Developing a product is a dynamic and nuanced process, encompassing planned activities that enable a…
Societal development goes hand in hand with data, and with the birth of the Internet, global data volume doubled every 40 months since the 1980s. Big data was coined as a concept in the 1990s to put a name to this data growth. Big data has volume (big), velocity (fast), and variety (diverse), and they are used across all disciplines. One of its important uses is definitely in medical research. Today, let’s join us at Blacksheep in exploring the roles of Big Data in medicine!
2. Transformative applications:
With access to much larger volumes of data, and with the right analytical methods, we can use Big Data to transform our lives: reduce development cost, reduce treatment costs, predict and prevent outbreaks of epidemics (such as COVID), give personalized healthcare, among other applications.
For example, drug development is a prolonged and expensive process. It is at large a chance discovery of various exploratory stages and rigorous testing phases. The lengthy drug development pipeline and the slim chance of success usually put financial strain for companies while also leaving patients with scarce treatment choices, especially those with rare diseases.
With big data, we can shorten the timeline. Data can help identify therapeutic targets, predict drug efficacy, and thus optimize the clinical trials.
Figure 1: Big data in medicine
Genomics is another emerging realm of medical research. Most notably, biobanks store biological specimens on both local and international levels. Some companies use biobank data for ancestry verification. Some multinational projects, such as Human Genome Project, use biobanks to build a genetics map of humankind. This map will then help predict and identify diseases, design “custom” drugs, and many more. We can also use big data in other applications of medical research, to name a few:
• Precision medicine, where treatments are customized for each patient
• Clinical data analysis, to assess efficacy of treatment, progression of diseases, and risk factors
• Remote monitoring and continuous care at the point of care. This brings better care for patients, and also better research data of the disease in concern
In Blacksheep’s case, we most notably make use of Big Data in the research & development of our ventilator. When the patient is connected to the ventilator, their patient profile is also set in a connected mobile device. The monitoring data is shown on both the machine’s screen and the mobile device, allowing the healthcare practitioners to monitor the patients from afar.
With sufficient data points, the machine also starts using machine learning and artificial intelligence to predict and adapt to the patient’s breathing patterns, making sure they get the personalized care they need.
Over a long period of time, encrypted ventilation data are also pooled as large epidemiological data. Medical researchers can glean insights, patterns and trends from the ventilator’s dashboard to arrive at critical decisions for preventing and controlling respiratory diseases.
Figure 2: Model of Blacksheep’s Ventilator – ROBO2
3. Big data changing the way we do things:
Big Data is transforming not only the various applications in research (“What”), but it is also transforming the way we do thing (“How”). We have emerged from the traditional method of Randomized Controlled Trial (RCT) to master clinical trial protocols, platform trials, basket/bucket designs, and umbrella designs.
• Basket trials focus on specific genomic alterations across various tumor types to tailor treatments
• Umbrella designs explore a single disease with different therapies for various mutations
• Platform trials, driven by big data, provide patients access to multiple trials with a single control arm compared to various experimental arms.
These new methods address the shortcomings of traditional ways of things, enhancing precision and accuracy of data collected, visualizing interactions of variables (e.g. different medication), and giving researchers handy daily updates. Surely the way to go forward!
4. Challenges and opportunities:
Even though big data is transformative in many fields, the sensitivity of medical research cautions us to be careful. There have been published cases of premature release of drugs (e.g. prematurely released drug Venetoclax in BELLINI trial raised mortality risk, prompting FDA to stop enrolment) and privacy breaches (e.g. exposing criminals’ relatives’ DNA data). Researchers must clarify questions about data ownership as well as establishing trustworthy research systems for participants, patients, and physicians.
On the other hand, we acknowledge that government regulators still grapple with a shifting legal framework encompassing information accessibility, power imbalances, compatibility, privacy, rushed drug releases, insufficient technology vetting, ethical concerns related to AI predictions, data ownership ambiguity, financial challenges, and a lack of public awareness for biobanks. Navigating this complex terrain requires careful consideration for the responsible and ethical use of big data in advancing medical research.
Photo by @BillionPhotos at Freepik
Despite the challenges, the transformative power that we identified at the start of this blog is sufficient to encourage the collective research community to work harder together. Big Data technology is getting more and more affordable, promoting collaboration among industry – regulatory bodies – academic institutions. Widespread internet access is also promoting citizen science, allowing everyone to participate in the data collection process. As humankind, we are balancing the challenges and opportunities of Big Data with deliberate, ethical approach across all scales and levels.
Big Data brings with it ample opportunities and challenges. The transformation of data into meaningful insights is stands as a crucial aspect. Upholding data security and transparency is a shared goal to build and sustain public trust as we journey towards groundbreaking advancements in personalized healthcare.