Influence Diagrams Research Articles

P0997 The Rectal Stump during and after subtotal colectomy for Ulcerative Colitis: A scoping review of surgical strategies, medical management options and cancer surveillance recommendations

Abstract Background There are multiple decision nodes, during or after a subtotal colectomy for UC, regarding the management of the rectal stump. Intra-operatively, the retained stump may be closed intraperitoneally in the pelvis, secured at the subcutaneous tissue, or exteriorised as a mucous fistula. Post-operatively, microscopic evidence of proctitis is present in the majority of UC patients.Given the increased risk of cancer in UC, the presence of a retained rectal stump necessitates endoscopic surveillance. The aim of this scoping review was to summarise all available evidence on these 3 aspects of the management of the rectal stump in UC. Methods A scoping review of the literature was performed. Relevant studies were identified through a systematic search of Ovid Medline and Embase. Inclusion criteria were adult population and diagnosis of UC. Cohort studies, review articles and guidelines were eligible for inclusion. Articles were screened and reviewed by 2 independent reviewers and conflicts resolved by a 3rd reviewer. The references were grouped according to the subject of interest. Results Initial search returned 1267 studies, and after title and abstract screening and full-text screening, 93 studies were found eligible for inclusion in the review. Surgical management of the rectal stump at subtotal colectomy remains controversial. Intra-peritoneal closure has been shown to have higher pelvic sepsis rates, whereas subcutaneous placement results in higher rates of wound infections. A mucous fistula has been shown to have the lowest overall complication rate. Microscopic findings compatible with diversion proctitis develop in most patients, with incidence ranging from 71.4% to 100%. However, only a minority of these patients (30-40%) develop symptoms. Suggested treatments for diversion proctitis include topical mesalamine, corticosteroids or short-chain fatty acids. The overall risk of rectal stump neoplasia in patients with UC after subtotal colectomy is as low as 0.7% (2021 systematic review), with prior colorectal neoplasia being a major risk factor. No universal standardized guidance exists regarding endoscopic surveillance in this patient population. Conclusion This scoping review has appraised the latest evidence on 3 crucial stages of the management of the rectal stump in UC. There is still uncertainty about the optimal surgical management of the stump, with different complication profiles. Medical management of diversion proctitis remains a major unmet need, and there are no randomized trials addressing this issue. There are no universally accepted guidelines on endoscopic surveillance of the rectal stump.

A knowledge graph-based intelligent planning method for remanufacturing processes of used parts

Intelligent remanufacturing process planning is crucial for the efficient and high-quality remanufacturing of used parts with complex failure characteristics. However, due to the varied failure characteristics of used parts, the diversity of remanufacturing processes, and complex non-linear relationships among remanufacturing process elements, relying solely on mathematical programming or manual empirical is difficult to effectively model and optimise the remanufacturing process planning. To this end, a knowledge graph-based intelligent planning method for remanufacturing processes is proposed to enhance efficiency and quality by combining mathematical programming and knowledge reuse. Firstly, with failure characteristics as decision nodes, a full-element remanufacturing process ontology model is constructed, linking used parts, failure characteristics, and corresponding process plans. The BERT-BiLSTM-CRF model extracts remanufacturing process entities, and a remanufacturing process knowledge graph (RPKG) is constructed. Secondly, an intelligent decision-making model based on graph multi-node path retrieval is proposed. Aim to minimise carbon emissions, time, and cost, combining feature similarity calculations and nearest neighbour search (NNS) to efficiently retrieve the optimal process plan for each failure characteristic. Then, the optimal process plans are merged based on process constraints to create the complete plan. Finally, a concrete case is given to verify the effectiveness and advantages of this method.

A Bayesian framework for learning proactive robot behaviour in assistive tasks

Socially assistive robots represent a promising tool in assistive contexts for improving people’s quality of life and well-being through social, emotional, cognitive, and physical support. However, the effectiveness of interactions heavily relies on the robots’ ability to adapt to the needs of the assisted individuals and to offer support proactively, before it is explicitly requested. Previous work has primarily focused on defining the actions the robot should perform, rather than considering when to act and how confident it should be in a given situation. To address this gap, this paper introduces a new data-driven framework that involves a learning pipeline, consisting of two phases, with the ultimate goal of training an algorithm based on Influence Diagrams. The proposed assistance scenario involves a sequential memory game, where the robot autonomously learns what assistance to provide when to intervene, and with what confidence to take control. The results from a user study showed that the proactive behaviour of the robot had a positive impact on the users’ game performance. Users obtained higher scores, made fewer mistakes, and requested less assistance from the robot. The study also highlighted the robot’s ability to provide assistance tailored to users’ specific needs and anticipate their requests.

Identifying NH3 emission mitigation techniques from farm to field using a Bayesian network.

This study addresses the challenge of reducing ammonia (NH3) emissions from agriculture by evaluating various mitigation techniques. The research utilized a Bayesian Belief Network (BBN) to integrate quantitative data on NH3 volatilization reduction with qualitative stakeholder perceptions, aiming to identify the best available techniques (BATs) that balance environmental, economic, and socio-cultural factors for farmers in the Veneto region of Italy. The BBN framework established probabilistic dependencies between variables related to livestock, crop type, manure storage, fertilization management, and pedo-climatic conditions. Stakeholder opinions were quantified through a value elicitation process and combined with the BBN to create an integrated Influence Diagram (ID). Results indicated that effective NH3 reduction requires a comprehensive approach across the entire agri-livestock supply chain. Based on the results obtained, no single technique clearly emerged as the primary focus, rather various areas would require improvement across the agri-livestock supply chain. However, if prioritizing techniques were necessary, efforts should concentrate on stable management of infirmary animals (HCInf), overcrowding reduction by decreasing the number of animals on densely populated farms (OC-Animal), and optimization of protein in animal ration (FDProt). These measures should be combined with effective manure application through slurry injection (INJSlu) in the field. Stakeholders showed reluctance towards more expensive or innovative methods, indicating that socio-cultural perceptions and economic feasibility can heavily influence the adoption of new technologies although they proved to be among the most environmentally effective. The primary insight from applying the BBNs was that selecting effective techniques necessitates a multi-perspective approach to foster consensus among stakeholders throughout the agri-livestock supply chain.

A Decision Tree-Driven IoT systems for improved pre-natal diagnostic accuracy

Prenatal diagnostics are vital for the woman as well as her unborn baby. The diagnostics help in the early identification of the possibility of complication and the initial measures that help to ameliorate the mother and the fetus health status are taken. Over the year’s various techniques have been employed in diagnosing genetic disorders before birth that lack effectiveness in terms of cost, time, and places to access ultra-modern health facilities. To overcome these problems, this paper puts forward a diagnostic model that integrates Internet of Things innovation with a Machine Learning approach which is the Decision Tree Algorithms. First, it implies the application of IOT devices in the collection of vital information like heart rate, blood pressure, glucose levels, and fetal movement. The data is structured in the form of a dataset and transmitted to a Big Data storage for warehousing and processing. Secondly, the DTA is employed to analyze the data and look for patterns and possibilities of future health complications. The DTA operates in that it divides the dataset into subsets considering specific features and formulates a tree-like model of decisions. At every node, the algorithm chooses the attribute which has the highest information gain, to partition the data into different classes. This process goes on until it reaches a decision node through which, it can decide probable health problems from the input data. To increase the reliability of the developed model this study fine-tunes the model by using a large database of pre-natal health records. The system is capable of collecting data in real-time and flagging data that needs attention in the case of any abnormality to the health professional. The above methodology was tested on a 1000-record database of pre-natal health records where the proposal achieved 95% possibility of potential health problems as against 85% by classical statistical analysis. Furthermore, the system scaled down the number of false positive cases by 20 percent and false negatives by 15 percent thus the efficacy of the system.

Studying Up Public Sector AI: How Networks of Power Relations Shape Agency Decisions Around AI Design and Use

As public sector agencies rapidly introduce new AI tools in high-stakes domains like social services, it becomes critical to understand how decisions to adopt these tools are made in practice. We borrow from the anthropological practice to "study up" those in positions of power, and reorient our study of public sector AI around those who have the power and responsibility to make decisions about the role that AI tools will play in their agency. Through semi-structured interviews and design activities with 16 agency decision-makers, we examine how decisions about AI design and adoption are influenced by their interactions with and assumptions about other actors within these agencies (e.g., frontline workers and agency leaders), as well as those above (legal systems and contracted companies), and below (impacted communities). By centering these networks of power relations, our findings shed light on how infrastructural, legal, and social factors create barriers and disincentives to the involvement of a broader range of stakeholders in decisions about AI design and adoption. Agency decision-makers desired more practical support for stakeholder involvement around public sector AI to help overcome the knowledge and power differentials they perceived between them and other stakeholders (e.g., frontline workers and impacted community members). Building on these findings, we discuss implications for future research and policy around actualizing participatory AI approaches in public sector contexts.

Cost-effectiveness of mineralocorticoid receptor antagonists in heart failure with reduced ejection fraction: the brazilian case with bayesian networks and markov influence diagrams

Abstract Background Heart failure (HF) is one of the leading causes of death worldwide, with a significant burden in middle-income countries, such as Brazil. Mineralocorticoid receptor antagonists (MRAs) have been established as a cornerstone in the treatment of HF with reduced ejection fraction (HFrEF), but their adoption has faced obstacles. Until recently, spironolactone was the only MRA available in Brazil, with restricted use due to associated side effects, such as gynecomastia and hyperkalemia. However, the introduction of new MRAs, such as finerenone and eplerenone, has the potential to change the therapeutic landscape. Understanding the cost-effectiveness of these agents in the Brazilian healthcare context is essential to optimize HF management. Methods A Bayesian Network approach complemented by Markov Influence Diagrams was employed to estimate incremental cost-effectiveness ratios (ICERs), presented in international dollars (Int$) gained per quality-adjusted life year (QALYs). Discontinuation rates for MRAs were incorporated into the model, reflecting real-world clinical practice, along with a 5% annual discount rate for both costs and effectiveness. To inform our model, a comprehensive systematic review was conducted, followed by a network meta-analysis (NMA) to assess the comparative effectiveness of ARMs. Data on incident cardiovascular outcomes were derived from a Brazilian real-world cohort of 1,098 patients with HFrEF. All cost assessments were made from the perspective of the Brazilian public health system, with values converted to Int$. Results The NMA highlighted that spironolactone [HR:0.75 (95%CI 0.67-0.84)], eplerenone [HR:0.84 (95%CI 0.77-0.93)] and finerenone [HR:0.90 (95%CI 0.82-0.98)] significantly reduced the relative risk of all-cause mortality compared to no MRA utilization. Notably, eplerenone significantly reduced hospitalizations due to HF [HR:0.60 (95%CI 0.41-0.90)] compared to no MRA therapy, with spironolactone and finerenone showing HRs of 0.68 (95%CI 0.40-1.17) and 0.83 (95%CI 0.59-1.15) . The analysis also revealed a notably higher risk of MRA discontinuation for finerenone (22%) and spironolactone (51%) compared to eplerenone. In cost-effectiveness comparisons, finerenone was dominated by alternatives, while eplerenone exhibited an ICER of Int$2,614 (95%CI 1,851-3,470)/QALY when compared to spironolactone. Both spironolactone and eplerenone emerged as cost-effective options when compared to no MRA therapy, with eplerenone being particularly favorable below the willingness-to-pay threshold of Int$8,900 per QALY. Conclusions In the Brazilian healthcare context, eplerenone will likely be the most cost-effective MRA compared to spironolactone, offering both a reduction in HF-related hospitalizations and a lower discontinuation rate. These findings underscore the value of integrating cost-effectiveness analyzes into healthcare decision-making processes.

Under what conditions? A scenario‐based approach for exploring the prerequisites of future events

AbstractIn an increasingly complex world, futures thinking can be used to understand the conditions that define future events' realization. This paper presents a novel approach to explore under what conditions some chosen future event would occur. The approach can be seen as a fusion of exploratory scenarios with the backward‐looking perspective of backcasting while resembling cross‐impact methods in how future events' realization arises from the interaction of several uncertain assumptions. The approach maps the causal mechanisms and assumptions that lead to the investigated event's realization, and results in a subset of assumption combinations that lead to the event being realized or not, and scenario sets where the event is either realized or not. This analysis provides insights beyond “Is the event likely to occur?”, revealing the various circumstances under which it can occur. We also provide ways for considering probabilities and deliberate decisions within the approach. We illustrate the approach with three example cases from different problem domains, such as reaching long‐term climate targets, and employing various methods, such as causal mapping, influence diagrams, and optimization. We conclude with a discussion on the approach's potential to enhance foresight practice, emphasizing its synergistic relation to existing methods and its contribution to a richer, more nuanced anticipation of the future.

Voluntary Planning and City Networks: A Systematic Bibliometric Review Addressing Current Issues for Sustainable and Climate-Responsive Planning

Over the years, energy saving and climate change have sparked a challenge in developing innovative spatial and urban planning tools, methods, and approaches for urban areas and territorial management. This challenge has pointed out a gap in the traditional planning framework in tackling energy and climate issues, highlighting the need for renovated spatial planning practices. The current effective measures carried out by the complex network of stakeholders (public and private) are fragmented, and the role of city networks in shaping decisions and interventions has emerged. In particular, among the approaches for urban and territorial planning and the development of climate-responsive measures, this research adopts a specific focus on voluntary planning. The authors, through a literature review and an analysis of nine city networks, investigated how this approach addresses energy and climate issues and how it is linked to the city networks in designing investments and interventions within the urban context. From the authors’ perspective, city networks are the operative component in designing local experiences and applications, contributing to achievement of the global energy and climate targets according to the current policies. In this context, successful results with respect to climate and energy challenges is expressed in the degree of the awareness and the commitment achieved by the local communities. Moreover, reaching the climate and energy goals is a representation of the outcome of the interaction between the (public or private) actors involved and the degree of a city’s climate-responsiveness, rather than from a normative constraint or an institutional framework.

Exploring the drivers behind visiting repair cafés: Insights from mental models

Community initiatives play a critical role in fostering a circular economy. Repair cafés, as free community repair events, have been found to be successful in promoting the culture of repair and educating diverse audiences on product durability. However, research on what drives visitors’ participation in such events is scarce. This information is needed to understand how the initiatives can develop and reach more visitors. This study aimed to explore the drivers behind visiting repair cafés using a mental model approach. Thirty visitors to Dutch repair cafés mapped their mental models of the motivational process behind attending the events by drawing influence diagrams and submitted to interviews that provided more in-depth discussions of their mapped mental models. The findings highlight the key drivers of repair café attendance — namely, environmental concerns; profiting from the knowledge, skills and materials available at repair cafés; the desire to demonstrate the importance of repair; and being part of a social movement. Interestingly, meeting others or experimenting with new repair methods were not seen as important drivers of visiting repair cafés. In conclusion, this study complements the earlier repair motivation literature and offers implications for how to promote consumer participation in repair initiatives.

From Information to Knowledge: A Role for Knowledge Networks in Decision Making and Action Selection

From Information to Knowledge: A Role for Knowledge Networks in Decision Making and Action Selection

Solving Complex Optimisation Problems by Machine Learning

Most optimisation research focuses on relatively simple cases: one decision maker, one objective, and possibly a set of constraints. However, real-world optimisation problems often come with complications: they might be multi-objective, multi-agent, multi-stage or multi-level, and they might have uncertainty, partial knowledge or nonlinear objectives. Each has led to research areas with dedicated solution methods. However, when new hybrid problems are encountered, there is typically no solver available. We define a broad class of discrete optimisation problem called an influence program, and describe a lightweight algorithm based on multi-agent multi-objective reinforcement learning with sampling. We show that it can be used to solve problems from a wide range of literatures: constraint programming, Bayesian networks, stochastic programming, influence diagrams (standard, limited memory and multi-objective), and game theory (multi-level programming, Bayesian games and level-k reasoning). We expect it to be useful for the rapid prototyping of solution methods for new hybrid problems.

Actual Cost of Extracorporeal Cardiopulmonary Resuscitation: A Time-Driven Activity-Based Costing Study.

To determine the actual cost and drivers of the cost of an extracorporeal cardiopulmonary resuscitation (E-CPR) care cycle. A time-driven activity-based costing study conducted from a healthcare provider perspective. A quaternary care ICU providing around-the-clock E-CPR service for out-of-hospital cardiac arrest (OHCA) and in-hospital cardiac arrest (IHCA) in Australia. The E-CPR care cycle was defined as the time from initiating E-CPR to hospital discharge or death of the patient. Detailed process maps with discrete steps and probabilistic decision nodes accounting for the complex trajectories of E-CPR patients were developed. Data about clinical and nonclinical resources and timing of activities was collected multiple times for each process . Total direct costs were calculated using the time estimates and unit costs per resource for all clinical and nonclinical resources. The total direct costs were combined with indirect costs to obtain the total cost of E-CPR. From 10 E-CPR care cycles observed during the study period, a minimum of 3 observations were obtained per process. The E-CPR care cycle's mean (95% CI) cost was $75,014 ($66,209-83,222). Initiation of extracorporeal membrane oxygenation (ECMO) and ECMO management constituted 18% of costs. The ICU management (35%) and surgical costs (20%) were the primary cost determinants. IHCA had a higher mean (95% CI) cost than OHCA ($87,940 [75,372-100,570] vs. 62,595 [53,994-71,890], p < 0.01), mainly because of the increased survival and ICU length of stay of patients with IHCA. The mean cost for each E-CPR survivor was $129,503 ($112,422-147,224). Significant costs are associated with E-CPR for refractory cardiac arrest. The cost of E-CPR for IHCA was higher compared with the cost of E-CPR for OHCA. The major determinants of the E-CPR costs were ICU and surgical costs. These data can inform the cost-effectiveness analysis of E-CPR in the future.

Consensus reaching with the dynamic hybrid trust network in group decision making based on an extensive bounded confidence

This study focuses on the consensus-reaching process (CRP) in social networks. Over the years, ample research has been conducted on CRP levels. However, most feedback mechanisms do not consider the decision maker’s (DM) willingness to accept the recommendations provided by these mechanisms. Therefore, this study proposes an extensive bounded confidence-based group consensus feedback mechanism that primarily consists of two parts: (a) the construction of a hybrid dynamic trust network and (b) the construction of an extensive bounded confidence model. In the first part, we propose an algorithm to calculate the importance of network nodes and apply it to the trust propagation and aggregation process. In the second part, we propose an extensive bounded confidence model to address the limitations of existing traditional bounded confidence models. In the proposed extensive bounded confidence model, the trust threshold is no longer a “switch” to determine whether a DM interacts with other DMs but a basis to determine the strength of the DMs’ interaction; moreover, the hybrid dynamic trust relationship will determine the negotiation sets. A practical case of site selection and comparative analysis verify the effectiveness and flexibility of the proposed mechanism.

Deep random forest with ferroelectric analog content addressable memory.

Deep random forest (DRF), which combines deep learning and random forest, exhibits comparable accuracy, interpretability, low memory and computational overhead to deep neural networks (DNNs) in edge intelligence tasks. However, efficient DRF accelerator is lagging behind its DNN counterparts. The key to DRF acceleration lies in realizing the branch-split operation at decision nodes. In this work, we propose implementing DRF through associative searches realized with ferroelectric analog content addressable memory (ACAM). Utilizing only two ferroelectric field effect transistors (FeFETs), the ultra-compact ACAM cell performs energy-efficient branch-split operations by storing decision boundaries as analog polarization states in FeFETs. The DRF accelerator architecture and its model mapping to ACAM arrays are presented. The functionality, characteristics, and scalability of the FeFET ACAM DRF and its robustness against FeFET device non-idealities are validated in experiments and simulations. Evaluations show that the FeFET ACAM DRF accelerator achieves ∼106×/10× and ∼106×/2.5× improvements in energy and latency, respectively, compared to other DRF hardware implementations on state-of-the-art CPU/ReRAM.

HAZMAT Technician-level Emergency Response: A Mental Model Framework for Radiological Dispersal Device (RDD) Incidents.

This research examines the cognitive frameworks used by HAZMAT technicians when responding to incidents involving Radiological Dispersal Devices (RDDs), which are conventional explosive devices with radioactive materials incorporated. The objective is to introduce the Expected Mental Model State (EMMS) as a comprehensive evaluation tool for assessing and enhancing the expertise and situational awareness of emergency responders dealing with radiation crises. Through a series of expert focus group sessions using the well-established qualitative methodology of grounded theory, an Expected Mental Model State (EMMS) was developed. The methodology used an influence diagram architecture to conceptually capture and codify key areas relevant to effective emergency response. The research identifies fourteen EMMS key conceptual domains, further elaborated into 301 subtopics, providing a multi-dimensional structure for the proposed mental model framework. Three pivotal notions of mental model emerged within the EMMS framework: Knowledge Topology, Envisioning (Belief), and Response and Operability. These notions were found to align with previous theories of mental models and are vital for understanding how HAZMAT technicians conceptualize and respond to RDD incidents. The study emphasizes the critical role of mental models in enhancing preparedness and effective response strategies during radiation emergencies. The EMMS framework offers a versatile methodology that can be adapted across various kinds of emergency responders and high-risk situations, including the broader Chemical, Biological, Radiological, and Nuclear (CBRN) spectrum. Using this EMMS framework to develop an EMMS Diagnostic Matrix can provide a roadmap for identifying areas for the development of specialized training modules that have the potential to significantly elevate both the quality and efficacy of responder training and preparation.

An interactive framework to support decision-making for Digital Twin design

Producing a Digital Twin (DT) involves many inter-linking decisions. Existing research tends to describe the parts of a DT and how they work, but not the decision-making that goes into building a DT nor the consideration of alternative design options. There is therefore a need for decision support to guide developers to create DTs efficiently while meeting functional requirements such as accuracy and interoperability. This paper presents an ontology-based decision support framework to achieve this need. Firstly an analysis of the decisions required to create a predictive maintenance DT for an automotive manufacturer is performed. The analysis found that each decision point produces an output by consideration of various influencing factors, such as time constraints, computation limits and the required fidelity of the model. The network of decisions is complex, with the outcomes of earlier decisions influencing later ones. An IDEF0 diagram was found to be a useful way to represent decisions, their dependencies and their cross-linking. This knowledge was used to populate an ontology of DT components for a predictive maintenance DT. The ability of an ontology to describe concepts explicitly using standardised vocabulary ensures the integrity of the decision-making guidance. A demonstration of the functionality of the ontology-based decision support framework was made before an evaluation of the concept. The research is a fundamental component in producing decision support for DT creators so that manufacturers can realise the benefits of a connected, responsive and flexible facility.

Optimizing Production Supply Chain With Markov Jump System for Logistics Collaboration

This study employs a novel Markov jump system model to address complexities and uncertainties in modern logistics management, particularly in supply chain logistics information networks. It introduces dynamic memory to tackle issues in traditional static networks, enabling modeling and control of this intricate system. By assessing decision node importance, a novel strategy optimization method is devised. Through information exchange and decision adjustments among cooperating nodes, the overall decision system performance is enhanced, resulting in a comprehensive logistics information coordination mechanism for production supply chains based on the Markov jump system. The research demonstrates that this approach considers node interactions and information exchange, using dynamic memory to improve system adaptability and robustness, ultimately enhancing overall decision performance and stability. This has practical value for decision support and system optimization in production supply chain logistics information networks, offering fresh insights into Markov jump system control.

Assessing the Impact of Risk Factors on Vaccination Uptake Policy Decisions Using a Bayesian Network (BN) Approach

This study evaluates the propagation impact of three risk categories (hazard and exposure, socio-economic vulnerability, and lack of coping capacity) and their associated factors on vaccination uptake policy decisions in Pakistan. This study proposed Bayesian influence diagrams using expert elicitation and data-driven approaches. The Bayesian network (BN) approach uses the best policy algorithm to determine the expected utility of decisions. The study found that the government’s firm vaccine uptake decisions had a positive effect in Pakistan. The findings on hazard and exposure-related factors show that people living in rural areas were more susceptible to COVID-19 than people living in urban areas. Among socio-economic vulnerability factors, household characteristics were affected due to household economic situations, fear of using health facilities due to the spread of COVID-19, lack of public transportation services, food insecurity, a temporary halt in education, and weak governance, which affected the vaccination uptake decision. The factors linked with coping capacity show that the government’s financial assistance and development of digital platforms raised digital health literacy and increased vaccine uptake decision utility. The proposed methodology and results of this study can be used to develop contingency planning for any future potential pandemic situations.

Label ranking oblique trees

Label ranking studies the problem of learning a preference model that maps instances to rankings over a finite set of predefined class labels. The training data used to solve this problem consists of instances labeled with rankings. Since these rankings are often incomplete, models need to be able to deal with missing information in the class labels to be more useful in practice. Several decision tree models have been proposed to learn from incomplete rankings, mainly using axis-parallel decision nodes, which is the standard approach for decision tree induction. In contrast to this strategy, this present work introduces a method for learning oblique decision trees for the label ranking problem, as they have been shown to improve performance in the standard classification scenario. Our experimentation shows that this method offers several advantages over the current decision tree model. Not only does it generate more compact tree structures, but it is also shown to achieve outstandingly better results for complete rankings and in cases with a low percentage of missing labels. Moreover, the proposed method is faster in the largest datasets than the current decision tree model.