Parkinson’s disease (PD) is characterized by highly heterogeneous motor and non-motor symptoms, and the rate of progression differs across patients, which makes accurate staging difficult and a major challenge. Prediction of PD stage is further complicated by the limitations of cross-sectional methods, which capture only a single time point and fail to reflect longitudinal symptom evolution. To overcome this limitation, in this study motor and non motor symptom domains are analyzed by applying Latent Growth Curve Modeling (LGCM) to measure baseline levels and longitudinal changes in motor function (Movement Disorder Society-Unified PD Rating Scale, MDS-UPDRS-III), impulsivity (Questionnaire for Impulsive-Compulsive Disorders, QUIP), anxiety (State-Trait Anxiety Inventory, STAI), and sleep (Epworth Sleepiness Scale). The coefficients obtained from the LGCM are used as inputs to a stacking machine learning (SML) framework to predict the Hoehn & Yahr stage at two future visits, V n (V10) and V n + 1 (V12). This hybrid approach, referred to as SML β , integrates multiple diverse base learners with a meta-modeling strategy, thereby enhancing prediction accuracy, capturing complex non-linear interactions, and reducing overfitting. Model validity is confirmed using 5-fold cross-validation. Using data from 571 participants in the Parkinson’s Progression Markers Initiative (PPMI), the SML β approach demonstrates strong predictive performance at visit V n (MAE = 0.1850, MSE = 0.0756, RMSE = 0.2750, R 2 = 0.8580 ) and at visit V n + 1 (MAE = 0.2050, MSE = 0.0864, RMSE = 0.2940, R 2 = 0.8080 ), outperforming individual learners. Explainable AI analysis using SHAP identifies motor and sleep trajectories, combined with demographic factors, as the most influential predictors. These findings demonstrate that SML β provides insight into variability in PD progression and enables robust, interpretable prediction of patient staging at future visits.

Vehicle-to-Everything (V2X) communication systems are central to the development of intelligent urban infrastructures, enabling seamless interaction between vehicles, infrastructure, personal devices, and pedestrians. This paper proposes a novel integration of V2X technologies with wearable health monitoring and machine learning to improve emergency response for Parkinson's disease patients. Each patient is monitored using clinical scores UPDRS I, II, and III, which respectively capture cognitive, functional, and motor impairment. These indicators are analyzed using a Support Vector Machine (SVM) model trained to classify emergency conditions in real time. SHAP-based interpretability is applied to provide transparency and support medical decision making. The proposed framework was evaluated using a synthetic dataset of 20 simulated Parkinson's patients. Alerts are transmitted via V2P to Roadside Units (RSUs), which coordinate with ambulances using V2V and V2I protocols. The system's performance was assessed via SUMO and OMNeT++ simulations. Results demonstrate feasibility in reducing delays and improving emergency interventions.

In this paper, we focus on addressing the challenge of patient triage at the emergency department. Most hospitals suffer from long waiting times at the emergency department reception, primarily due to a high volume of incoming patients. A significant proportion of these individuals do not have urgent cases or are less urgent compared to others. Nevertheless, their presence occupies significant time slots, leading to delays for patients in urgent need of attention. To automate the triaging process and streamline patient consultation order, thus improving patient care, we propose an automatic method based on a hybrid concept that combines a feature extraction algorithm and an artificial intelligence neural network tool. This tool is capable of classifying patients according to their case severity and organizing their admissions. Simulation results demonstrate that our model can automatically classify patients with high accuracy and facilitates patient admissions by speeding up their care and considering the waiting time acceptable threshold relevant to their specific cases.

Vehicular ad hoc networks (VANETs) have attracted considerable interest in recent years, with a focus on enhancing road safety and reducing traffic accidents. The adoption of VANETs in healthcare holds great promise, especially during emergencies like accidents. The issue concerns reducing the travel time for transporting patients from their accident location to hospitals using Vehicle-to-Everything (V2X) technology. This article aims to address this issue and conduct a new study based on V2X communication technologies to analyze and reduce ambulance response times. We integrate together Vehicle-to-Vehicle (V2V) with Vehicle-to-Infrastructure (V2I) communications technologies, allowing ambulances to communicate with both other vehicles and roadside infrastructure. Collectively, these technologies can be employed to shorten the emergency services’ arrival time at accident scenes. In VANETs, connectivity to the ambulance system can be established seamlessly, enabling direct communication with the patient without the need for any other intervention. Sensors installed on the roads (Roadside Units - RSU) act as routers to transmit messages to the ambulance receiver. Furthermore, we aim to garner more attention for this field, which is expected to reshape the future of urban mobility. Additionally, we will focus on various studies related to vehicular communication issues and their resulting outcomes to conclude with an analysis aimed at enhancing patient routing management.

― This paper addresses surgical scheduling problem on the operational decision level. The problem consists of assigning an intervention date and operating room (OR) to elective surgeries, taking into account limited resources of OR and surgeons. The Healthcare System (HS) is studied in this paper as a Discrete Event System. The main purpose of our study is to model and analyze the HS using two complementary formalisms Timed Coulored Petri Nets (TCPN) and (max, +) Algebra. To do so, TCPN model is first developed to model and study the patient care flow behavior, in order to evaluate its performances. Based on TCPN model, (max, +) equations are then developed to represent the system behavior by linear models and to calculate the occurrence dates of surgery activities. Owing to the both proposed models it is possible to design a provisional schedule of elective interventions, that will be used to suggest optimization strategies aimed at improving the HS performances. An illustrative example is given to show the effectiveness of the proposed approach.

This article is devoted to the study and the control of a multimodal transportation system (MTS) modeled by colored hybrid Petri nets (CHPNs) and (max, +) algebra. The studied MTS is composed of multiple connected stations served by large capacity transportation modes (such as trains and subways) and a finite number of bus shuttles with limited capacities that ensure the exchange of passengers between these stations. The MTS is studied in this article as a hybrid dynamical system (HDS). A nonstationary linear (max, +) model based on the CHPN model representing the behavior of the MTS is developed by taking into account the delays of bus shuttles that may be caused by unpredictable incidents (such as breakdowns and accidents). Through the resultant model, we analyze the system evolution over time and evaluate arrival/departure times of transportation means to/from the various connected stations and also passengers waiting times. In addition, an optimal control approach regarding just-in-time criterion is proposed to optimize two crucial parameters, namely: waiting times of passengers at the connected stations and the number of bus shuttles to be deployed on the network. In addition, the ability of the adapted control approach to deal with bus shuttle delays caused by unpredictable incidents and how the impact of these delays on passengers waiting times can be prevented will be studied. Finally, some relevant scenarios will be studied and discussed in order to illustrate and validate the suggested approach.

This paper discusses the use of Petri net languages, particularly, its subclass “timed event graph” for modeling a public transport network. The behavior of the network is described by a particular algebraic structure called (max, +) algebra. We show that the modeling of such a network is possible under some hypotheses. We propose a Petri net tool with some conflicts to model this network without taking into account these assumptions. The behavior of this Petri net in (max, +) algebra is presented. An example is given to illustrate our results.