Koninklijke Philips Corporation N.v.

North American Philips Corporation

Philips Electronics North America Corporation

Koninlijke Philips Electronics N.v.

Larry James Eshelman

Srinivas Gutta

Hugo Strubbe

John G Milanski

J David Schaffer

Daniel Pelletier

Minnan Xu

Larry Nielsen

Mohammed Saeed

Brian David Gross

Bryan Conroy

Erina Ghosh

James David Schaffer

Joseph James Frassica

Keith E Mathias

Abigail Acton Flower

Adam Jacob Seiver

Cristhian Potes

Emma Holdrich Schwager

Stephanie Lanius

Robert Randall Entrekin

Walid Ali

Kwok Pun Lee

Claire Levrier

Walid S I Ali

Wei Zong

Eric Thomas Carlson

Srinivasan Vairavan

Claude Cohen-Bacrie

Colleen Michelle Ennett

Lin Yang

Jean-Michel LaGrange

Nicholas Villain

Kostyantyn Volyanskyy

Syed Waseem Haider

Pelletier Daniel

James A Hoekema

Richard A Caruana

Omar Abdala

A machine learning model, including: a categorical input feature, having a defined set of values; a plurality of non-categorical input features; a word embedding layer configured to convert the categorical input feature into an output in a word space having two dimensions; and a machine learning network configured to receive the output of the word embedding layer and the plurality of non-categorical input features and to produce a machine learning model output.

Word embedding for non-mutually exclusive categorical data

In a risk level assessment method for a plurality of clinical conditions as follows, a set of laboratory test results () are stored with time stamps for a patient, including at least one hematology test result and at least one arterial blood gas (ABG) test result. For each clinical condition, a risk level is determined for the clinical condition based on a clinical condition-specific sub-set of the stored set of laboratory test results. This determination is made conditional on the stored clinical condition-specific sub-set of laboratory test results being sufficient to determine the risk level. A time stamp is assigned to each determined risk level based on the time stamps for the laboratory test results of the clinical condition-specific sub-set of laboratory test results. A display device () displays the determined risk level and the assigned time stamp for each clinical condition whose determined risk level satisfies a display criterion.

System for laboratory values automated analysis and risk notification in intensive care unit

A method for training a baseline risk model, including: pre-processing input data by normalizing continuous variable inputs and producing one-hot input features for categorical variables; providing definitions for clean input data and dirty input data based upon various input data related to a patient condition; segmenting the input data into clean input data and dirty input data, wherein the clean input data includes a first subset and a second subset, where the first subset and the second subset include all of the clean input data and are disjoint; training a machine learning model using the first subset of the clean data; and evaluating the performance of the trained machine learning model using the second subset of the clean input data and the dirty input data.

Multilayer perceptron based network to identify baseline illness risk

Various embodiments described herein relate to methods and apparatus for robust classification. Many real-world datasets suffer from missing or incomplete data. By assigning weights to certain features of a dataset based on which feature(s) are missing or incomplete, embodiments of the prevention can provide robustness and resilience to missing data.

Robust classifier

A system () for assessing fluid responsiveness includes an infusion pump () in communication with at least one processor (), and a plurality of physiological monitors () operable to receive physiological signals from an associated patient. Physiological signals () acquired from the associated patient () during a fluid challenge are synchronized with a timing signal () of the infusion pump () administering the fluid challenge. One or more dynamic indices and/or features () is calculated from the synchronized physiological signals (), and one or more dynamic indices and/or features () is calculated from baseline physiological signals () acquired from the associated patient () prior to the fluid challenge. A fluid responsiveness probability value () of the patient () is determined based on dynamic indices and/or features () from the synchronized physiological signals () and dynamic indices and/or features () from the baseline physiological signals ().

Method and system for assessing fluid responsiveness using multimodal data

The following relates generally to the medical monitoring arts, medical warning systems concerning a monitored patient, and so forth. In clinical settings, alarms are usually triggered when a single-parameter or a multi-parameter score exceeds certain thresholds. When a score needs to be determined, if certain parameters are not available, the common practice is to use the most recent measurements of the parameters for the score calculation. However, a patient's status may change from moment to moment. The parameters measured hours ago may not be a good indicator of the patient's current status. This uncertainty can put deteriorating patients at great risk. An embodiment uses statistical methods to estimate a range of scores and the probability of these scores if old measurements have to be used for score determination. Instead of giving a single number at a time, a confidence interval may be displayed to emphasize the fact that the score is determined partially based on old measurements. If there is a chance that the actual score is higher and may exceed a critical alarm threshold, a notification can be issued to advise a new measurement reading to improve score confidence.

Method for score confidence interval estimation when vital sign sampling frequency is limited

A medical modeling system and method predict a risk of a physiological condition, such as mortality, for a patient. Measurements of a plurality of predictive variables for the patient are received. The plurality of predictive variables are predictive of the risk of the physiological condition. The risk of the physiological condition is calculated by applying the received measurements to at least one model modeling the risk of the physiological condition using the plurality of predictive variables. The at least one model includes at least one of a hidden Markov model and a logistic regression model. An indication of the risk of the physiological condition is output to a clinician.

Modeling techniques for predicting mortality in intensive care units

An apparatus () for predicting patient respiratory stability includes a patient data memory () which stores patient data for a patient () and an analyzer () in communication with the memory computes a measure of patient respiratory stability. The analyzer applies one or more rules to the patient data that are based on a plurality of parameters which in combination, have been identified as being predictive of patient respiratory instability, such as mean airway pressure (MAWP), plateau pressure (PP), arterial oxygen saturation (SaO2 or SpO2), and heart rate (HR). Based on the application of the rules, the analyzer determines the measure of patient respiratory stability.

Apparatus for measuring and predicting patients' respiratory stability

A medical system () and method monitor a patient. Patient data for the patient received. The patient data includes vital sign measurements and laboratory results. A vital signs instability index (VIX) regarding a physiological condition of the patient is calculated from the received vital sign measurements. A laboratory instability index (LIX) regarding the physiological condition is calculated from the received laboratory results. The VIX and the LIX are integrated into an indicator of patient deterioration.

Method of rendering hemodynamic instability index indicator information

In a patient monitoring system (), shorter interval physiological parameters and longer interval clinical data are collected from a monitored patient (). A composite acuity score generator () generates or updates a composite acuity score indicative of wellbeing of the patient () based at least on the sensed physiological parameters and the longer interval data. A monitor () displays current values of at least one of selected sensed physiological parameters, longer interval data, and the composite acuity score.

Apparatus to measure the instantaneous patients' acuity value

A method for determining the presence or absence of malignant features in medical images, wherein a plurality of base comparison or training images of various types of lesions taken of actual patient is examined by one or more image reading experts to create a first database array. Low-level features of each of the lesions in the same plurality of base comparisons or training images are determined using one or more image processing algorithms to obtain a second database array set. The first and second database array set are combined to create a training database array set which is input to a learning system that discovers/learns a classifier that maps from a subset of the low-level features to the expert's evaluation in the first database array set. The classifier is used to determine the presence of a particular mid-level feature in an image of lesion in a patient based solely on the image.

Method and apparatus for automatically developing a high performance classifier for producing medically meaningful descriptors in medical diagnosis imaging

Cross over (S) in a genetic algorithm () is adapted for deriving an optimal mask (S), or set of segments of a line. Each mask of a chromosome is subject to cross over with the respective mask of the other parent. Any overlapping part, whether a filtering () or pass-through part (), is retained in the child () to preserve commonality. The part is preferably, potentially extended, according to one parent or the other, as decided pseudo-randomly (). In a preferred application, spectrums of candidate blood constituents are masked for fitting to ensemble spectrums of test blood samples (S, S). The developed masks are applicable to constituent spectrums to create masked spectrums (S) which are then applicable to an actual blood sample to be analyzed (S).

Segment-preserving crossover in genetic algorithms

The invention recommends television programs that are similar to shows identified by a user by computing a similarity metric between programs both in a user-specified selected set and in an identified time interval. The selected set comprises programs currently of interest to the user, for allowing the user or viewer to easily select one or more programs of interest. The similarity metric is a sum of weighted scores for each matching attribute between programs in the selected set and programs in the identified time interval. Shows that are actually selected for viewing are observed and the weightings, w, assigned to each matching program attribute are adjusted, so that over time, the similarity metric, S, more accurately reflects the viewer's idea of 'similar shows.'

Method and apparatus for generating television program recommendations based on similarity metric

An animated virtual creature is generated on a display such as a television set, in order to simulate a pet or to facilitate user interface functions. In one embodiment, one or more signals corresponding to the program being watched are monitored. When certain events are detected based on this monitoring, the animated character is controlled in a manner that corresponds to the detected event. In another embodiment, the animated virtual creature responds to program selections made by a user in a program recommendation system.

Virtual creature displayed on a television

An interaction simulator, such as a chatterbot, is connected with an external database, such as an electronic program guide. The information gathered during interaction, particularly conversational, is parsed and used to augment the database data. The interaction simulator may be guided by the data residing in the database so as to help fill in recognizable gaps by, for example, intermittently asking questions relating to the subject data requirement. The interaction simulator may be provided with specific response templates based on the needs of the database and a corresponding set of templates to extract the information required by the database. Another example database may be for recording and indexing by key word stories or other free-form verbal data uttered by the user. The interaction simulator may be programmed to help the user develop the story using templates designed for this purpose.

Growing community of inventors

Ossining, NY, United States of America

Larry James Eshelman