Evidation Health, Inc.

The Procter Gamble Company

The Procter & Gamble Company

Raghunandan Melkote Kainkaryam

Luca Foschini

Faiz Feisal Sherman

Ankur Purwar

Eamon Caddigan

Andrea Varsavsky

Stephen Casperson

Michael Frederick Niebauer

Filip Jankovic

Arinbjörn Kolbeinsson

Juan Ignacio Oguiza Mendez

A machine learning prediction system can analyze a dataset of users with self-reported symptoms and associated data from a wearable device to impact measure the impact of an acute health condition (such as the flu) at the population level. The machine learning prediction system can train a machine learning model to recognize individual acute health condition patterns based on differences in user activity with respect to the characteristics of determined baseline periods. For example, per-individual normalized change with respect to baseline aggregated at the population level can be used to determine individual acute health condition patterns and predict the onset of certain acute health conditions using a trained machine learning model. In response to predictions, the machine learning prediction system can take interventions to manage the impact of a predicted acute health condition on an individual.

Sensor-based machine learning in a health prediction environment

Disclosed is a method comprising accessing, by a machine learning system, a set of data records for a plurality of users, the data records representative of physical statistics measured for each of the plurality of users over a time period. At least a subset of the data records comprises patterns of missing data for at least a portion of the time period. The method also comprises generating a set of masked data records by masking a subset of the data records in accordance with a pattern of natural missingness from a data record. The method also comprises generating, by the machine learning system, a set of learned representations from at least the set of masked data records. Finally, the method comprises fine tuning, by the machine learning system, a machine learning model using the set of learned representations, the machine learning model configured to perform a downstream machine learning task.

Systems and methods for self-supervised learning based on naturally-occurring patterns of missing data

An active learning system can analyze a dataset of users with self-reported symptoms and associated data from wearable devices to train a baseline machine learning model to predict symptoms of a chronic health condition based on wearable device data. For example, symptoms can be predicted in terms of lost physical activity, increased sleep requirements, and changes in resting heart rate. Using the baseline model, the active learning system can train and refine individual user-specific models to predict the onset of chronic health condition symptoms over time. These models can be used to predict symptoms for inclusion in a log of symptoms for the target user (which may be used by a healthcare provider to personalize treatment for the target user) or to provide interventions to the user (for example, warning of a predicted severe symptom day). In some implementations individual chronic health condition models are maintained and updated using active learning techniques.

Active learning for wearable health sensor

Disclosed are hair analysis systems and methods comprising: (a) capturing an image of a user at as captured by a camera and sending the image to a hair analysis processor; (b) analyzing the user's hair condition at the hair analysis processor, based on the image from the camera by using a model that is trained using a plurality of images of users that each feature one or more micro features of a respective user's hair, and providing an analysis result to a display; and (c) displaying at the display the analysis result to the user. The present invention provides the system and the method with an improved sensitivity.

Systems and methods for hair analysis

Disclosed are hair analysis systems and methods comprising: (a) a step to capture an image at least of the top of the head of a user at an image capture unit and to send the image from the image capture unit to a hair analysis unit; (b) a step to analyze the user's hair coverage and/or scalp coverage condition at hair analysis unit, based on the image from the image capture unit by using a deep neural network that predicts user's hair coverage and/or scalp coverage relative to a gender population and is trained on class labels acquired by crowd sourcing, and to provide an analysis result to a display unit; and (c) a step to display at a display unit the analysis result to the user. The present invention provides the system and the method with an improved sensitivity.

Systems and methods for hair coverage analysis

Disclosed are hair analysis systems and methods comprising: (a) a step to capture an image of a user at an image capture unit and to send the image from the image capture unit to a hair analysis unit; (b) a step to analyze the user's hair condition at hair analysis unit, based on the image from the image capture unit by using a deep neural network, and to provide an analysis result to a display unit; and (c) a step to display at a display unit the analysis result to the user. The present invention provides the system and the method with an improved sensitivity.

Growing community of inventors

Cincinnati, OH, United States of America

Raghunandan Melkote Kainkaryam