Allergies, Author Interviews, Dermatology, JAMA, Stanford, Technology / 03.03.2018
AI Trained Computer Program Can Monitor Health Forums To Detect Adverse Drug Reactions
MedicalResearch.com Interview with:
[caption id="attachment_40358" align="alignleft" width="200"]
Dr. Sarin[/caption]
Kavita Sarin, M.D., Ph.D.
Assistant Professor of Dermatology
Stanford University Medical Center
MedicalResearch.com: What is the background for this study? What are the main findings?
Response: Drug reactions occur in the majority of patients undergoing cancer therapies. Half of serious drug reactions are detected after market approval which can result in painful complications and interruption in therapy. Post-market drug surveillance platforms such as FDA monitoring rely on medical publications and physician reporting and take time to identify trends. We sought to determine if we could identify trends in patient discussions in internet health forums to more rapidly identify chemotherapeutic drug reactions. We chose skin reactions as a proof-of-principle because patients can more easily describe what they see on their skin.
Julia Ransohoff, a medical student, and Azadeh Nikfarham, an informatics postdoctoral fellow trained a computer to recognize when a patient undergoing anti-cancer treatment with PD-1 antagonists or EGFR-inhibitors described a drug reaction in their internet forum posts.
Dr. Sarin[/caption]
Kavita Sarin, M.D., Ph.D.
Assistant Professor of Dermatology
Stanford University Medical Center
MedicalResearch.com: What is the background for this study? What are the main findings?
Response: Drug reactions occur in the majority of patients undergoing cancer therapies. Half of serious drug reactions are detected after market approval which can result in painful complications and interruption in therapy. Post-market drug surveillance platforms such as FDA monitoring rely on medical publications and physician reporting and take time to identify trends. We sought to determine if we could identify trends in patient discussions in internet health forums to more rapidly identify chemotherapeutic drug reactions. We chose skin reactions as a proof-of-principle because patients can more easily describe what they see on their skin.
Julia Ransohoff, a medical student, and Azadeh Nikfarham, an informatics postdoctoral fellow trained a computer to recognize when a patient undergoing anti-cancer treatment with PD-1 antagonists or EGFR-inhibitors described a drug reaction in their internet forum posts.




























