Quantum AI : Synergies to Catalyze Next-Generation Healthcare
Quantum AI is no longer a thing of science fiction. The technology is here, now. Healthcare is one industry that holds a lot of potential to integrate quantum. While we are still a while away from commercially available quantum computers, it does open up the discussion about “the possible.”
“Life can only be understood backwards; but it must be lived forwards.”
What are quantum computers?
Quantum computers differ from classical computers in that they go beyond the traditional “zero or one” bit model. Quantum bits, called qubits, can be both zero, one, or zero and one at the same time. This ability to be in the same state at the same time is called superposition.
Superposition, along with entanglement, allows quantum computers to perform numerous calculations in parallel. In doing so, it creates substantially more computational processing power to solving complex problems.
Thanks to technological advances such as cloud computing, we now have more computational power at our fingertips than ever before. These advantages resulted in breakthroughs in natural language processing, image recognition, and machine learning, among other areas.
However, quantum computers with AI will eventually far exceed anything we see today. This advancement will lead to new opportunities and challenges in several industries, including healthcare.
What is Quantum AI?
Quantum AI is the use of quantum computing for computation of machine learning algorithms. Quantum AI can help achieve results that are not possible to achieve with classical computers.
AI has made rapid progress over the past decade, it has not yet overcome technological limitations. With the unique features of quantum computing, obstacles to achieve AGI (Artificial General Intelligence) can be eliminated. Quantum computing can be used for the rapid training of machine learning models and to create optimized algorithms. An optimized and stable AI provided by quantum computing can complete years of analysis in a short time and lead to advances in technology. Neuromorphic cognitive models, adaptive machine learning, or reasoning under uncertainty are some fundamental challenges of today’s AI. Quantum AI is one of the most likely solutions for next-generation AI.
Recently, Google announced TensorFlow Quantum (TFQ): an open-source library for quantum machine learning, in collaboration with the University of Waterloo, X, and Volkswagen. The aim of TFQ is to provide the necessary tools to control and model natural or artificial quantum systems. TFQ is an example of a suite of tools that combines quantum modeling and machine learning techniques.
1. Convert quantum data to the quantum dataset: Quantum data can be represented as a multi-dimensional array of numbers which is called as quantum tensors. TensorFlow processes these tensors in order to represent create a dataset for further use.
2. Choose quantum neural network models: Based on the knowledge of the quantum data structure, quantum neural network models are selected. The aim is to perform quantum processing in order to extract information hidden in an entangled state.
3. Sample or Average: Measurement of quantum states extracts classical information in the form of samples from the classical distribution. The values are obtained from the quantum state itself. TFQ provides methods for averaging over several runs involving steps (1) and (2).
4. Evaluate a classical neural networks model: Since quantum data is now converted into classical data, deep learning techniques are used to learn the correlation between data.
The other steps of evaluating cost function, gradients, and updating parameters are classical steps of deep learning. These steps make sure that an effective model is created for unsupervised tasks.
AI in Healthcare: A glance
The rapid explosion in AI has introduced the possibility of using aggregated healthcare data to produce powerful models that can automate diagnosis and also enable an increasingly precision approach to medicine by tailoring treatments and targeting resources with maximum effectiveness in a timely and dynamic manner.
“The inconvenient truth” is that at present the algorithms that feature prominently in research literature are in fact not, for the most part, executable at the frontlines of clinical practice.
Artificial intelligence and machine learning are the promising techniques of the healthcare and have shown great prediction and results. However, there is enough room left for more scientific work and improvement due to the limitation in a large amount of high-quality data, user’s inability to access a large amount of data, inability to understand how to apply each unique method properly, and more.
“If a doctor makes a medical mistake, it can result in one death or coma. If an AI makes a mistake, it could be devastating — possibly resulting in hundreds or thousands of deaths!”
Data privacy and security: Is healthcare worth the cost?
Sensitive health data, including genetic testing & bio metrics, are used to train the machine learning algorithms behind new drug discovery and cures, more accurate diagnostics, and personalized treatments.
Data is susceptible to hacking and privacy breaches, such as the 2017 cyber attack on the United Kingdom’s NHS. Meanwhile, biometric data collected from wearables can be hacked or sold to public or private sectors actors to target advertising or real and “fake news” for political or social campaigns. Anonymization and data protection regulation are a start but fall far from guaranteeing security.
At the World Economic Forum Davos summit in January 2018, historian Noah Yuval Harari asked the audience: “Does my data about my DNA, brain, body, life, belong to me, a corporation, government, or the human collective?”
Should public health records and data be provided, without monetary compensation, for the public benefit? What’s your opinion?
Even World Health Organisation (WHO) report has cautioned against overestimating the benefits of artificial intelligence (AI) for health at the expense of core investments and strategies to achieve universal health coverage.
AI’s benefits in healthcare may largely outweigh security and privacy risks, but it is important for healthcare organizations to still take these risks into account when developing cybersecurity programs and ensuring HIPAA privacy compliance.
How Quantum AI make difference:
Will the predicted future prognosis impact the patient’s current mental health? What if health insurers or employers use the information to make negative coverage or employment decisions? These are questions circulating for current healthcare technologies, of course. Quantum amplifies the need for a thoughtful approach to predictive medicine.
Quantum computing has the potential to give individuals much clearer insights into their future healthcare risks. Patients tend to be receptive to this information when they understand those risks might migrate via preventative medicine. However, when the future prognosis indicates health conditions with grim outlooks, ethical situations arise.
As we begin to enter an age of personalised healthcare, dependent on genomics, individual physiology and pharmacokinetics the need to take huge amounts of data and process it in a format for clinical use will become more urgent. Quantum AI may be our best tool for achieving this.
Combining AI with quantum computing will provide access to the current evidence and enable meaningful use of the electronic data continuously generated in the delivery of care. Realization of personalized medicine will need to draw on analysis of mega-data and bring together measures of physiology, imaging, genomics, wearable technology, screening measures, patient records, environment measures and more.
Creating the safest medical data systems ever?
In recent TED talk, Shohini Ghose mentioned the use of quantum uncertainty for encryption as one of the most probable applications of quantum computing. She believes it could be used for creating private keys for encrypting messages sent from one location to another — so that hackers could not copy the key perfectly due to quantum uncertainty. They would have to break the laws of quantum physics to hack such keys. Imagine that level of security with regards to sensitive medical information: electronic health records, genetic and genomic data, or any other private information that the health system generates about our bodies.
There are already some examples. In January 2018, a joint China-Austria team showed that communication between continents with quantum encryption was possible. The latest breakthrough achieved by this group consists of combining quantum communication from the Micius satellite with the fiber-optic network in Beijing. It is the first practical proof that the technology that allows networks to use quantum encryption is already available. How long will it be before we see a commercial application? We probably won’t have to wait for long.
Will Quantum AI replace clinician?
Quantum AI will bring tremendous precision to diagnosis and prognostication. This isn’t to say they will replace humans: what those technologies will provide is a recommendation, one that is perhaps more accurate than it has ever seen, but it will take a savvy, caring, and attentive physician and healthcare team to tailor that recommendation to — and with — the individual seated before them. Over 2,000 years ago, Hippocrates said, “It is more important to know what sort of person has [a] disease than to know what sort of disease a person has.”
In a 1981 editorial on using a computer to interpret risk after exercise stress testing, Robert Califf and Robert Rosati wrote, “Proper interpretation and use of computerised data will depend as much on wise doctors as any other source of data in the past.” This is a timeless principle, so long as it is humans we are discussing and not brake parts on an assembly line.
We come back in the end to the glorious fact that we are human, that we are embodied beings, a mind with all its complexities in a body that is equally complex. The interplay between one and the other remains deeply mysterious. What is not mysterious is this: when we are ill, we have a fundamental need to be cared for; disease infantilises us, particularly when it is severe, and though we want the most advanced technical skills, scientific precision, the test therapy, and though we would want our physicians to “know” us (and unlike the time of Hippocrates, such knowing includes the genome, proteome, metabolome, transcriptome, predictions driven by AI, and so on), we badly want it to be expressed in the form of a caring, conscientious physician and healthcare team.
“We want those who care for us to know our hearts, our deepest fears, what we live for and would die for. That is, and it always will be, our deepest desire. ~ Abraham Verghese, MD Department of Medicine Stanford University”
Although quantum AI is an immature technology, there are improvements in quantum computing which increase the potential of quantum AI. We must look ahead to what a quantum society might entail and how the quantum design choices made today might impact how we live in the near future.
*Opinions expressed are solely my own and do not express the views or opinions of my employer or organizations associated.
