Cerner Innovation, Inc.

Sasanka Are

Andrew Roberts

Kanakasabha K Kailasam

Douglas S McNair

John Matthew Sugden

Jeffrey W Wall

John Christopher Murrish

Mario Manese

William Stadler

Bryce Schaffter

Brian Thurston

Randall Wald

J D Martindale

Nicholas Jingyi Ma

Janae Lenox

Pedro Alves

A decision support method and system is provided for monitoring and treating pediatric obesity. Embodiments include generating obesity risk curves corresponding to obesity risk levels, for example, severe and morbid obesity risk levels. Generating obesity risk curves depends on predicting at least one health proxy such as, for example, spend data and chronic conditions. Generating severe obesity curves depends on an age-dependent multiplier. An obesity risk level is assigned to a target pediatric patient using the obesity risk curves dependent on the age-dependent multiplier. In some aspects, an intervening response is initiated based on the assigned obesity risk level.

Decision-support tools for pediatric obesity

Methods, systems, and computer-readable media are provided for managing health status of persons with a chronic condition including providing dynamic, adaptive monitoring, detection, and prediction of suicide risk to a person at risk for suicide related to mental health. In an embodiment, a patient-assessment application is used to obtain information periodically on a patient's mental health status. Based on this information, a logistic regression model is employed to determine a patient's probability of attempting suicide. The probability is evaluated against a default threshold to determine if the patient's status has changed significantly, and if the threshold is exceeded, an action is evoked. In one embodiment, the action includes providing notice to the patient's care provider, caregiver, or case manager.

Decision support for managing mental health conditions

A decision support tool is provided for identifying and assisting clinicians with patient ventilator asynchrony. The information used to make the identification may include data from a patient's ventilator including the volume, flow, and pressure associated with that ventilator. At least some of this information may be used to compute one or more features for a time series of the data received for the patient. These features may be used in connection with heuristic rules and machine learning algorithms to identify instances of patient ventilator asynchrony. Based on the identification, one or more intervening actions may be initiated to reduce the impact of patient ventilator asynchrony.

Patient ventilator asynchrony detection

Embodiments of the invention provide decision support services, including an enhanced user interface. A reason for a clinical visit is determined and an initial workflow may be provided via the user interface during a clinical visit. The workflow may include a set of initial user interface elements that are determined based on a context associated with the clinical visit. The set of initial user interface elements may include a first initial interface element associated with a pre-identified clinical concept. During the clinical visit, a first suggested interface element can be provided. The first suggested interface element is generated during the workflow based on detecting a selection of the first initial interface element. The first suggested interface element can be associated with a first suggested clinical concept that is related to the pre-identified clinical concept.

User interface for clinical decision support

Methods, systems, and computer-readable media for a system and method are provided for assessing the value of predictive models monitoring medical conditions. Trends in an individual's medical condition are determined based on monitoring values, and the trends are associated with the actions performed in response to the monitoring values and in accordance with the predictive models. The trends may indicate that an individual's condition is improving, worsening, or remaining stable in response to the action taken. Models used for multiple conditions for an individual or for a population of individuals may be assessed in this manner to generate knowledge regarding the performance of the models based on the actions taken. This knowledge may be used to assess the value of the models in terms of the models' performance and may provide insight on way to improve the models.

Monitoring predictive models

Methods and systems for managing patient attributions are provided. Interaction events between clinicians and the patient are identified, and using times associated with each interaction, a time series of the interactions for each clinician may be constructed. Care responsibility curves measuring a clinician's care responsibility level over time may be generated using the time series, an initial care responsibility level assigned to each interaction and a rate of decay for each interaction, which may be based on the type of action and type of clinician who interacted with the patient. A care responsibility score for each clinician may be determined from the clinician's care responsibility curve, and a patient-attribution assignment record may be created to attribute the patient to one of the clinicians based on a ranking of the clinicians' care responsibility scores.

Systems and methods for managing caregiver responsibility

A decision support tool is provided for predicting uterine contractions. The predicted contractions are determined from measurements of uterine activity (UA). The contraction forecast may be made using a plurality of trained predictive models. The forecasts are formed with linear regressive models based, at least in part, on UA data from a reference population. The predicted contractions may be predictions of contraction duration, contraction peak, and time between contractions. In this way, these predicted contractions may be used for decision support for care plans during labor, such as increased monitoring and/or modifying the care plan.

Forecasting uterine activity

A decision support tool is provided for predicting the neonatal vitality scores of a fetus during delivery, the scores being an indicator of future health for the infant anticipated to be born within a future time interval, measured as time to birth. The predicted neonatal vitality score is determined from measurements of physiological variables monitored during labor, such as uterine activity and fetal heart rate. Fetal heart rate variability and patterns may be detected and computed using the monitored physiological variables, and neonatal vitality scores may be predicted based, at least in part, on the variability metrics and fetal heart rate patterns. Scores may be predicted for different delivery methods, such as vaginal delivery or cesarean delivery, for different time-to-birth intervals. In this way, these scores may be used for decision support for care plans during labor, such as increased monitoring and/or modifying the delivery type.

Forecasting neonatal vitality

A decision support tool is provided for predicting a patient's length of stay within a healthcare unit, such as the emergency department. The predicted length of stay may be determined using patient information and facility information, which includes information about the department and the facility in which the department is located. The patient information and the facility information may be used to determine feature values input into a plurality of machine learning models. The models may be used sequentially such that initial models are used to predict variables relating to the patient's length of stay and output of such models is used with a length-of-stay model to determine the predicted length of stay. One or more response actions may be automatically initiated based on the predicted length of stay. Such response actions may include resource management actions to allocate resources within the healthcare unit.

Decision support tool for determining patient length of stay within an emergency department

Improved risk categorization is provided for clinical decision support and forecasting future health care spend. A risk index is provided that improves on other risk stratification models by synthesizing electronic medical records and health questionnaires with an individual patient's claim histories. Machine learning algorithms catalogue patients into distinct group clusters, based on risk which may be associated with annual health care spending, thereby enabling administrators to forecast future health care spending on the individual and population level.

Machine learning clinical decision support system for risk categorization

A decision support tool is provided for discharging a patient by predicting the probability of a patient's readmission with pneumonia based on information available prior to discharge. The information used to make the prediction may include labs, vitals, diagnoses, and medications from prior encounters and from the current encounter. At least some of this information may be used to compute one or more severity metrics for the patient, such as a cancer score, an epilepsy or seizure score, a pneumococcal pneumonia score, and an instability score, to be input into one or more prediction models. An ensemble of machine learning models may be applied to the patient information to generate a prediction of that patient being readmitted with pneumonia within a future time interval. Based on the prediction, one or more intervening actions may be initiated to reduce the probability of readmission.

Pneumonia readmission prevention

Systems, methods and computer-readable media are provided for predicting probability of a clinical invoice being paid by a specified date. A clinical invoice is a request for payment. The clinical invoice can take the form of an insurance claim, bill to a person (e.g., self-insured, co-pay), or submission to a government entity (e.g., Medicare, Medicaid). Healthcare facilities do not know how long they will have to wait between submitting an invoice and receiving compensation from government, insurance, or other payers. The methods described herein can be used to estimate the probability of payment occurring by a specified date. This information can be used to triage outstanding claims for investigation and to improve outstanding cash forecasts. The technology described herein uses survival curves to estimate when an invoice will be paid.

Projecting time-to-pay of healthcare invoices

Methods and systems for predicting deterioration of a patient's condition within a future time interval based on a time series of values for monitored physiological variables measured from a patient, and in some instances, providing advanced notice to clinicians or caregivers when deterioration is forecasted or modifying treatment for the patient are provided. In particular, deterioration of a patient's condition is based on a Hopf bifurcation model and is predicted using a ratio of deviations for monitored physiological variables. A ratio of deviations relates the standard deviation and root mean square of successive differences for a set of physiological values measured over time. The RoD for one or more variables, such as heart rate, respiratory rate, and blood pressure, may be used to predict the likelihood of the patient's condition deteriorating into an unstable state as what occurs in a Hopf bifurcation.

Early warning system and method for predicting patient deterioration

Methods and systems for managing care team assignment's for individuals, such as a patient, are provided. Embodiments include receiving indicators of actions that are initiated by a clinician and associated with a patient's care. Using times associated with each action, a time series indicating contribution levels for each clinician may be constructed. Care contribution curves measuring a clinician's care contribution level over time may be generated using the time series and a rate of decay for each action, which may be based on the type of action and the role of the clinician who initiated the action. A care contribution score for each clinician may be determined from the clinician's care contribution curve, and a care team assignment for the patient may be created based on care contribution scores for each clinician who initiated an action.

Growing community of inventors

Kansas City, MO, United States of America

Sasanka Are