Today's Clinical Lab - News, Editorial and Products for the Clinical Laboratory
Clinicians reviewing lab test results on a tablet
Clinical labs may be shifting to a data-centric model
 iStock, Zinkevych

Lab of the Future: Shifting to a Data-Centric Approach

​​​​​​Among the changes could be the creation of a patient’s ‘digital twin’

Juan Cruz Cuevas, MS, PhD, MBM
Juan Cruz Cuevas, MS, PhD, MBM
Juan Cruz Cuevas, MS, PhD, MBM

 Juan Cruz Cuevas, MS, PhD, MBM, is senior vice president of marketing and business development at Probius. Passionate about marketing disruptive technologies, he has led commercialization projects in several successful companies in life sciences and health care.

ViewFull Profile
Learn about ourEditorial Policies.
Published:May 06, 2024
|3 min read
Register for free to listen to this article
Listen with Speechify

The world of diagnostic medicine is swiftly evolving, inciting a revolution of sorts within the laboratories that support its growth. 

Advances in artificial intelligence have become a catalyst for disruption, allowing the lab of the future to unfold now. This revolution will be fueled with one crucial shift: replacing today’s reagent-centric model with a data-centric approach.

Complexity in assays is not efficient

Laboratory medicine is a digital science. Large healthcare institutions produce a wealth of biological data, from simple numerical results to complex “omics” assays. Enriched with clinical data, laboratory medicine will allow for an increase in pathophysiological insights, improving patient care. 

Today, offering timely and objective data to healthcare professionals requires laboratory medicine to rely on numerous bespoke assays and complex analytical techniques. It includes multiple specific reagents, instruments, and sample preparation techniques that drive complexity, specialization, and cost while increasing regulatory burdens. 

This reagent- and analyte-centric lab is inefficient. Consider a typical scenario: A physician hypothesizes that a patient may have a specific health problem. 

In turn, a lab receives that patient’s blood samples to test for a panel, requiring specific sample extraction and preparation, reagents, and equipment. Results take time to process, so the patient has a return visit scheduled. If the physician’s initial hypothesis is wrong, the process starts over, elongating diagnosis time and increasing costs. 

But change is coming to the current state of affairs. Recent technological advances in lab automation have enhanced modern laboratory medicine by adding value and efficiency. 

Yet automation can take us only so far. Reimaging laboratory workflow will expand data collection and integration, moving us toward the lab of the future and bringing testing closer to the patient.

The emergence of a patient’s ‘digital twin’

What if health care could start with a “hypothesis-free” approach to patient care, one that takes a general snapshot of molecules and signatures in a sample? 

This model could facilitate a physician’s iteration in real time, analyzing only what is needed while the patient is still in the doctor’s office, or moving quickly to identify which biomarker is not in the normal range or has changed since the last test. Is this possible with proteins, metabolites, and molecules? 

New applications of nuclear magnetic resonance and mass spectrometry, innovations in spectroscopy, and novel technologies in metabolomics and proteomics are enabling a different approach to healthcare: the “digital twin.” By using reagent-less techniques that can create low-bias mathematical representation of the molecules in a sample, technology can create a digitized version of the patient.

Providers can use a digital twin to quickly compare it with other samples or against samples from the same patient across time. This approach would allow development of new digital assays and classifiers in real time just by reanalyzing data instead of reanalyzing aliquots of a sample.

The dawn of the data-centric era 

As with all medical breakthroughs, the biggest challenge to adopting a novel approach will be with regulatory approval. We have seen this before with whole-genome assays. Lesson learned? Regulators, experts, and manufacturers will work together because efficient, predictive healthcare lies in offering physicians and patients accurate, precise information. 

As business dynamics change, so will expectations within the lab. To embrace these changes requires proof of efficiency and effectiveness. Simplifying the lab workflow for workers and automation platforms and accelerating the time to diagnosis may be the impetus for acceptance.  What is certain is that AI and data will drive changes in lab medicine, and patients will ultimately benefit from those changes.

The lab of the future is a reality that healthcare professionals are progressively living in today. The shift from the reagent-centric to data-centric model is redefining the contours of laboratory medicine, proving that the heart of the lab beats with data. This shift enables more efficient diagnostics, real-time insights, and unprecedented advances in preventive and personalized medicine.