System and method for determining side-effects associated with a substance

A non-transitory computer readable medium that includes instruction code that facilitates determining adverse effects associated with a substance, the instruction code being executable by a machine for causing the machine to perform acts comprising:

• controlling a first recurrent neural network (RNN) to identify a first portion of a received data associated with an adverse effect to thereby determine the adverse effect associated with the received data;
• controlling a second RNN to identify a second portion of the received data associated with a substance and a third portion of the received data that indicates a relationship between the substance and the adverse effect to thereby determine the substance associated with the received data and the relationship between the substance and the adverse effect;
• aggregating and relating the adverse effect, substance, and relationship;
• and
• generating a report to convey the relationship between the substance and the adverse effect,
• wherein the first recurrent neural network corresponds to a long short-term memory (LSTM) recurrent neural network (RNN) that corresponds to a real-value multi-dimensional vector that represents knowledge in the database, and
• wherein the LSTM RNN is configured to learn an effective vector representation of the database when learning to classify whether a word in the received data is related to a disease/symptom, which facilitates leveraging, by the LSTM RNN, textual information about disease and symptom in the database.

A method for determining adverse effects associated with a substance, the method comprising:

• identifying, by a first recurrent neural network (RNN), a first portion of received data associated with an adverse effect to thereby determine the adverse effect associated with the received data;
• identifying, by a second RNN, a second portion of the received data associated with a substance and a third portion of the received data that indicates a relationship between the substance and the adverse effect to thereby determine the substance associated with the received data and the relationship between the substance and the adverse effect;
• aggregating and relating the adverse effect, substance, and relationship;
• and
• generating a report to convey the relationship between the substance and the adverse effect,
• wherein the first RNN is coupled to a terms database that includes a plurality of terms associated with diseases and symptoms,
• wherein the first recurrent neural network corresponds to a long short-term memory (LSTM) RNN that corresponds to a real-value multi-dimensional vector that represents knowledge in the database, and
• wherein the LSTM RNN is configured to learn an effective vector representation of the database when learning to classify whether a word in the received data is related to a disease/symptom, which facilitates leveraging, by the LSTM RNN, textual information about disease and symptom in the database.