Massachusetts Institute of Technology

International Business Machines Corporation

Collin M Stultz

John V Guttag

Uri Kartoun

Kenney Ng

Zeeshan H Syed

Kristen Ann Severson

Paul D Myers

Wangzhi Dai

Philip Pohong Sung

Yun Liu

A computer system selects features of a dataset for predictive modeling. A first set of features that are relevant to outcome are selected from a dataset comprising a plurality of cases and controls. A subset of cases and controls having similar values for the first set of features is identified. The subset is analyzed to select a set of additional features relevant to outcome. A first and second predictive model are evaluated to determine that the second predictive model more accurately predicts outcome, wherein the first predictive model is based on the first set of features and the second predictive model is based on the first set of features and the additional features. The second predictive model is utilized to predict outcomes. Embodiments of the present invention further include a method and program product for selecting features of a dataset for predictive modeling in substantially the same manner described above.

Data model processing in machine learning employing feature selection using sub-population analysis

Aspects of the invention include includes identifying a respective estimated clinical risk score for each of a first group of patients and a second group of patients. An alternative probability estimate is generated using a same set of inputs used to determine each respective estimated clinical risk score. An unreliability of a patient's clinical risk score is determined based at least in part on a feature of the patient and on a difference between the alternative probability estimate and the determined respective estimated clinical risk score.

Assessing unreliability of clinical risk prediction

A computer system trains a predictive model. A plurality of subsets of features are selected from a dataset comprising a plurality of cases and controls and a plurality of features. Cases and controls are matched to select a plurality of case-control subsets for each subset of features, each case-control subset having similar values for the corresponding subset of features. For each case-control subset, a statistical significance of each feature of the plurality of features absent from the subset of features used to match the case-control subset is identified. A final subset of features is selected based on satisfying a statistical significance of each feature for the plurality of case-control subsets. A predictive model is trained using the final subset of features. Embodiments of the present invention further include a method and program product for training a predictive model in substantially the same manner described above.

Data model processing in machine learning using a reduced set of features

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

Newton, MA, United States of America

Collin M Stultz