How AI is revolutionizing functional medicine and modern nutritional therapy

How AI is revolutionizing functional medicine and modern nutritional therapy

Functional medicine is at a turning point. Never before has it been possible to measure so many biomarkers simultaneously – from micronutrients and inflammatory markers to genetic variants and epigenetic patterns. But with the growing wealth of data comes a growing challenge:

How can this complex information be interpreted quickly, precisely and systematically in order to develop effective therapies?

This is exactly where EVER-KI comes in – an innovative platform that combines functional diagnostics and artificial intelligence to support therapists in creating individualized nutrient and system protocols.

From measurement to meaning – why interpretation is the bottleneck

Modern diagnostics – whether blood analysis, genetic testing, or laser spectroscopy – now generates datasets with hundreds of parameters. This wealth of information is a treasure, but it also carries risks:

• Misinterpretation due to overcomplexity,
  
• Time required for manual evaluation,
  
• Dependence on the experience of individual experts.
  

Especially with new measurement methods such as laser spectroscopy (e.g. LIBS, which stands for Laser-Induced Breakdown Spectroscopy), which can determine precise concentrations of minerals and trace elements directly in the tissue (intracellularly), the interpretation is crucial.

Laser spectroscopy is an optical emission spectroscopy in which a short, high-energy laser pulse hits the skin (or another material) and creates a microscopically small plasma there

This plasma contains atoms and ions from the sample matrix (e.g., skin, tissue, fluid).
When the excited atoms return to their ground state, they emit light at characteristic wavelengths . This light is analyzed spectroscopically – each element has a specific emission spectrum (“fingerprint”).

Why laser spectroscopy is a game changer

Laser spectroscopy uses a short laser pulse to measure the elemental composition of tissue – in seconds, not days. The method has been shown in scientific studies to be precise, reproducible, and capable of measuring multiple elements [1] [2]. 

• Nature Scientific Reports (2023): LIBS measurements on tissue samples show exact concentration maps of Na, K, Mg with high correlation to reference values. [4]
  
• SPIE Proceedings (1999): Laser ablation can reliably determine mineral distributions in skin, nails and teeth – directly, without chemical preparation. [3]
  

This method enables, for the first time, non-invasive, intracellular mineral analyses that provide a true picture of the current micronutrient status in the tissue – a crucial advantage over conventional blood analyses.

In the DACH region (Germany, Austria, Switzerland), optical measurement methods such as SO/Check (Holigomed) or comparable systems like VitaMedScan are gaining increasing importance as functional-analytical tools. These technologies utilize laser-based spectroscopy (e.g., LIBS) and bioinformatic algorithms to map relative concentrations of minerals, trace elements, and toxic metals in tissue within minutes. In Germany, Austria, and Switzerland, they are already being used in health centers, functional medicine practices, and biohacking studios for monitoring progress, tracking nutritional programs, and optimizing personalized vitality strategies.

Important: However, it is not the measurement itself, but the correct interpretation of the values ​​and their interactions that determines therapeutic success.

EVER AI: Intelligent interpretation instead of data overload

EVER-AI was developed to solve precisely this bottleneck:

A learning AI that recognizes patterns from thousands of parameters, sets priorities, and generates therapy recommendations that are both comprehensible and evidence-based.

The AI ​​analyzes:

• absolute values ​​(e.g. magnesium, zinc, potassium, calcium, trace elements, heavy metals),
  
• Ratios such as Ca/Mg, Na/K, Zn/Cu,
  
• and derived functional indicators such as redox status, detoxification capacity, cell membrane stability or mitochondrial stress.
  

This results in 3-4 main priorities, each linked to specific micronutrient and lifestyle recommendations – including an explanation of why this particular intervention currently offers the greatest leverage. In this way, raw data is transformed into a structured, understandable, and actionable concept.

About the EVER AI database

The EVER AI is based on a continuously growing knowledge base from functional medicine, cellular metabolism, epigenetics, and neuroscience.

Reiner Kraft, Ph.D., has invested more than 10,000 hours in research and practice over the past ten years, evaluating hundreds of scientific studies and integrating the findings into a data-driven, self-experimenting biohacking approach. This knowledge has been systematically applied and validated in his work as a longevity coach – with the goal of measurably optimizing individual health, performance, and quality of life.

These experiences and insights are now incorporated into the analyses and recommendations of the EVER AI – always with a focus on functional balance, prevention, and long-term vitality.

From data to system intelligence: How EVER AI thinks

EVER's technical core consists of several analysis layers:

1. Data Acquisition & Normalization:
   
   Raw data from laser spectroscopy or laboratory analysis are calibrated, scaled, and transferred into a standardized analysis model.
   
   
2. Ratio recognition & pattern analysis
   
   AI algorithms detect systemic imbalances: such as electrolyte dysregulation, redox imbalance, mitochondrial stress or suboptimal detoxification.
   
   
3. Prioritization & Contextualization
   
   Instead of giving 50 recommendations at once, EVER-AI focuses on the 3-4 most important system priorities – those that need to be stabilized first.
   
   
4. Recommendation & Explanation
   
   For each priority, EVER-KI creates a report with specific nutritional and lifestyle measures and a physiological rationale that is comprehensible – even for therapists without years of experience.
   
   
5. Feedback & Learning:
   
   The AI ​​continuously learns from new data: Which measures were implemented, which effects were observed – and dynamically adapts its models.
   
   

Practical example from application

Laser data showed the following in one patient:

• Magnesium and potassium deficiencies,
  
• an excessively high Ca/Mg ratio,
  
• and indications of increased oxidative stress.
  
  

The EVER AI generated three priorities:

1. Stabilize redox balance (N-acetylcysteine, alpha-lipoic acid, selenium),
   
2. Regulate mineral system (magnesium glycinate, potassium citrate),
   
3. Improve detoxification capacity (sulfur-containing nutrients, liver support).
   

The EVER AI automatically interprets the measurement data within minutes, providing data-driven suggestions for potential imbalances and optimization approaches. This analysis can offer valuable insights but does not replace a therapeutic assessment.

The final evaluation and implementation of the recommendations always remain the responsibility of the therapist, who reviews, validates, and individually adapts the AI ​​results to the patient.

This results in an immediately usable, personalized protocol – objectively supported by technology, but always professionally guided by humans.

The vision: Functional medicine reimagined

EVER pursues a clear vision:

An intelligent system that supports therapists in functional medicine and micronutrient therapy in making evidence-based decisions faster, more precisely and reproducibly.

Our goal:

• Democratize access to functional diagnostics.
  
• Making experiential knowledge scalable.
  
• Making systemic connections visible before symptoms arise.
  
• Bridging the gap between modern technology, biochemistry, and preventive medicine.
  

EVER-AI is not a replacement for therapists – but a tool that multiplies expertise.

Current status & invitation to collaborate

The EVER AI is currently in the testing phase. Initial practical experience shows:

• significantly shorter analysis times,
• high agreement with expert assessments,
• clear and comprehensible recommendations.

Currently, the focus is on the evaluation of laser spectroscopy data (SO/Check).
In the next phases, whole blood mineral analyses and other functional laboratory parameters integrated to make the system analysis even more precise and comprehensive.

We invite physicians, therapists and coaches in functional medicine to participate in this pilot project and contribute their feedback to iteratively develop the AI ​​evaluations.

The goal is to continuously improve the functionality and precision of EVER analyses through practical feedback from therapeutic applications

Every piece of feedback from practice helps to make AI evaluation more targeted, understandable and clinically relevant – a shared learning process for even more precise functional medicine.

👉 Register now and test EVER AI

More about the founder

Dr. Reiner Kraft is co-founder of EVER, holds a PhD in Computer Science and is a researcher with over 20 years of experience in AI and systems thinking.

After a career at IBM, Yahoo and Zalando, he devoted himself entirely to optimizing body and mind through functional medicine, epigenetics and neuroscience.

More about his background and research

‍

References

[1] Janovszky, P., Kéri, A., Palásti, DJ et al. (2023). Quantitative elemental mapping of biological tissues by laser-induced breakdown spectroscopy using matrix recognition. Scientific Reports 13:10089.

[2] Gondal, M.A. (2020). Laser induced breakdown spectroscopy for detection of heavy metals in cancerous and healthy colon tissues.

[3] Samek, Ota; Liska, Miroslav; Kaiser, Jozef; Krzyzanek, Vladislav; Beddows, David CS; Belenkevitch, Alexander; Morris, Gavin W.; Telle, Helmut H. (1999). Laser ablation for mineral analysis in the human body: integration of LIFS with LIBS. In Proceedings of SPIE - Biomedical Sensors, Fibers, and Optical Delivery Systems, Vol. 3570, pp. (January 1999). DOI:10.1117/12.336941 

[4] Janovszky, P.; Keri, A.; Palásti, DJ; Brunnbauer, L.; Domoki, F.; Limbeck, A.; Galbács, G. (2023). Quantitative elemental mapping of biological tissues by laser-induced breakdown spectroscopy using matrix recognition. Scientific Reports, 13, 10089. DOI:10.1038/s41598-023-37258-y