Koninklijke Philips Corporation N.v.

Fmr Corp.

Verily Life Sciences LLC

Yugang Jia

Reza Sharifi Sedeh

Yuechen Qian

Brian David Gross

Saeed Reza Bagheri

Merlijn Sevenster

Choo Chiap Chiau

Daniel Robert Elgort

John Blair

Ayman Alalao

Michael Martin Scheja

Mina Deng

Eran Rubens

Thomas Andre Forsberg

Hanqing Cao

Vikrant Suhas Vaze

Bidhan Roy

Renjun Yu

Amol Vinayak Jadhav

Qianxi Li

Hong Lin

Jianxiong Zhang

Wei Wang

Yang Yang

Hua Zhai Solomon

Nikhil Raikar

Prabhakar Mani

Mark Homer

Behlool Sabir

Pramod Divakarmurthy

Sina Rashidian

Introduced here is an interactive digital health system (or simply 'interactive system') that is able to update a knowledge base used to facilitate semi-automated conversations to account for feedback. The interactive system can include a collection of modules that, in operation, can provide or support coaching services in the digital health domain, Upon receiving input indicative of a question from a patient, these modules allow the interactive system to perform language modeling to identify content objects in a knowledge base that are relevant to the question. Moreover, the interactive system may update the knowledge base to account for feedback, thereby making the knowledge base more robust to a broad range of questions.

Approaches to hybrid learning of personalized recommendations and interactive digital health system for implementing the same

Systems and methods for deriving classification rules from documents and a database using rule-based machine learning. The method includes extracting first variables from documents corresponding to an organization. The method further includes extracting second variables from a database corresponding to the organization. The method also includes filtering the extracted second variables based on at least one of null values, repeat variables, location variables, ID variables, or data variables. The method further includes deriving first classification rules based on the first variables using a rule-based machine learning algorithm. The method also includes calculating an accuracy of the derived first classification rules. The method also includes deriving second classification rules based on the first variables and the filtered second variables. The method further includes determining a suggested additional variable based on the derived second classification rules and the calculated accuracy.

Systems and methods for machine learning based rule discovery for data migration

The present disclosure pertains to a system configured to generate computer simulations of patient loads for units of health care facilities. The system is configured to: obtain past patient census information for an individual unit of a health care facility, the past patient census information comprising a quantity of patient visits to the individual unit during past periods of time; determine intra-period variation and inter-period variation in the quantity of patient visits to the individual unit during the past periods of time; classify the individual unit based on the intra-period and inter-period variations; and generate a computer simulation of patient loads for the individual unit based on the classification. The computer-simulated patient loads comprise a quantity of patient visits to the individual unit during one or more future periods of time. The computer simulation is performed using a non-parametric simulation algorithm.

Health care facility unit computer simulation system

A patient monitor () includes a display (). Patient values () are obtained for one or more known variables of a risk prediction function (). One or more unknown variables of the risk prediction function are determined, and at least one hyperplane () is defined as values assumable by the one or more unknown variables. Values of the risk prediction function are computed over the at least one hyperplane using the obtained patient values. A visualization template is selected from a database of visualization templates () using template selection indices including the risk prediction function and the one or more unknown variables. Using the visualization template, a visualization () of the computed values of the risk prediction function over the at least one hyperplane is displayed.

Contextualized patient-specific presentation of prediction score information

The present invention provides a system and method for evaluating Range of Motion of a subject. An aspect of the present invention proposes a system for evaluating Range of Motion of a subject, comprising markers attached to at least two joints of a body part of the subject respectively; an image capturing device for capturing images of the markers when the subject is doing an exercise with the body part attached with the at least two markers; and an evaluating device communicated with the image capturing device, wherein the evaluating device includes a determining unit configured to determine whether the exercise done by the subject is valid for the evaluation of Range of Motion of the body part of the subject, and a calculating unit configured to, if the exercise is valid, calculate the parameters related to Range of Motion of the body part of the subject according to the images related to the valid exercise. Thus, the work load of clinicians can be greatly reduced during the process of evaluating Range of Motion, and the accuracy of the evaluation of Range of Motion can be improved as well.

System and method for evaluating range of motion of a subject

Disclosed is a computer-implemented method () of assigning a task to a mobile communication device () belonging to a pool () of mobile communication devices, wherein each mobile communications device is associated with a trusted owner and is locatable by means of location information, the method comprising generating () a task to be performed; generating a set of task locations at which the task can be performed; receiving () location information for said mobile communications devices; deriving () a location for each mobile communications device from said location information; using the derived location to calculate () a cost score for each mobile communication device, said cost score indicating the cost of the trusted owner of said mobile communication device to reach a target location; and assigning () the task to a selected location in said set and to one of said mobile communications devices, wherein the task is assigned to the one of said mobile communications devices based on the calculated cost scores. A computer program product including program code for executing this method on a computer processor and a system adapted to execute this method are also disclosed.

Task assignment method, computer program product and task assignment system

A database merger method () merges two or more anonymized healthcare databases (X, Y). Each anonymized healthcare database has personally identifying information anonymized including having medical care units replaced by medical care unit placeholders. In the database merger method, statistical patient feature distributions are computed for medical care unit placeholders in the anonymized healthcare databases. Medical care unit placeholders in different anonymized healthcare databases are matched by matching corresponding statistical patient feature distributions for the respective medical care unit placeholders. Patients in different anonymized healthcare databases are matched. The patient matching is performed within matched pairs of medical care unit placeholders to improve computational efficiency. A databases alignment table () is generated identifying the matched patients, or a merged anonymized healthcare database is generated that merges patient features in the different anonymized healthcare databases for each matched patient into a single patient entry.

Hospital matching of de-identified healthcare databases without obvious quasi-identifiers

The present invention provides a training garment () for persons suffering from upper limb dysfunction. According to one aspect of the invention, the training garment () comprises a shoulder garment (), which comprises a shoulder portion () adapted to be worn across a person's shoulder and a first main body portion () adapted to be worn around the trunk of the person. Both ends of the shoulder portion () are attached to the first main body portion (), and the shoulder portion () has an area () for receiving a shoulder marker. The proposed training garment (), due to its special design of the shoulder portion () and the first main body portion (), can prevent displacement of the shoulder marker while the person is performing active rehabilitation exercises, such as raising up his arm, and therefore, it can improve the recognition accuracy of the movement tracking system for the rehabilitation training.

Training garment for person suffering from upper limb dysfunction

Methods and apparatuses are described for recommending digital content in a network environment. A web server determines a session context of a user associated with a remote device in which the user interacted with digital content objects. The web server identifies prior content interactions in which prior users interacted with digital content objects. The web server builds a recommendation feature vector from the session context and the prior content interactions. The web server trains a machine learning model using the generated recommendation feature vector to minimize a predicted rating. The web server selects target digital content objects that have a predicted rating of the user that is at a threshold. The web server provides indicia of the selected digital content objects to the remote device. The web server causes at least one of the selected target digital content objects to be transmitted from a content server to the remote device.

Recommending digital content objects in a network environment

Growing community of inventors

Winchester, MA, United States of America

Yugang Jia