CDF-Lyme™: A Composite Diagnostic Fingerprint for Chronic Lyme

A Multi-System Framework for High-Specificity Diagnosis

 This paper is part of the CYNAERA Lyme Library a growing systems based resource for chronic Lyme to improve diagnosis and care.

By Cynthia Adinig

Introduction: Why Lyme Disease Is Still Being Missed

Chronic Lyme disease is often treated as a straightforward tick-borne infection. In practice, it behaves as a multi-system condition shaped by infection persistence, immune variability, co-infections, and environmental exposure. While early detection frameworks work for a subset of patients, a significant portion present later with symptoms that are distributed across neurological, autonomic, inflammatory, and musculoskeletal systems.

These patients are rarely evaluated as a whole. Instead, symptoms are fragmented across specialties, with cognitive dysfunction sent to neurology, tachycardia to cardiology, pain to rheumatology, and fatigue often dismissed altogether. The result is a pattern recognition failure, not a lack of disease presence. Lyme-associated illness is frequently underdiagnosed, misclassified, or delayed due to this structural disconnect (Stanek et al., 2012; Steere et al., 2016).

Emerging clinical and patient-led data consistently show that Lyme disease is not a uniform condition, but a system-level disruption influenced by pathogen persistence, immune response variability, co-infections, treatment timing, and environmental exposures. This aligns with CYNAERA’s broader modeling work, which organizes Lyme into interacting domains rather than a single diagnostic category.

The Composite Diagnostic Fingerprint (CDF-Lyme™) was developed to address this gap. It translates Lyme disease into a structured, multi-domain diagnostic model that reflects how the condition actually presents in real-world patients.

What Is CDF-Lyme™?

CDF-Lyme™ is a composite diagnostic framework that evaluates Lyme disease through cross-system pattern recognition rather than single-test confirmation. Instead of asking whether a patient meets one narrow diagnostic threshold, the model assesses how strongly their clinical presentation aligns with a broader Lyme-associated illness pattern across multiple domains.

The framework is derived from CYNAERA’s Lyme Disease Phenotyping System, which organizes disease expression across ten core domains including infection burden, immune response, neurological involvement, autonomic instability, and structural modifiers. These domains reflect how symptoms cluster, evolve, and interact over time, rather than presenting as isolated findings.

CDF-Lyme™ translates these domains into a quantifiable diagnostic fingerprint. Each domain contributes weighted evidence based on signal strength, reliability, specificity, data completeness, and contextual modifiers such as co-infections or environmental exposure. This allows the model to identify disease patterns even when traditional testing is inconclusive or incomplete.

Importantly, CDF-Lyme™ is not designed as a replacement for existing diagnostics, but as a unifying framework that integrates fragmented clinical signals into a coherent structure. By doing so, it improves recognition of probable Lyme-associated illness and supports more consistent evaluation across clinical and research settings. CDF-Lyme™ is also designed to function upstream of treatment modeling. Within CYNAERA’s broader system, diagnostic fingerprinting informs phenotype-based intervention strategies, including remission-oriented approaches that depend on accurate classification of system state and disease architecture.

The Core Problem: Lyme as a Pattern Recognition Failure

Lyme disease is frequently underdiagnosed not because the condition is rare, but because its presentation is distributed across systems.

Patients often present with:

• cognitive impairment and neuroinflammatory symptoms

• autonomic instability including POTS-like features

• chronic fatigue and post-exertional worsening

• migratory musculoskeletal pain

• gastrointestinal and metabolic disruption

These features are typically evaluated in isolation. Without a system-level model, the overall disease pattern is missed. CDF-Lyme™ resolves this by converting multi-domain signals into a single diagnostic structure.

The 10 Core Domains of CDF-Lyme™

CDF-Lyme™ evaluates disease across ten interacting domains:

1. Infection Burden, Persistence, and Co-Infection Signal

2. Immune Response and Inflammatory Pattern

3. Neurocognitive and Neuroinflammatory Signal

4. Autonomic, Cardiovascular, and Circulatory Instability

5. Musculoskeletal and Connective Tissue Pattern

6. Gastrointestinal, Metabolic, and Nutritional Disruption

7. Hormonal and Endocrine Modulation

8. Sleep, Pain, and Neurological Excitability

9. Functional Severity and Disease Progression

10. Social, Structural, and Diagnostic Modifiers

These domains reflect real-world disease expression rather than isolated diagnostic criteria.

The CDF-Lyme™ Formula 

For a given patient p, the CDF-Lyme™ score is calculated across K domains:

CDF_Lyme(p) = Σ [ w_k · D_k(p) · R_k · S_k · U_k(p) · M_k(p) ]

Where:

• D_k(p) = Domain signal (strength of clinical presence from 0 to 1)

• R_k = Reliability (consistency across cohorts from 0 to 1)

• S_k = Specificity (ability to distinguish Lyme from other conditions from 0 to 1)

• U_k(p) = Usability of data (completeness and quality from 0 to 1)

• M_k(p) = Modifier term (co-infection load, environmental exposure, timing effects)

• w_k = Domain weight (relative importance, sum of all weights = 1)

Each domain produces a Domain Trust Score, and the final CDF-Lyme™ value is a weighted sum across all domains.

This structure ensures the model remains:

• interpretable for clinicians

• auditable for payers and regulators

• adaptable for incomplete data scenarios

Domain Trust Calculation

For each domain k:

T_k = D_k × R_k × S_k × U_k × M_k

Weighted contribution:

C_k = w_k × T_k

Final score:

CDF_Lyme(p) = Σ C_k

This approach allows Lyme disease to be identified through pattern coherence, not just severity within a single domain.

Interpretation Bands

• ≥ 0.75 → High-confidence Lyme-associated illness

• 0.50–0.74 → Probable Lyme pattern

• 0.30–0.49 → Partial or overlapping phenotype

• < 0.30 → Low likelihood of Lyme as primary driver

These thresholds support early identification even when testing is incomplete.

Diagnostic Fingerprint Calculation: Worked Example

Below is an illustrative example demonstrating how CDF-Lyme™ is applied in practice. Values are representative and designed to show how the model behaves under real-world conditions where data may be incomplete.

Patient Profile

• History of tick exposure in an endemic region

• Delayed diagnosis following initial flu-like illness

• Persistent fatigue, brain fog, and sensory sensitivity

• POTS-like symptoms including tachycardia and dizziness when standing

• Migratory joint and muscle pain

• Gastrointestinal disruption and food sensitivity

• Partial response to prior antibiotic treatment

• Environmental sensitivity, including symptom worsening in high humidity and mold exposure

Step 1: Domain Scoring

Each domain is scored across five parameters:

• D_k: Domain signal (0–1)

• R_k: Reliability (0–1)

• S_k: Specificity to Lyme (0–1)

• U_k: Usability of available data (0–1)

• M_k: Modifier (co-infection, environment, timing effects)

Example Domain Values

Domain	D_k	R_k	S_k	U_k	M_k	T_k (Product)	w_k	C_k (Contribution)
Infection & Co-Infection	0.90	0.88	0.92	0.75	0.90	0.493	0.14	0.0690
Immune / Inflammatory	0.75	0.80	0.85	0.65	0.85	0.266	0.10	0.0266
Neurocognitive	0.85	0.82	0.84	0.70	0.80	0.328	0.10	0.0328
Autonomic	0.92	0.90	0.88	0.85	0.88	0.480	0.12	0.0576
Musculoskeletal	0.80	0.78	0.80	0.70	0.85	0.297	0.10	0.0297
GI / Metabolic	0.70	0.75	0.78	0.65	0.80	0.213	0.08	0.0170
Endocrine	0.60	0.70	0.75	0.60	0.75	0.142	0.06	0.0085
Sleep / Neuro Excitability	0.78	0.80	0.82	0.70	0.82	0.293	0.08	0.0234
Functional Decline	0.88	0.85	0.80	0.90	0.90	0.485	0.12	0.0582
Structural Modifiers	0.90	0.88	0.78	0.95	0.92	0.568	0.10	0.0568

Step 2: Final Score Calculation

CDF_Lyme(p) = Σ C_k

Adding contributions:

0.0690

• 0.0266 = 0.0956

• 0.0328 = 0.1284

• 0.0576 = 0.1860

• 0.0297 = 0.2157

• 0.0170 = 0.2327

• 0.0085 = 0.2412

• 0.0234 = 0.2646

• 0.0582 = 0.3228

• 0.0568 = 0.3796

Final Score

CDF-Lyme(p) = 0.38

Interpretation

A score of 0.38 falls within the 0.30–0.49 range, indicating:

Partial or overlapping Lyme-associated phenotype

However, the model highlights strong signal concentration in:

• infection/co-infection domain

• autonomic instability

• functional decline

• structural diagnostic delay

This pattern suggests a high likelihood of Lyme-associated illness that has been partially captured but not fully validated through conventional testing.

Clinical Implications

Based on this fingerprint:

• Further evaluation for co-infections (Babesia, Bartonella) is recommended

• Autonomic testing should be prioritized

• Environmental factors (mold, humidity) should be assessed

• Stabilization strategies should begin before full diagnostic confirmation

This example demonstrates how CDF-Lyme™ identifies clinically meaningful patterns even when data is incomplete, reducing reliance on binary test results and improving early recognition of complex cases.

Why This Matters

Without a composite model, this patient would likely remain:

• partially diagnosed

• misclassified across specialties

• delayed in receiving targeted care

CDF-Lyme™ converts fragmented signals into a structured diagnostic fingerprint, enabling earlier and more accurate intervention.

Why This Model Is Different

Traditional diagnostic models rely on:

• binary test results

• isolated symptoms

• single-specialty evaluation

CDF-Lyme™ instead evaluates:

• cross-system interaction

• temporal variability

• environmental triggers

• structural barriers to diagnosis

This reflects how Lyme disease actually behaves in real patients.

Clinical and Research Applications

CDF-Lyme™ is designed for use across multiple settings:

Clinical Care

Supports earlier recognition and reduces diagnostic fragmentation

Research and Trials

Improves cohort stratification and signal detection

Public Health

Enhances prevalence estimation by capturing underdiagnosed populations

CYNAERA Integration

Works alongside SymCas™ (flare prediction), IACC Twin™ (simulation), and VitalGuard™ (environmental risk modeling)

Economic and System Impact

Lyme disease often leads to prolonged diagnostic pathways involving multiple specialties, redundant testing, and delayed treatment.

By introducing a structured diagnostic framework, CDF-Lyme™ has the potential to:

• reduce diagnostic timelines

• decrease unnecessary testing

• improve treatment targeting

• lower long-term disability burden

This aligns with CYNAERA’s broader Diagnostic Multiplier™ approach, which corrects for underdiagnosis and system inefficiencies.

Conclusion: Toward a New Diagnostic Standard

Lyme disease has remained difficult to diagnose not because it is rare or poorly understood, but because it has been approached through fragmented, single-system models that fail to capture its full complexity. Patients experience a distributed pattern of dysfunction across immune, neurological, autonomic, and metabolic systems, yet diagnostic frameworks have historically evaluated these signals in isolation.

CDF-Lyme™ introduces a structured alternative. By integrating multi-domain signals into a composite diagnostic fingerprint, it enables earlier recognition, improved stratification, and a more accurate representation of disease burden. This approach reflects how Lyme disease actually behaves, rather than how traditional models attempt to define it. This diagnostic structure also supports alignment with emerging intervention models. Within CYNAERA’s Lyme framework, remission-oriented approaches such as Personalized CRISPR Remission™ for Lyme, rely on accurate phenotype and system-state classification, which begins with models like CDF-Lyme™. When diagnosis is more precise, downstream treatment logic becomes more targeted and effective.

As healthcare systems move toward precision medicine, frameworks like CDF-Lyme™ will play a critical role in identifying complex, underrecognized conditions and ensuring that patients are no longer overlooked within clinical and research environments. The shift is not simply toward better testing, but toward better recognition of patterns that have always been present but rarely seen as a whole.

CYNAERA Framework Papers

This paper draws on a defined subset of CYNAERA Institute white papers that establish the methodological and analytical foundations of CYNAERA’s frameworks. These publications provide deeper context on prevalence reconstruction, remission, combination therapies and biomarker approaches. Our Long COVID,  ME/CFS, Lyme and CRISPR Remission Libraries are also in depth resources.

• Primary Chronic Trigger 

• Lyme Prevalence Model US-CCUC

• Corrected National Prevalence Estimates for (IACCs)

• Personalized CRISPR Remission™ for Long COVID

• Personalized CRISPR Remission™ for Lyme

• A Nobel-Scale Advance: AI-Powered CRISPR Platform for IACCs

• CYNAERA’s VitalGuard™ Environmental Flare Risk Engine

• SymCas™: Symptom Modeling Flare Prediction in IACCs

  
  

Author’s Note:

All insights, frameworks, and recommendations in this written material reflect the author's independent analysis and synthesis. References to researchers, clinicians, and advocacy organizations acknowledge their contributions to the field but do not imply endorsement of the specific frameworks, conclusions, or policy models proposed herein. This information is not medical guidance.

Patent-Pending Systems

Bioadaptive Systems Therapeutics™ (BST) and affiliated CYNAERA frameworks are protected under U.S. Provisional Patent Application No. 63/909,951. CYNAERA is built as modular intelligence infrastructure designed for licensing, integration, and strategic deployment across health, research, public sector, and enterprise environments.

Licensing and Integration

CYNAERA supports licensing of individual modules, bundled systems, and broader architecture layers. Current applications include research modernization, trial stabilization, diagnostic innovation, environmental forecasting, and population level modeling for complex chronic conditions. Basic licensing is available through CYNAERA Market, with additional pathways for pilot programs, institutional partnerships, and enterprise integration.

About the Author 

Cynthia Adinig is the founder of CYNAERA, a modular intelligence infrastructure company that transforms fragmented real world data into predictive insight across healthcare, climate, and public sector risk environments. Her work sits at the intersection of AI infrastructure, federal policy, and complex health system modeling, with a focus on helping institutions detect hidden costs, anticipate service demand, and strengthen planning in high uncertainty environments.

Cynthia has contributed to federal health and data modernization efforts spanning HHS, NIH, CDC, FDA, AHRQ, and NASEM, and has worked with congressional offices including Senator Tim Kaine, Senator Ed Markey,  Representative Don Beyer, and Representative Jack Bergman on legislative initiatives related to chronic illness surveillance, healthcare access, and data infrastructure. In 2025, she was appointed to advise the U.S. Department of Health and Human Services and has testified before Congress on healthcare data gaps and system level risk.

She is a PCORI Merit Reviewer, currently advises Selin Lab at UMass Chan, and has co-authored research  with Harlan Krumholz, MD, Akiko Iwasaki, PhD, and David Putrino, PhD, including through Yale’s LISTEN Study. She also advised Amy Proal, PhD’s research group at Mount Sinai through its CoRE advisory board and has worked with Dr. Peter Rowe of Johns Hopkins on national education and outreach focused on post-viral and autonomic illness. Her CRISPR Remission™ abstract was presented at CRISPRMED26 and she has authored a Milken Institute essay on artificial intelligence and healthcare.

Cynthia has been covered by outlets including TIME, Bloomberg, Fortune, and USA Today for her policy, advocacy, and public health work. Her perspective on complex chronic conditions is also informed by lived experience, which sharpened her commitment to reforming how chronic illness is understood, studied, and treated. She also advocates for domestic violence prevention and patient safety, bringing a trauma informed lens to her research, systems design, and policy work. Based in Northern Virginia, she brings more than a decade of experience in strategy, narrative design, and systems thinking to the development of cross sector intelligence infrastructure designed to reduce uncertainty, improve resilience, and support institutional decision making at scale.

References

1. Stanek G, Wormser GP, Gray J, Strle F. 2012. Lyme borreliosis. The Lancet.https://doi.org/10.1016/S0140-6736(11)60103-7

2. Steere AC, Strle F, Wormser GP, et al. 2016. Lyme borreliosis. Nature Reviews Disease Primers.https://doi.org/10.1038/nrdp.2016.90

3. Kugeler KJ, Schwartz AM, Delorey MJ, et al. 2021. Estimating the frequency of Lyme disease diagnoses. Emerging Infectious Diseases.https://doi.org/10.3201/eid2702.202731