Frederik Gailly

Clinical recommendations are often expressed in narrative form, which limits their direct execution, auditability, and patient-specific interpretation. This paper presents a hybrid decision-support framework that combines Decision Model and Notation (DMN), survey-weighted rule-ensemble learning, and counterfactual sensitivity analysis. The framework is evaluated using an NHANES-derived fasting cohort for classification of documented diabetes status. The full fasting analysis cohort contained 2,582 participants, and a non-diagnostic laboratory subgroup, Gate0, contained 2,111 participants. On untouched test data, the rule-ensemble model achieved ROC–AUC and PR– AUC values of 0.959 and 0.873 in the full fasting cohort and 0.861 and 0.499 in Gate0. Four clinically interpretable candidate rules were selected using validation data only. A nonnegative survey-weighted logistic model removed one redundant rule and converted the remaining three binary activations into an auditable DMN score and model-estimated probability. The final DMN achieved ROC–AUC 0.769, PR–AUC 0.153, and Brier score 0.029 in the untouched Gate0 test set. In small rule-defined test subgroups, hypothetical five-unit BMI reductions lowered mean model-estimated probability by 2.40 to 5.89 percentage points when one or more BMI thresholds were crossed. These findings characterize policy sensitivity rather than causal effects and require external validation.

In times of armed conflicts, various security check-points are placed by authorities to control the flow of merchandise into and within areas of conflicts. The flow of humanitarian trucks that is added to regular flow of commercial trucks together with the complex security procedures create congestion and long waiting times at the security check-points. This causes distribution costs to increase and shortages of relief-aid to the affected civil people to occur. The present study proposes a decision-support tool to assist planners and policymakers in building efficient plans for the distribution of relief-aid, taking into account congestion at security check-points. The proposed tool is built around a multi-item humanitarian distribution planning model which has as objective to minimise distribution and backordering costs subject to capacity constraints that reflect congestion effects using nonlinear clearing functions. Using the 2014 Gaza war as a case study, we illustrate the application of the proposed tool, model the underlying relief-aid humanitarian supply chain, estimate clearing functions at different security check-points, and conduct computational experiments. Our results show that taking congestion into account in distribution planning reduces average lead times, backorders, and distribution costs.

A sharing platform is a digital platform that facilitates access to underutilized goods by renting or lending them to others. Users become less dependent on ownership which improves efficiency, sustainability, and the sense of community. The Sharing Economy (SE) is considered a complex domain because value co-creation can occur between multiple types of platform users. Developing platform software that offers the right functionality for the intended digital platform is therefore challenging. To address this complexity, an ontology can be utilized, which is an explicit specification of a conceptualization that provides a controlled vocabulary and shared meaning regarding a domain. The use of a sharing platform ontology allows for more effective communication and knowledge sharing amongst stakeholders in platform development and eventually drives the platform software development process. However, currently, it is not known how to develop such an ontology. In previous research, we developed the Digital Platform Ontology (DPO) and an extension of the DPO for describing platform business model choices. The DPO describes the digital platform domain in terms of digital platform types, including sharing platforms. However, a method to use the DPO and its business model extension for developing an organization-specific ontology that describes the functionality and business model of a specific existing or intended sharing platform was lacking. In this paper, we develop such a method using the Design Science Research Methodology (DSRM) and demonstrate it using a proof-of-concept based on the BlaBlaCar and Couchsurfing platforms.