hidden

Big Data: The Double-Edged Sword

In today’s climate, industries often talk about the new buzz word of this era, Big data. In this case, Big data refers to data on the macro scale (mostly unorganized and unstructured). The utilization of Big data has tremendous potential for various industries, healthcare included. Facebook, Amazon, Netflix, for example, incorporate big data for their digital structures, creating algorithms to match customers with their interests. Some experts in discussing big data have described it as the three or four Vs; Volume rereferring to a large amount of data; Velocity referring to the timely generation of data; Variety rereferring to the multiple forms of data (e.g., genetics, emails, numbers, surveys); Veracity referring to the quality of the data. I recently discussed the potential of big data in medicine in my expert review article (https://www.tandfonline.com/doi/abs/10.1080/23808993.2018.1528871).

For example, Big data can be utilized to improve decision-making when combined with other emerging technology such as artificial intelligence or quantum internet. It is possible that Big data can combine clinical characteristics (e.g., high HbA1C, high cholesterol, hypertension), multi-omics (e.g., genes, protein, metabolites), lifestyle (e.g., smoking cigarettes, exercise, physical activities, sleep hygiene), and environmental factors (e.g., air pollution, PM2.5, traffic noises) with artificial intelligence in future clinical trials. (Figure) As Dr. Jacqueline Tamis-Holland discussed in the AHA meeting today, current clinical trials do not confirm the genotype-guided antiplatelet therapy. However, this remains just a pipe dream at the present moment. So far, all Big data techniques are primarily descriptive and retrospective. In the future, with advanced computational power (aka quantum computing), leveraging Big data in medicine is promising.

Source: Krittanawong et al. JACC 2017

Big data also has its limitations, and there are several lessons we must learn before implementing it effectively. First, big data is never well-curated and comes with a large degree of heterogeneity. Thus, selecting the correct technology with human power to curate Big data is crucial. Second, analytic companies can misinterpret big data by using incorrect research questions to test their hypothesis or using the wrong tool to analyze the associated data, resulting in delivering false messages. Surgisphere is a prime example of what can go wrong through the analysis of big data. Surgisphere claimed to collect data from over 1000 hospitals worldwide. Although this is possible and emerging technology can accomplish this task with minimal human resources, it is unlikely that this data can also be well-curated. In addition, healthcare data is challenging to work with, as the integration of electronic medical records (EHRs) and data privacy are primary barriers. Another example is the Cambridge Analytica case, where data obtained from Facebook was used without consent.

When appropriately utilized, Big data can be a game-changer for various industries, including the healthcare industry. This requires well-curated data, pertinent research questions, transparency, appropriate analytic tools, and advanced computational powers. In the wrong hands, Big data can be a potent threat that can disrupt industries as a whole.

 

hidden

Tech in Cardiology

Tech in Cardiology

On a recent flight from San Francisco, I found myself sitting in a dreaded middle seat.  To my left was a programmer typing way in Python, and to my right was an oncologist flipping through a slide set on chemotherapy trials.  While this may sound like the beginning of a bad joke, I remember this moment because it got me thinking about the influence of tech on medicine.  The purpose of my trip, by the way, was to interview for a fellowship position in cardiology, a specialty with arguably some of the most impressive tech.

 

Wearables

Not to discount advances in medical devices (e.g. leadless pacemakers, bioprosthetic valves), the emergence of consumer-facing wearable devices is as trendy as ever.  Google recently collaborated with AHA to build its fitness app (Google Fit), which uses algorithms to quantify physical activity in terms of “heart points.”1  The Apple Health app now incorporates EKG capabilities, allowing patients to record episodes of arrhythmias—something I have certainly witnessed in cardiology clinic.2

 

Big data

Big data is an increasingly prominent component of clinical research, and a number of joint ventures with medical and tech leaders have emerged.  One Brave Idea3 is a research collaboration between AHA and Verily (Alphabet’s life sciences division) which uses genomics to study coronary artery disease.  Meanwhile, Verily’s Project Baseline4 is a massive longitudinal observational study—a modern version of the Framingham Heart Study.

 

Artificial intelligence

AI could eventually play a prominent role in medical diagnosis and decision-making.  The Stanford Machine Learning Group5 has developed a neural network that outperforms cardiologists in diagnosing arrhythmias on EKG—a significant improvement on existing algorithms which are often unreliable.  AI also carries vast potential in radiologic interpretation.  Already, Veril is using machine learning to interpret retinal images not only to detect diabetic retinopathy and macular edema but also to extrapolate information about cardiovascular risk.6

 

EMR

Electronic medical records represent an obvious space for tech innovation.  Fast Healthcare Interoperability Resources (FHIR) are making it easier to share health information across our disjointed EMR systems.  Providers are now able to push health data directly to patients’ iPhones using Apple Health Records.7  One can only speculate whether we will see a legacy software giant compete directly in the EMR space.

 

Cardiology and the rest of medicine has long excelled at basic science and translational research, but digital tech is increasingly creeping in.  We are in a tech zeitgeist, and this is good for both patients and providers.

 

References:

  1. https://www.heart.org/en/news/2018/08/21/google-just-launched-heart-points-here-are-5-things-you-need-to-know
  2. https://www.apple.com/healthcare/site/docs/Apple_Watch_Arrhythmia_Detection.pdf
  3. https://www.onebraveidea.org/
  4. https://verily.com/projects/precision-medicine/baseline-study/
  5. https://stanfordmlgroup.github.io/projects/ecg/
  6. https://blog.verily.com/2018/02/eyes-window-into-heart-health.htm
  7. https://www.apple.com/healthcare/health-records/