Multimodal modeling systems and methods for predicting and managing dementia risk for individuals
AssigneeHuman Longevity, Inc.
InventorsDavid Stanley Karow, Naisha Shah, Christine Menking Swisher, Natalie Marie Schenker-Ahmed, Peter Garst, Ilan Shomorony
Life of this patent
Estimating the term…
Abstract
The disclosure relates to systems, software and methods for diagnosis or prognosis of subjects for dementia, including, classification and treatment of subjects who have been diagnosed with or deemed at risk of dementia. The methods are based, in part, on the multimodal analysis of a plurality of features, e.g., genetic features such as SNPs or chromosome regions, including, loci or genes related thereto and structural brain features such as MRI images of brain or brain regions.
Claims41
A computer readable medium comprising computer-executable instructions, which, when executed by a processor, cause the processor to carry out a method or a set of steps for diagnosing dementia in a subject, the method or steps comprising,
- a) extracting, into a diagnostic model, a plurality of features comprising
- 1) structural features of a brain tissue of the subject or a region thereof;
- 2) genetic features from the subject's biological sample;
- 3) optionally actionable risk features;
- and
- 4) further optionally epidemiological features;
- b) mathematically integrating the structural features and the genetic features in the diagnostic model to output a first integrated score;
- c) optionally integrating actionable risk features in the diagnostic model to output a second integrated score and/or further integrating epidemiological features in the diagnostic model to output a third integrated score and outputting a risk score based on the first, second or third integrated scores;
- and
- d) diagnosing dementia based on the risk score.
A system for diagnosing dementia, comprising,
- a) a receiver for receiving a plurality of features comprising
- 1) structural features of a brain tissue of the subject or a region thereof;
- 2) genetic features from the subject's biological sample;
- 3) optionally actionable risk features;
- and
- 4) further optionally epidemiological features;
- b) a first integrator for integrating structural features and genetic features to output a first integrated score;
- c) an optional second integrator for integrating actionable risk features in the diagnostic model to output a second integrated score and a further optional third integrator for integrating the epidemiological features in the diagnostic model to output a third integrated score;
- and
- d) a scorer for determining a risk of dementia based on the first, second or third integrated score, wherein the risk score is used to diagnose dementia.
A method for diagnosing dementia in a subject, comprising,
- a) extracting, into a diagnostic model, a plurality of features comprising
- 1) structural features of a brain tissue of the subject or a region thereof;
- 2) genetic features from the subject's biological sample;
- 3) optionally actionable risk features;
- and
- 4) further optionally epidemiological features;
- b) mathematically integrating the structural features and the genetic features in the diagnostic model to output a first integrated score;
- c) optionally integrating actionable risk features in the diagnostic model to output a second integrated score and/or further integrating epidemiological features in the diagnostic model to output a third integrated score and outputting a risk score based on the first, second or third integrated scores;
- and
- d) diagnosing dementia based on the risk score.
Dependencies are inferred from the claim text.