EHR Data Analytics – Diabetic Drug for Cancer



One of the major benefits of electronic health records (EHRs) is their ability to capture data in a form that can be used for clinical research. Data gathered from retrospective chart reviews tends to have a level of statistical validity that limits its use in clinical research. However, when large volumes of data is gathered from thousands of patient records its statistical validity increases significantly, in some cases approximating the value of data obtained prospectively.  In addition, this information can be gathered as secondary data at a fraction of the cost of performing traditional double-blinded clinical studies.  The dramatic rise in the use of electronic health records has created a wealth of digital data that has the potential to lead to significant advanced in scientific knowledge.

A recent study published by Vanderbilt University Medical Center has identified the potential value of a commonly used diabetes drug as a potential agent that may also be effective in the treatment of cancer. The researchers combined data from the Mayo Clinic and Vanderbilt University Medical Center, allowing them to have a very large number of patients with digital records included in the study; well over 100,000. The study demonstrated a survival benefit for patients who are using metformin (Glucophage), a common oral hypoglycemic agent is by diabetic patients. They found that there was a significant survival benefit for patients with breast and colorectal cancer, and a potential benefit for patients with lung and prostate cancer.

The exact mechanism whereby metformin may improve survival in patients with various forms of cancer is unknown. However, other studies have suggested that metformin may have a role in cancer treatment. Metformin is a relatively safe drug that has been used for many years. Its use has been largely limited to the diabetic population, however this study suggests it may have a role in treating cancer patients without diabetes. The researchers identified a 23% reduction in mortality in patients who are taking metformin for type II diabetes as compared to patients who do not have diabetes and who were not taking metformin. Diabetic patients were taking insulin but not metformin found a have a significantly increased mortality rate over diabetic patients taking metformin.

This study offers support for the value of electronic data for clinical research gathered during routine medical care. While data gathered from prospective clinical studies has long been considered to be the gold standard for making clinical informed decisions, retrospective gathering of data from very large numbers of clinical encounters from tens of thousands of patients may have value that approaches the value of prospective data. Central to the value of this data is its accuracy and completeness. This remains one of the most vexing challenges in healthcare. The majority of data captured by electronic health record systems is in a form that is difficult to use for secondary purposes. These challenges are related to a lack of business incentives and implemented standards, however once these barriers are overcome researchers will have access to massive amounts of data that can be used for retrospective research.

The researchers in this article discussed the value of natural language processing (NLP)in the analysis of records. However data entered directly into the system in a structured format, preferably codified, would offer a higher degree of accuracy and reliability than unstructured data mined through natural language processing techniques.

The potential for using massive quantities of data captured by EHRs for dramatic breakthroughs in clinical medicine is unprecedented. The vast majority of digital health care information has been captured in the last three years in the United States secondary to the dramatic increase in the adoption of electronic health records. Efforts that focus on getting data of high integrity from these systems will be an area of active engagement in the healthcare information technology industry for many years to come.

The full article was published by the Journal of the American Medical Informatics Association and is available here.  Multiple researchers where engaged in this study and the Reference: J Am Med Inform Assoc doi:10.1136/amiajnl-2014-002649. 

The opinions represented above, unless otherwise attributed, are those of the author of this article: Michael Stearns MD.

Six Barriers to Interoperabilty

Large institutions face problems with internal and external interoperability.  Many, like the Cleveland Clinic, may have hundreds of systems that have to be coordinated in order for meaningful information to be shared amongst members of the same healthcare institution.  The data is often fragmented and stored in databases using formats and codified terminologies that are highly proprietary.  These challenges are difficult but can be partially managed with interfaces and when appropriate by choosing multiple products from the same vendor.

However, patients are typically seen at multiple locations. On average the severity and complexity of a given patient’s conditions are directly proportional to the number of different databases in which medical information about that patient are stored.  Thus even an “ideal” institution that invests heavily in interoperability remains at the mercy of other systems with which they must communicate.

With perhaps the one exception being mediation reconciliation, there has been relatively little progression in interoperability over the past 30 years. This has occurred despite the many government and healthcare community initiatives that have been launched to make systems interoperable.   Why is this so and what could actually be done to overcome barriers to interoperability?

  1. Physician Attitudes Toward Interoperability: Regarding the reasons for lack of interoperability, perhaps a leading consideration and one that is not spoken of very often, is a lack of understanding amongst physicians of the value of interoperability.  Doctors are trained to be able to evaluated a patient who presents with no prior records, as this remains a common occurrence.  Most physicians would agree that if the information was available in a format that was reliable and formatted in a way that it was directly relevant to patient care, then it would be very useful to have the full record of care.  However, it may not be a high priority, and in some cases physicians may see access to a complete record as information overload creating additional pressure on the limited amount of time they have to provide patient care.  If physicians felt that interoperability was essential, they would demand it from their institutions and be willing to making greater investments in health information exchange.  Targeted educational initiatives that illustrate the value of interoperability to physicians, in particular when they impact patient safety, medicolegal risk, and reimbursement, may be of value if they encourage providers to demand access to complete medical records.  However, the information that is obtained from other systems and shared with providers needs to be formatted in a manner that will allow for efficient reviewing.  It will also need to be accurate and complete.
  2. Lack of Implemented/Mandated Standards: The lack of standards is often cited as a barrier to interoperability.  However, numerous standards have been vetted and are available that would make a significant difference in improving the flow of information in medical communities.  These include the CCD, cCDA, FIRH, HL7 V3, CDC requirements for immunization registries, numerous codified terminologies, and several others.  However, many of these standards have not been mandated or when they are there are marked gaps in how the implementations may be “interpreted.”  Thus, developing additional standards is not as important as taking the ones that have already been developed and creating incentives for their use, including common methods for working with them in live settings.
  3. Business Disincentives to Interoperability – Don’t Make it Too Easy to Leave:  Healthcare institutions often do not have strong business incentives to invest in interoperability.   They depend upon community physicians making referrals to their systems for labs, diagnostic procedures, surgeries, admissions and other revenue generating activities.  Many have acquired physician practices or provided EHR software, training, hosting and technical support for affiliated physicians in their communities via the Stark Antitrust Exception.  In general these systems encourage or require physicians who are employed or affiliated to use a single EHR platform.  Since the hospital is providing software and technical support, it is in their best interest to invest in knowledge resources that fully understand a given single system.  In addition, the cost of the EHR product and its support in the clinics are covered by the hospital (up to 85% of costs in the Stark Antitrust Exception) which may foster a form of IT dependency on the hospitals.  In some cases, the hospital also owns the database that houses the medical records of the patients.  Considering all these factors together, hospitals (and EHR vendors) have concerns about the impact of seamless interoperability on their retention rates.  Physicians are largely dissatisfied with their current EHR platforms and if their ability to change to a new system were to relatively straightforward, they may opt to transition to another vendor platform.  This may be one of the reasons that hospitals are in general not demanding low cost and low resource intensive interoperability from their EHR vendors, and their vendors also not business incentive to allow for their current customers to switch to a competitor. There may not be a straightforward solution to this barrier other than the institution of mandatory requirements for interoperability.
  4. Breach Concerns: Other concerns that are often cited include hospital and provider fears over the ramifications of a breach of protected information, as the covered entity has responsibility for breaches even if the breach occurred once the data was out of its hands.  For example, if an HIE were to be breached the hospital that sent the data to the HIE would be required to contact all of the affected patients and possible penalties.  Since breaches are increasingly common occurrences, the stigma associated with a breach in a setting where the covered entity has made every reasonable effort to be compliant with security requirements and protocols needs to be reduced.  In addition, penalties should not be applied if the covered entity is compliant with reasonable breach protection requirements. Until the fear of breaches is addressed it may negatively influence the willingness of hospitals to engage and invest in interoperability.
  5. Competitive Marketing Analytics: A related concern that may give hospital management teams pause is their concern over how data exported from their systems will be used by their competitors.  Hospitals often compete by stating that they have the lowest rate of complications in the community.  A competitor will full access to data may be able to challenge marketing materials provided by another system once they “reanalyze” the data. This is another barrier that will be difficult to overcome short of the adoption of interoperability requirements.
  6. The Monetary Value of Data:  Healthcare data has value in the industry and several companies have successful business models related to selling data to clinical and marketing research organizations.  Once data is shared with other organizations its proprietary value may be impacted negatively, or it may enhance the value of a competitors data (e.g., if the data that was shared lead to a competitor having a larger cohort of patients with a disease that is being targeted by pharmaceutical research organizations). The ownership of data is under constant debate, and until there is legal precedent that establishes the ownership of data, including the patient’s right to their own healthcare date, this will be a difficult barrier to overcome. One approach might be to make it mandatory that organizations share data that is needed for patient care without restriction.

In summary, U.S. healthcare would have seamless interoperability today if it was a true priority.  Until the business and other barriers are addressed interoperability is unlikely to be more that a discussion topic at HIT meetings for years to come.  Perhaps the most promising change is the marked increase in the use of technology by patients, the principal stakeholders in healthcare. This will allow them to become more engaged in the process of sharing data. Also encouraging is that none of the 6 barriers to interoperability noted above are of great concern or interest to patients, and in most cases it is likely that they would want to see them removed as quickly as possible.

Comments welcome…

The information presented in this article is the opinion, unless otherwise stated, of its author, Michael Stearns, MD.





ACO Survey – Interoperability and Cost of HIT are “Burdens”

This article (link below) reports findings from a survey of 62 accountable care organizations (ACOs) reported by the eHealth Initiative and Premier, Inc. 90% reported that the cost of HIT and its return on investment had become “crippling concerns.”  Areas that were seen as underutilized or underserved included:

  • Patient engagement tools
  • Referral management tools
  • Telemedicine
  • Remote monitoring
  • Personal health records
  • Smartphone applications
  • Data interoperability
  • Data quality
  • Health information exchange strategies
  • Analytics
  • Patient reported data mining
  • Unstructured data mining
  • Revenue cycle management
  • Master Patient Index (MPI)
  • Risk management

Improvements were seen in outcomes, cost, efficiencies, quality of care, reductions in hospital admissions/readmissions and ED visits, although they were modest.

Commentary:  This article provides very useful information and identifies the need to remove barriers to access to information.  The majority of ACOs reported they are  “facing significant obstacles in integrating and blending data from disparate sources.”  At this time a lack of implemented standards and success with removing business disincentives towards interoperability are threatening to compromise the success of accountable care initiatives.  Patients may be the only stakeholders with the legal and political clout to successfully promote cost-effective reform in this space; but as of yet they are relatively unengaged.

Article Link: The Landscape of Accountable Care and Connected Health: Results from the 2014 National Survey of Accountable Care Organizations.

Patients as Medical Record Keepers


A number of concerns have been raised by the medical community about giving patients control of their own version of their medical record.   Patients may elect to redact certain information from their medical records that they may view as sensitive (e.g., mental health history, history of drug and/or alcohol use, sexually transmitted diseases, etc.).  This has the potential to compromise the clinical record and hence clinical care.  However, it is extremely common for patients to present to clinicians for evaluation without any medical records. At that point the history must be taken directly from the patient.  Patients may again elect not to share sensitive information with the provider during the process of providing a verbal history.This is not considered to be outside the realm of typical patient care

The majority of patients would not remove information from the records they are maintaining.  In contrast, they have the time and motivation to assemble the entire record of care across the entire healthcare ecosystem.  These compiled records can then be presented to a treating physician and are likely to be far superior to having no records whatsoever during a patient encounter.  The provider will know that the records have been maintained by the patient and will need to maintain awareness that the information provided may not be complete and accurate.  .

In summary, allowing patients to maintain and edit their own medical records is no worse than relying on patients to provide an accurate history during a patient encounter.  It also allows the patient to provide a highly complete clinical record to a treating physician.  Providers will need to maintain awareness that some patients may elect to modify information in the record,  However, the advantages of allowing patients to maintain their own records greatly outweighs the inherent disadvantages of having an incomplete or absent record.

The information in this post represents the opinions of Dr. Michael Stearns

AMA Focus On EHR Usability – Not Enough?

Physicians in general are not satisfied with their EHRs, citing problems related to loss of productivity, difficult to learn tools, and excessive data entry requirements.  The AMA recently announced a framework for EHR usability which is an important component of any effort to improve physician satisfaction.  However, there are several other considerations that would allow marked improvements in user satisfaction with EHRs that do not require modifications to existing systems. These include advanced user training, workflow optimization, and improving the business acumen of EHR users.

The AMA outlined eight key challenges providers face when using EHRs.

  1. Enhance physicians’ ability to provide high-quality patient care;
  2. Support team-based care;
  3. Promote care coordination;
  4. Offer product modularity and configurability;
  5. Reduce cognitive workload;
  6. Promote data liquidity;
  7. Facilitate digital and mobile patient engagement; and
  8. Expedite user input into product design and post-implementation feedback.

All of these represent important considerations that EHR software vendors in particular need to address during software design and software implementation.  Solutions to each of these challenges are discussed in detail in the article (link below).

However, they do not specifically address several areas of need and opportunity that have impacted the use of EHRs. Given competing priorities and the software development life-cycle, in general many of these changes will not reach users for a minimum of 12-18 months. A small but growing number of EHR users have managed to take full advantage of their current systems to create patient care and business environments that have resulted in:

  1. Marked improvements in patient care
  2. High levels of user satisfaction with their EHR systems
  3. Increase levels of compliance with documentation and coding requirements
  4. Significant increases in revenue, primarily tied to increases in patient volume and adherence to clinical guidelines.

How can this be achieved?

1. Gaining an advanced knowledge of the EHR system: Providers rarely have more than a limited understanding of their EHRs.  Financial pressures and limited EHR vendor implementation resources typically result in inadequate implementations. Providers and their staff tend to learn just enough to generate notes, orders, manage results, and submit claims.  They typically do not have a full understanding of the capability of their systems and how it can be customized for marked improvement in workflow proficiency. Practices that become “experts” in their EHR and practice management systems have much higher satisfaction rates than those who only understand its basic features. Seeing a doctor who only has basic knowledge of their EHR is akin to employing an accountant who barely knows how to use a spreadsheet.

2. Assessing office workflow: Dramatic gains in efficiency have been achieved by practices that analyze the role of each office staff member and how the EHR can be used to greatest advantage to protect the practice’s most valuable resource: physician time. This requires knowledge of how other similar practices have achieved optimal results and a comprehensive understanding of the EHR and practice management system’s capabilities.

3. Understanding the business rules of medicine: Providers in general have a fairly limited understanding of specific payer rules on reimbursement tied to documentation and coding.  EHRs generally have automated coding support that when used by someone with advanced coding knowledge can significantly improve the accuracy of coding.  Most providers using EHRs are not aware of data elements supported by evaluation and management (E/M) coding guidelines that are not captured or addressed by their EHR systems.  A example of this is the ability to recognize 3 chronic conditions and their statuses in the HPI, or the ability to recognize that manual review of an image has twice the value of reviewing a report for the same image when determining the level of complexity of medical decision making.  A full understanding of these business rules and many others allow providers to make informed decisions when determining the final E/M code.

The Solution:

A focus on usability, as proposed by the AMA, is an essential aspect of any effort to improve the use and value of EHRs.  In addition, providers, vendors and consultants need to focus on getting providers and their staffs to more fully embrace and understand the features of their EHR and PM systems.  The value of workflow optimization in any industry cannot be overemphasized.  EHRs offer features that allow for significant improvements in workflow and documentation efficiency that users have generally not used to their advantage. No one would challenge a provider earning increased revenue if it was tied to increases in patient volume.  Finally, EHRs are not only clinical tools but also business tools.  A full understanding of coding principles and how a specific EHR supports decision making tied to E/M and other types of coding is greatly empowering to physicians.

Link to AMA Framework Document: Improving Care: Priorities to Improve Electronic Health Record Usability

The information contained within this article, unless otherwise attributed, represent the opinions of its author Michael Stearns, MD, CPC, who serves as a health information technology and compliance consultant.

Please submit comments.  Dr. Michael Stearns can be reached at

EHRs and the ICD-10 Transition: Planning for 2015

This article (link below) was published by AHIMA and reprinted with permission by Physician’s Practice.  It details recommendations regarding how EHRs users and vendors should approach the transition from ICD-9-CM to ICD-10-CM.  EHR vendors that are transitioning to SNOMED CT before the October 1, 2015 deadline for using ICD-10-CM will be able to offer a relatively smooth transition.  In some cases EHR users maintain local ICD-9-CM codes (e.g., templates, pick lists for diseases, etc.).  These individuals will need to work with their EHR vendors to identify where in their EHRs locally maintained ICD-9-CM codes may reside, and the steps needed to update them to ICD-10-CM.

Article Link: EHRs and the ICD-10 Transition: Planning for 2015

Author of article (and this post): Michael Stearns, MD, CPC

Adoption of HIE and Patient Engagement Low in Practices

The August 2014 edition of the Journal “Health Affairs” published the results of a survey conducted by representatives from AHRQ, ONC, Harvard and the University of Michigan.

The article is titled “Despite Substantial Progress In EHR Adoption, Health Information Exchange And Patient Engagement Remain Low In Office Settings.”

Key findings of this 2013 survey:

  1. EHR adoption continued to increase, with 78% of practices reporting the adoption of some type of EHR and 48% had the features needed for the use of a “basic EHR.”  Providers in solo practices and non-primary care specialties has the lower rate of adoption.
  2. Only about 14% of providers share data electronically with other providers outside of their organization.
  3. The survey found that 30% of physicians routinely used secure messaging capabilities with patients.
  4. It also found that 24% routinely provided patients with the ability to view online, download, or transmit their health record.

Editorial Comment*:  This is an excellent and informative article about the state of health information exchange (HIE) and patient engagement in the U.S. in 2013.  HIE is plagued by limitations related to the cost of interfaces, lack of adoption of required technologies, business disincentives, privacy concerns, a lack of implemented standards, and challenges associated with reconciling data from disparate sources.   Patient engagement represents another challenging area of healthcare as patient have not traditionally been taking advantage of patient portals and PHRs.  A lack of interoperability, requiring patients to manually enter data in PHRs, would benefit from greater levels of health information exchange.  As the authors note in the discussion of this article, greater attention needs to be paid to policies that will facilitate the broader adoption of HIE and patient engagement tools.

Link to full article (requires subscription to Health Affairs): “Despite Substantial Progress In EHR Adoption, Health Information Exchange And Patient Engagement Remain Low In Office Settings”

The abstract is available here.

Author Affiliations:

1. Michael F. Furukawa ( is a senior staff fellow in the Center for Delivery, Organization, and Markets at the Agency for Healthcare Research and Quality, in Rockville, Maryland. He was director of the Office of Economic Analysis, Evaluation, and Modeling at the Office of the National Coordinator for Health Information Technology (ONC) in the Department of Health and Human Services when this article was written.
2. Jennifer King is chief of the Research and Evaluation Branch in the Office of Economic Analysis, Evaluation, and Modeling at the ONC.
3. Vaishali Patel is a senior adviser in the Office of Planning, Evaluation, and Analysis at the ONC.
4. Chun-Ju Hsiao is a health scientist administrator in the Center for Quality Improvement and Patient Safety at the Agency for Healthcare Research and Quality.
5. Julia Adler-Milstein is an assistant professor in the School of Information and the School of Public Health, University of Michigan, in Ann Arbor.
6. Ashish K. Jha is a professor of health policy and management at the Harvard School of Public Health, in Boston, Massachusetts.

Citation: Michael F. Furukawa, Jennifer King, Vaishali Patel, Chun-Ju Hsiao, Julia Adler-Milstein and Ashish K. Jha, Despite Substantial Progress In EHR Adoption, Health Information Exchange And Patient Engagement Remain Low In Office Settings, Health Affairs, no. (2014): doi: 10.1377/hlthaff.2014.0445

* The Editorial Comment represents the opinions of Michael Stearns, MD.

Challenges with the use of digital healthcare data

While healthcare institutions are busy collecting terabytes of data the vast majority of digital information captured has no secondary use value. Information is created by proprietary systems using non-standard terminologies or it consists of claims data that may or may not truly represent what transpired during clinical care.   However, if information could be captured from systems in a manner that maintains it integrity the value to patient care, clinical research, and the business of medicine would be enormous.  Efforts to require systems to record all data in standardized formats need to continue and to be accelerated.

While this does seem like something that should not be that difficult to resolve, no community in the world has overcome barriers to complete interoperability.  There is a tremendous opportunity for talented individuals to acquire a deep understanding of the life cycle of data, including how the following entry and usage points:

  • Its point of capture in an EHR, patient oriented device, billing application etc.
  • The use of standard terminologies (e.g., SNOMED CT, LOINC, others)
  • Its local storage for primary uses (e.g., documentation for patient care, clinical decision support, etc.)
  • Its method of storage locally (level of detail captured, data/time stamps, post-coordination, etc.)
  • How it is exported and in what vehicles(e.g., HL7 messages, CCD, cCDA, etc.)
  • How data in imported from other systems

Dr. Michael Stearns