survivorship Matters
Identifying duplicate records is only the beginning of effective master data management.
Consider a physician represented by three different records.
One record may contain the most accurate name and professional identifiers. Another may have a more current practice address. A third may contain additional valid telephone numbers or other valuable contact information.
Simply selecting one record and deleting the others can result in the loss of important business information.
An effective mastering solution must determine not only which records belong together, but also which information should survive, which information should be replaced, and which information should be preserved alongside existing values.
That requires business rules operating at the individual data-element level, with different precedence and consolidation logic depending on the type of information involved.
This was a central design principle of the solution.
The result was not simply fewer records. It was a more complete, accurate, and useful representation of the healthcare professional.
Why This Capability Remains Important in 2026
Despite major advances in enterprise data management, the underlying problem remains.
Healthcare organizations increasingly use standardized identifiers such as National Provider Identifiers (NPI) and DEA registration numbers. However, these identifiers are not consistently available, validated, or incorporated into every business system.
CRM platforms, medical education applications, physician engagement systems, and external data feeds can still generate inconsistent or duplicate provider records.
Modern data platforms and artificial intelligence may make it easier to process large volumes of information, but they do not eliminate the need for sound matching logic, carefully designed survivorship rules, and reliable data governance.
In fact, as organizations become increasingly dependent on advanced analytics and AI, accurate provider identity becomes even more important.
Sophisticated analytics cannot compensate for an unreliable understanding of who the underlying records actually represent.
How JMC Analytics Can Help
JMC Analytics brings direct, hands-on experience designing, building, and operating a comprehensive healthcare provider identity resolution and master data management solution.
Our capabilities include:
- Assessing existing physician and healthcare provider data quality.
- Identifying duplicate and conflicting records across disparate systems.
- Designing advanced identity matching algorithms and scoring methodologies.
- Establishing matching precedence and confidence rules.
- Developing field-level survivorship and data consolidation logic.
- Reconciling enterprise identifiers and enriching existing records.
- Creating golden-record strategies that preserve valuable information.
- Developing statistical reporting and ongoing quality monitoring.
- Implementing reliable, repeatable production matching processes.
- Identifying and addressing the upstream causes of recurring data quality problems.
Engagements may range from a focused assessment or proof of concept to the design and implementation of a comprehensive provider data mastering capability.
The objective is not merely to eliminate duplicate records. It is to create a trusted, maintainable foundation for physician information that improves business operations, strengthens enterprise technology investments, and enables better decisions.
Healthcare Market Intelligence, Market Share & Opportunity Analytics
Connecting Clinical Activity, Market Intelligence, and Commercial Sales to Reveal Business Opportunities
Pharmaceutical and medical device companies invest substantial resources in understanding the markets they serve.
They purchase external market intelligence, collect information from physicians and hospitals, maintain detailed sales and implant records, and rely on field sales organizations to gather additional competitive information.
Yet one of the most important questions remains surprisingly difficult to answer:
How much business is actually occurring in our market, how much of that business are we capturing, and where are we missing opportunities?
The challenge is rarely a lack of information.
The problem is that external procedure data, clinical records, sales-representative intelligence, hospital information, and internal commercial transactions frequently exist in disconnected systems.
These systems may use entirely different identifiers, inconsistent account structures, and incompatible definitions of hospitals, physicians, procedures, and products.
Connecting them requires more than building a dashboard. It requires sophisticated data integration, matching methodologies, business rules, statistical validation, and a thorough understanding of the underlying business.
The principal consultant behind JMC Analytics has developed and implemented these capabilities across multiple cardiovascular product lines at one of the world’s leading medical device companies.
Two initiatives illustrate the approach.
Case Study 1: Coronary Stent Market Intelligence and Hospital Opportunity Analysis
The Business Challenge
Within a major coronary business, understanding hospital-level market share required comparing estimated market demand for bare-metal and drug-eluting stents with actual company sales.
External procedure information was available through LexisNexis datasets, but those records could not be directly compared with the company’s internal commercial information.
The external datasets identified hospitals using identifiers such as HMS POID, while internal sales information relied on SAP customer identifiers.
Complicating the situation, a single hospital identified by one external HMS POID could correspond to multiple internal SAP customer IDs, often reflecting different locations or organizational arrangements.
Without resolving these relationships, market volume and sales could be incorrectly attributed, creating misleading market share estimates and unreliable targeting information.
The Solution
Designed and developed an ongoing analytical process that integrated external coronary procedure information with internal hospital and commercial sales data.
The solution included several important capabilities.
External-to-Internal Hospital Matching
Developed methodologies to connect hospitals identified by external HMS POIDs with their corresponding internal SAP customer records.
The approach accounted for situations in which a single external hospital identifier related to multiple internal customer IDs.
This reconciliation was essential to accurately compare external procedure activity with company sales at the hospital level.
Procedure-Based Market Sizing
Used external coronary procedure volumes to estimate the potential number of bare-metal and drug-eluting stents associated with each hospital.
Because a coronary procedure may involve more than one stent, procedure counts could not simply be treated as product unit counts.
Developed a methodology that applied appropriate conversion factors to procedure volumes to estimate potential stent demand by product category.
This created a more meaningful basis for comparing market activity with actual commercial performance.
Hospital-Level Market Share Estimation
Compared projected stent demand with actual company sell-in data to develop hospital-level estimates of market penetration.
This allowed the business to move beyond simply knowing how many products had been sold.
It provided an analytical basis for understanding how those sales compared with the estimated overall opportunity at each hospital.
Data Validation and Outlier Detection
Developed statistical sanity checks to identify hospitals where attributed procedure volumes fell outside expected tolerances.
These controls helped flag potential problems involving hospital matching, data attribution, procedure volumes, and other inconsistencies before they distorted the analysis.
Sales Targeting and Forecasting
Used the resulting market estimates to identify hospitals where projected procedure-based demand substantially exceeded actual company sales.
These differences helped reveal potential targeting opportunities and provided additional information for sales planning and forecasting.
Business Impact
The coronary analytics initiative established an ongoing capability for translating external procedure information into commercially useful market intelligence.
It provided a more complete picture of hospital-level market potential, supported estimates of product penetration, and helped identify opportunities that could not be recognized from internal sales information alone.
Importantly, the analytical process incorporated both sophisticated identifier reconciliation and data quality controls, helping make the resulting information more reliable for business decision-making.
Case Study 2: Structural Heart Clinical-to-Implant Analytics
The Business Challenge
Years later, a different cardiovascular business faced a related challenge.
The organization needed to understand the relationship between patients receiving CT scans as part of an evaluation for transcatheter aortic valve replacement (TAVR) and patients subsequently receiving the company’s implanted heart valves.
External clinical imaging information and internal commercial implant records existed in separate systems.
The data was not designed to be connected, and inconsistencies involving patient attributes, dates of birth, time-zone conversions, and repeated clinical events complicated the matching process.
An earlier matching methodology identified 21,652 clinical-to-implant relationships.
The opportunity was to improve matching accuracy and coverage, then use the expanded information to develop a more complete picture of the patient journey and potential commercial opportunities.
The Solution
Led the architecture and development of an advanced analytics solution that connected external clinical imaging information with internal implant transactions, hospital records, and sales territory information.
The solution included:
Advanced Patient Matching
Developed and refined a hierarchy of matching rules to identify relationships between clinical imaging records and subsequent implant transactions.
The methodology addressed inconsistent identifiers, date-of-birth discrepancies, time-zone issues, and other challenges that conventional matching techniques could not adequately resolve.
Clinical Episode Analysis
Developed logic to distinguish meaningful clinical episodes from repeated or potentially unrelated events, helping prevent duplicate clinical activity from distorting the analysis.
Clinical-to-Commercial Linkage
Connected qualifying clinical events with subsequent implant transactions within defined time windows.
This created a stronger foundation for understanding the progression from clinical evaluation to commercial implant activity.
Hospital and Territory Alignment
Integrated clinical and implant information with hospital and sales territory data to support analysis at the account, territory, district, and regional levels.
Patient Journey and Opportunity Analytics
Developed analytical measures to examine conversion patterns, elapsed time between clinical events and implants, and differences across hospitals and geographic areas.
These measures helped identify potential opportunities for further commercial investigation.
Executive Reporting and Interactive Analysis
Established an analytical foundation supporting executive dashboards, geographic comparisons, hospital opportunity analysis, and interactive exploration of business questions.
The solution incorporated Snowflake, SQL, Tableau, Python, Streamlit, and AI-assisted analytical capabilities.
Measurable Results
The enhanced methodology substantially increased the number of clinical imaging records connected with commercial implant transactions.
- 21,652: Clinical records matched using the earlier baseline methodology.
- 39,080: Clinical CT records matched using the enhanced methodology.
- 17,428: Additional clinical records connected to implant activity.
- 80.5%: Increase in matched clinical records compared with the earlier methodology.
This improvement created a significantly stronger analytical foundation for examining clinical-to-commercial conversion, patient journey timing, geographic patterns, and potential business opportunities.
The 80.5% improvement represents an increase in matched clinical records, not an increase in sales or market share.
A Repeatable Capability, Not a One-Time Solution
Although the coronary and structural heart initiatives involved different products, data sources, and business questions, they shared a common analytical foundation.
Both required connecting external healthcare activity with internal commercial information.
Both involved complex matching challenges because the source systems were never designed to communicate with one another.
Both required business rules and validation methods to make the resulting information reliable.
And both transformed previously disconnected data into information that could help commercial organizations better understand their markets.
The coronary initiative demonstrated how external procedure volumes could be translated into estimates of product demand, market penetration, targeting opportunities, and forecasting inputs.
The structural heart initiative demonstrated how sophisticated patient-level matching could reveal previously unidentified relationships between clinical activity and actual implant transactions.
Together, these projects demonstrate a broad, reusable capability for healthcare market intelligence rather than a solution developed for a single product or business unit.
Why This Matters to Pharmaceutical and Medical Device Companies in 2026
The need to connect market activity with commercial performance extends across healthcare.
Medical device companies may need to compare procedure volumes with implant or product sales.
Pharmaceutical companies may need to reconcile claims, prescription activity, treatment patterns, provider information, and commercial performance.
In both industries, valuable market intelligence may come from external data providers, clinical registries, healthcare institutions, or information gathered directly by field sales representatives.
However, information is only useful when it can be reliably associated with the correct physicians, hospitals, procedures, products, and commercial transactions.
A well-designed analytical capability can support several important business objectives.
Market Share and Market Penetration
Compare estimated market demand with actual sales or implant activity to evaluate commercial penetration and identify areas of potential competitive opportunity.
Physician and Hospital Targeting
Identify healthcare providers and institutions with significant clinical or procedure activity relative to company sales, enabling more focused account planning and commercial engagement.
Sales Forecasting
Use procedure trends, estimated product utilization, and historical commercial performance to strengthen forecasts and market planning.
Territory and District Performance
Evaluate commercial results in the context of estimated market opportunity rather than relying exclusively on historical sales totals.
Sales Force Effectiveness
Provide field teams with more meaningful intelligence about the accounts and healthcare professionals they serve.
Data Quality and Analytical Reliability
Identify inconsistent hospital mappings, incomplete external data, implausible procedure volumes, and other conditions that could undermine business conclusions.
How JMC Analytics Can Help
JMC Analytics helps pharmaceutical, medical device, and other healthcare organizations develop practical market intelligence capabilities that connect external healthcare activity with internal commercial results.
Potential engagements include:
- Integrating external procedure, claims, clinical, and market research datasets with internal commercial information.
- Reconciling external hospital and physician identifiers with enterprise customer and provider records.
- Addressing complex one-to-many relationships between external facilities and internal customer accounts.
- Developing procedure-to-product conversion methodologies for estimating market demand.
- Building hospital, physician, territory, and regional market share or penetration analyses.
- Creating statistical controls to detect outliers, inconsistent mappings, and unreliable market estimates.
- Connecting patient-level clinical activity with subsequent treatment, implant, or commercial events where appropriate data is available.
- Identifying commercial targeting opportunities and supporting forecasting models.
- Developing dashboards, reports, and interactive analytical applications for commercial leadership and field organizations.
- Establishing repeatable data integration and analytical processes that can be maintained over time.
Engagements may range from a focused assessment or proof of concept to the development of a comprehensive market intelligence capability.
The objective is to help healthcare organizations understand not simply what they have sold, but what the market opportunity actually looks like—and where their next opportunities may exist.
Healthcare Revenue Recovery & Reimbursement Analytics
Turning Unreimbursed Healthcare Services Into Recoverable Revenue
Healthcare organizations can provide medically necessary services, incur substantial costs, and still fail to receive reimbursement to which they may be entitled.
The problem is particularly challenging for hospitals serving large populations of Medicaid-eligible, uninsured, and financially vulnerable patients.
Incomplete patient information, inconsistent identifiers, fragmented medical records, and complex reimbursement requirements can prevent otherwise eligible claims from being submitted or successfully processed.
The financial consequences can be substantial.
When hospitals cannot recover revenue for services already provided, they have fewer resources available to support operations, invest in patient care, and serve their communities.
JMC Analytics brings firsthand experience developing sophisticated patient-matching and reimbursement analytics solutions designed to address these challenges.
The Business Challenge
While working on a Deloitte Consulting engagement supporting the Louisiana Department of Health and Hospitals, the principal consultant behind JMC Analytics was responsible for developing solutions to improve Medicaid and Medicare reimbursement recovery.
The state’s public hospital system faced significant financial pressures associated with uncompensated care.
Many patients arrived without complete identification or reliable demographic information. Some could not provide Social Security numbers, while others supplied incomplete or inconsistent personal information.
These circumstances made it difficult to determine whether patients were eligible for Medicaid coverage.
As a result, eligible medical services could go unbilled, leaving the hospital system with substantial unrecovered costs.
The problem extended beyond identifying patients.
Hospital systems also struggled to consolidate patient histories, reconcile billing information, identify previously submitted claims, and resolve reimbursement denials.
Some claims remained unpaid for extended periods, placing additional pressure on hospital finances.
The business objective was straightforward:
Identify legitimate reimbursement opportunities that existing processes had missed, establish the information needed to support those claims, and help recover revenue for services already delivered.
The Solution: Advanced Patient Matching and Claims Reconciliation
Developed and deployed a comprehensive analytical solution that connected hospital patient information with Medicaid and Medicare eligibility data.
The approach combined sophisticated patient identity matching, reimbursement eligibility analysis, accounts receivable reconciliation, and claims tracking.
Its principal capabilities included:
Advanced Patient Identity Resolution
Developed multi-level matching algorithms to identify patients in government eligibility records even when hospital information was incomplete, inconsistent, or inaccurate.
Rather than relying exclusively on exact matches involving names, Social Security numbers, or other identifiers, the solution evaluated available patient information through multiple matching approaches.
This made it possible to identify potential eligibility relationships that conventional processes could overlook.
Medicaid Eligibility Matching
Compared hospital patient records with Medicaid eligibility information to identify previously unrecognized reimbursement opportunities.
The objective was to determine whether medical services already provided could qualify for Medicaid reimbursement despite the absence of complete eligibility information at the time of treatment.
Accounts Receivable Reconciliation
Cross-referenced newly identified reimbursement opportunities against hospital accounts receivable records.
This was a critical control.
Before pursuing reimbursement, the process needed to establish that the associated services had not already been billed or paid.
The reconciliation helped distinguish genuinely missed opportunities from claims that had already entered the reimbursement process.
Claims Information Management
Developed a system to capture and track information needed to support reimbursement activity.
This included patient identifiers, Medicaid and Medicare information, demographic details, diagnosis codes, procedure codes, and other relevant claims information.
The solution provided a more organized foundation for preparing, investigating, and tracking reimbursement opportunities.
Claims Tracking and Financial Reporting
Developed reporting capabilities that allowed hospital financial management to monitor newly identified claims, reimbursement activity, and associated remittances.
These capabilities helped connect the analytical identification of missed opportunities with the financial processes needed to pursue and monitor recovery.
Medicare Claims Correction and Resubmission
In addition to the Medicaid eligibility matching initiative, the engagement included significant work supporting the correction and resubmission of Medicare claims.
Some claims had been denied or remained unpaid because of incomplete information, administrative errors, or other issues requiring investigation and correction.
During applicable resubmission opportunities, these claims needed to be reviewed, corrected where appropriate, and prepared for further processing.
This work supported efforts to recover reimbursement for eligible services that had not been successfully paid through the original claims process.
Together, the Medicaid and Medicare initiatives addressed two related challenges: identifying reimbursement opportunities that had never been properly recognized and helping resolve claims that had previously failed to produce payment.
Business Results and Financial Impact
The Medicaid matching solution identified a significant population of previously unrecognized reimbursement opportunities.
Eligible medical events were subsequently submitted to Louisiana Medicaid, resulting in additional reimbursement to the public hospital system.
The initiative contributed meaningful financial benefits by helping recover funds associated with healthcare services that had already been provided.
Although detailed historical recovery metrics are no longer available, the project demonstrated that sophisticated patient identity matching and claims reconciliation could uncover substantial financial value hidden within existing hospital records.
For a public hospital system operating under significant financial pressure, additional reimbursement represented more than an accounting improvement.
It provided resources that could support hospital operations and the continued delivery of care to vulnerable patient populations.
Why This Capability Matters Today
The underlying problems remain relevant across healthcare.
Hospitals and health systems continue to manage large volumes of patient, eligibility, clinical, and financial information across systems that do not always communicate effectively.
Incomplete patient identities, changing coverage information, inconsistent records, and unresolved claims can create reimbursement gaps.
Modern analytics provides additional opportunities to address these challenges, but success still depends on accurately identifying patients, connecting related records, validating reimbursement opportunities, and maintaining reliable financial controls.
A strong revenue recovery capability must do more than identify potential claims.
It must help distinguish valid reimbursement opportunities from previously billed or paid services, assemble the necessary supporting information, and provide visibility into the status of the recovery process.
How JMC Analytics Can Help
JMC Analytics can help healthcare organizations evaluate and improve the analytical processes underlying reimbursement identification and revenue recovery.
Potential engagements include:
- Assessing patient identity and eligibility matching processes.
- Developing advanced matching methodologies for incomplete or inconsistent patient information.
- Connecting patient records with available Medicaid, Medicare, and other eligibility information.
- Identifying potentially missed reimbursement opportunities.
- Reconciling candidate claims against accounts receivable and payment records.
- Improving the identification and tracking of denied, incomplete, or unresolved claims.
- Developing claims information management and financial reporting capabilities.
- Creating analytical controls to reduce duplicate billing and improve data reliability.
- Supporting the design of repeatable revenue recovery and reimbursement analytics processes.
Engagements may range from a focused assessment of existing data and reimbursement processes to the design and development of a comprehensive analytical solution.
The objective is to help healthcare organizations recognize legitimate reimbursement opportunities, improve financial performance, and preserve resources needed to deliver patient care.