Admittedly, the question in the title “Why Model-Guided Medicine will become a main pillar for the future health care system?” is more of rhetorical nature, since Model-Guided Medicine (MGM) is not argued to come, but is already there—only that we do not perceive it as such, or even have begun to use its potential towards more dynamic and personalised applications. The current form of MGM is often characterised by heterogeneity, sequential processes, and a largely analogue approach. Our ability to translate medical knowledge into models has advanced, but many of these models are still isolated in their application, lack digital integration, and are far from the personalised care we envision. The transition to MGM is not merely evolutionary but represents a completely new understanding of health care, aiming to overcome many of the limitations encountered thus far, see Fig. 1. By focusing on comprehensive data utilisation, patient-centric modelling, and adaptive learning, MGM introduces a dynamic and interactive healthcare environment. Combining and modelling decision- and process-relevant aspects, based on mathematically sound and transparent methods allows for Model-Based Medical Evidence (MBME), introduced by Berliner and Lemke in 2008 [2], which extends beyond existing clinical knowledge to simulate situations and processes anew [3]. Figure 1 illustrating MGM integrates both virtual and real-world components to provide a comprehensive approach to health care. At the core of the virtual part are four essential components: the digital patient model, environments, processes, and stakeholders. The digital patient model encompasses comprehensive health data integration, personalised decision support, and dynamic simulation and modelling, leveraging real-time patient data, clinical guidelines, and predictive analytics. The environments component includes physical and clinical settings, data-driven contexts, and professional and social environments, incorporating healthcare infrastructure, IoT devices, and healthcare providers. Processes cover clinical and operational workflows, educational and training methodologies, and interaction and communication systems, facilitating automation, simulation-based learning, and telemedicine. Stakeholders involve patient-centric aspects, healthcare professional expertise, and systemic and ethical considerations, addressing patient preferences, clinical experience, and data privacy. In the real-world part, the component “Stakeholders’ Expertise, Values, and Preferences” encompasses personal life factors, healthcare accessibility, and living environment, integrating family and friends, work, daily activities, sleep, nutrition, and environmental factors. Together, these components form a holistic model that bridges the virtual and physical realms, ensuring patient-specific models and simulations are central to personalised healthcare delivery.

Fig. 1

Model-Guided Medicine (MGM) including model-based medical evidence (MBME) integrates evidence-based medicine (EBM) with virtual models, enriching patient care with factors of environment, stakeholders, and processes to facilitate comprehensive, model-based decision-making

The foundation of our current treatment concept, of EBM, is composed of best research evidence, clinical experience, and patient values, see Fig. 2, right. While clinical experience and patient values consider the actual state and the individuum, best research evidence traditionally relies on controlled studies and literature. Medical knowledge, especially that from clinical trials, is organised and communicated in respect to general models, such as the TNM staging model. These models are essential to make complex data sets usable across disciplines and large patient cohorts. While supporting the applicability of EBM, they aim for the reduction of the individual to only a few confined features. EBM and applied models therefore can only provide mean recommendations for the mean, but for the same reason often fail to fully address the unique needs of an individual patient. EBM is still an important achievement compared to medicine without modelled research results and only limited patient influence, as it once began with eminence-based medicine (EMM), see Fig. 2, left.

Fig. 2

A comparison between the basis of our current treatment concept of evidence-based medicine (EBM) on the right, which, even with its limitations, is still an important achievement compared to eminence-based medicine (EMM) on the left

Today’s increasingly precise research methods, from genomic analyses to complex MRI reconstruction models, are contributing to an impressive array of personalised treatment options. This growing wealth of data underscores the need for models to efficiently structure medical knowledge and effectively deliver personalised medicine. As we move into an era of continuously and quickly increasing amounts of data, the need for specialised digital tools to manage the complexity and diversity of models is becoming increasingly urgent. The development and digitization of models thus forms the crucial bridge between theoretical research and practical application in everyday clinical practice. Decisions and processes in medicine are influenced and surrounded by their environment, including human interactions, access to tools, and other elements of the surrounding, which have traditionally been acknowledged yet insufficiently integrated into decision-making, and so are neither part of EMM nor EBM. With MGM, not only is this integration possible, but for the first time, the virtualisation of environments, processes, and interactions is used consciously and explicitly to influence real clinical practice. This approach enriches the understanding of patient care by modelling environmental factors and processes, thus enhancing the accuracy and timing of support systems.

The results from the modelled world of MGM must be translated back into clinical practice, affecting daily care through informed scientific evidence, decision-making, and actions. Digital simulations using artificial intelligence (AI), enhanced by explainable AI and advanced human–computer interfaces, allow for precise and transparent forecasting of complex treatment options. Furthermore, the transformation of virtual models into physical artefacts through techniques like 3D printing enhances clinical expertise and patient communication, by testing potential procedures on patient-specific models.

The following list provides a brief overview of the developments and capabilities from EBM to MGM:

Comprehensive Data Utilisation

EBM traditionally relies on controlled studies, clinical trials, and literature to draw conclusions and create evidence-based guidelines.

MGM leverages real-time patient data, environmental inputs, and broader health determinants for a more holistic and individual view.

Patient-Centric Modelling

EBM provides care recommendations based on broader population data and established guidelines, with some attention to individual patient characteristics.

MGM offers individualised care plans by integrating personal health data, lifestyle factors, and genetic information, allowing for more tailored interventions.

Adaptive Learning

EBM adjusts to new research findings but the adoption of new evidence into clinical practice may not be immediate.

MGM continuously evolves through adaptive learning algorithms that update models in real-time, ensuring that the latest data informs patient care more rapidly.

Predictive Health Analytics

EBM utilises statistical methods and historical data to predict outcomes and inform clinical guidelines, which contribute to evidence-based practice.

MGM employs predictive models to anticipate health trajectories and potential risks, aiming for preemptive and personalised care strategies.

Dynamic Interaction

EBM is traditionally a rather static interaction between patients and healthcare providers, relying on periodic consultations and standardised questionnaires.

MGM supports dynamic and continuous interaction through interactive platforms that allow patients to engage with and contribute to their health data models, enhancing patient involvement in their care.

Automation in Care Adjustment

EBM treatment adjustments are based on periodic assessments and manual updates to care plans, which can introduce delays.

MGM utilises AI to automatically refine and adjust treatment protocols as patient conditions change, ensuring more timely and responsive care.

Ethics and Privacy in Design

EBM adheres to established medical ethics and legal regulations in data handling, ensuring that ethical considerations and privacy safeguards are foundational.

MGM integrates ethical considerations and privacy safeguards into the design of its modelling systems, addressing societal impacts and particularly in the context of more complex and sensitive data usage.

Collaborative Intelligence

EBM relies on the expertise of healthcare professionals, supported by clinical guidelines and evidence-based research.

MGM encourages a synergy between human medical expertise and machine learning, creating a collaborative intelligence that enhances diagnostic and therapeutic outcomes through the integration of human judgement and advanced computational models.

MGM does not simply augment EBM practices but redefines them through a commitment to ethical, patient-centred care, integrating real-time patient data, environmental inputs, and broader health determinants for a holistic view. This innovative approach transforms the healthcare landscape by fostering collaborative intelligence between human expertise and machine learning, ultimately improving diagnostic and therapeutic outcomes.