Massachusetts Institute of Technology

Quanta Computer Incorporated

Health at Scale Corporation

Predictive Modeling, Inc.

John V Guttag

Frederic Durand

Zeeshan H Syed

William T Freeman

Michael Rubinstein

Hao-yu Wu

Eugene Inghaw Shih

Neal Wadhwa

Collin M Stultz

Guha Balakrishnan

Philip Pohong Sung

Dahee Lee

Tiange Zhan

Yun Liu

Heart rates and beat lengths of a subject can be extracted from videos of the subject by measuring subtle head motion caused by the Newtonian reaction to the influx of blood at each beat. Embodiments track features on the video images of the subject's head and perform principal component analysis (PCA) to decompose the feature location-time series into a set of component motions. The method or system then selects a component that best corresponds to heartbeats based on its temporal frequency spectrum. Finally, the motion projected to this component is analyzed and peaks of the location-time series are identified, which correspond to heartbeats. Pulse rate measurements or heart rate measurements of the subject are output.

Pulse detection from head motions in video

The present disclosure relates to providing personalized prediction and prevention of various types of medical events (e.g., emergency department visits, hospital admissions, complications) using machine-learning algorithms. An exemplary method comprises: obtaining a plurality of feature values of the patient; providing the plurality of feature values to a set of one or more trained machine-learning models to obtain: a first probabilistic value indicating a likelihood of a future medical event, a second probabilistic value indicating a likelihood of a reason for the future medical event, a third probabilistic value indicating a likelihood that the future medical event can be prevented, displaying, on the display, a risk value of the future medical event based on the first probabilistic value, a reason of the future medical event based on the second probabilistic value, an interceptability value of the future medical event based on the third probabilistic value.

Prediction and prevention of medical events using machine-learning algorithms

A computer-based system and method to assign patients to providers. In one embodiment, the invention predicts the performance of provider-patient pairs in terms of different outcome-, financial- and satisfaction-related metrics across providers using advanced machine learning methodologies to develop distinct models for each of these metrics across each of the providers using a historical database. In another embodiment, patients are assigned to providers in a batch or online manner using this information through an optimization framework that looks to maximize or minimize arbitrary combinations of the outcome-, financial-, and satisfaction-related metrics subject to practical operational constraints. In another embodiment, the invention includes logic to avoid 'boxing' providers and uses exploration to continuously update the profiles of providers for metrics in a manner that accounts for provider performance getting better or worse over time, and the historical database not being representative of all potential patients to be assigned by this system.

System to improve the logistics of clinical care by selectively matching patients to providers

A computer-based system to determine whether patients should be treated as inpatients or outpatients. The invention makes personalized predictions about the risk and timing of adverse outcomes for the patient, and further assesses how this risk and timing may vary if the patients are treated as inpatients or outpatients. This information informs how patients are assigned to an appropriate therapy. The invention includes logic relevant to predicting patient risk, decoupling patient risk into components inherent to the patient as well as additions/subtractions associated with the choice of treatment, and predicting the timing of adverse outcomes given censored data. The invention can be extended to use in a broad range of other application domains (e.g., matching learners to courses either offered in-classroom or online for education).

System to determine inpatient or outpatient care and inform decisions about patient care

Heart rates and beat lengths can be extracted from videos by measuring subtle head motion caused by the Newtonian reaction to the influx of blood at each beat. In an embodiment of the present invention, a method tracks features on the head and performs principal component analysis (PCA) to decompose their trajectories into a set of component motions. The method then selects a component that best corresponds to heartbeats based on its temporal frequency spectrum. Finally, the motion projected to this component is analyzed and peaks of the trajectories are identified, which correspond to heartbeats.

In an embodiment, a method converts two images to a transform representation in a transform domain. For each spatial position, the method examines coefficients representing a neighborhood of the spatial position that is spatially the same across each of the two images. The method calculates a first vector in the transform domain based on first coefficients representing the spatial position, the first vector representing change from a first to second image of the two images describing deformation. The method modifies the first vector to create a second vector in the transform domain representing amplified movement at the spatial position between the first and second images. The method calculates second coefficients based on the second vector of the transform domain. From the second coefficients, the method generates an output image showing motion amplified according to the second vector for each spatial position between the first and second images.

Linear-based Eulerian motion modulation

Linear-based eulerian motion modulation

In one embodiment, a method of amplifying temporal variation in at least two images comprises examining pixel values of the at least two images. The temporal variation of the pixel values between the at least two images can be below a particular threshold. The method can further include applying signal processing to the pixel values.

In one embodiment, a method of amplifying temporal variation in at least two images includes converting two or more images to a transform representation. The method further includes, for each spatial position within the two or more images, examining a plurality of coefficient values. The method additionally includes calculating a first vector based on the plurality of coefficient values. The first vector can represent change from a first image to a second image of the at least two images describing deformation. The method also includes modifying the first vector to create a second vector. The method further includes calculating a second plurality of coefficients based on the second vector.

Eulerian motion modulation

Complex-valued phase-based eulerian motion modulation

A method for the machine generation of a model for predicting patient outcome following the occurrence of an event. In one embodiment the method includes the steps of obtaining a physiological signal of interest, the physiological signal having a characteristic; obtaining a time series of a signal characteristic; dividing the time series into a plurality of window segments; converting the time series from time-space to beat-space; computing the power in various frequency bands of each window segment; computing the 90th percentile of the spectral energies across all window segments for each frequency band; and inputting the data into a machine learning program to generate a weighted risk vector.

Method and apparatus for beat-space frequency domain prediction of cardiovascular death after acute coronary event

A method and apparatus for predicting patient outcome from a physiological segmentable signal of a patient. In one embodiment, the method comprises the steps of obtaining the physiological segmentable signal of the patient; segmenting the physiological segmentable signal into a plurality of separate segmentable components; calculating a time series of the morphological distance between adjacent separate segmentable components of the plurality of separate segmentable components; and predicting patient outcome in response to the time series of the morphological distance. In another aspect, the invention relates to a method for extracting information from physiological signals for one or more subjects including the steps of partitioning the physiological signal into a plurality of components, grouping the components into a plurality of information classes, assigning a unique symbol to each information class, mapping each component to the assigned symbol, and examining one or more such sequences for clinical significance.

Method and apparatus for predicting patient outcomes from a physiological segmentable patient signal

The application relates a methodology and apparatus for identifying predictive patterns for acute clinical events in the absence of prior knowledge. Principles of conservation are used to identify activity that consistently precedes an outcome in patients, and describe a two-stage process that allows us to more efficiently search for such patterns in large datasets. This is achieved by first transforming continuous physiological signals from multiple patients into symbolic sequences, and by then searching for patterns in these reduced representations that are strongly associated with an outcome.

Growing community of inventors

Lexington, MA, United States of America

John V Guttag