Fear of cancer recurrence (FCR) is a significant psychological concern for cancer survivors and is associated with quality of life. While traditional methods for assessing FCR often rely on self-reported questionnaires, these are not always available in clinical settings, and there is no effective measure to reliably identify individuals at risk. This paper proposes two semi-supervised learning (SSL) frameworks to predict FCR using healthcare reimbursement data, which is routinely collected but often underutilized for psychological outcomes such as FCR. Our approach leverages both labeled cases of FCR (patients classified with respect to FCR) and unlabeled cases through a sequential neural network pipeline combined with an autoencoder architecture. The preliminary results demonstrate that SSL can significantly enhance prediction performance, addressing the scarcity of labeled data while offering a scalable framework for real-world healthcare applications, and suggest promising directions for leveraging SSL techniques in predicting high-risk cases based on healthcare reimbursement data. This ongoing work focuses on improving the early identification of high-risk patients, aiming to enable timely interventions and personalized care.

The increasing availability of Electronic Health Records (EHRs) data presents novel opportunities to create data driven tools based on Artificial Intelligence for clinical purposes. While healthcare reimbursement data may not strictly constitute EHRs, they nonetheless offer valuable insights into patients’ medical pathways, including medical visits, procedures, and medication usage. However, the inherent complexity and dimensionality of this type of data pose significant hurdles for the direct application of Machine Learning techniques. Consequently, unsupervised methods for encoding patients’ medical data while reducing dimensionality are imperative. In this regard, representation learning emerges as a interesting approach for creating meaningful patient representations.Our contribution involves a comprehensive benchmarking assessment of three prominent representation learning paradigms. We aim to encode and cluster breast cancer patients’ medical pathways using reimbursement data extracted from the French Nationwide Healthcare Database (SNDS). Our findings underscore the limitations of solely evaluating representation learning approaches based on classical machine learning performance metrics. Thus, we advocate for evaluating the quality of the patients’ representation learning latent space through statistical analyses and developing new metrics that reflect the clinical reality of patients.

Breast cancer is the prevalent and leading cause of mortality among women in France, with profound impacts on physical, emotional, and psychological well-being. Despite advances in treatment, the fear of cancer recurrence (FCR) persists among survivors and may lead to increased healthcare utilization and diminished overall well-being. However, accurately predicting FCR probability using traditional statistical models and machine learning (ML) algorithms remains a challenge due to the complex interplay of healthcare data over time. In this study, we propose an approach utilizing neural network-based predictive models and healthcare reimbursement data to predict FCR likelihood in women five years post-diagnosis. Our proposed method integrates temporal information and leverages both labeled and non-labeled medicoadministrative data through Neural Network (NN) architectures and semi-supervised learning techniques, offering a promising avenue for personalized risk assessments and tailored intervention strategies for BC survivors. The ongoing experimental results using ML and NN demonstrate promising outcomes, suggesting that neural network models may have the potential to further improve the prediction performance.

This article proposes a framework of personalized feedback mechanism to help multiple inconsistent experts to reach consensus in group decision making by allowing to select different feedback parameters according to individual consensus degree. The general harmony degree (GHD) is defined to determine the before/after feedback difference between the original and revised opinions. It is proved that the GHD index is monotonically decreasing with respect to the feedback parameter, which means that higher parameter values will result in higher changes of opinions. An optimization model is built with the GHD as the objective function and the consensus thresholds as constraints, with the solution being personalized feedback advices to the inconsistent experts that keep a balance between consensus (group aim) and independence (individual aim). This approach is, therefore, more reasonable than the unpersonalized feedback mechanisms in which the inconsistent experts are forced to adopt feedback generated with only consensus target without considering the extent of the changes acceptable by individual experts. Furthermore, the following interesting theoretical results are also proved: 1) the personalized feedback mechanism guarantees that the increase of consensus level after feedback advices are implemented; 2) the GHD by the personalized feedback mechanism is higher than that of the unpersonalized one; and 3) the personalized feedback mechanism generalizes the unpersonalized one as it is proved the latter is a particular type of the former. Finally, a numerical example is provided to model the feedback process and to corroborates these results when comparing both feedback mechanism approaches.

In the bounded confidence model, it is widely known that individuals rely on the opinions of their close friends or people with similar interests. Meanwhile, the decision maker always hopes that the opinions of individuals can reach a consensus in a required time. Therefore, with this idea in mind, this article develops a consensus reaching model with time constraints and minimum adjustments in a group with bounded confidence effects. In the proposed consensus approach, the minimum adjustments rule is used to modify the initial opinions of individuals with bounded confidence, which can further influence the opinion evolutions of individuals to reach a consensus in a required time. The properties of the model are studied, and detailed numerical examples and comparative simulation analysis are provided to justify its feasibility.

Nowadays, in the social network–based decision-making processes, like the ones involved in e-commerce and e-democracy, multiple users with different backgrounds may take part and diverse alternatives might be involved. This diversity enriches the process, but at the same time, increases the uncertainty of opinions. This uncertainty can be considered from two different perspectives: (i) the uncertainty in the meaning of the words given as preferences, that is, motivated by the heterogeneity of the decision makers; and (ii) the uncertainty inherent to any decision-making process that may lead to an expert not being able to provide all their judgments. The main objective of this study is to address these two types of uncertainty. To do so, the following approaches are proposed: First, to capture, process, and keep the uncertainty in the meaning of the linguistic assumption, the Interval Type-2 Fuzzy Sets are introduced as a way to model the experts' linguistic judgments. Second, a measure of the coherence of the information provided by each decision maker is proposed. Finally, a consistency-based completion approach is introduced to deal with the uncertainty presented in the expert judgments. The proposed approach is tested in an e-democracy decision-making scenario.

On-line platforms foster the communication capabilities of the Internet to develop large-scale influence networks in which the quality of the interactions can be evaluated based on trust and reputation. So far, this technology is well known for building trust and harnessing cooperation in on-line marketplaces, such as Amazon (www.amazon.com) and eBay (www.ebay.es). However, these mechanisms are poised to have a broader impact on a wide range of scenarios, from large scale decision making procedures, such as the ones implied in e-democracy, to trust based recommendations on e-health context or influence and performance assessment in e-marketing and e-learning systems. This contribution surveys the progress in understanding the new possibilities and challenges that trust and reputation systems pose. To do so, it discusses trust, reputation and influence which are important measures in networked based communication mechanisms to support the worthiness of information, products, services opinions and recommendations. The existent mechanisms to estimate and propagate trust and reputation, in distributed networked scenarios, and how these measures can be integrated in decision making to reach consensus among the agents are analysed. Furthermore, it also provides an overview of the relevant work in opinion dynamics and influence assessment, as part of social networks. Finally, it identifies challenges and research opportunities on how the so called trust based network can be leveraged as an influence measure to foster decision making processes and recommendation mechanisms in complex social networks scenarios with uncertain knowledge, like the mentioned in e-health and e-marketing frameworks.

Social networks are the most preferred mean for the people to communicate. Therefore, it is quite usual that experts use them to carry out Group Decision Making processes. One disadvantage that recent Group Decision Making methods have is that they do not allow the experts to use free text to express themselves. On the contrary, they force them to follow a specific user–computer communication structure. This is against social network nature where experts are free to express themselves using their preferred text structure. This paper presents a novel model for experts to carry out Group Decision Making processes using free text and alternatives pairwise comparisons. The main advantage of this method is that it is designed to work using social networks. Sentiment analysis procedures are used to analyze free texts and extract the preferences that the experts provide about the alternatives. Also, our method introduces two ways of applying consensus measures over the Group Decision Making process. They can be used to determine if the experts agree among them or if there are different postures. This way, it is possible to promote the debate in those cases where consensus is low.

The age of the population in the developed countries is increasing as well as the life expectancy for this population. This suppose a challenge for the health care system that requires of new tools to be able to face the increasing expenses that this ageing in the population suppose. With this regard, it has been demonstrated that promoting physical activity in the elderly, could prevent functional decline, frailty, falls, and fractures and reduce the risk of premature mortality. However, in order to obtain the maximum benefits of this physical activity, the activity prescription and health coaching support requires to be tailored to the functional and personal characteristics of each individual [23]. Therefore, it is of vital relevance to have tools to asses the elderly physical condition in an easy way using low cost and simple tools. In this contribution we present a preliminary version of a mobile health application, m-health app, specially aimed for the elderly population. The proposed approach offers to the health practitioners a reliable, real-time, affordable and easy to use tool to evaluate senior patients physical condition. This m-Health System could be a promising approach not only for physical assessment but as well as a tool in intervention programs to asses the patient evolution.

Intuitionistic fuzzy preference relation are gaining increasing relevance in the field of group decision making as they provide the experts with means to allocate the uncertainty inherent in their proposed opinions. A key issue in this field is to reach a solution accepted by the majority of the members of the group. In this contribution we present a new confidence-consistency based consensus model. Moreover to rank the alternatives we present the implementation of Orlovsky's non-dominance concept to define the fuzzy quantifier guided non-dominance choice degree for intuitionistic fuzzy preference relations.

With the incorporation of web 2.0 frameworks the complexity of decision making situations has exponentially increased, involving in many cases many experts, and a potentially huge number of different alternatives, leading the experts to present uncertainty with the preferences provided. In this context, is where Intuitionist fuzzy preference relations plays a key roll as they provide the experts with means to allocate the uncertainty inherent in their proposed opinions. However, in many occasions the experts are unable to give a preference due to different reasons, therefore effective mechanism to cope with missing informations are more than necessary. In this contribution, we present a new GDM approach able to estimate the missing information and at the same time provide a mechanism to bring closer the experts opinions in a iterative process in which the experts confidence plays a key role.

Preference modelling based on Atanassov's intuitionistic fuzzy sets are gaining increasing relevance in the field of group decision making as they provide experts with a flexible and simple tool to express their preferences on a set of alternative options, while allowing, at the same time, to accommodate experts' preference uncertainty, which is inherent to all decision making processes. A key issue within this framework is the provision of efficient methods to rank alternatives, from best to worse, taking into account the peculiarities that this type of preference representation format presents. In this contribution we analyse the relationships between the main method proposed and used by researchers to rank alternatives using intuitionistic fuzzy sets, the score degree function, and the well known choice degree based on Orlovsky's non-dominance concept for the case when the preferences are expressed by means of fuzzy preference relations. This relationship study will provide the necessary theoretical results to support the implementation of Orlovsky's non-dominance concept to define the fuzzy quantifier guided non-dominance choice degree for intuitionistic fuzzy preference relations.

Uncertainty, hesitation and vagueness are inherent to human beings when articulating opinions and preferences. Therefore in decision making situations it might well be the case that experts are unable to express their opinions in an accurate way. Under these circumstances, various families of preference relations (PRs) have been proposed (linguistic, intuitionistic and interval fuzzy PRs) to allow the experts to manifest some degree of hesitation when enunciating their opinions. An extreme case of uncertainty happens when an expert is unable to differentiate the degree up to which one preference is preferred to another. Henceforth, incomplete preference relations are possible. It is worth to bear in mind that incomplete information does not mean low quality information, on the contrary, in many occasions experts might prefer no to provide information in other to keep consistency. Consequently mechanism to deal with incomplete information in decision making are necessary. This contribution presents the main consistency based completion approaches to estimate incomplete preference values in linguistic, intuitionistic and interval fuzzy PRs.