In June, the city of Chicago will be flooded by physicians and nurses from all over the world who are attending one of the largest international cancer conferences: The American Society of Clinical Oncology Annual Meeting. This event is expected to draw more than 25,000 people who are involved in the treatment of cancer or in cancer research.
These days, cancer treatment is more complex than ever before. The science is rapidly evolving, and new information is being presented at a speed that exceeds human capacity to read, analyze and incorporate it into clinical practice. This is why the IBM Watson project has partnered with such facilities as the New York-headquartered Memorial Sloan-Kettering Cancer Center to provide a level of advanced clinical decision support to busy cancer clinicians.
Oncologists and oncology nurses spend countless hours trying to keep up with the latest advances in cancer research and drug development. Meanwhile, they are also occupied with maintaining cancer registries that contain patient records from hospitals and community cancer centers. In some instances, cancer centers are outpatient treatment facilities that use a different EHR system than the hospital, so interoperability challenges directly impact workflow efficiency. Until we see a universal health information exchange system across the entire country, these types of data challenges will continue to require manual processes for importing or exporting patient records from one EHR system to another.
Cancer registries are databases that are managed by healthcare professionals called cancer registrars. These individuals manage and analyze patient health data and maintain and compile that information to meet national accreditation standards and to report on research, quality improvement, patient monitoring, cancer surveillance and program planning. Cancer centers in the community provide aggregate data to support national cancer registry efforts. The National Cancer Data Base (NCDB) is a joint program of the Commission on Cancer of the American College of Surgeons and the American Cancer Society. The NCDB is a nationwide oncology outcomes database for more than 1,500 U.S. cancer programs accredited by the Commission on Cancer.
Since many cancer centers and hospitals have created cancer registries, one may think that it would be easy and efficient for them to examine this data and identify opportunities for clinical quality improvement. However, things are not so simple in the world of oncology. Directly linking cancer registries to EHRs is one of the major interoperability challenges in oncology. Right now, many cancer registrars are manually extracting patient records from EHRs and entering that information into their registries.
So, when cancer centers wish to examine their aggregate patient data to identify opportunities for quality improvement, registrars often have to spend many hours working closely with nurses and other clinicians to manually extract the right patient records from EHRs and collect the relevant clinical data. Some of the structured data may be captured in the cancer registry, so abstracting that information may be fairly easy. However, sometimes the registrar must manually analyze unstructured data in an EHR or structured data that is not a cancer-registry data field. This can be a laborious process.
Let me illustrate with an example. The treatment of certain types of advanced lung cancer can be tailored based on the results of certain molecular biomarkers. such as epidermal growth factor receptor (EGFR) and Anaplastic Lymphoma Kinase (ALK). These specific biomarkers must be ordered by a physician when the patient is diagnosed with lung cancer. The biomarker results may guide the medical treatment of the patient.
There are now several FDA-approved targeted drug therapies that have shown to improve clinical outcomes in certain lung cancer patients who have positive EGFR or ALK biomarkers. Additional drugs are evaluating other biomarkers in these patients. So, if a cancer center wanted to evaluate their quality and performance in the treatment of patients with advanced lung cancer based on EGFR or ALK biomarkers, they may want to know how many patients are being tested for these biomarkers. The answer to this clinical quality question may require manual data abstraction from patient records because such data as EGFR and ALK biomarkers is often not included in a centralized database such as a cancer registry.
The future of improving cancer care depends on our ability to find more efficient ways to exchange patient data across different EHR systems. This universal interoperability problem is one of the biggest challenges in oncology. Another major challenge involves the aggregate analysis of unstructured data in an EHR that is not captured in a cancer registry. As the cancer community starts adding additional clinically relevant data points into their cancer registries, they will have access to a searchable database that can help them identify opportunities for clinical quality improvement. Furthermore, as natural language processing systems find more ways to analyze unstructured data in EHRs, cancer registrars may be able to retrieve and incorporate this information into their registries.
About the author:
Joseph Kim is a physician technologist who has a passion for leveraging health IT to improve public health. Dr. Kim is the founder of NonClinicalJobs.com and is an active social media specialist. Let us know what you think about the story; email firstname.lastname@example.org or contact @SearchHealthIT on Twitter.