Cerner Innovation, Inc.

In some examples, data associated one or more medical presentations of a person is received. A mapping that associates the data to one or more candidate diagnoses is determined. The one or more candidate diagnoses correspond to one or more possible medical conditions associated with the person. A validation score for a first candidate diagnosis, of the one or more candidate diagnoses, is generated based on a set of features associated with the person. The validation score indicates an accuracy of the candidate diagnosis. At least partially in response to the generating of the validation score, an indicator is caused to be provided at a user device. The indicator indicates the validation score.

System, methods and computer storage media are disclosed for providing a decision support tool for reducing readmissions of AMI patients through early prediction of readmission. An AMI patient may be identified using a working diagnosis and/or an elevated troponin level. One or more machine learning models may be utilized to predict readmission at a time prior to discharge. Based on the prediction, an intervening action may be automatically initiated. Further embodiments include training machine learning model(s) to predict readmission of an AMI patient. In some embodiments, a first model may be trained using reference patient data as it existed at a predetermined time following the patient's admission (e.g., 12 hours after admission), and a second model may be trained using reference patient data as it existed at a later time (e.g., discharge). Readmission risk scores from each model may be combined to determine an overall risk for an AMI patient.

Methods, systems, and computer-readable media are disclosed herein that conduct security penetration testing. In accordance with embodiments, a security extension is run in a web browser in order to record a user interface workflow and to generate a test script of the user interface workflow. The test script is executed in an application in order to perform penetration testing of the user interface workflow, in some embodiments. Based on the outcomes of the penetration testing, a security report may be generated in order to identify one or more security vulnerabilities in the user interface workflow.

Methods, systems, and computer-readable media are disclosed that the likelihood that a medical order for multiple pharmaceutical drugs may be stolen or diverted. Generally, a current data set for a medical order for pharmaceutical drugs is received. Each of the drugs is associated with a set of features. An impact score is generated for each of the features for each drug based on historical effects. Test data is also used to evaluate the diversion prediction accuracy of a plurality of machine learning models, when compared to historical diversion data for the drugs. The most accurate machine learning model is utilized to make a diversion probability prediction for those features having the highest impact scores, for the drugs in the medical order. A recommended action is generated and provided based on the diversion probability.

Systems, methods, and storage media useful in a healthcare cloud computing platform to transform, deduplicate and store medical data from third-party databases to a patient's primary medical record in the healthcare cloud computing platform. Exemplary implementations may: load and read data from third-party databases, and determine if it is duplicative of what is in the patient's primary record. Other embodiments, provide a method for ranking medical data from two different third-party databases to determine which medical data should be written to the patient's primary medical record in the healthcare computing platform.

Methods, systems, and computer-readable media are provided for delivering healthcare records with low latency. Healthcare data is collected from various disparate healthcare data sources. The data is filtered in accordance with routing rules to identify healthcare data to deliver to a processing node. The routing rules specify that healthcare data from a particular originating source of a particular data type is to be delivered to a particular processing node. The healthcare data is converted to a local format for use by a computing solution. This system of delivering healthcare data with low latency ensures that the data is delivered to the correct location in the correct format, even if the routing rules change.

Methods, systems, and computer-readable media are disclosed herein for generating a disease-agnostic data model that can be used to predict the onset of multiple chronic diseases in individual patients. In an aspect, the data model is made by autonomously selecting features from longitudinal medical records of patients having chronic diseases that will become predictors for the onset of a chronic disease. The features are vectorized around a disease onset date and processed through a recurrent neural network to produce the data model. Then, the data model may leveraged to predict, for new longitudinal medical records that are input, a future time period when another patient is predicted to experience the onset of the chronic disease. The same data model may utilized to make predictions for multiple chronic diseases.

Systems and methods are described for procedurally-based decision support using ontology-based classification of database records. The procedural decision support can facilitate extraction of contextually relevant data from a database. The data may be formatted for compatibility with a knowledge-based data library using one or more scripts and populated in the library as an entity. Classification of the entity can be reasoned using the available data. One or more classifications of the entity may be returned to the procedural decision support to facilitate computation of a recommendation.

A system and computer-implemented method includes querying a data source for treatment plan templates based on a medical condition of a patient. Raw data related to treatment plan templates is received from the data source. The raw data includes text information. Raw data is parsed, and tags are identified. elements are extracted from the tags using complex regular expression and keywords. Formatted data is constructed from the elements in a machine-readable format. The elements are arranged in a hierarchical structure within the formatted data. Structured data having data frames is generated based on the formatted data. The structured data is provided to a medical provider for review. An update in the structured data is received from the medical provider based on a deviation in schedule provided in the treatment plan templates. The treatment plans are generated based on incorporation of the update into the structured data.

Methods, computer systems, and computer-storage medium are provided for providing clinical information for a person, such as a test result, in real time where the information is automatically pushed to a selected notification device of a physician. A graphical representation is generated for a clinician to select clinical notification options. Received selections create a notification to be automatically sent to one or more clinician devices. Automatic notifications reduce delay in clinician action when new clinician information is provided.