Issam Nouaouri

Evidential data mining for length of stay (LOS) prediction problem

Hospitals need to optimize their healthcare planning and organization to minimize costs. The indicator that is often used to measure the efficiency in hospital is the average length of stay. Many studies show a strong and obvious correlation between the costs of patients and the impatient Length Of Stay (LOS). In this paper, We propose to apply data mining techniques to predict the LOS. An evidential variant of data mining, called also evidential data mining, have been used to reduce the impact of uncertainty and missing data. New measures of itemset support and association rule confidence are applied. We introduce the Evidential Length Of Stay prediction Algorithm (ELOSA) that allow the prediction of the length of stay of a new patient. Therefore, the inpatient length of stay (LOS) can be predicted efficiently, the planning and management of hospital resources can be greatly enhanced. The proposal is evaluated on a real hospital dataset using 270 patient traces.

Scheduling of stabilization surgical cares in case of a disaster

In this paper, we focus on assigning and scheduling stabilization surgical cares in operating rooms in case of a disaster. In such situation, surgeons are nomadic. Each victim is characterized by an emergency degree and a ready date in the hospital. In order to satisfy the increasing surgical need, the medical staffs can be reinforced during the time. The objective function defers those used in normal situation, it is about saving the maximum of human lives. So, we propose an integer linear program performed by the Cplex solver. Computational experiments show that a substantial aid is proposed by using this program.

A SAT approach for maximizing satisfiability in qualitative spatial and temporal constraint networks

In this paper, we focus on a recently introduced problem in the context of spatial and temporal qualitative reasoning, called the MAX-QCN problem. This problem involves obtaining a spatial or temporal configuration that maximizes the number of satisfied constraints in a qualitative constraint network (QCN). To efficiently solve the MAX-QCN problem, we introduce and study two families of encodings of the partial maximum satisfiability problem (PMAX-SAT). Each of these encodings is based on, what we call, a forbidden covering with regard to the composition table of the considered qualitative calculus. Intuitively, a forbidden covering allows us to express, in a more or less compact manner, the non-feasible configurations for three spatial or temporal entities. The experimentation that we have conducted with qualitative constraint networks from the Interval Algebra shows the interest of our approach.

A Practical Approach for Maximizing Satisfiability in Qualitative Spatial and Temporal Constraint Networks

We introduce and study the problem of obtaining a spatial or temporal configuration that maximizes the number of constraints satisfied in a qualitative constraint network (QCN). We call this problem the MAX-QCN problem and prove that it is NP-hard for most of the qualitative calculi. We also propose a complete generic branch and bound algorithm for solving the MAX-QCN problem. This algorithm builds on techniques used in the literature for solving the consistency checking problem and the minimal labeling problem of a given QCN. In particular, we make use of a tractable subclass of relations, a chordal graph provided by a triangulation of the input QCN, and the partial weak composition as a filtering method. The experimentation that we have conducted with QCNs from the Interval Algebra and the Region Connection Calculus shows the interest of our proposed algorithm.

A Hybrid Evolutionary Algorithm for Maximizing Satisfiability in Temporal or Spatial Qualitative Constraints

In this paper we tackle the MAX-QCN optimization problem, which consists in characterizing a consistent scenario that maximizes the satisfiability of a spatial or temporal qualitative constraint network (QCN). We propose an original hybrid evolutionary algorithm for solving the MAX-QCN problem, which we call EAMQ for short. This EAMQ method consists in randomly generating an initial population of consistent G-scenarios, and then realizing in an iterative manner an evolution of this population by generating new G-scenarios from crossover operations applied on the better individuals of the population at hand. Additionally, every time a new scenario is generated, an exploration of its neighborhood is realized in order to obtain a better scenario. Preliminary experiments conducted on QCNs of the Interval Algebra show the interest of our approach for solving the MAX-QCN problem.

Scheduling Patients in Emergency Department by Considering Material Resources

Abstract Health organizations are complex to manage due to their dynamic processes and distributed hospital organization. It is therefore necessary for healthcare institutions to focus on this issue to deal with patients’ requirements. Preparing a schedule for patients in the emergency department is a complex task, which requires taking into account numerous rules, related to various aspects: respect the triage process (emergency degrees of patients), respect the availability of resources, etc. In this paper, we present a mixed integer linear programming (MILP) approach to facilitate this task. The objective is to minimize the total waiting time of patient’s in the emergency department. We consider simultaneously four patients’ process: registration and triage, consultation, treatment and hospitalization. The model is characterized by the availability of both human (triage staff, physician, nurse) and material resources (bed) in each process through the stay of patient in the ED except for triage and registration which does not require a bed. To solve this model, we used the commercial solver IBM ILOG CPLEX Optimization Studio. The program has been tested on a set of instances. Numerical results show that the proposed approach can significantly improve the efficiency of emergency department by reducing the total waiting time of patients.

Operating Schedule: Take into Account Unexpected Events in Case of a Disaster

In case of a disaster thousands of people may be affected. The needs for medical and surgical treatments overwhelm hospitals’ capabilities. A disaster is characterized by different disruptions which perturb largely the execution of the established plans. In hospital and more precisely in operating theatres, the decision-makers have to manage these disruptions in real time. In this setting, we propose a reactive approach in order to optimize the operating rooms scheduling taking into account unexpected events. In this chapter we focus on the insertion of unexpected new victim in the pre-established operating schedule and the overflow of surgical processing time. The purpose is to treat all disruptions and so to save the maximum of human lives. We propose heuristic approach performed by the Cplex solver. Empirical study shows that a substantial aid is obtained by using the proposed approach in case of disaster.