25 August 2015. Medical researchers found electronic triggers that alert physicians when test results suggest a potential for cancer, reduce delays for patients needing follow-up care. The team led by Hardeep Singh, a professor at Baylor College of Medicine in Houston, published its findings yesterday in Journal of Clinical Oncology (paid subscription required).
In addition to his position at Baylor, Singh is also chief of health policy at DeBakey VA Medical Center in Houston in the center’s quality and informatics program. Singh and colleagues from Baylor and nearby medical centers in Texas, investigated tools that could harness the growing use of electronic health records to close the gaps in time between screening tests identifying patients possibly with cancer and getting the follow-up diagnostics needed by those patients.
The researchers wrote an algorithm that reviewed electronic health records of more than 10,600 patients under the care of 72 primary care physicians recruited for the study over 15 months. For the study, physicians and their patients were randomly assigned to a group receiving conventional care and follow-up, and a group where electronic records were automatically reviewed for lab results indicating possible cancer occurrence. Those lab tests included iron deficiency anemia, fecal occult blood test (blood in stool sample), prostate specific antigen, and imaging showing abnormal results, such as lung X-rays.
Patients in the automatic review group had their records checked twice a month for suspicious results, and if found, the records would be manually reviewed, then physicians would be alerted with secure e-mail messages. Physicians in the conventional follow-up group would be alerted to suspicious results through their normal information channels.
The records review showed 1,256 patients, about 12 percent of the total, with lab results indicating potential cancer signs, and at risk of delayed diagnostic evaluation. Among participants in the group with records that were automatic reviewed, patients with results showing potential colorectal or prostate cancer received follow-up diagnostics, such as a colonoscopy, faster than those where their physicians were informed through conventional channels.
For patients with indications of lung cancer, differences between the two groups were not large enough to be statistically reliable. In addition, by the end of the study, more patients whose records were automatically reviewed received follow-up diagnostic evaluations than patients of physicians who used conventional information channels.
Singh presented early results of his research to the Institute of Medicine last August. The institute plans to issue a report on problems with diagnostics this fall. “Missed or delayed diagnoses are among the most common patient safety concerns in outpatient settings,” says Singh in a Baylor statement, “and measuring and reducing them are a high priority. Solutions that harvest and put to use the vast amount of electronic clinical data being collected are essential.”
Read more:
- Flatiron, Guardant Partner on Cancer Genomics, Analytics
- Computer Model Provides Early Sepsis Alert
- Alliance to Collect Mobile Health Data for Clinical Trials
- Patent Awarded for Early, Pre-Symptom Cancer Tests
- Health Data, Analytics Firms to Boost Cancer Trial Access
* * *
You must be logged in to post a comment.