Nothing is as thorny for healthcare providers as being confronted with a patient who is clearly hurting but does not know the exact source of the pain or how to describe its intensity, making detection, diagnosis, evaluation, and treatment extremely difficult. Researchers at Stanford University School of Medicine are working on a solution that may prove beneficial to the health services industry and boost sales at OEMs serving the sector.
The researchers are examining the possibility of developing a diagnostic tool that uses functional magnetic resonance imaging (fMRI) and support vector machines (SVMs) to more accurately determine both the source and level of pains without any input from the patient. Such a tool will improve diagnosis and accelerate treatment by physicians.
Here's how the researchers explained the challenge as well as the potential opportunity for a pain diagnostic tool in a report in PLosOne, a journal of peer-reviewed science:
- Individuals with major cognitive or communicative impairments, such as intensive care unit patients or older adults with dementia, may not be able to provide valid self-reports of pain. For those individuals, there are few methods for determining the presence or absence of pain. While behavioral tools exist (such as those assessing facial expressions, vocalizations, and body movements), they too may fail individuals with paralyses or other disorders affecting motor behavior. There is, therefore, a need to develop a pain assessment tool that is based on physiology, and requires no communication on the part of patients.
The “Eureka” moment isn't here yet, but the researchers are getting some promising results and are already fielding questions about the potential for such a device from medical offices, hospitals, and patients. In addition to benefiting the direct users, the pain diagnostic tool would also create sales opportunities for OEMs as well as semiconductor and magnetic material manufacturing companies.
In a series of experiments, the Stanford University researchers demonstrated high pain detection accuracy (up to 80 percent) and concluded that “fMRI with SVM learning can assess pain without requiring any communication from the person being tested.” They, however, suggested additional tasks for researchers to undertake before their findings can be used in clinical settings.
A successful replication of their experiments could be beneficial, not only to patients, but also to medical equipment manufacturers. Pain is a common problem that everyone may want to get rid off, but the unfortunate truth is that localizing the source of the problem to ensure effective diagnosis is often difficult. Researchers understand that most times people, when asked by physicians, cannot pin down the source of their pain, hence the focus on developing a tool that can take the guesswork out of the situation.