Platform for assessing and treating individuals by sourcing information from groups of resources

Abstract

Disclosed embodiments include a server computer system that can create a patient profile identifying a group of individuals including a user of a client device and only one patient corresponding to an individual other than the user of the client device. The patient profile can include an assessment and a treatment for the patient based on the assessment. The server computer system can receive, from the client device over a computer network, data values selected by the user of the client device, where the data values are indicative of observations of the patient's activity. The server computer system can further update the patient profile based on the received data values such that the data values influence the treatment, and send, to the client device over the computer network, a message including guidance for the user of the client device to implement the treatment.

1 . (canceled) 
     
     
         2 . A method comprising:
 obtaining, by a computer system, a first dataset including indicators of a plurality of symptoms experienced by a patient, each symptom being associated with a condition and characterized by at least one severity value for the symptom;   discovering, by the computer system, based on the first dataset, a coexistence of simultaneous conditions that are independent of each other but contribute to at least some of the plurality of symptoms, wherein discovering the coexistence of simultaneous conditions comprises:
 determining causal relationships between dimensions of a plurality of other datasets associated with other patients based on a causality algorithm that discovers relationships between unclassified combinations of symptoms or conditions and treatments; and 
 classifying the first dataset as similar to a second dataset of the plurality of other datasets based on the plurality of symptoms in the first dataset and the causal relationships between the dimensions of the second dataset; 
   deriving, using a data mining algorithm, a vector of scores for each of the plurality of other datasets that represents a fitness of a given treatment to a set of symptoms or conditions in a respective dataset of the plurality of other datasets;   training the causality algorithm based on the vector of scores for each of the plurality of other datasets to improve classification and reclassification of the first dataset as being similar to selected datasets in the plurality of other datasets; and   selecting, by the computer system, a treatment for the simultaneous conditions based on a result of the classification of the first dataset as being similar to the selected dataset.   
     
     
         3 . The method of  claim 2 , further comprising:
 receiving a new severity value for a first symptom associated with the first dataset;   updating the first dataset to include the new severity value; and   reclassifying the first dataset as similar to a third dataset of the plurality of other datasets based on the update to the first dataset.   
     
     
         4 . The method of  claim 2 , further comprising:
 receiving contextual information indicative of an occurrence of an event related to the patient's activity, wherein the contextual information indicates any of a change in the patient's activity, a location of the patient when the event occurred, an environmental condition at the patient's location when the event occurred, or a point in time when the event occurred;   updating the first dataset with the contextual information; and   reclassifying the first dataset as similar to a third dataset of the plurality of other datasets based on the update to the first dataset.   
     
     
         5 . The method of  claim 2 , wherein selecting the treatment comprises selecting a measurable goal for achievement by the patient, and wherein the method further comprises:
 causing an electronic message to be sent to a client device, the electronic message including the selected measurable goal.   
     
     
         6 . The method of  claim 5 , further comprising:
 tracking a progress of the measurable goal and electronically communicating suggestions to the client device for additional actions depending on the progress, wherein the additional actions are identified based on a symptom impacted by the measurable goal; and   automatically updating the first dataset with the measurable goal and the tracked progress.   
     
     
         7 . The method of  claim 5 , wherein selecting the measurable goal comprises selecting the measurable goal based on a measure of progress of a patient associated with the selected dataset when the patient associated with the selected dataset implemented the measurable goal. 
     
     
         8 . The method of  claim 7 , wherein selecting the measurable goal comprises:
 detecting an update to the selected dataset; and   modifying the measurable goal based on the update to the selected dataset.   
     
     
         9 . The method of  claim 2 , wherein the severity value for a first symptom is based on at least one of an intensity value, a frequency value, or a duration value of the first symptom. 
     
     
         10 . The method of  claim 2 , wherein the severity value for a first symptom is based on at least one of an intensity value, a frequency value, or a duration value that is adjusted by an age value or a gender value for the patient. 
     
     
         11 . The method of  claim 2 , wherein a symptom of the plurality of symptoms for one of the simultaneous conditions is masked by another of the simultaneous conditions. 
     
     
         12 . The method of  claim 2 , wherein the causality algorithm comprises a Bayesian network. 
     
     
         13 . A system comprising:
 at least one processor; and   at least one non-transitory computer readable storage medium storing instructions, execution of which by the at least one processor causes the system to:
 obtain a first dataset including indicators of a plurality of symptoms experienced by a patient, each symptom being associated with a condition and characterized by at least one severity value for the symptom; 
 discover, based on the first dataset, a coexistence of simultaneous conditions that are independent of each other but contribute to at least some of the plurality of symptoms, wherein discovering the coexistence of simultaneous conditions comprises:
 determining causal relationships between dimensions of a plurality of other datasets associated with other patients based on a causality algorithm that discovers relationships between unclassified combinations of symptoms or conditions and treatments; and 
 classifying the first dataset as similar to a second dataset of the plurality of other datasets based on the plurality of symptoms in the first dataset and the causal relationships between the dimensions of the second dataset; 
 
 derive, using a data mining algorithm, a vector of scores for each of the plurality of other datasets that represents a fitness of a given treatment to a set of symptoms or conditions in a respective dataset of the plurality of other datasets; 
 train the causality algorithm based on the vector of scores for each of the plurality of other datasets to improve classification and reclassification of the first dataset as being similar to selected datasets in the plurality of other datasets; and 
 select a treatment for the simultaneous conditions based on a result of the classification of the first dataset as being similar to the selected dataset. 
   
     
     
         14 . The system of  claim 13 , wherein the instructions when executed further cause the system to:
 receive a new severity value for a first symptom associated with the first dataset;   update the first dataset to include the new severity value; and   reclassify the first dataset as similar to a third dataset of the plurality of other datasets based on the update to the first dataset.   
     
     
         15 . The system of  claim 13 , wherein the instructions when executed further cause the system to:
 receive contextual information indicative of an occurrence of an event related to the patient's activity, wherein the contextual information indicates any of a change in the patient's activity, a location of the patient when the event occurred, an environmental condition at the patient's location when the event occurred, or a point in time when the event occurred;   update the first dataset with the contextual information; and   reclassify the first dataset as similar to a third dataset of the plurality of other datasets based on the update to the first dataset.   
     
     
         16 . The system of  claim 13 , wherein selecting the treatment comprises selecting a measurable goal for achievement by the patient, and wherein the instructions when executed further cause the system to:
 cause an electronic message to be sent to a client device, the electronic message including the selected measurable goal.   
     
     
         17 . The system of  claim 16 , wherein the instructions when executed further cause the system to:
 track a progress of the measurable goal and electronically communicating suggestions to the client device for additional actions depending on the progress, wherein the additional actions are identified based on a symptom impacted by the measurable goal; and   automatically update the first dataset with the measurable goal and the tracked progress.   
     
     
         18 . The system of  claim 16 , wherein selecting the measurable goal comprises selecting the measurable goal based on a measure of progress of a patient associated with the selected dataset when the patient associated with the selected dataset implemented the measurable goal. 
     
     
         19 . A non-transitory computer readable storage medium storing instructions, execution of which by one or more processors causes the one or more processors to:
 obtain a first dataset including indicators of a plurality of symptoms experienced by a patient, each symptom being associated with a condition and characterized by at least one severity value for the symptom;   discover, based on the first dataset, a coexistence of simultaneous conditions that are independent of each other but contribute to at least some of the plurality of symptoms, wherein discovering the coexistence of simultaneous conditions comprises:
 determining causal relationships between dimensions of a plurality of other datasets associated with other patients based on a causality algorithm that discovers relationships between unclassified combinations of symptoms or conditions and treatments; and 
 classifying the first dataset as similar to a second dataset of the plurality of other datasets based on the plurality of symptoms in the first dataset and the causal relationships between the dimensions of the second dataset; 
   derive, using a data mining algorithm, a vector of scores for each of the plurality of other datasets that represents a fitness of a given treatment to a set of symptoms or conditions in a respective dataset of the plurality of other datasets;   train the causality algorithm based on the vector of scores for each of the plurality of other datasets to improve classification and reclassification of the first dataset as being similar to selected datasets in the plurality of other datasets; and   select a treatment for the simultaneous conditions based on a result of the classification of the first dataset as being similar to the selected dataset.   
     
     
         20 . The non-transitory computer readable storage medium of  claim 19 , wherein execution of the instructions further causes the one or more processors to:
 receive a new severity value for a first symptom associated with the first dataset;   update the first dataset to include the new severity value; and   reclassify the first dataset as similar to a third dataset of the plurality of other datasets based on the update to the first dataset.   
     
     
         21 . The non-transitory computer readable storage medium of  claim 19 , wherein selecting the treatment comprises selecting a measurable goal for achievement by the patient, and wherein the instructions when executed further cause the system to:
 cause an electronic message to be sent to a client device, the electronic message including the selected measurable goal.