Sequence Of Visits Research Articles

82 Linear mixed models for dissecting social and direct genetic effects of automatic feeder visit sequences

Abstract In this study, we delved into the feeding behaviors of 548 swine, using 114,263 records from FIRE feeders to uncover the direct and social genetic effects of feeding duration. We aimed at dissecting direct and social effects and genetics and environmental components of feeding duration using linear mixed-effects models (LMMs). To accomplish this, we fit and compared several models. The full model included direct and social genetic effects and permanent environmental effects or the social effects or both sets of effects. All models included the effect of the social group. This model facilitates a comprehensive understanding of the determinants of feeding times as it related to social interaction sequences. A novel aspect of our study is the use of sequence of feeder visits as a proxy to social interaction at the feeder, so separate social genetic and social permanent environmental effects of an individual from the ‘Social Group’ effect. The analysis reveals that the full model offers the best fit to the data, as indicated by the smallest Akaike Information Criterion (AIC). However, comparisons with reduced models suggest a partial confounding between additive genetic and permanent environmental effects at both additive and social levels. Notably, the variance explained by the social group remains consistent across models, implying minimal confounding with this factor and underscoring the distinct impact of social dynamics. The observation that social direct genetic effects do not significantly overlap (e.g., M1 vs M2) is promising, suggesting the potential to address the confounding between additive genetic (A) and permanent environmental (PE) effects by incorporating a more detailed pedigree analysis. By presenting variance components and model fit indices (Table 1), our research illuminates the intricate interactions among genetic, environmental, and social factors affecting swine behavior. The use of mixed-effects modeling in this study advances our understanding of the temporal dynamics of animal social behavior, emphasizing the importance of detailed statistical analysis in behavioral research.

The Dial-a-Tour Problem

This article delves into the Dial-a-Tour Problem (DATP) frequently encountered in local travel agencies, known for their personalized and hands-on customer service. In the DATP, multiple tourist groups are efficiently matched with different vehicles using vanpooling, maximizing vehicle occupancy while ensuring seamless transfers to the local attractions included in their booked tours. Each tourist group is picked up from and returned to their respective hotels after their journey. The predetermined locations and the sequence of visits for each tour are known in advance. Therefore, the primary objective is to minimize the number of vehicles required to fulfill all requests and maintain the desired level of service.To tackle this challenge, the article presents a comprehensive approach. It introduces a mixed-integer linear model, two constraint programming formulations, and a novel operator called the k-buffer insertion operator. This operator serves as the centerpiece of a descent heuristic proposed in the study.Extensive evaluation across a diverse range of randomly generated instances underscores the superiority of the proposed constraint programming formulations over the mixed integer linear programming model. However, it is noteworthy that the proposed heuristic surpasses even the most effective constraint programming formulation. This highlights its remarkable efficiency in solving real-size instances within notably brief computation times. Such prowess underscores the practical utility of this heuristic in effectively tackling the complexities inherent in the Dial-a-Tour Problem.

Topic modelling for spatial insights: Uncovering space use from movement data

We present a novel approach to understanding space use by moving entities based on repeated patterns of place visits and transitions. Our approach represents trajectories as text documents consisting of sequences of place visits or transitions and applies topic modelling to the corpus of these documents. The resulting topics represent combinations of places or transitions, respectively, that repeatedly co-occur in trips. Visualisation of the results in the spatial context reveals the regions of place connectivity through movements and the major channels used to traverse the space. This enables understanding of the use of space as a medium for movement. We compare the possibilities provided by topic modelling to alternative approaches exploiting a numeric measure of pairwise connectedness. We have extensively explored the potential of utilising topic modelling by applying our approach to multiple real-world movement data sets with different data collection procedures and varying spatial and temporal properties: GPS road traffic of cars, unconstrained movement on a football pitch, and episodic movement data reflecting social media posting events. The approach successfully demonstrated the ability to uncover meaningful patterns and interesting insights. We thoroughly discuss different aspects of the approach and share the knowledge and experience we have gained with people who might be potentially interested in analysing movement data by means of topic modelling methods.

Treatment pathways defined as the sequence of visits to the public health system of patients with cardiomyopathies in Poland in the period 2016-2021.

Treatment pathways defined as the sequence of visits to the public health system of patients with cardiomyopathies in Poland in the period 2016-2021.

Who is your prenatal care provider? An algorithm to identify the predominant prenatal care provider with claims data.

Using claims data to identify a predominant prenatal care (PNC) provider is not always straightforward, but it is essential for assessing access, cost, and outcomes. Previous algorithms applied plurality (providing the most visits) and majority (providing majority of visits) to identify the predominant provider in primary care setting, but they lacked visit sequence information. This study proposes an algorithm that includes both PNC frequency and sequence information to identify the predominant provider and estimates the percentage of identified predominant providers. Additionally, differences in travel distances to the predominant and nearest provider are compared. The dataset used for this study consisted of 108,441 live births and 2,155,076 associated South Carolina Medicaid claims from 2015-2018. Analysis focused on patients who were continuously enrolled throughout their pregnancy and had any PNC visit, resulting in 32,609 pregnancies. PNC visits were identified with diagnosis and procedure codes and specialty within the estimated gestational age. To classify PNC providers, seven subgroups were created based on PNC frequency and sequence information. The algorithm was developed by considering both the frequency and sequence information. Percentage of identified predominant providers was reported. Chi-square tests were conducted to assess whether the probability of being identified as a predominant provider for a specific subgroup differed from that of the reference group (who provided majority of all PNC). Paired t-tests were used to examine differences in travel distance. Pregnancies in the sample had an average of 7.86 PNC visits. Fewer than 30% of the sample had an exclusive provider. By applying PNC frequency information, a predominant provider can be identified for 81% of pregnancies. After adding sequential information, a predominant provider can be identified for 92% of pregnancies. Distance was significantly longer for pregnant individuals traveling to the identified predominant provider (an average of 5 miles) than to the nearest provider. Inclusion of PNC sequential information in the algorithm has increased the proportion of identifiable predominant providers by 11%. Applying this algorithm reveals a longer distance for pregnant individuals travelling to their predominant provider than to the nearest provider.

An efficient hybrid genetic algorithm for the traveling salesman problem with release dates

This paper deals with a generalization of the classic traveling salesman problem where each customer is associated with a release date, defined as the time at which the desired product becomes available at the depot. In this problem, a single uncapacitated vehicle is allowed to perform multiple trips in order to satisfy all demands. However, the vehicle cannot start a route unless all the products associated with the demands in the route are released. As a consequence, there might be a waiting time before starting the next route. The objective of the problem is to minimize the completion time of the service, defined as the time at which the vehicle returns to the depot after satisfying all demands. We propose a hybrid genetic algorithm that incorporates more advanced mechanisms to evaluate individuals and to ensure population diversity. We also introduce a novel dynamic programming splitting algorithm that converts a sequence of visits to customers, the so-called giant-tour, into the best set of routes that respects the sequence. Computational experiments performed on 522 benchmark instances show that our approach is able to find all 154 known optimal solutions from the literature. In addition, we were able to improve the best-known upper bounds for 364 instances in significantly shorter computational times when compared to the state-of-the-art.

Decision support framework for home health caregiver allocation using optimally tuned spectral clustering and genetic algorithm

Population aging is a global challenge, leading to increased demand for health care and social services for the elderly. Home Health Care (HHC) is a vital solution to serve this segment of the population. Given the increasing demand for HHC, it is essential to coordinate and regulate caregiver allocation efficiently. This is crucial for both budget-optimized planning and ensuring the delivery of high-quality care. This research addresses a fundamental question in home health agencies (HHAs): “How can caregiver allocation be optimized, especially when caregivers prefer flexibility in their visit sequences?”. While earlier studies proposed rigid visiting sequences, our study introduces a decision support framework that allocates caregivers through a hybrid method that considers the flexibility in visiting sequences and aims to reduce travel mileage, increase the number of visits per planning period, and maintain the continuity of care – a critical metric for patient satisfaction. Utilizing data from an HHA in Tennessee, United States, our approach led to an impressive reduction in average travel mileage (up to 42%, depending on discipline) without imposing restrictions on caregivers. Furthermore, the proposed framework is used for caregivers’ supply analysis to provide valuable insights into caregiver resource management.

A planar graph cluster‐routing approach for optimizing medical waste collection based on spatial constraint

AbstractMedical Solid Wastes (MSWs) are major hazardous materials containing harmful biological or chemical compounds that present public and environmental health risks. The collection and transportation of waste are usually informed by optimized work‐balanced routing based on comprehensive spatial data in urban traffic networks, called a Vehicle Routing Problem (VRP). This may be unsuitable for MSWs as their special category means they impose additional complexity. The present article develops a planar graph‐based cluster‐routing approach for the optimal collection of MSWs informed by a Geospatial Information System (GIS). The problem is first formulated as a mixed integer linear program in road network spatial data, in the context of Tehran city. The work has two key aims: (i) to minimize the total routing cost of MSW collection and transfer to waste landfills; (ii) to balance workload across waste collectors. There are three main contributions of the proposed approach: (i) to simplify the large search space area by converting the road network to a planar graph based on graph theory, spatial parameters, and topological rules; (ii) to use a modified K‐means algorithm for clustering; (iii) to consider average traffic impacts in the clustering stage and momentary traffic in the route planning stage. A planar graph extraction procedure is applied to capture the network sketch (i.e., a directed graph) from the traffic roadway network. An iterative cluster‐first‐route‐second heuristic is employed to solve the proposed routing problem. This heuristic customizes a K‐means algorithm to determine the optimal number and size of clusters (i.e., routes). A Traveling Salesman Problem (TSP) algorithm is applied to regulate the optimal sequence of visits to medical centers. The experimental results show improvements in balancing collectors' workload (i.e., ~4 min reduction in the standard deviation of average travel time) with reductions in travel time (i.e., an average ~1 h for the entire fleet and ~4 min per route). These findings confirm that the proposed methodology can be considered as an approach for optimizing waste collection routes.

A multi-view heterogeneous knowledge learning method for personalized POI recommendation

Existing POI recommendation methods often fail to capture the fine-grained preferences of users and face the challenge of modeling multiple relationships. Moreover, knowledge graph-based recommendation methods are limited in storing dynamic user trajectories, making them unsuitable for POI recommendation scenarios. In this paper, we propose a Multi-View Heterogeneous Knowledge learning model that utilizes techniques for heterogeneous knowledge representation learning and multi-view context modeling. Our model comprehensively models user preferences and the relationships between users and POIs by utilizing information from users’ visiting sequences and POI attributes knowledge graph. Specifically, we design a heterogeneous knowledge embedding method to learn the representation of users and POIs using POI attribute knowledge and users’ visiting sequences. Additionally, we constructed a user trajectory similarity graph and a POI attribute similarity graph to explore potential relations between users and between POIs. The former measures the similarity of user behaviors based on user visit sequences, and the latter quantifies the similarity between different POIs through a novel feature mapping method. Finally, we propose a multi-view hybrid learning method that combines unsupervised and supervised learning paradigms to model complex relationships, improving the overall recommendation performance. Extensive experiments on real-world datasets validate the effectiveness of our method.

Considerations for multidisciplinary management of synchronous primary breast cancer and primary lung cancer - Analysis of thirty-one patients.

The simultaneous (synchronous) presence of primary breast cancer and primary lung cancer diagnosed in a single individual is not an uncommon phenomenon. However, reference data for treatment strategy is scarce and "chaotic". In the present study we discuss the management strategy for this group of patients. We retrospectively reviewed patients in the primary breast cancer database of the Breast Center and the primary lung cancer database of the Thoracic Surgery Department I of Peking University Cancer Hospital. Patients with synchronous primary breast cancer and primary lung cancer who underwent surgery between December 2010 and December 2023 were included in the study. The sequence of outpatient visits, recommendations of multidisciplinary teams, perioperative treatment, and surgical procedures were reviewed. Meanwhile, survival analysis based on propensity score matching with 1:1 ratio was performed between the 31 patients and those with lung cancer only during the same period. A total of 31 patients with synchronous primary breast cancer and primary lung cancer were identified; all of the patients were women. The average age was 61 years. A total of 24 of the patients had visited the breast center first, and routine chest computed tomography (CT) showed evidence of primary lung cancer. The other seven patients had visited the thoracic surgery clinic first, and routine positron emission tomography (PET)-CT revealed the coexistence of primary breast cancer. All the patients had multidisciplinary team consultations, after which 20 patients were recommended to have preoperative treatment for breast cancer, two patients were recommended to have preoperative treatment for lung cancer, and nine patients were recommended to undergo surgery directly. After surgery, 23 patients received postoperative adjuvant treatment for breast cancer, and no patients needed postoperative adjuvant treatment for lung cancer. Survival analysis showed that there was no significant difference between the 31 patients and those with lung cancer only. Routine chest CT is needed for breast cancer patients before surgery, and PET-CT is required for the accurate staging of lung cancer patients. A multidisciplinary expert team should manage synchronous primary breast cancer and primary lung cancer. Emphasis should be placed on patients who need preoperative treatment before surgery. Particularly, for patients who need preoperative chemotherapy, a regimen should be chosen that balances the treatment of lung cancer and breast cancer.

Transformer-based time-to-event prediction for chronic kidney disease deterioration.

Deep-learning techniques, particularly the Transformer model, have shown great potential in enhancing the prediction performance of longitudinal health records. Previous methods focused on fixed-time risk prediction, however, time-to-event prediction is often more appropriate for clinical scenarios. Here, we present STRAFE, a generalizable survival analysis Transformer-based architecture for electronic health records. The input for STRAFE is a sequence of visits with SNOMED-CT codes in OMOP-CDM format. A Transformer-based architecture was developed to calculate probabilities of the occurrence of the event in each of 48 months. Performance was evaluated using a real-world claims dataset of over 130000 individuals with stage 3 chronic kidney disease (CKD). STRAFE showed improved mean absolute error (MAE) compared to other time-to-event algorithms in predicting the time to deterioration to stage 5 CKD. Additionally, STRAFE showed an improved area under the receiver operating curve compared to binary outcome algorithms. We show that STRAFE predictions can improve the positive predictive value of high-risk patients by 3-fold. Finally, we suggest a novel visualization approach to predictions on a per-patient basis. Time-to-event predictions are the most appropriate approach for clinical predictions. Our deep-learning algorithm outperformed not only other time-to-event prediction algorithms but also fixed-time algorithms, possibly due to its ability to train on censored data. We demonstrated possible clinical usage by identifying the highest-risk patients. The ability to accurately identify patients at high risk and prioritize their needs can result in improved health outcomes, reduced costs, and more efficient use of resources.

A Pale Persephone: On the Works of Theresa Hak Kyung Cha

ABSTRACT This essay interlaces personal narrative with an analysis of the video and textual works of the Korean American artist Theresa Hak Kyung Cha. I begin with a sequence of visits to the Puck Building, the site of Cha’s murder in 1980, in an ill-fated attempt to recover her presence in luxury penthouse suites now owned by the Kushner family. I move toward the screen as a site of permanence where I can unearth Cha’s ruminations on history, mythology, language, and cinema.

Multivitamins Supplement Uses and Reason Uses by Mother'S for Their Children Less than 24 Months Age Visiting King Abdulaziz Medical City

Background: This study aimed to assess mothers' knowledge regarding multivitamin use for their children in primary health care settings. Methods: It is a cross-sectional survey targeting mothers visiting Primary Health Care. A questionnaire with 14 questions was distributed among two major primary care clinics. Sampling was convenient, and randomness was assumed by visit sequence, on a first-come, first-served basis, and those who agreed to participate. Mothers visiting the Pediatric and Well Baby Clinic within the PHC centers for immunization of their children (under 2 years old) may have been disproportionately selected by this sampling method. The data were entered and analyzed using SPSS with univariate analysis on each question and use of chi-square, exploring mothers' reasons and practices of vitamin use. Results: In our survey, most mothers (62.3%) believed that the best age of giving multivitamins to their children is in the 1st year of life. Twenty-five percent (25%) believed giving at 2 years old is best. Forty-five percent (45%) believed that multivitamins are good for both boys and girls, whereas 33.5% believed that only girls needed it, and 21% believed that only boys need multivitamins. Mothers who believed that children need multivitamins in the first year of life were 2.3 times more likely to give multivitamins to their children than mothers who believed that multivitamins are important after the first year of life. Mothers who believed that their children benefit most from multivitamins in the first year of life were 1.85 times more likely to give them multivitamins to help increase their weight and physical development. Conclusion: Mothers who know foods containing vitamins are 3 times more likely to give multivitamins to their children. In this study, there is no significant difference between the opinions of mothers giving and not giving multivitamins to increase appetite for physical development beyond the first year of life or prevent diseases or for children with chronic illnesses. Others knowledgeable about foods containing multivitamins were similar to mothers who had no knowledge of buying and preparing foods at home.

Impact of rater change on data variability in ADAS‐Cog and CDR assessments

AbstractBackgroundThe past decade has seen numerous research trial failures in Alzheimer’s Disease. The CDR and ADAS‐Cog are the two most frequently used primary outcome measures of memory and cognition in clinical trials of Alzheimer’s Disease (AD). Given the high number of failed AD trials in recent years, data reliability of these measures is paramount. In an effort to minimize data variability and increase data quality, study designs often require the same rater assesses the subject/caregiver at each study visit. However, the impact of rater change on data reliability of these measures is largely unknown. This analysis investigates the impact of rater change on data variability in these measures.MethodData from 13 multinational clinical trials of early symptomatic and mild to moderate AD were analyzed. ADAS‐Cog and CDR assessments conducted by site raters were arranged according to visit sequence and divided into two groups: Rater Change (different raters administered subject’s consecutive visits) and No Rater Change (same rater administered consecutive visits). Visit‐to‐visit absolute score changes for CDR‐SB and ADAS‐Cog Total Score were calculated, and frequency distributions were evaluated.ResultWelch corrected, two sample t‐tests were conducted to compare score changes between rater change groups. For CDR, the Rater Change group showed a higher mean visit‐to‐visit score change (mean = 1.26, SD = 1.32) compared to the No Rater Change (mean = 1.02, SD = 1.13) group. The Rater Change group also showed a higher mean score change on ADAS‐Cog (mean = 4.44, SD: 3.77 and mean ‐ 4.06, SD = 3.50, for Rater Change and No Rater Change Groups, respectively). These group differences reached significance for both ADAS‐Cog (t = ‐7.2925, df = 9769.1, p < .001) and CDR (t = ‐11.228, df = 6122.7, p < .001).ConclusionThe analysis indicates significantly different score changes when there is a rater change between visits than not for both CDR and ADAS‐Cog assessments. These findings highlight the importance of rater consistency in reducing variability in an effort to improve data quality in AD trials.

Siamese learning based on graph differential equation for Next-POI recommendation

Next Point-of-Interest (POI) recommendation is highly challenging in its ill-posedness of data sparsity and elusive motives. Many models, including sequence- and graph-based, have been proposed to alleviate these problems. However, they still contain drawbacks: they either need a more accurate depiction of users’ complex trajectories or novel perspectives on temporal-variant features in the discretized sequences of visits. To better cope with the two challenges, we proposed a novel time-continuous model, namely POIGDE. Our model explicitly exploits continuous variation of users’ interests by solving a graph differential equation (GDE) on users’ interaction behaviors. To maintain an invariant distribution while solving GDEs, we utilize a time-serial graph along with an interval-aware attention mechanism to learn the dynamics of interest transference. This novel update mechanism helps to track the original data distribution by confining the update process in a linear combination manner. Under this restriction, our model can obtain item representations for prediction, which share the same distribution as the actual POIs with which users interact. This practice also applies Siamese Learning in the POI recommendation to directly learn from the representation of ground-truth labels. By comparison with positive samples, the inferred probability of POIs being visited in the future can be obtained based on similarity (i.e., mean square error) between high-dimensional representations of the corresponding POIs. Our model outperforms state-of-the-art models on three real-world datasets by 0.16-23.44%, showing its potential and prospects in the POI recommendation domain.

Dynamic routing for the Electric Vehicle Shortest Path Problem with charging station occupancy information

We study the problem of an Electric Vehicle (EV) having to travel from an origin to a destination in the shortest amount of time. We focus on long-distance settings, where the shortest path between the origin and the destination has energy requirements exceeding the EV autonomy. The EV may charge its battery at public Charging Stations (CSs), which are subject to unknown arrivals of exogenous vehicles requiring uncertain charging times. Thus, the waiting times at CSs are uncertain. Similar to other contributions in the literature, we model CSs using appropriately defined queues, whose status is revealed upon the EV arrival. However, following recent technological advances, we also consider that the status of each CS is updated in real-time via binary Occupancy Indicator (OI) information signaling if a CS is busy or not. Therefore, we assume that the EV continuously receives OI updates on all CSs. At each update, we determine the sequence of CSs to visit along with associated charging quantities. We name the resulting problem as the Electric Vehicle Shortest Path Problem with charging station Occupancy Indicator information (EVSPP-OI). In this problem, we consider that the EV is allowed to partially charge its battery, and we model charging times via piecewise linear charging functions that depend on the CS technology.We propose a Markov Decision Process formulation for the EVSPP-OI, which aims at optimizing the EV routing and charging policy. To solve the problem, we develop a reoptimization algorithm that establishes the sequence of CS visits and charging amounts based on system updates. Specifically, we propose a simulation-based approach to estimate the waiting time of the EV at a CS as a function of its arrival time. As the path to a CS may consist of multiple intermediate CS stops, estimating the arrival times at each CS is fairly intricate. To this end, we propose an efficient heuristic that yields approximate lower bounds on the arrival time of the EV at each CS, which are used to derive an estimation of the waiting time at each CS. We use these estimations to define a compatible deterministic version of the EVSPP, which we solve with an existing algorithm. We conduct a comprehensive computational study and compare the performance of our methodology with a benchmark that observes the status of CSs only upon arrival (i.e., with no OI information). Results show that our method reduces waiting times and total trip duration by an average of 23.7%–95.4% and 1.4%–18.5%, respectively.

Temporal variation of floral reward can improve the pollination success of a rare flowering plant

Many pollinating animals visit a variety of flowering plant species. Rare plant species pollinated by such generalists may experience a low quality or quantity of pollination, depending on the pollinators’ foraging behaviour. How plants cope with this rarity disadvantage is not well understood. One possibility would be to offer a higher floral reward, for example, a higher nectar sugar concentration. However, since nectar production is costly, rare plants may only be able to increase their nectar concentration for a limited time and offer little reward afterwards. In this study, we performed a laboratory experiment with bumblebees (Bombus terrestris) foraging on artificial flowers of two colours to investigate whether the bees’ foraging behaviour produces a rarity disadvantage and if so, whether the rare flower type could improve its pollination success through temporal variation of its nectar sugar concentration, i.e. a temporary increase of nectar sugar followed by a period with low concentration. We found that when both flower colours offered equal rewards, the rare colour received only slightly fewer visits per flower, but had a considerably lower expected pollination success based on the bumblebees’ visitation sequences. Temporal variation of the rare colour’s sugar concentration increased both the quantity and quality of visits it received. This positive effect was reduced when there were fewer rare flowers or when two bumblebees foraged simultaneously. Our results suggest that temporal variation of floral rewards can alleviate, but not completely eliminate the rarity disadvantage.

Mapping Choice of Healthcare Institutes for Cancer Care: A Study in Northeast India.

To map and identify the sequence of visitation to institutes by patients with common cancers. This paper used a mixed method to follow a descriptive multiple-embedded case study. Participants selected in phase one were 388 by stratified random sampling, and in phase two, by purposive sampling, a semi-structured interview was conducted for 21 participants (15 participants and six key informants-oncologists: radiation - 2, medical - 2, surgical - 1 and gynaecology - 1). Ethical clearances were received from the study institutes. Informed consent was obtained from the participants. Sparse research exists on mapping and choices of healthcare settings by cancer patients from northeast India. The main finding comprises a vivid overview of the decisions taken by cancer patients to get their necessary treatment based on all factors mitigating and inhibiting. Up to five hospitals for cancer treatment across the country. Private hospitals were preferred on the first visit by 74 percent (287), followed by the government by 26 percent (101); this, however, changes in subsequent hospital choices, with the latter preferred over the other, which could be due to the long duration of cancer treatment that is directly influenced by the paying capacity of the individual. Visitation was not limited to famous cancer hospitals, but few participants reported accessing herbal medicines, Ayurveda and Homoeopathy. Mapping patient choices of cancer institutes by patients from northeast India is essential as the challenges faced are unique to the region. By mapping patient choices of cancer institutes, insights into the preferred healthcare facilities can influence policies to improve the accessibility of cancer facilities. Findings from this study can support improving access to quality healthcare services, promoting cultural sensitivity, enhancing the quality of care, and informing policy planning and resource allocation.

Acquisition of temporal patterns from electronic health records: an application to multimorbid patients

BackgroundThe exponential growth of digital healthcare data is fueling the development of Knowledge Discovery in Databases (KDD). Extracting temporal relationships between medical events is essential to reveal hidden patterns that can help physicians find optimal treatments, diagnose illnesses, detect drug adverse reactions, and more. This paper presents an approach for the extraction of patient evolution patterns from electronic health records written in Catalan and/or Spanish.MethodsWe propose a robust formulation for extracting Temporal Association Rules (TARs) that goes beyond simple rule extraction by considering the sequence of multiple visits. Our highly configurable algorithm leverages this formulation to extract Temporal Association Rules from sequences of medical instances. We can generate rules in the desired format, content, and temporal factors while accounting for different levels of abstraction of medical instances. To demonstrate the effectiveness of our methodology, we applied it to extract patient evolution patterns from clinical histories of multimorbid patients suffering from heart disease and stroke who visited Primary Care Centers (CAP) in Catalonia. Our main objective is to uncover complex rules with multiple temporal steps, that comprise a set of medical instances.ResultsAs we are working with real-world, error-prone data, we propose a process of validation of the results by expert practitioners in primary care. Despite our limited dataset, the high percentage of patterns deemed correct and relevant by the experts is promising. The insights gained from these patterns can inform preventive measures and help detect risk factors, ultimately leading to better treatments and outcomes for patients.ConclusionOur algorithm successfully extracted a set of meaningful and relevant temporal patterns, especially for the specific type of multimorbid patients considered. These patterns were evaluated by experts and demonstrated the ability to predict risk factors that are commonly associated with certain diseases. Moreover, the average time gap between the occurrence of medical events provided critical insight into the term of these risk factors. This information holds significant value in the context of primary healthcare and preventive medicine, highlighting the potential of our method to serve as a valuable medical tool.

Integrated production scheduling and vehicle routing problem with energy efficient strategies: Mathematical formulation and metaheuristic algorithms

This paper addresses integrated production and distribution scheduling problem in which orders/jobs are undergone a single operation on any one of the identical machines in parallel and upon the completion of the production they are distributed to destined customers by limited number of vehicles. Customers located in dispersed regions place their orders with predetermined demand size and time windows. On production side, machines operate under discrete speed modes, low of which requires less energy cost or vice versa. On distribution side, energy consumed by a vehicle varies depending on the size of load on it. Therefore, objective is minimizing the sum of the weighted cost emanating from early and tardy deliveries plus production and distribution costs. Operational decisions for (i) production are to determine the allocation of jobs to the machines and sequence of jobs on any machine as well as speed mode of each machine for a particular job. As for (ii) distribution: We need to decide vehicle assignment to specific subset of consolidated jobs and the sequence of customer visitation for each vehicle. We develop a formulation for the problem at hand involving parallel machine scheduling and vehicle routing to obtain solutions to optimality. Not surprisingly, however, CPLEX only provides optimum solution for all instances with customer number up to and 6, for which reason we present two metaheuristics, namely Memetic Algorithm (MA) and Iterated Local Search (ILS) for practical sized instances. Computational results indicate that ILS yields better solutions in shorter times as compared to its counterpart.