Researchers at Massachusetts General Hospital and Harvard Medical School have developed a method of extracting symptom information from electronic health records (EHRs) to allow physicians to identify psychiatric disorders missed in traditional sources of clinical data. Findings were presented in Biological Psychiatry.
The method extracts relevant symptom information from notes in EHRs, identifying disorders including schizophrenia, anxiety, major depressive disorder and posttraumatic stress disorder. The characterization of these patients based on their symptoms could predict a length of hospital stay and time to readmission more accurately than traditional use of data.
"Many efforts to use clinical documentation in electronic health records for research aim to identify individual symptoms, like the presence or absence of psychosis," said Thomas McCoy Jr., MD, co-first author with Sheng Yu, PhD. But this approach misses the complex overlap of symptoms between different mental disorders.
"My co-authors and I developed a method that instead captures symptom dimensions, or sets of symptoms, informed by the National Institute of Mental Health Research Domain Criteria," said McCoy.
In testing the methods feasibility and accuracy, researchers compared information on symptom dimensions from physicians notes of 4,687 patients with the patients genomic information.
"The recognition that the genetic basis of psychiatric illness crosses traditional boundaries has encouraged efforts to understand psychopathology according to dimensions, rather than simply presence or absence of symptoms," said McCoy. "We are making the scoring software freely available and hope this work will enable transdiagnostic dimensional phenotypes to be used in efforts to achieve precision psychiatry.”