Koninklijke Philips Corporation N.v.

Erina Ghosh

Christopher Edward Haverstock

Emma Holdrich Schwager

Larry James Eshelman

Richard Earl Gregg

Cristhian Potes

Stephanie Lanius

David Paul Noren

Mohammad Shahed Sorower

Oladimeji Feyisetan Farri

Bryan Conroy

Cristhian Mauricio Potes Blandon

Eric Thomas Carlson

Srinivas Hariharan

Claire Yunzhu Zhao

Kailash Swaminathan

Bo Liu

Vinod Kumar

Daniel Craig McFarlane

Chaitanya Kulkarni

Kristen Tgavalekos

Vikram Shivanna

Ting Feng

The present disclosure is directed to systems and methods for developing an individual-specific patient baseline for a target patient. An exemplary method involves: determining one or more acuity scores for the target patient; identifying patient health data corresponding to one or more low acuity time periods; storing retrospective clinical data from a group of patients in a second database; comparing the patient health data corresponding to the one or more low acuity time periods with retrospective clinical data from a group of patients by identifying one or more patient subgroups; determining the individual-specific patient baseline using an adaptive baseline selection algorithm, wherein the adaptive baseline selection algorithm is used to determine whether to determine the individual-specific patient baseline using patient health data or using retrospective clinical data from one or more patient subgroups; and displaying, using a user interface, the individual-specific patient baseline.

Methods and systems for patient baseline estimation

In various embodiments, a first classification assigned to a periodic component of an electrical waveform that represents electrical activity in a patient's heart may be identified. A corresponding periodic component of a hemodynamic waveform that represents hemodynamic activity in the patient's cardiovascular system may be analyzed. The corresponding periodic component may be causally related to the periodic component of the electrical waveform. Based on the analysis, the previously-assigned classification may be assigned to the corresponding periodic component of the hemodynamic waveform in response to a determination, based on the analyzing, that the previously-assigned classification also applies to the corresponding periodic component. In a database of hemodynamic templates, a hemodynamic template associated with the previously-assigned classification may be updated to include one or more features of the corresponding periodic component of the hemodynamic waveform.

Template-based analysis and classification of cardiovascular waveforms

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

A method () for training a scoring system () comprising the steps of: (i) providing () a scoring system comprising a scoring module (); (ii) receiving () a training dataset comprising a plurality of patient data and treatment outcomes; (iii) analyzing (), using a clinical decision support algorithm, the training dataset to generate a plurality of clinical decision support recommendations; (iv) clustering (), using the scoring module, the plurality of clinical decision support recommendations into a plurality of clusters; and (v) identifying (), using the scoring module, one or more features of at least one of the plurality of clusters, and generating, based on the identified one or more features, one or more inclusion criteria for the at least one of the plurality of clusters.

Method and system for automated inclusion or exclusion criteria detection

When evaluating the quality of photoplethysmography (PPG) signal () measured from a patient monitor (e.g., a finger sensor or the like), multiple features of the PPG signal are extracted and analyzed to facilitate assigning a score to the PPG signal or portions (e.g., heartbeats) thereof. Heartbeats in the PPG signal are segmented out using concurrently captured electrocardiograph (ECG) signal (), and for each heartbeat, a plurality of extracted features are analyzed. If all extracted features satisfy one or more predetermined criteria for each feature, then the heartbeat waveform is compared to a predefined heartbeat template. If the waveform matches the template (e.g., within a predetermined match percentage or the like), then the heartbeat is classified as 'clean.' If the heartbeat does not patch the template, or if one or more of the extracted features fails to satisfy its one or more pre-determined criteria, the heartbeat is classified as 'noisy.'

Method to quantify photoplethysmogram (PPG) signal quality

Instructions () cause a processor () to: classify a clinical report for a subject under evaluation by one of anatomical organ or disease; identify and retrieve clinical reports for the same subject from the healthcare data source(s); group the retrieved clinical report by one of anatomical organ or disease; select a group of the clinical report, wherein the group includes reports for a same or related one of the anatomical organ or the disease; build a model that predicts semantic relationships between nodes in the reports in the selected group of reports based on one or more of extracted parameters or keywords; compare one of the parameter values or the keywords across the reports using the model; construct a graphical timeline of the reports; highlight differences in the parameter values or the keywords based on a result of the compare; and visually present the graphical timeline with the highlighted differences.

Clinical report retrieval and/or comparison

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

In various embodiments, a first classification assigned to a periodic component of an electrical waveform that represents electrical activity in a patient's heart may be identified (). A corresponding periodic component of a hemodynamic waveform that represents hemodynamic activity in the patient's cardiovascular system may be analyzed (). The corresponding periodic component may be causally related to the periodic component of the electrical waveform. Based on the analysis, the previously-assigned classification may be assigned () to the corresponding periodic component of the hemodynamic waveform in response to a determination, based on the analyzing, that the previously-assigned classification also applies to the corresponding periodic component. In a database () of hemodynamic templates, a hemodynamic template associated with the previously-assigned classification may be updated () to include one or more features of the corresponding periodic component of the hemodynamic waveform.

Display screen with animated icon

Growing community of inventors

Boston, MA, United States of America

Erina Ghosh