Due to its complex, multi-herb nature, many patients who use Complementary and Alternative Medicine (CAM) do not have full knowledge of the ingredients included in their remedies. Lack of disclosure about CAM can place patients at risk, as some herbal products can have adverse interactions with pharmaceuticals or cause harmful side effects. This proposal seeks to address that challenge by developing a computer-aided expert system that can algorithmically determine the content of a patient's CAM herbal remedy. In the absence of reliable patient recall, the envisioned system employs proven analytics techniques and a known set of data- including historical patient records and patient-reported data, such as patient demographic and symptomatic details-to statistically generate a prescription list. The envisioned analytics engine will be a powerful clinical decision support tool that enhances patient safety and patient-provider communication surrounding CAM use. Phase I activities will generate a prototype for evaluating one frequently encountered condition: the common cold. This prototype will provide a solid foundation for system expansion, in Phase II, to cover a broad range of diseases and conditions.
Despite their growing prevalence, Complementary and Alternative Medicine (CAM) therapies are seldom a topic of discussion between healthcare professionals and patients;patient-provider communication and patient disclosure rates are further complicated by the language barrier (Eisenberg et al. 1993). Lack of communication about CAM can place patients at risk, as some herbal products can have adverse interactions with pharmaceuticals or cause harmful side effects (Kupiec et al. 2005). The computer-aided expert system, as envisioned in this application, will fill a critical void in our healthcare system's ability to thoroughly document CAM usage in patient medication history, equip providers to make more informed clinical decisions, and-by avoidance or earlier detection of herb-drug interactions-improve patient safety and quality of care.
