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.