Intelligent analytics help enable better oncology performance

Challenges within oncology, and workflow efficiencies with intelligent analytics

Oncologists share many of the challenges facing practicing physicians across the globe, including physician shortages coupled with growing demand for services, increased information overload, and incomplete patient information with which to make clinical decisions. Electronic health records (EHR) are the primary technology used by clinicians to document and order care. Although sufficient in their capabilities, EHRs cannot intelligently analyze large volumes of complex and heterogeneous data to serve up insights to support a physician’s ability to diagnose and treat a patient within accepted clinical best practices. Having actionable data at the point of care that is generated through advanced analytics improves operational efficiency for oncologists. It also leaves them more time for direct patient care, augments their domain expertise in underserved geographies, and enables a consistent standard of care.

For oncologists to diagnose and determine the best treatment for a cancer patient, they must be able to digest and analyze the patient’s data, best-practice oncology guidelines, current medical research, and the availability of an appropriate clinical trial if appropriate. Information overload can be overwhelming for clinicians since EHR systems cannot identity relevant data in the context of a patient’s needs, nor are the best-practice guidelines embedded in the system. Not having access to clinical best practices results in an estimated 40% of cancer care being off guideline (Smith, et al., J Clin Oncol 19:2886-2897). The sheer volume of oncology research might discourage an oncologist from looking for relevant findings.

Challenges within Oncology
Drivers of clinical variation include the lack of available resources, lack of adherence to best practice standards, physician experience, cost of care, and patient preference. Implications include mortality and/or morbidity as well as unwarranted costs. Unwarranted variation in clinical practices is driven in part by lack of convenient access to clinical best practices. Best practice guidelines are available but not embedded in the EHR, making it a challenge for oncologists to match best practice treatments to an individual patient. By embedding guidelines in a clinician’s native workflow through EHRs, oncologists can be provided with actionable data at the point of care ultimately improving operational efficiency.

In addition, clinical trials are chronically under-enrolled because oncologists and patients are unaware of available trials. Oncologists may know of their own institution’s clinical trials but not those happening elsewhere. Matching patients to clinical trials is even more challenging given the difficulty in identifying eligible patients and the lack of automated workflow between oncologists and clinical trial coordinators. Without automation, an oncologist would need to review 163 patients per trial on average to replicate the historical patient enrollment for each trial. Automated eligibility screening reduces that reviewing workload by 85% to 24 patients per trial (Ni, et al., April 2015, BMC Medical Informatics and Decision Making). Providing actionable data to oncologists will likely improve both patient experience and medical outcomes. Efficient access to available clinical trials and patient-matching algorithms that only review patients who passed the eligibility screening would likely increase enrollment into clinical trials.

Intelligent Analytics and Workflow Efficiencies
Technology can mitigate these challenges by integrating actionable insights through existing clinician workflow technology such as EHR. Using the EHR as the foundation and as a source of a patient’s clinical data, oncologists can apply advanced analytics to evaluate individual conditions and, using best-practice guidelines, identity potential treatment options. Oncologists that need to view the results of the intelligent analytics in order to evaluate a patient’s potential treatment options can decide how to proceed and implement that plan all within the workflow of their patient’s EHR. Additionally, the oncologist needs to review possible clinical trials that might be appropriate and, if one is selected, automate a referral to the clinical trial coordinator.

Having the relevant data, intelligent analytics, and workflow within an oncologist’s primary technology tool (the EHR) will yield operational efficiencies and reduce delays in determining and executing treatment options. Metrics to determine cost and quality improvements must also be incorporated, so that if necessary, process or data changes can be made to improve performance.

For more details on how intelligent analytics and workflow efficiencies can transform the health sector for oncologists, download the IDC Analyst Connection,

“Improving Oncology Performance through Analytics,” sponsored by IBM Watson Health.

Sponsored By: IBM Watson Health