Analytics And Machine Learning Framework For Actionable Intelligence From Clinical And Omics Data

Ravishankar Krishnan Iyer (Inventor), Arjun Prasanna Athreya (Inventor), Richard M Weinshilboum (Inventor), Liewei Wang (Inventor), William V Bobo (Inventor), Mark A. Frye (Inventor)

Research output: Patent

Abstract

The present disclosure provides methods for accurately predicting the dynamics of symptom response to drugs or other interventions for the treatment of major depressive disorder or other psychological conditions. These methods can allow for a shortening of the time period necessary for the evaluation of a drug or other therapeutic intervention. These predictive methods are based on measured and/or self-reported symptom severity measures at two or more points in time. These measures are then discretized into symptom classes (e.g., low, moderate, severe) and the symptom classes are then applied to the predictive model to predict the progression of symptoms and/or the effectiveness of a drug or other therapeutic intervention. The predictive methods may be augmented by metabolomics data, genomics data, or other objective measures taken from a patient, allowing the use of objective physiological measures to diagnosis and treat psychological conditions heretofore diagnosed and assessed using only subjective, self-reported measures.
Original languageEnglish (US)
U.S. patent number11869633
StatePublished - Jan 9 2024

Fingerprint

Dive into the research topics of 'Analytics And Machine Learning Framework For Actionable Intelligence From Clinical And Omics Data'. Together they form a unique fingerprint.

Cite this