Cerner Innovation, Inc.

Other

Oracle International Corporation

Cerner Corporation

Douglas S McNair

Kanakasabha K Kailasam

John Christopher Murrish

Sasanka Are

Kiran Kambhampati

Tanuj Gupta

David Cohen

J Bryan Ince

Josh Smith

Alex Vickers

William Stadler

Mark A Hoffman

Michael Alan Ash

Bharat Sutariya

Hugh H Ryan

Leo V Perez

Andrew Roberts

Brian J Lancaster

John Kuckelman

Thomas Anthony Fangman

Michael E Yarbrough

Kent D Parkins

Mario Manese

John H Gragg

Pedro Alves

Systems, methods and computer-readable media are provided for identifying patients having an elevated near-term risk of chronic kidney disease (CKD) progression, including predicting an individual's risk of progression to Stage 3 CKD within a future time interval, which may be up to 36 months. Based on the prediction, appropriate care providers may be notified so that the risk of CKD progression may be mitigated. In an embodiment, measurements of physiological variables are obtained, including serial measurements for uric acid levels from a longitudinal time series of serum or plasma samples spanning the previous two to five years. An annualized uric acid velocity of the patient is determined and used to generate a multivariable mathematical model for determining a likelihood of risk for developing Stage 3 CKD within 36 months.

Predicting newly incident chronic kidney disease

Technologies are provided for an improved classifier apparatus and processes for improving the accuracy of classification technology including example applications of such classifiers. A process includes applying clustering to variables contributing to the classification task. The clusters may be represented in a 1-dimensional, 2-dimensional, or 3-dimensional matrix that is a spatial abstraction of the interrelationships. A convolutional transformation may be applied to the matrix so as to reduce the effective dimensionality of the classification problem and improve the signal-to-noise ration. A deep learning neural network method may be applied to the transformed network to generate an improved classification model, which may be utilized by a decision support tool. One embodiment comprises a decision support tool for detecting risk of venous thrombosis and venous thromboembolism (VTE) in a patient, based on phenotype and genomics information.

Classifier apparatus with decision support tool

Various tools are disclosed for providing assistive or augmentative means to enhance the fluency and accuracy of persons having speech disabilities. These technologies may automatically ascertain and dynamically improve the accuracy with which automatic speech recognition (ASR) systems recognize utterances of persons having impaired speech conditions. In an embodiment, digitized audio information about a speaker's utterance is processed to determine a set of candidate words matching the utterance. From these candidate words, a set of concepts is determined using a finite state machine model. A pictogram representing each concept is identified and presented to the speaker so that the speaker may select the pictogram corresponding to the best match of his or her intended meaning associated with the utterance. An action corresponding to speaker's selection then may be performed. For example, displaying or synthesizing speech from textual information describing the selected concept.

Tool for assisting people with speech disorder

Systems, methods, and computer-readable storage media are provided for determining and ascribing clinical conditions or diagnoses to patients and provide them to a caregiver, such as attending clinicians or other appropriate health services personnel. In particular, embodiments of the disclosure determine likely phenotypic findings that are salient to the decision-making context for a current human patient, based on anticipative sequence-mining and trajectory-mining. A sequential pattern mining and sequence itemset matching system is provided for determining likely, temporally-relevant concepts that are manifested in the information that is produced during the course of a patient's care. A clinician or caregiver may be provided the sequence itemset matching by generating a list or notice. In addition or alternatively, the results may be stored in an EHR associated with the patient.

Clinical decision support system using phenotypic features

Systems, methods, and computer-readable media are provided for identification of patients having an elevated near-term risk of chronic kidney disease progression, including quantitatively predicting whether or not an elevated risk of progression of Stage 3 or Stage 4 chronic kidney disease is likely within a time interval of up to 36 months subsequent to computing the prediction. Based on the prediction, appropriate care providers may be notified so that the risk of CKD progression may be mitigated. In some embodiments, serial measurements are obtained of urine osmolality, and a challenge with an AVP V2 antagonist and serum sodium concentration is provided. From a time series based on the serial measurements, estimates of each variable's velocity and/or doubling-time may be determined. These values then may be combined via a multivariable mathematical model for providing a leading indicator of near-term future abnormalities in kidney function.

Predicting chronic kidney disease progression

Systems, methods, and computer-readable media are provided for patient case and care complexity characterization, and detecting matches of an individual patient's record with collections of other patients' records, based on serial, longitudinal patterns, for facilitating efficient health services utilization, implementing programs to reduce complexity, preventive medicine, and risk management in health care. In an embodiment, time series are formed by electronically representing information pertaining to successive longitudinal episodes of health services utilization and the circumstances in which the episodes were incurred; calculating time-series K-nearest-neighbor clusters and distances for each combination; determining the cluster to which a given candidate patient complexity record is nearest, and prescribing one or more interventions specific to hazards that are characteristic of trajectories that are members of that cluster, or that are deemed to be relevant to mitigating those hazards, thereby preventing the adverse outcomes and subsequent excess utilization that are prevalent in that cluster.

Discovering context-specific complexity and utilization trajectories

Decision support technology is provided for use with patients who may be prone to a cardiovascular condition such as acute coronary syndromes. A mechanism is provided to determine a patient's risk for experiencing a cardiovascular ischemic event at a future time interval based on temporal patterns determined using physiological parameters of the patient such as serum or blood uric acid and/or C-reactive protein (CRP). A forecast or score may be determined indicating whether or not temporal patterns merit intervention to prevent occurrence or reoccurrence of ischemic events, or for determining adherence to or efficacy of treatment or preventive interventions. Based on the forecast or score, appropriate response action such as automatically issuing an alert or notification to a caregiver associated with the patient, may be determined, recommended, or implemented.

Determining a cardiovascular ischemic event and decision support tool

A system, method and article of manufacture are presented for improving therapy such as adjustment of a chronotherapeutic pharmaceutical regimen. Physiological variables are measured longitudinally and a time series of the measurements is constructed. In some cases, a time series is pre-whitened and transformed to a frequency spectrum while applying multi-taper filtering, and entropy or other statistical measures are calculated for the power spectral distribution. Improved timing, medication and dosage are individually or collectively improved and/or verified through successive testing. An improvement is illustrated for hypertension, using medication to achieve autonomic control and to reduce blood pressure variability and to reduce spectral diversion.

Personal analysis and chronotherapy

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

Systems and methods are provided for evaluating an alarm condition for a monitored patient in a population of one or more patients. One or more physiological parameters pertaining to the patient, or physiological variables, are used to form a time series describing the patient status. A quantile threshold is determined for a patient. A monitor is initialized and begins generating a binary raw alarm signal. The binary signal is filtered with a low pass filter, and the filtered data is subjected to a quantile operation to determine if a particular sample exceeds the determined quantile threshold. If the quantile threshold is exceeded, then a check is performed to see if the raw binary alarm signal also indicates an alarm. If both the preliminary alarm indication and the raw binary signal indicate an alarm, then an alarm is emitted; otherwise monitoring continues.

Stream-based alarm filtering

Methods and systems for enhanced natural language processing of clinical documentation are provided. Using natural language processing, a clinical condition is extracted from unstructured data within a current electronic document. A clinical ontology identifying itemsets associated with the clinical condition is retrieved, and indicators of relevant clinical concepts, as identified from the ontology, are searched from within the patient's longitudinal record, which comprises documentation from at least a prior encounter. Based on the whether the clinical concepts are present in the patent's record, a confidence is assigned to the NLP-extracted clinical condition, and one or more actions may be performed.

Systems and methods for enhancing natural language processing

Technologies are provided for identifying individuals having a risk of non-adherence to or from a prescribed treatment program; for predicting and the risk, which may be determined as a forecast over a future time span; and evaluating it to further determine or invoke specific actions to mitigate the risk or otherwise improve likelihood of compliance. A singular spectrum analysis (SSA) is utilized to analyze temporal properties of a time series determined from measured or observational data to determine an emergent pattern. Based on this pattern, a risk of non-adherence, including relapse or absconding, over a future time interval by the individual may be determined and utilized to implement an intervening action.

Computer-decision support for predicting and managing non-adherance to treatment

A system, method, and computer-readable media are provided for facilitating clinical decision making, and in particular, decision making based on a third party's clinical situation by determining and providing useful, up-to-date information, such as patient-related information to a decision maker. In one embodiment, a user first identifies an information item concerning a patient. Based on that item, a set of related information items is determined and prioritized, and a reference pointer, which identifies the set of related information, is generated. The reference pointer is communicated to the user's mobile device. Subsequently, the user's mobile device requests information from the set of information items associated with the reference pointer, and provides information authorization information. Following authentication of the user's credentials, updates of information from the set of information items may be communicated to the user's mobile device as they become available.

Proximity-based mobile-device updates of electronic health records

System, methods and computer-readable media are provided for facilitating decision support by assessing the severity of injuries and the acute risk of physiologic deterioration and short-term mortality in trauma patients, both on the scene where emergency medical personnel initially evaluate and treat trauma victims and while in-transit to receive care at a health care facility. Embodiments of the invention provide a quantitative numerical score and calculated probabilities of deterioration and/or mortality, based on multi-variable statistical regressions. In some embodiments, fuzzy-set mathematics are employed in the regressions to account for physiologic and epistemologic uncertainty that are inherent in one or more emergency personnel members' observations and recordings of a plurality of measurements periodically during the time on-scene and during transit. Embodiments also enable the prediction of the other outcomes of trauma patients, such as the intensity of care that will likely be required prior to hospital arrival.

On-scene and pre-hospital risk evaluation (OSPRE)

Methods, systems, and computer-readable media are provided for facilitating record matching and entity resolution and for enabling improvements in record linkage. A power-spectrum-based temporal pattern-specific weight may be incorporated into record linkage methods to enhance the record linkage accuracy and statistical performance. For example, in embodiments, a value-specific weight may be calculated from a population-based frequency of field-specific values and provides an opportunity to capture and measure the relative importance of specific values found in a field. A timeseries-derived Bayesian power spectrum weight may be calculated from the population-based frequency of temporal pattern-specific values in terms of intensities at various frequencies of the power spectrum computed from the timeseries, and further provides an opportunity to capture and measure the relative importance of specific sequences of care episodes.

Growing community of inventors

Leawood, KS, United States of America

Douglas S McNair