How can Artificial Intelligence (AI) and Human Genome Sequencing (HGS) Tranform Personalised Healthcare | Health and Technology

How can Artificial Intelligence (AI) and Human Genome Sequencing (HGS) Tranform Personalised Healthcare | Health and Technology
How can Artificial Intelligence (AI) and Human Genome Sequencing (HGS) Tranform Personalised Healthcare 

How can Human Genome Sequencing and Artificial Intelligence (AI) transform personalised healthcare?

The sequencing of the first human genome was a massive PSU that cost $2.7 billion and took about 15 years to complete. The current cost of sequencing the human genome has dropped dramatically. The cost has dropped from $4000 in 2015 to less than $300 today.

Some genomic companies are aiming to bring the cost down to less than $100. At these prices the question arises, when is it negligible not to sequence the human genome?

One study found that early diagnosis of cancer could save the American medical system an average of $26 billion per year. Comparative sequencing would cost each American a one-time cost of $100 billion, and this cost could be further reduced if economies of scale are taken into account.

Outside of finding genetic predispositions to cancer, genome sequencing is directly relevant to the identification of a variety of inherited genetic disorders such as single gene inheritance, multifactorial inheritance, chromosomal abnormalities and diseases associated with mitochondrial inheritance.

Now, let's imagine the benefits to society if a subset of machine learning called deep learning is used to analyze this treasure trove of genetic information. 

Based on the neural networks of the brain, deep learning is one of the most important tools that data scientists rely on. Deep learning analyzes data and uses pattern recognition to build sophisticated models that can learn complex patterns and generalize those patterns to identify datapoints. Those datapoints can be complex and the more data a deep learning system operates on with the more impressive results.

By incorporating the entire human population into a deep learning system, machine learning algorithms can identify potential biomarkers for cancer or other diseases. In addition, the system can dive deeper into genetic family trees to find out which genes are responsible for different traits or diseases.

While none of this is revolutionary for practitioners of AI, the problem is our reliance on old governments that rely on decades-old technology, many times fax machines are still used to send patient data back and forth. The time has come to modernize this archaic system.

Now imagine if the next time you went to your doctor, they could instantly access your genome, and feed your latest symptoms into a computer so that the AI ​​returns results immediately with recommendations for treatment options. May be With wearable devices that track real-time health data, going to the doctor may not even be necessary.

The most effective solution would be for healthcare workers to be trained in genetic counseling, the process of examining individuals and their bloodlines who are affected or at risk of genetic disorders. The most important step in genetic counseling is to recommend the best treatment options based on that person's genetic profile.

Another advantage is targeting neglected rare diseases, a rare disease identified as a health condition that affects a smaller number of people than the more common diseases affecting the general population. These rare diseases are often too expensive to target in a conventional way.

A deep learning system can compare datasets (genetic profiles) to potentially identify genetic precursors of these rare diseases. Rare diseases affect 30 million Americans alone and cost the American medical system $1 trillion a year.

A valid argument against the above would be a potential loss of user privacy. These concerns can be addressed by using an advanced type of machine learning called federated learning. No personally identifiable data is required to be shared with Federated Learning. Federated learning brings machine learning models into a data source, allowing the data to be stored in a secure location. An easier solution would be for a patient (or parent) to approve access to personally identifiable data to reduce privacy concerns.

This type of solution could be important in helping bring personalized medicines to market. Knowing which molecules to target in an individual is critical to fully transitioning to personalized medicine.

The drug will be 3-D printed with the dosage, shape, size and release characteristics carefully designed to specifically target an individual as a result of personalized healthcare. Not only would gender, weight and other physical variables be considered, but drugs could be designed to specifically target a molecule that may only be present in certain genomes belonging to certain population groups.

Deep learning being used successfully to predict the bond between a drug and a target molecule was successfully tested by researchers at the Gwangju Institute of Science and Technology in Korea, as published in the Journal of Chemininformatics.

A fragmented privatized healthcare system may conflict with the above, but this scenario can be tested today by ambitious politicians who are particularly interested in moonlighting thinking in public health systems.

Estonia is truly a leader in this, with the Estonian Genome Project being a population-based biological data base and biobank that includes health records from a large percentage of the Estonian population. The Israel Genome Project is another ambitious project to sequence the more than 100,000 members of the Israeli population.

The clear leader in this space is the UK, where Genomics England collaborates with the NHS to continuously improve genomic testing to help doctors and clinicians diagnose, treat and prevent diseases such as rare diseases and cancer. They also have a goal of indexing 100,000 members.

One problem with the above nationalized databases is that the indexed population is still relatively small. Large datasets will result in higher performance by AI systems when used to identify patterns in the data. More importantly, it will result in equal access to healthcare for the entire population.

Also, data from more diverse ethnic backgrounds would be beneficial to prevent potential AI bias issues. AI bias stems from data that lack diversity, including genetic diversity. For example, Canada would be in the best position to take advantage of this, as it has one of the largest immigrant populations in the world, with 20% of Canada's population born abroad. This is in contrast to the Estonian and Israeli systems which suffer from a lack of ethnic diversity.

Standardizing genome sequencing and using deep learning could provide huge financial savings and health benefits to Canada's healthcare system. A system often labeled by Canadians as being broken with long wait times.

The above requires ambitious thinking, even if any country that adopts this moonlight thinking will save taxpayer money, invest in the future, increase the quality of life, and extend the lifespan of its general population. Will lead the world in providing equitable access to personalized health care and personalized medicine.

Source: unite.ai, directnews99.site