Source: Deutsche Nachrichten
Modern medicine stands as one of the greatest achievements of our era. It can detect, classify, and treat conditions with unprecedented precision. Yet its very success reveals a structural limitation: our medical system is largely reactive, intervening only once a disease has become visible.
When symptoms appear. When thresholds are crossed. When a lab result turns abnormal. In short: when a diagnosis can be made.
Most of us have experienced the flip side. You go in for regular check-ups, your individual lab results fall neatly within normal ranges, and yet your overall biological state quietly drifts over months or years without triggering a single alarm.
That is because biological developments begin long before clinical detection. Metabolism, the immune system, hormonal balance, inflammation, diet, sleep, stress, and environmental factors continuously interact. Health is not a static baseline, but a dynamic equilibrium.
This equilibrium has a name: homeostasis. It describes the body’s ability to preserve inner stability even as external and internal conditions continuously change. Humans are not static systems; we are living networks of biological processes undergoing constant adaptation.
This is precisely where modern prevention faces its challenge. Biological parameters fluctuate continuously. What matters is not every minor change, but whether the body can continue to compensate and preserve its individual homeostasis – or whether its overall state is beginning to drift. This shift can happen well before a single test value crosses a diagnostic threshold.
Pre-Pathology: The Space Before Diagnosis
Between stable homeostasis and manifest disease lies a transitional biological space – one many recognize from hearing their doctor say, ‘We’ll just have to wait and see.’ A lab value has shifted, but on its own, it is not enough to make a clear diagnosis. SF2 is investigating whether the combined interaction of many parameters can reveal an overall biological state during this waiting period.
“We propose the working term pre-pathology to characterize this transitional phase – not as a new diagnostic label, but as a methodological framework for the stage between stable homeostasis and active illness,” says Francisco Webber, CEO & Chief Scientist of SF2 Systems.
Pre-pathology is not about diagnosing illness sooner. Instead, it names an intermediate space where changes in a person’s overall biological system might be assessed well before standard diagnostic criteria are met.
This opens a new entry point for preventative healthcare. Effective prevention isn’t simply a matter of earlier diagnosis – it’s about gaining insight into biological developments prior to clinical onset.
Understanding the Patient, Not the Lab Value
Viewing lab values in isolation simply falls short. A single value might be analyzed with total clinical accuracy and yet reveal only a fraction of what is actually happening.
The true signal lies in the context: How do multiple parameters relate to one another? How do they evolve over time? Is the organism continuing to adapt, or is it exhibiting a persistent drift in its overall state?
SF2 Systems’ technology, Semantic Folding Sensor Fusion, maps multiparametric data into connected state spaces. This yields Patient State Fingerprints –compact, comparable representations of an individual’s overall biological state that provide a qualitative measure of homeostasis. SF2 uses the term semantic drift to describe recurring patterns that shift away from baseline reference states.
Such a drift is not automatically a sign of disease. Differentiating normal variations from pathology in humans is complex: biological states naturally vary with time of day, diet, sleep, exertion, hormones, stress, and environmental factors.
Crucially, SF2 does not need to know the underlying biological cause to identify a reproducible drift pattern. Identifying the pattern comes first; defining its biological and clinical meaning follows.
Metaphorically, this state information acts much like a canary in a coal mine: it does not explain the cause or diagnose a condition – it simply provides an early warning that conditions have changed and require attention.
While conventional medicine remains indispensable for evaluating, diagnosing, and treating active diseases, SF2 turns its focus to the critical window before disease takes root.
Routine Blood Data as the Foundation
The first step utilizes data already produced in everyday clinical workflows.
SF2 Systems and the Medical University of Vienna are scientifically evaluating whether routine lab data can be read as a unified system state, revealing cross-parametric shifts.
Routine clinical data is uniquely suited for this work: it is well-established, widely available, and provides a rigorously controlled environment for methodological study.
Time is the essential factor in state-based prevention:
– A single test result is merely a snapshot.
– A longitudinal profile shows a trajectory.
Only repeated measurements can distinguish whether a variation is random and transient, or part of a deeper, sustained trend.
“Laboratory medicine is facing a key challenge: precision medicine must be integrated into diagnostic practice. Current reference ranges are population-based – a value may look perfectly normal for one person while representing a marked departure from another’s individual equilibrium. The future lies in personalized reference limits and evaluating multi-parameter patterns over time, rather than looking at isolated values. Whether such patterns can be methodologically derived from routine clinical data in a robust manner is precisely what we are evaluating across several projects,” says Ap. Prof. Priv.-Doz. Mag. DDr. Helmuth Haslacher, Head of the MedUni Vienna Biobank and Senior Physician at the Department of Laboratory Medicine, MedUni Vienna.
Genetics and Non-Invasive Diagnostics on the Horizon
Over the long term, two additional layers of information could become important: genetic context and frequent, low-friction metabolic measurements.
Genetic information can provide vital context regarding the individual background against which biological changes occur. While genetics defines neither health nor disease, it helps us interpret personal differences more accurately.
For longitudinal monitoring, sampling frequency represents a critical determinant. Recent research out of Vienna shows that finger sweat can be utilized for metabolomic analysis.
Simple, non-invasive sampling could ultimately facilitate metabolic datapoints between routine check-ups. While both represent future avenues, SF2’s immediate research focuses squarely on routine clinical lab data.
Vienna as an Innovation Hub
Vienna’s clinical and scientific ecosystem offers fertile ground for research into data-driven preventative care. Combining routine clinical data with genetic context and longitudinal metabolic tracking could create entirely new reference frameworks for individual biological states – backed by clinical medicine, research, and public healthcare institutions.
Prevention Before Diagnosis
This question is also gaining weight in healthcare policy.
Healthcare systems are under severe pressure: chronic illness is on the rise, demographics are aging, and healthcare costs are soaring. At the same time, massive volumes of medical data are generated daily yet we barely tap into them to better understand health as an active, fluid state.
A pre-pathological view of the system doesn’t open with the question:
What disease does this person have?
It intervenes earlier: Is this person still maintaining their individual homeostasis, or is their biological state beginning a sustained drift?
Defined in these terms, prevention is
Not reactive.
Not symptom-driven.
Not purely threshold-bound.
Instead, it is longitudinal, data-driven, and systemic.
While future medicine must remain equipped to diagnose and cure disease, it must also learn to better grasp, track, and protect human homeostasis over the lifespan.
About SF2 Systems
SF2 Systems GmbH, based in Vienna, Austria, develops Semantic Folding Sensor Fusion, a technology for analyzing the states of complex systems. It transforms multivariate data into compact, comparable State Fingerprints.
In addition to industrial applications, SF2 is investigating how this approach can be applied to biological and medical state data. Medical applications are currently in the research and scientific evaluation stage and are not approved for medical diagnostic use.