Your cardiovascular system deserves its own normal range.

SaluTests is a software-based physiological modelling and phenotyping platform. It can be configured for different institutional contexts, including research, advanced wellness, physiological assessment, clinical research, and, where appropriate, clinical or trial decision support, e.g., as CDSS (Clinical Decision Support System) or Digital Health & Corporate Wellness Optimizer / Physiological Capital Ledger. Its core function is not to replace a diagnostic measurement or clinical diagnosis, but to characterize individual physiological regulation by deriving dynamic phenotypes from cardiovascular signals and their responses to controlled physiological perturbations. Rather than defining an individual primarily by population averages or diagnostic labels, SaluTests models the individual's physiological response architecture and how that architecture changes under different conditions. SaluTests therefore functions as a physiological intelligence layer that can be adapted to partner-specific applications without requiring dedicated proprietary diagnostic hardware. Its regulatory qualification is determined by the intended purpose and functionality of each specific deployment and version of the system. Regulatory requirements are therefore considered together with the intended use and deployment context of each partner project. We did not start with a software product and look for a clinical problem. We started with a physiological model and built the computational infrastructure required to observe it continuously. Scientifically validated physiological model → computational engine → partner-specific application.

The reference is neither a population-wide average nor a static diagnostic label. The primary reference is the individual's own physiological response architecture under controlled perturbations, including standardized clino-orthostatic positional shifts. This allows SaluTests to examine how the cardiovascular system dynamically regulates hemodynamics across changing physiological states, rather than simply determining whether an isolated measurement falls inside or outside a population-derived reference range. In this framework, the clinically or scientifically relevant question is not only “How does this value compare with the population?”, but “How does this individual's regulatory system respond when challenged?” The individual's reproducible physiological responses therefore provide the reference framework against which subsequent changes can be characterized.

SaluTests analyzes cardiovascular dynamics derived from optical pulse-wave signals, with particular attention to how multiple physiological domains change and interact over time. Rather than reducing the recording to isolated values such as heart rate or a single variability index, the system preserves pulse-wave morphology within strictly defined Trusted Windows and reconstructs coordinated physiological domains. These domains characterize cardiac activity, its systemic energy cost, vascular compensatory activity, and blood-volume reserves. The resulting representation is not intended to be a collection of independent biomarkers. It describes the dynamic organization of cardiovascular regulation — the physiological architecture through which the system maintains stability and responds to perturbation.

SaluTests is not validated by asking whether its output reproduces a diagnostic label or a population classification. The underlying physiological model is evaluated by examining whether it captures reproducible physiological responses to controlled perturbations and whether independently derived physiological domains show meaningful concordance. Controlled perturbations provide a structured way to observe the regulatory system rather than relying exclusively on static measurements. The resulting response architecture can then be examined across repeated measurements, experimental conditions, physiological states, and partner-specific interventions. Subsequent translational studies examine whether identified physiological phenotypes correspond to differentiated responses to specific interventions. The central validation question is therefore: Does the model reliably capture meaningful differences in physiological regulation? The conceptual sequence is: controlled perturbation → reproducible physiological response → physiological phenotype → intervention response A diagnosis may describe what condition is present. The physiological phenotype addresses a different question: what regulatory configuration may be producing the observed state?

Conventional physiological assessment often interprets individual measurements against population-derived reference ranges or considers measurements separately. SaluTests instead treats individual reactivity as part of the reference framework. It analyzes changes in pulse-wave morphology during controlled perturbations and reconstructs the coordinated behaviour of multiple hemodynamic domains. This allows the system to characterize different configurations of cardiac activity, vascular compensation, systemic energy cost, and blood-volume reserves that may produce superficially similar observable states. Thus, two individuals may present with the same measured value while reaching that state through substantially different physiological configurations. To illustrate this (Same Number. Different Physiology): • Conventional view: BP = 145 mmHg ➔ Judged as an absolute number above a population threshold. It receives a rigid classification and standard guideline (trial & error or polypill) pathway, with outcomes monitored only afterwards. • SaluTests view: BP = 145 mmHg ➔ Judged merely as an observed parameter. The core focus shifts to the response architecture and different physiological phenotypes (e.g., BP increased through blood volume expansion or vascular constriction), with the response dynamically monitored in real time. Ultimately, the number (e.g., BP = 145 mmHg) is the observation. The phenotype (e.g. a volume-dominant [sensitive to diuretics] or vasoconstriction-dominant [sensitive to vasodilators] regulatory configuration) describes the physiological response architecture that may help inform the selection and evaluation of interventions.

In our framework, a phenotype is not a static catalog of physical traits or categorical health labels. It is defined as an individual's unique regulatory response architecture and the metabolic or dynamic 'price' the organism pays to sustain internal stability. This means that the true markers of health and longevity are the phenotypical variations hidden underneath identical health and clinical baselines. Two individuals can display the exact same textbook 'normal' values, yet belong to entirely different physiological phenotypes. While one maintains this norm effortlessly, the other may achieve it through critical over-compensation, exhausting structural and volumetric reserves. It is this hidden regulatory strain that eventually breaks down and manifests outwardly as symptoms of disease. Furthermore, this phenotypical sovereignty persists even after pathology develops: the dynamic cost of adapting to a disease state is deeply heterogeneous across individuals. By decoding these distinct regulatory configurations before they collapse into uniform diagnostic buckets, SaluTests provides pharmaceutical R&D, clinical trials, and elite performance teams with a precise mathematical layer for patient stratification and proactive intervention mapping.

Biological signals inevitably contain noise and artefacts. The objective of SaluTests is therefore not to eliminate every irregularity through aggressive signal transformation, but to identify time windows in which the physiological recording is sufficiently reliable for analysis. Through its Trusted Windows approach, the system identifies valid segments of the raw recording while preserving the recorded pulse-wave morphology within those windows. This avoids relying on destructive smoothing as a substitute for physiological validity. Morphological features that may carry information about vascular and hemodynamic regulation are therefore retained rather than being removed simply because they deviate from an expected waveform. In this sense, SaluTests separates signal validity from signal alteration: unreliable portions can be excluded, while valid physiological morphology is retained in its native form.

Conventional machine-learning approaches can derive predictive relationships from physiological signals without necessarily providing an explicit physiological representation of the mechanisms underlying those relationships. SaluTests takes a different approach through its proprietary Neurosymbolic Biometric Intelligence (NBI)™ engine. First, the system does not treat the continuous physiological stream as an undifferentiated input. It identifies strictly defined Trusted Windows and preserves the recorded pulse-wave morphology within those windows rather than smoothing or destructively filtering it. These signals are then used to reconstruct four core hemodynamic domains: cardiac activity, its systemic energy cost, vascular compensatory activity, and blood-volume reserves. Second, the symbolic layer constrains inference through explicit physiological rules, constraints, and deterministic models. The platform therefore evaluates dynamic interactions among the physiological domains within physiologically admissible states. This makes each conclusion traceable to defined rules and measured variables rather than relying solely on opaque statistical correlation.

SaluTests separates the physiological engine from the application layer. The same underlying physiological model can be applied to different questions depending on the partner, population, intervention, and intended use. The translational pathway is therefore: research discovery → physiological model → computational engine → partner-specific application. For example, a physiological phenotype may be used to characterize heterogeneity within an apparently similar population, investigate differentiated responses to an intervention, monitor changes in resilience, or support individualized physiological assessment. In pharmaceutical and therapeutic research, this creates a potential framework for identifying mechanistic phenotypes within apparently homogeneous syndromes and exploring whether those phenotypes correspond to differentiated treatment responses. SaluTests does not assume that one physiological phenotype maps automatically to one diagnosis or one treatment. Rather, it provides a physiological representation that can be investigated and operationalized within the context of a specific partner project.

SaluTests uses Physiological Health Capital to describe an individual's available physiological capacity for adaptive regulation, recovery, and maintenance of functional stability. This differs from conventional concepts of health based primarily on the absence of disease or on population-derived biomarker ranges. The framework distinguishes between the Price of Living — the ongoing physiological resources and regulatory effort required to maintain stability — and the Price of Health — the capacity to respond flexibly to perturbation and return toward an individual's characteristic physiological state. The computational concept of Price of Orchestration describes the regulatory effort associated with maintaining coordinated function across interacting physiological domains. Physiological Health Capital is therefore not a score derived from isolated biomarkers. It is a dynamic representation of the regulatory capacity available to an individual and how that capacity changes over time and in response to interventions. This framework also introduces the concept of Health Capital Realization: the degree to which resources or interventions directed toward maintaining or improving health are expressed as measurable changes in physiological adaptive capacity. In principle, this creates a way to investigate not only how much is invested in health, but how that investment is physiologically realized. Health Capital Realization = physiological response gained per unit/type of health intervention

Current pilot deployments use validated third-party optical sensors capable of providing access to raw PPG data through compatible Bluetooth Low Energy infrastructure. The platform has been tested with Polar Verity Sense and Polar OH1/OH1+ sensors using compatible mobile logging utilities for raw signal acquisition and SDK dataset export. This acquisition layer is currently part of the deployment architecture rather than the core SaluTests physiological engine. A dedicated SaluTests acquisition layer is part of the platform roadmap, allowing the complete signal-acquisition-to-phenotyping workflow to be progressively brought under SaluTests control. Hardware requirements may therefore evolve as the acquisition layer develops.

SaluTests is designed as a physiological intelligence layer rather than a fixed clinical information-system integration. The core engine processes physiological signals, reconstructs individual response architecture, and generates physiological phenotypes. How these outputs are exposed to a partner's environment depends on the intended application, workflow, and data architecture of the deployment. For this reason, SaluTests does not impose a one-size-fits-all API, FHIR, or HL7 integration model at the platform level. Integration interfaces can be defined during partner-specific deployment and co-development, including API-based access where appropriate and interoperability with existing clinical or research systems where required. Detailed integration architecture, data schemas, and deployment interfaces are discussed as part of the partner-specific technical and regulatory assessment.

Confidentiality, data integrity, and separation of physiological data from subject identity are treated as architectural requirements. Physiological data are encrypted in transit using TLS 1.3 and encrypted at rest using AES-256 standards. The cloud architecture separates physiological signal processing from subject identity wherever the deployment architecture permits. Access controls, auditability, data minimisation, and partner-specific data governance requirements are incorporated into deployment design. Specific compliance and data-processing requirements are determined according to the intended use, jurisdiction, institutional environment, and contractual structure of each deployment.

SaluTests is designed primarily for innovation-driven partnerships rather than a conventional off-the-shelf software procurement pathway. We work with innovation, R&D, strategic partnership, research, clinical, pharmaceutical, wellness, longevity, and human-performance organizations to define how the physiological engine can address a specific unmet need. A partner engagement can begin with a scientific discussion, followed by a review of the intended application, physiological question, population, intervention or perturbation, data architecture, and deployment requirements. Where appropriate, technical documentation, phenotype-related reports, validation materials, and deployment architecture can then be reviewed under the appropriate confidentiality framework. Research discovery → physiological model → partner-specific study → application and deployment.

The difference is not primarily the number of measurements collected, but what those measurements are intended to reveal. Consumer health platforms have made physiological monitoring accessible through attractive interfaces, continuous tracking, gamification, and increasingly sophisticated signal processing. These are valuable achievements. However, attractiveness, engagement, and quantity of metrics should not come at the expense of the fidelity or physiological significance of signal acquisition and interpretation. A large number of measurements does not necessarily produce a deeper understanding of physiology. A metric can be accurate as a measurement and still have limited physiological meaning when interpreted as an isolated value or population-derived proxy. This is particularly important when signal processing is optimized primarily for stability, readability, or user experience. For example, smoothing can produce a cleaner and more visually coherent waveform, while simultaneously removing morphological variations that may be physiologically informative. SaluTests therefore takes a different approach: rather than optimizing the signal primarily for presentation, it seeks to preserve valid physiological morphology and determine when the recording itself is sufficiently trustworthy for physiological inference. SaluTests focuses instead on individual physiological dynamics: how multiple regulatory domains interact, how the system responds to controlled perturbation, and how those responses change over time. A metric can therefore be accurate without necessarily being physiologically informative. SaluTests is designed to move from isolated measurements toward an integrated representation of individual physiological regulation. The objective is consequently not to produce more metrics, but to extract more physiological meaning from the information contained in the signal. More data is not necessarily more knowledge. More metrics are not necessarily more physiology.

Existing frameworks such as allostatic load have made an important contribution by recognizing that health cannot be understood through isolated biomarkers alone. However, they primarily characterize the accumulated burden of physiological dysregulation through composite sets of measurements. Extending the analogy of notes, musical compositions, and orchestras, allostatic load can be viewed in this context as a structured record of what has been observed: which physiological “notes” are present, how many are altered, and in what proportions. SaluTests addresses a different question: how are those physiological components actually coordinated like in a music composition or sounded in orchestration? Two individuals may therefore exhibit similar numbers or magnitudes of physiological deviations while maintaining very different relationships among the underlying regulatory systems. One configuration may remain highly coordinated and adaptable—physiologically consonant—while another may exhibit marked discordance between regulatory domains, or require more regulatory effort to maintain apparently similar concordance in the composition. In this sense, the distinction is between the inventory of physiological strain (the cost of orchestration) and the architecture of physiological integration (for supporting living or health). SaluTests describes this integrative dimension through the concept of Physiological Consonance: the degree to which interacting physiological domains remain dynamically coordinated across changing states and controlled perturbations. The objective is therefore not simply to count how many physiological systems show signs of strain, but to characterize how the system as a whole is organized, how much regulatory effort is required to maintain stability or resiliency, and how flexibly that organization responds to perturbation.

No. HRV represents an important and physiologically rich component of cardiovascular regulation, but it captures only one aspect of the broader integrative architecture addressed by SaluTests. Heart-rate variability reflects dynamic variation in cardiac cycle length and its modulation by multiple physiological processes. Its physiological significance cannot, however, be reduced to a single index, nor can HRV by itself represent the complete coordination among cardiac activity, vascular regulation, blood-volume distribution, and the energetic cost of maintaining systemic stability. Physiological Consonance addresses this broader level of organization. It concerns the dynamic relationships among multiple physiological domains and how those relationships are maintained, altered, or restored under changing conditions and controlled perturbations. This distinction also separates the SaluTests framework from approaches in which HRV is used as a general-purpose proxy for autonomic balance, adaptation, resilience, stress, or psychological state.