Posted by: Dr Churchill | February 5, 2019

BioTech AI & ML innovations

Screen Shot 2019-02-05 at 9.24.37 AM

All current AI/ML-based innovations have vast potential to make all biotech, bioengineering, new-pharma and all healthcare and medicine, far more accessible, inexpensive, democratic, patient-centric and compassionate — by allowing all Doctors, Clinicians, and Health providers, to be far more efficient, greatly more effective, and thus enabling all of them to spend more face-to-face time with the patients, thus understanding the deep issues facing our people….

Because indeed, artificial intelligence (AI) and machine learning (ML) have tremendous potential to improve healthcare at multiple levels, from basic biomedical sciences to precision medicine and population health. Along with big data and digital health, AI/ML could help achieve the transformation to value-based care and the Quadruple Aim (improved health outcomes, lower costs, and better patient/clinician experience).

One area that machine learning is significantly evolving is genomics—the study of the complete set of genes within an organism. While much attention has been paid to the implications for human health, genetic sequencing and analysis could also be ground-breaking for agriculture and animal husbandry. When researchers can sequence and analyze DNA, something that artificial intelligence systems make faster, cheaper and more accurate, they gain perspective on the particular genetic blueprint that orchestrates all activities of that organism. With this insight, they can make decisions about care, what an organism might be susceptible to in the future, what mutations might cause different diseases and how to prepare for the future.

We expect that artificial intelligence (AI) systems will generate upwards of $67 billion in revenue from basic healthcare and biotechnology globally, over the next few years time…

Screen Shot 2019-02-05 at 9.29.42 AM

The most noteworthy healthcare AI/ML-based innovations that have been released commercially or successfully deployed in academic medical settings this past decade offer innovative diagnostic techniques, such as AI-based radiology and specialty imaging tools from the leading digital health start-ups that have been cleared by the U.S. Food and Drug Administration (FDA) for patient care use.

IDx-DR – AI-based tool for fully automated diabetic retinopathy screening:
Imagen OsteoDetect – AI-based detection of wrist fractures:
Zebra Medical – AI-based algorithm for coronary artery disease detection:
Viz.AI Contact – AI-based clinical decision support for stroke detection on CT scans:
MaxQ AI Accipio Ix – AI-based clinical decision support for intracranial hemorrhage detection on CT scans:
Innovations #6 and #7 come from Apple and Amazon, reflecting the strong commitment of these technology leaders to healthcare innovation.

Screen Shot 2019-02-05 at 9.25.18 AM

Apple Watch 4 – The latest version of the popular Apple Watch comes with a medical-grade, FDA-cleared electrocardiogram (ECG) device and AI-based algorithms for cardiac arrhythmia & fall detection:
Amazon Comprehend Medical – A natural language processing (NLP) service that simplifies using ML to extract relevant medical information from unstructured text, such as notes notes and reports typically found in electronic health records (EHR):

Can AI/ML help bring more humanity and compassion to healthcare?

That’s exactly what a team of clinical researchers at Stanford University set out to do with their innovation expressed in their startup medical company.

Screen Shot 2019-02-05 at 9.23.33 AM

Compassionate Intelligence, is based on an AI-based algorithm that analyzes EHR data in order to identify patients likely to benefit from palliative care:

Both conventional ML algorithms and more sophisticated AI approaches using deep learning (neural networks) have been used in the life sciences. Innovations that recognize the promising use of AI/ML in chemoinformatics and bioinformatics (specifically, drug discovery/design and genomics/genetics, respectively).

Drug Discovery/Design – These two review articles from 2018 provide a comprehensive introduction to this topic: “The rise of deep learning in drug discovery” (, and “Machine learning in chemoinformatics and drug discovery” (

Screen Shot 2019-02-05 at 9.23.50 AM

Genomics/Genetics – Genome Sequencing and Gene Editing

Since the illnesses an individual experiences in a lifetime are largely determined by their genetics, there has been significant interest to better understand our genetic makeup for years. Our progress was stalled by the complexity and enormity of the data that needed to be evaluated. With advances in artificial intelligence and machine learning applications, researchers are better able to interpret and act on genomic data through genome sequencing and gene editing.

Screen Shot 2019-02-05 at 9.24.07 AM

CRISPR: When changes are made to DNA at a cellular level, it’s called gene editing.

The use of CRISPR in our lives is about personalized medicine and life-saving therapies developed for you and you alone:
One of the most exciting prospects about gene technology is the development of precision or personalized medicine. The field, which enables interventions specific to a patient or population of genetically similar individuals, is expected to reach $87 billion by 2023. Historically, cost and technology limited the implementation of personalized medicine, but machine learning techniques are helping to overcome these barriers. Machines help identify patterns within genetic data sets and then computer models can make predictions about an individual’s odds of developing a disease or responding to interventions.

A genome sequence is a specific order of DNA building blocks (A, T, C, G) in a living organism; the human genome is made up of 20,000 genes and more than 3 billion base pairs of these genetic letters. Sequencing the genome is a critical first step to understanding it. The latest technology called high-throughput sequencing (HTS) allows the sequencing of DNA to occur in one day—a process that once took a decade when it was first done.

Screen Shot 2019-02-05 at 9.29.42 AM

As a more specific, noteworthy example, this research paper describes an open-source AI/ML software tool called DeepVariant, developed by Google for more efficient and accurate DNA sequencing (i.e. living organism’s genetic code:


Dr Churchill


CRISPR is also an acronym for Clustered Regularly Interspaced Short Palindromic Repeat. This name refers to the unique organization of short, partially palindromic repeated DNA sequences found in the genomes of bacteria and other microorganisms.

Screen Shot 2019-02-05 at 9.33.21 AM

Now if our public Innovation policies about BioTech and Genetics become more open and thus allow far more CRISPR experimentation — we might be able to overcome the Chinese and all others on the race to Humanity’s future.

Let’s engage in that in earnest and thus change our personal and national future at once for the better.

BioEngineering Genetic innovation is our Destiny — let’s act like it.


Leave a Reply

Please log in using one of these methods to post your comment: Logo

You are commenting using your account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s


%d bloggers like this: