The world we live in today is one where individual, personalized experiences have become the norm. From the music we listen to, to the TV shows we stream and purchases we make, these are often recommendations based on data collected about us including our purchasing and streaming histories. We often take this ability to know and understand our wants and needs, for granted.
When it comes to monitoring our health and how we care for ourselves, the situation is much the same. Wearable devices such as smart watches and fitness trackers are becoming more widely worn and have made it possible to monitor our ‘health stats’ such as heart rate, calories burned and hours of sleep. This is all vital data that we need to be more effective in utilizing to inform how we eat, sleep and exercise.
As well as how we monitor our own health, the pharma industry is also looking at this data to take an increasingly personalized approach in designing therapies and treatments, to accurately predict and manage what health conditions may arise amongst certain patient groups. Despite pharma’s progress in developing personalized treatments, there is still work to be done before healthcare is tailored to each of our needs. In order to achieve this, we need vast amounts of data and insights on different individuals to create truly personalized medicine and care, and often these huge datasets cannot be collected or analyzed manually.
Combine this challenge with the complexity of the human body, it means we still have a very poor understanding of how human body mechanisms reacts and copes with different diseases. This is where sophisticated technology such as machine learning, to help manage the cast quantities of data, is crucial.
Luckily, we are in a position where this technology is available to us. We just need to apply it in the right manner to take full advantage of its use and the insights it can provide with electronic medical records, to potentially save lives and revolutionize healthcare as we know it.
The data-boom powering personalised healthcare
Although we haven’t reached it yet, truly personalized medicine at scale is only a few years away, and AI technology will be a key driver in achieving this. The amount of data we collect is significantly increasing, with IDC research predicting that the global datasphere will grow from 33 zettabytes of data in 2018, to 175 zettabytes by 2025. To put that into perspective, to download 175 zettabytes of data on the average internet connection speed, it would take 1.8 billion years!
This huge dataset, which includes genetic information and electronic health records like medical history and allergies, has allowed clinicians to look more closely at individual patients and their conditions, in ways that they couldn’t have done before. They are now able to leverage machine learning to identify trends, patterns and anomalies in the data that can help experts make better-informed decisions.
The application of data analytics is also important for personalizing clinical trials and experiences for those enrolled on them. Many trials are still undertaken by giving the same drug or treatment to lots of different people and using a statistical approach, focusing on how the majority react. This is not a ‘personalized’ approach, as every human being has a unique genetic make-up and specific biomarkers. As a result, drug efficacy can differ from person to person – and this should be reflected in the way clinical trials are carried out.
Building a clear view of every patient
Each one of us has a unique variation of the human genome, so the ability to understand which gene mutations or differences may cause specific illnesses will be instrumental for clinicians to predict a health condition before it arises, and prevent it from developing. This understanding lends itself to more comprehensive disease management plans to mitigate risks when they do arise.
One example of providing earlier intervention in action, is with cancer treatments. A few years ago, the same treatment was once routinely given to patients with the same type and stage of cancer. However, we now understand that different people may experience unique genetic changes in their cancer cells and/or their genetics will affect how their body responds to the cancer; both these factors will affect how their cancer progresses. With better understanding of disease progression through the analysis of patient data, precision medicine and targeted therapies can be developed and used to help predict which treatments a patient’s tumor is most likely to respond to.
To be able to provide personalized medicine to this extent, building a full view of every patient is key. To do so, we must collate data on a daily basis with health records and lifestyle behaviors from disparate sources into one full view. This data is crucial to understand and analyze the needs of each patient, which can be used to inform both how drugs are developed, and the type of care that a patient receives. It is these huge datasets that hold vital clues to how chronic diseases manifest so pharmaceuticals and clinicians can identify patterns between lifestyles and illnesses developing to provide earlier intervention.
However, the ability to do this, hinges on being able to collect, map and analyze insights from vast amounts of data across disparate sources – a process that cannot be carried out manually. To put the amount of power it would take to process the data manually into perspective, it would require the equivalent of the sun’s output power for a whole week just to model a single human’s genome. Clearly, this is not a sustainable model, and will not allow us to personalize healthcare at scale.
AI: The key ingredient for truly personalised medicine
This is where AI comes into its own, and can provide huge benefits in solving the key challenges healthcare providers face when it comes to big data – velocity, volume, variety and veracity. In fact, nearly 80% of respondents in a recent Oracle Health Sciences survey revealed that they expect AI and machine learning to improve treatment recommendations for individuals.
The benefits are clear. With AI and machine learning capabilities, pharmaceutical companies can collect, store and analyze large data sets at a far quicker rate than by manual processes. This enables them to carry out research faster, based on data about genetic variation from a huge wealth of patients, and develop targeted therapies faster. In addition, it provides a clearer view on how small, specific groups of patients with certain shared characteristics react to treatments, and therefore how to precisely map the right quantities and doses of treatments to give to individuals.
As a result, this optimizes the level of patient care clinicians can provide. In an ideal world, we want to prevent disease. By having more information at our fingertips about why, how and in which person diseases develop, we can introduce preventative measures and treatments much earlier, sometimes even before a patient starts to show symptoms.
How can personalised medicine advance?
Personalized medicine has the potential to improve, and even save the lives of many people, and AI and machine learning are a driving force behind making future breakthroughs. By harnessing their power along with cloud computing processing, we can also then begin to reap the benefits of more innovative technologies that are emerging in the industry including using 3D printing to offer a tailored dose of a drug to each patient.
As wearable technologies and IoT devices continue to rise in use, with an expected 1.3 billion IoT subscriptions expected by 2023, and 26.6 billion IoT devices in use in 2019, the amount of personal data we collect on ourselves will only grow – opening more opportunities for bespoke healthcare experiences for patients.
There are still many challenges that lie ahead for personalized medicine, and a way to go for it to be perfected. But as AI becomes more widely adopted in medicine, a future of workable, effective and personalized healthcare will certainly be achievable.
- Alan Payne, CIO at Sensyne Health.
- we've featured the best cloud storage.