Adaptive medical documentation system

Abstract

Adaptive medical data collection for medical entities may involve triggering an analysis of electronic records in response to information input into an Electronic Medical Record (EMR) of a patient. Determining a potential condition for the patient based on the analysis. Identifying additional information indicated as relevant to the potential condition of the patient, and generating a request for the identified additional information.

What is claimed is: 
     
         1 . A computerized method carried out by at least one server having at least one processor for adaptive medical data collection, the method comprising:
 triggering a probabilistic analysis of electronic records in response to a first set of information input into an Electronic Medical Record (EMR) of a patient;   determining, with the at least one processor, a first potential condition for the patient based on the probabilistic analysis;   identifying, with the at least one processor, a second set of information indicated as relevant to the first potential condition of the patient;   generating, with the at least one processor, a first request for the second set of information by identifying an established collection of information associated with the first potential condition of the patient and providing the first request for the second set of information in a preformatted medical form established for the collection of the second set of information, wherein the preformatted medical form is populated using the established collection of information associated with the first potential condition of the patient, and wherein the preformatted medical form is automatically adapted based on the first set of information input into the EMR;   receiving at least a portion of the second set of information;   repeating the triggering of the probabilistic analysis; and   re-performing, with the at least one processor, the probabilistic analysis using the second set of information to identify a second potential condition.   
     
     
         2 . The method of  claim 1 , further comprising
 identifying a third set of information relevant to the second potential condition of the patient based on the re-performed probabilistic analysis; and   generating, with the at least one processor, a second request for the third set of information wherein the preformatted medical form is automatically adapted based on the second set of information received subsequent to the first request.   
     
     
         3 . The method of  claim 1 , wherein triggering the probabilistic analysis of the EMR comprises triggering an analysis of ontologies of arbitrary contexts, clinical data records, practice data records, clinical guidelines, or EMRs of prior patients of a medical entity. 
     
     
         4 . The method of  claim 1 , wherein triggering comprises recognizing an input of data into the EMR of the patient. 
     
     
         5 . The method of  claim 1 , wherein triggering the probabilistic analysis comprises triggering an application of a machine learned model to the EMR. 
     
     
         6 . The method of  claim 5 , wherein triggering the application of the machine learned model comprises a triggering an application of a Bayes Net model trained using a Markov Chain Monte Carlo (MCMC) method, and an Expectation Maximization method based model. 
     
     
         7 . The method of  claim 1 , wherein determining the first potential condition for the patient comprises determining a probability the first potential condition applies to the patient, and comparing the probability to a predetermined probability threshold. 
     
     
         8 . The method of  claim 1 , wherein triggering the probabilistic analysis comprises triggering an application of a first machine learned model to the EMR, and identifying other information regarding the first potential condition of the patient comprises applying a second machine learned model to the second set of information. 
     
     
         9 . A system for adaptive medical data collection, the system comprising:
 at least one memory operable to store Electronic Medical Records (EMRs) and other medical data relating to conditions of patients of a medical facility; and   a processor configured to:   trigger a probabilistic analysis of electronic records in response to a first set of information input into an EMR of a patient, the probabilistic analysis comprising a probabilistic network of associated terms derived from the other medical data;   determine a first potential condition for the patient based on the probabilistic analysis;   identify a second set of information indicated as relevant to the first potential condition of the patient from the probabilistic network; and   generate a first request for the second set of information by identifying an established collection of information associated with the first potential condition of the patient and providing the first request for the second set of information in a preformatted medical form established for the collection of the second set of information, wherein the preformatted medical form is populated using the established collection of information associated with the first potential condition of the patient, and wherein the preformatted medical form is automatically adapted based on the first set of information input into the EMR and data input into the EMR subsequent to the generation of the first request;   receive at least a portion of the second set of information   repeat the triggering of the probabilistic analysis; and   re-perform the probabilistic analysis using the second set of information to identify a second potential condition.   
     
     
         10 . The system of  claim 9 , further comprising:
 identifying a third set of information relevant to the second potential condition of the patient based on the re-performed probabilistic analysis; and   generate a second request for the third set of information wherein the preformatted medical form is automatically adapted based on at least a portion of the second set of information received subsequent to the first request.   
     
     
         11 . The system of  claim 9 , wherein the other medical data comprises ontologies of arbitrary contexts, clinical data records, practice data records, clinical guidelines, or EMRs of prior patients of a medical entity. 
     
     
         12 . The system of  claim 9 , wherein the probabilistic analysis is triggered by a recognition of data input into the EMR of the patient. 
     
     
         13 . The system of  claim 9 , wherein the probabilistic analysis comprises the application of a machine learned model. 
     
     
         14 . The system of  claim 13 , wherein the machine learned model comprises a generative probabilistic model. 
     
     
         15 . A non-transitory computer readable storage medium having stored therein data representing instructions executable by a programmed processor for adaptive medical data collection, the storage medium comprising the instructions for:
 triggering a probabilistic network analysis of electronic records in response to a first set of information input into an Electronic Medical Record (EMR) of a patient;   determining a first potential condition for the patient based on the probabilistic analysis;   identifying a second set of information indicated as relevant to the first potential condition of the patient;   generating a first request for the second set of information by selecting an established collection of information associated with the first potential condition of the patient and providing the first request for the second set of information in a preformatted medical form established for the collection of the second set of information, wherein the preformatted medical form is populated using the established collection of information associated with the first potential condition of the patient, and wherein the preformatted medical form is automatically adapted based on the first set of information input into the EMR;   receiving at least a portion of the second set of information;   repeating the triggering of the probabilistic analysis; and   re-performing the probabilistic network analysis of the EMR using the at least the portion of the second set of information to update at least one probability of the probabilistic network.   
     
     
         16 . The medium of  claim 15 , further comprising:
 identifying a third set of information relevant to a second potential condition of the patient; and   generating, a second request for the third set of information wherein the preformatted medical form is automatically adapted based on at least a portion of the second set of information received subsequent to the first request.   
     
     
         17 . The medium of  claim 16 , wherein when adequate information is not available the instructions further comprise:
 identifying a fourth set of information regarding the second potential condition of the patient based on the third set of information;   updating at least one probability of the probabilistic network; and   generating a third request for the fourth set of information based on the updated probability.   
     
     
         18 . The medium of  claim 15 , wherein the instructions further comprise performing the instructions iteratively until it is determined that adequate information has been requested such that each probability of the probabilistic network is either below a first threshold or above a second threshold. 
     
     
         19 . The medium of  claim 15 , wherein information is requested using electronic forms. 
     
     
         20 . The medium of  claim 15 , wherein triggering comprises recognizing an input of data into the EMR of the patient.