Ladies and Gentlemen! This is no humbug. Why Model-Guided Medicine will become a main pillar for the future healthcare system.

PURPOSE: Model-Guided Medicine (MGM) is a transformative approach to health care that offers a comprehensive and integrative perspective that goes far beyond our current concepts. In this editorial, we want to take a closer look at this innovative concept and how health care could benefit from its further development and application. METHODS: The information presented here is primarily the opinion of the authors and is based on their knowledge in the fields of information technology, computer science, and medicine. The contents are also the result of numerous discussions and scientific meetings within the CARS Society and the CARS Workshop on Model-Guided Medicine and are substantially stimulated by the available literature on the subject. RESULTS: The current healthcare landscape, with its reliance on isolated data points and broad population-based recommendations, often fails to integrate the dynamic and patient-specific factors necessary for truly personalised care. MGM addresses these limitations by integrating recent advancements in data processing, artificial intelligence, and human-computer interaction for the creation of individual models which integrate the available information and knowledge of patients, healthcare providers, devices, environment, etc. Based on a holistic concept, MGM will become effective tool for modern medicine, which shows a unique ability to assess and analyse interconnected relations and the combined impact of multiple factors on the individual. MGM emphasises transparency, reproducibility, and interpretability, ensuring that models are not black boxes but tools that healthcare professionals can fully understand, validate, and apply in clinical practice. CONCLUSION: The practical applications of MGM are vast, ranging from optimising individual treatment plans to enhancing the efficiency of entire healthcare systems. The research community is called upon to pioneer new projects that demonstrate MGM's potential, establishing it as a central pillar of future health care, where more personalised, predictive, and effective medical practices will hopefully become the standard.

Modeling and processing up-to-dateness of patient information in probabilistic therapy decision support.

OBJECTIVES: Probabilistic modeling of a patient's situation with the goal of providing calculated therapy recommendations can improve the decision making of interdisciplinary teams. Relevant information entities and direct causal dependencies, as well as uncertainty, must be formally described. Possible therapy options, tailored to the patient, can be inferred from the clinical data using these descriptions. However, there are several avoidable factors of uncertainty influencing the accuracy of the inference. For instance, inaccuracy may emerge from outdated information. In general, probabilistic models, e.g. Bayesian Networks can depict the causality and relations of individual information entities, but in general cannot evaluate individual entities concerning their up-to-dateness. The goal of the work at hand is to model diagnostic up-to-dateness, which can reasonably adjust the influence of outdated diagnostic information to improve the inference results of clinical decision models. METHODS AND MATERIALS: We analyzed 68 laryngeal cancer cases and modeled the state of up-to-dateness of different diagnostic modalities. All cases were used for cross-validation. 55 cases were used to train the model, 13 for testing. Each diagnostic procedure involved in the decision making process of these cases was associated with a specific threshold for the time the information is considered up-to-date, i.e. reliable. Based on this threshold, outdated findings could be identified and their impact on probabilistic calculations could be reduced. We applied the model for reducing the weight of outdated patient data in the computation of TNM stagings for the 13 test cases and compared the results to the manually derived TNM stagings in the patient files. RESULTS: With the implementation of these weights in the laryngeal cancer model, we increased the accuracy of the TNM calculation from 0.61 (8 out of 13 cases correct) to 0.76 (10 out of 13 cases correct). CONCLUSION: Decision delay may cause specific patient data to be outdated. This can cause contradictory or false information and impair calculations for clinical decision support. Our approach demonstrates that the accuracy of Bayesian Network models can be improved when pre-processing the patient-specific data and evaluating their up-to-dateness with reduced weights on outdated information.

Digital patient models based on Bayesian networks for clinical treatment decision support.

Increasing complexity in the management of oncologic diseases due to advances in diagnostics and individualized treatments demands new techniques of comprehensive decision support. Digital patient models (DPMs) are developed to collect, structure, and evaluate information to improve the decision-making process in tumour boards and surgical procedures in the operating room (OR). Laryngeal cancer (LC) was selected as a prototype to build a clinical decision support system (CDSS) based on Bayesian networks (BN). The model was built in cooperation with a knowledge engineer and a domain expert in head and neck oncology. Once a CDSS is developed, individual patient data can be set to compute a patient-specific BN. The modelling was based on clinical guidelines and analysis of the tumour board decision making. Besides description of the modelling process, recommendations for standardised modelling, new tools, validation and interaction of extensive models are presented. The LC model contains over 1,000 variables with about 1,300 dependencies. A subnetwork representing TNM staging (303 variables) was validated and reached 100% of correct model predictions. Given the new methods and tools, construction of a complex human-readable CDSS is feasible. Interactive platforms with guided modelling may support collaborative model development and extension to other diseases. Appropriate tools may assist decision making in various situations, e.g. the OR.

Considering Information Up-to-Dateness to Increase the Accuracy of Therapy Decision Support Systems.

During the diagnostic process a lot of information is generated. All this information is assessed when making a final diagnosis and planning the therapy. While some patient information is stable, e.g., gender, others may become outdated, e.g., tumor size derived from CT data. Quantifying this information up-to-dateness and deriving consequences are difficult. Especially for the implementation in clinical decision support systems, this has not been studied. When information entities tend to become outdated, in practice, clinicians intuitively reduce their impact when making decisions. Therefore, in a system's calculations their impact should be reduced as well. We propose a method of decreasing the certainty of information entities based on their up-to-dateness. The method is tested in a decision support system for TNM staging based on Bayesian networks. We compared the actual N-state in records of 39 patients to the N-state calculated with and without decreasing data certainty. The results under decreased certainty correlated better with the actual states (r=0.958, p=0.008). We conclude that the up-to-dateness must be considered when processing clinical information to enhance decision making and ensure more patient safety.

Validation workflow for a clinical Bayesian network model in multidisciplinary decision making in head and neck oncology treatment.

PURPOSE: Oncological treatment is being increasingly complex, and therefore, decision making in multidisciplinary teams is becoming the key activity in the clinical pathways. The increased complexity is related to the number and variability of possible treatment decisions that may be relevant to a patient. In this paper, we describe validation of a multidisciplinary cancer treatment decision in the clinical domain of head and neck oncology. METHOD: Probabilistic graphical models and corresponding inference algorithms, in the form of Bayesian networks, can support complex decision-making processes by providing a mathematically reproducible and transparent advice. The quality of BN-based advice depends on the quality of the model. Therefore, it is vital to validate the model before it is applied in practice. RESULTS: For an example BN subnetwork of laryngeal cancer with 303 variables, we evaluated 66 patient records. To validate the model on this dataset, a validation workflow was applied in combination with quantitative and qualitative analyses. In the subsequent analyses, we observed four sources of imprecise predictions: incorrect data, incomplete patient data, outvoting relevant observations, and incorrect model. Finally, the four problems were solved by modifying the data and the model. CONCLUSION: The presented validation effort is related to the model complexity. For simpler models, the validation workflow is the same, although it may require fewer validation methods. The validation success is related to the model's well-founded knowledge base. The remaining laryngeal cancer model may disclose additional sources of imprecise predictions.

Towards the Consideration of Diagnostic Delay in Model-Based Clinical Decision Support.

Diagnostic delay involves the peril of information becoming outdated. It is a challenging task to quantify the up-to-dateness of clinical information and the consequences of diagnostic delay with the goal of considering them in clinical decision support. We propose an approach to integrating the up-to-dateness of clinical information in a model-based therapy decision support system.

A Guide for Constructing Bayesian Network Graphs of Cancer Treatment Decisions.

In complex cancer cases, Bayesian networks can support clinical experts in finding the best patient-specific therapeutic decisions. However, the development of decision networks requires teamwork of at least one domain expert and one knowledge engineer making the process expensive, time-consuming, and prone to misunderstandings. We present a novel method for guided modeling. This method enables domain experts to model collaboratively without the need of knowledge engineers, increasing both the development speed and model quality.

Accessing Patient Information for Probabilistic Patient Models Using Existing Standards.

Clinical decision support systems (CDSS) are developed to facilitate physicians' decision making, particularly for complex, oncological diseases. Access to relevant patient specific information from electronic health records (EHR) is limited to the structure and transmission formats in the respective hospital information system. We propose a system-architecture for a standardized access to patient specific information for a CDSS for laryngeal cancer. Following the idea of a CDSS using Bayesian Networks, we developed an architecture concept applying clinical standards. We recommend the application of Arden Syntax for the definition and processing of needed medical knowledge and clinical information, as well as the use of HL7 FHIR to identify the relevant data elements in an EHR to increase the interoperability the CDSS.

Web-tool to Support Medical Experts in Probabilistic Modelling Using Large Bayesian Networks With an Example of Hinosinusitis.

For many complex diseases, finding the best patient-specific treatment decision is difficult for physicians due to limited mental capacity. Clinical decision support systems based on Bayesian networks (BN) can provide a probabilistic graphical model integrating all necessary aspects relevant for decision making. Such models are often manually created by clinical experts. The modeling process consists of graphical modeling conducted by collecting of information entities, and probabilistic modeling achieved through defining the relations of information entities to their direct causes. Such expert-based probabilistic modelling with BNs is very time intensive and requires knowledge about the underlying modeling method. We introduce in this paper an intuitive web-based system for helping medical experts generate decision models based on BNs. Using the tool, no special knowledge about the underlying model or BN is necessary. We tested the tool with an example of modeling treatment decisions of Rhinosinusitis and studied its usability.