A pinboard by
George Ng

I have a Doctorate in Biotechnology and I'm a machine learning expert based in Hong Kong.


Novel AI study suggests we can know if we're still around in 5 years time. By scanning our organs.

When AI Knows Your Organs' Health

A proper prediction of patient's longevity has been hampered by doctors' inability to measure the health of each organ. A recent study published in the Nature journal Scientific Reports. Where artificial intelligence was used to analyse the images of 48 patients' organs, with a 69% certainty which patients will die in five years. This is comparable to the accuracy of human doctors in predicting a patient's lifespan.

Don't Believe It?

Researchers applied feature engineering and deep learning methods to predict the age of a person. Early diagnose of critical illness is valuable as it empowers doctors with medical insights for designing customised treatment to prolong life. medical interventions

How Does It Work?

The team performed a backward-looking case-control study, with matching used to control for non-imaging clinical and demographic variables that were expected to be highly predictive of five-year mortality rate. Using training data sets they assessed the predictive performance of the feature engineering and deep learning methodologies based on a 6-fold cross-validation experiment. A qualitative visual comparison was made between the cases correctly identified as mortality or survival cases by the deep learning and feature engineering models.

AI And Breast Cancer Detection

Another related development is the early detection of breast cancer. Survival rates of breast cancer characterised by early detection are 99% as opposed to only 27% with late diagnosis. The Intelligent Bra (iTBra) comprises of breast sensor patches embedded into bras, engineered to detect dynamic circadian temperature fluctuations of breast tissue.

What's Wrong With The Mammogram?

In contrast with mammography and ultrasound, which rely on specular reflective capabilities of varying tissue densities, the solution is tissue agnostic and detects early circadian cellular changes in all tissue types and varied age groups. Dense breast tissue is comprised of less fat and more connective/fibrous and glandular tissue, and ranges in severity from Level A to Level D. As the density of breasts increases, the ability of the mammogram to detect cancer decreases.

The cancer risk in women with highly dense breast tissue can be up to 6 times higher compared to normal/fatty tissue and follows an acceleration of breast cancer. Using the iTBra means no more biopsies and avoids false positives.


Precision Radiology: Predicting longevity using feature engineering and deep learning methods in a radiomics framework.

Abstract: Precision medicine approaches rely on obtaining precise knowledge of the true state of health of an individual patient, which results from a combination of their genetic risks and environmental exposures. This approach is currently limited by the lack of effective and efficient non-invasive medical tests to define the full range of phenotypic variation associated with individual health. Such knowledge is critical for improved early intervention, for better treatment decisions, and for ameliorating the steadily worsening epidemic of chronic disease. We present proof-of-concept experiments to demonstrate how routinely acquired cross-sectional CT imaging may be used to predict patient longevity as a proxy for overall individual health and disease status using computer image analysis techniques. Despite the limitations of a modest dataset and the use of off-the-shelf machine learning methods, our results are comparable to previous 'manual' clinical methods for longevity prediction. This work demonstrates that radiomics techniques can be used to extract biomarkers relevant to one of the most widely used outcomes in epidemiological and clinical research - mortality, and that deep learning with convolutional neural networks can be usefully applied to radiomics research. Computer image analysis applied to routinely collected medical images offers substantial potential to enhance precision medicine initiatives.

Pub.: 12 May '17, Pinned: 09 Jun '17