AUTOMATIC CODING OF PATIENT OUTCOMES
First Claim
1. A system for classifying a health condition of a patient, the system comprising:
- a model creation engine configured to create a medical classification model by at least;
receiving an identification of a clinical feature that is to be associated with a health condition, the identification being provided by one or more of an automated analysis of an electronic medical reference and a manual expert identification of the clinical feature, the clinical feature comprising one or more of the following features;
an identified medication, a clinical event, a microbial culture feature, and a radiology feature,creating a rule that maps the clinical feature to the health condition in a model data repository comprising physical computer storage, wherein the rule reflects a relationship between the clinical feature and the health condition,automatically learning a weight to apply to the rule with a supervised machine learning algorithm by at least analyzing the clinical feature with respect to pre-identified outcomes in a training data set, the training data set comprising first structured clinical event data, the rule reflecting a strength of the relationship between the clinical feature and the health condition, andstoring, in the model data repository, the learned weight associated with the rule for subsequent usage in identifying a patient health condition; and
an outcome identification module comprising computer hardware, the outcome identification module configured to at least;
access patient data corresponding to a patient, the patient data comprising second structured clinical event data stored in an electronic health record (EHR) database,analyze the second structured clinical event data to determine whether the clinical feature exists in the clinical event data,apply the rule and the weight of the medical classification model to the clinical feature to infer a possible health condition of the patient by at least matching the rule with a selected clinical feature in the second structured clinical event data corresponding to the patient, andprovide one or more billing codes configured to be processed by a medical billing system, said one or more billing codes being based at least in part on the possible health condition of the patient.
1 Assignment
0 Petitions
Accused Products
Abstract
Systems and methods can mine structured clinical event data in an electronic health record (EHR) system to determine patient outcomes. Mining the structured clinical event data instead of or in addition to mining discharge summaries can increase the accuracy of patient outcome identification. Sophisticated language models can be used to extract outcomes from discharge summaries while also inferring outcomes from cues or hints contained in the structured clinical event data. For example, the clinical event data can include information regarding treatments and medications prescribed by clinicians to specifically manage patient complications; thus, presence or absence of relevant treatments in the clinical event data can provide independent indicators to disambiguate cases where current language processing approaches fail.
-
Citations
29 Claims
-
1. A system for classifying a health condition of a patient, the system comprising:
-
a model creation engine configured to create a medical classification model by at least; receiving an identification of a clinical feature that is to be associated with a health condition, the identification being provided by one or more of an automated analysis of an electronic medical reference and a manual expert identification of the clinical feature, the clinical feature comprising one or more of the following features;
an identified medication, a clinical event, a microbial culture feature, and a radiology feature,creating a rule that maps the clinical feature to the health condition in a model data repository comprising physical computer storage, wherein the rule reflects a relationship between the clinical feature and the health condition, automatically learning a weight to apply to the rule with a supervised machine learning algorithm by at least analyzing the clinical feature with respect to pre-identified outcomes in a training data set, the training data set comprising first structured clinical event data, the rule reflecting a strength of the relationship between the clinical feature and the health condition, and storing, in the model data repository, the learned weight associated with the rule for subsequent usage in identifying a patient health condition; and an outcome identification module comprising computer hardware, the outcome identification module configured to at least; access patient data corresponding to a patient, the patient data comprising second structured clinical event data stored in an electronic health record (EHR) database, analyze the second structured clinical event data to determine whether the clinical feature exists in the clinical event data, apply the rule and the weight of the medical classification model to the clinical feature to infer a possible health condition of the patient by at least matching the rule with a selected clinical feature in the second structured clinical event data corresponding to the patient, and provide one or more billing codes configured to be processed by a medical billing system, said one or more billing codes being based at least in part on the possible health condition of the patient. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10)
-
-
11. A method of classifying a health condition of a patient, the method comprising:
-
receiving an identification of clinical features associated with one or more outcomes of patient care; storing rules in a model data repository, the rules mapping the clinical features to the one or more outcomes; using a machine learning process to automatically learn weights to apply to the rules by analyzing the clinical features with respect to known outcomes of patients stored in a training data set, the training data set comprising first structured clinical event data in an electronic health record (EHR) system; and storing, in the model data repository, the learned weights together with the rules for subsequent inferring of possible outcomes of patient care from second structured clinical event data; wherein at least said automatically learning the weights is implemented by a computer system comprising computer hardware. - View Dependent Claims (12, 13, 14, 15, 16, 17, 18, 19, 20, 21)
-
-
22. Non-transitory physical computer storage comprising instructions stored therein for implementing, in one or more processors, operations for classifying a health condition of a patient, the operations comprising:
-
accessing patient data corresponding to a patient, the patient data comprising clinician notes associated with the patient and structured clinical event data stored in an electronic health record (EHR) data repository; analyzing the clinician notes to extract language features; analyzing the structured clinical event data to extract clinical features; and applying a probabilistic function to the language features and the clinician features to identify one or more possible outcomes associated with care of the patient.
-
- 23. The non-transitory physical computer storage of claim 23, wherein the probabilistic function comprises a logistic regression function.
-
27. A method of classifying a health condition of a patient, the method comprising:
by a computer system comprising computer hardware; accessing patient data corresponding to a patient, the patient data comprising structured clinical event data stored in an electronic health record (EHR) data repository; analyzing the structured clinical event data to extract clinical features; and applying a probabilistic function to the clinician features to identify one or more outcomes associated with care of the patient.
- 28. The method of claim 28, wherein the probabilistic function comprises a logistic regression function.
Specification