Search

Episode mining is a research area in data mining, where the aim is to discover interesting episodes, that is, subsequences of events, in an event sequence. The most popular episode-mining task is frequent episode mining (FEM), which consists of identifying episodes that appear frequently in an event sequence, but this task has also been extended in various ways. It was shown that episode mining can reveal insightful patterns for numerous applications such as web stream analysis, network fault management, and cybersecurity, and that episodes can be useful for prediction. Episode mining is an active research area, and there have been numerous advances in the field over the last 25 years. However, due to the rapid evolution of the pattern mining field, there is no prior study that summarizes and gives a detailed overview of this field. The contribution of this article is to fill this gap by presenting an up-to-date survey that provides an introduction to episode mining and an overview of recent developments and research opportunities. This advanced review first gives an introduction to the field of episode mining and the first algorithms. Then, the main concepts used in these algorithms are explained. After that, several recent studies are reviewed that have addressed some limitations of these algorithms and proposed novel solutions to overcome them. Finally, the paper lists some possible extensions of the existing frameworks to mine more meaningful patterns and presents some possible orientations for future work that may contribute to the evolution of the episode mining field. [ABSTRACT FROM AUTHOR]

Sequential pattern mining is a dynamic and thriving research field that aims to extract recurring sequences of events from complex datasets. Traditionally, focusing solely on the order of events often falls short of providing precise insights. Consequently, incorporating the temporal intervals between events has emerged as a vital necessity across various domains, e.g. medicine. Analyzing temporal event sequences within patients’ clinical histories, drug prescriptions, and monitoring alarms exemplifies this critical need. This paper presents innovative and efficient methodologies for mining frequent chronicles from temporal data. The mined graphs offer a significantly more expressive representation than mere event sequences, capturing intricate details of a series of events in a factual manner. The experimental stage includes a series of analyses of diverse databases with distinct characteristics. The proposed approaches were also applied to real-world data comprising information about subjects suffering from sleep disorders. Alluring frequent complete event graphs were obtained on patients who were under the effect of sleep medication.

Data mining is one of the emerging technologies used in many applications such as Market analysis and Machine learning. Temporal data mining is used to get a clear knowledge about current trend and to predict the upcoming future. The rudimentary challenge in introducing a data mining procedure is, processing time and memory consumption are highly increasing while trying to improve the accuracy, precision or recall. As well as, while trying to reduce the processing time or memory consumption, accuracy, precision and recall values are reducing significantly. So, for improving the performance of the system and to preserve the memory and processing time, Three-Dimensional Fuzzy FP-Tree (TDFFPT) is proposed for Temporal data mining. Three functional modules namely, Three-Dimensional Temporal data FP-Tree (TTDFPT), Fuzzy Logic based Temporal Data Tree Analyzer (FTDTA) and Temporal Data Frequent Itemset Miner (TDFIM) are integrated in the proposed method. This algorithm scans the database and generates frequent patterns as per the business need. Every time a client purchases a new item, it gets stored in the recent database layer instead of rescanning the entire records which are placed in the old layer. The results obtained shows that the performance of the proposed model is more efficient than that of the existing algorithm in terms of overall accuracy, processing time, reduction in the memory utilization, and the number of databases scans. In addition, the proposed model also provides improved decision making and accurate pattern prediction in the time series data. [ABSTRACT FROM AUTHOR]

We propose a new pruning constraint when mining frequent temporal patterns to be used as classification and prediction features, the Semantic Adjacency Criterion [SAC], which filters out temporal patterns that contain potentially semantically contradictory components, exploiting each medical domain's knowledge. We have defined three SAC versions and tested them within three medical domains (oncology, hepatitis, diabetes) and a frequent-temporal-pattern discovery framework. Previously, we had shown that using SAC enhances the repeatability of discovering the same temporal patterns in similar proportions in different patient groups within the same clinical domain. Here, we focused on SAC's computational implications for pattern discovery, and for classification and prediction, using the discovered patterns as features, by four different machine-learning methods: Random Forests, Naïve Bayes, SVM, and Logistic Regression. Using SAC resulted in a significant reduction, across all medical domains and classification methods, of up to 97% in the number of discovered temporal patterns, and in the runtime of the discovery process, of up to 98%. Nevertheless, the highly reduced set of only semantically transparent patterns, when used as features, resulted in classification and prediction models whose performance was at least as good as the models resulting from using the complete temporal-pattern set. [ABSTRACT FROM AUTHOR]

Abstract Background The 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. Methods We 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. Results As 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. Conclusion Our 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.

Background: The 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. Methods: We 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. Results: As 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. Conclusion: Our 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. [ABSTRACT FROM AUTHOR]

In this study, we implemented a hybrid approach, incorporating temporal data mining, machine learning, and process mining for modeling and predicting the course of treatment of Intensive Care Unit (ICU) patients. We used process mining algorithms to construct models of management of ICU patients. Then, we extracted the decision points from the mined models and used temporal data mining of the periods preceding the decision points to create temporal-pattern features. We trained classifiers to predict the next actions expected for each point. The methodology was evaluated on medical ICU data from the hypokalemia and hypoglycemia domains. The study's contributions include the representation of medical treatment trajectories of ICU patients using process models, and the integration of Temporal Data Mining and Machine Learning with Process Mining, to predict the next therapeutic actions in the ICU. [ABSTRACT FROM AUTHOR]

We propose a framework for provision of decision support through the continuous prediction of recurring targets, in particular clinical actions, which can potentially occur more than once in the patient's longitudinal clinical record. We first perform an abstraction of the patient's raw time-stamped data into intervals. Then, we partition the patient's timeline into time windows, and perform frequent temporal patterns mining in the features' window. Finally, we use the discovered patterns as features for a prediction model. We demonstrate the framework on the task of treatment prediction in the Intensive Care Unit, in the domains of Hypoglycemia, Hypokalemia and Hypotension. [ABSTRACT FROM AUTHOR]

A temporal model describes processes as a sequence of observable events characterised by distinguishable actions in time. Conformance checking allows these models to determine whether any sequence of temporally ordered and fully-observable events complies with their prescriptions. The latter aspect leads to Explainable and Trustworthy AI, as we can immediately assess the flaws in the recorded behaviours while suggesting any possible way to amend the wrongdoings. Recent findings on conformance checking and temporal learning lead to an interest in temporal models beyond the usual business process management community, thus including other domain areas such as Cyber Security, Industry 4.0, and e-Health. As current technologies for accessing this are purely formal and not ready for the real world returning large data volumes, the need to improve existing conformance checking and temporal model mining algorithms to make Explainable and Trustworthy AI more efficient and competitive is increasingly pressing. To effectively meet such demands, this paper offers KnoBAB, a novel business process management system for efficient Conformance Checking computations performed on top of a customised relational model. This architecture was implemented from scratch after following common practices in the design of relational database management systems. After defining our proposed temporal algebra for temporal queries (xtLTLf), we show that this can express existing temporal languages over finite and non-empty traces such as LTLf. This paper also proposes a parallelisation strategy for such queries, thus reducing conformance checking into an embarrassingly parallel problem leading to super-linear speed up. This paper also presents how a single xtLTLf operator (or even entire sub-expressions) might be efficiently implemented via different algorithms, thus paving the way to future algorithmic improvements. Finally, our benchmarks highlight that our proposed implementation of xtLTLf (KnoBAB) outperforms state-of-the-art conformance checking software running on LTLf logic. [ABSTRACT FROM AUTHOR]

We propose a new pruning constraint when mining frequent temporal patterns to be used as classification and prediction features, the Semantic Adjacency Criterion [SAC], which filters out temporal patterns that contain potentially semantically contradictory components, exploiting each medical domain’s knowledge. We have defined three SAC versions and tested them within three medical domains (oncology, hepatitis, diabetes) and a frequent-temporal-pattern discovery framework. Previously, we had shown that using SAC enhances the repeatability of discovering the same temporal patterns in similar proportions in different patient groups within the same clinical domain. Here, we focused on SAC’s computational implications for pattern discovery, and for classification and prediction, using the discovered patterns as features, by four different machine-learning methods: Random Forests, Naïve Bayes, SVM, and Logistic Regression. Using SAC resulted in a significant reduction, across all medical domains and classification methods, of up to 97% in the number of discovered temporal patterns, and in the runtime of the discovery process, of up to 98%. Nevertheless, the highly reduced set of only semantically transparent patterns, when used as features, resulted in classification and prediction models whose performance was at least as good as the models resulting from using the complete temporal-pattern set.

As big data mining technology penetrates into various fields, cross-domain topics driven by data predictive analysis have become important entry points for solving traditional problems. Due to the complex changes of the pressure sensor and the interaction of different grouped trains during the train braking process, the mechanism modeling is difficult, the data is highly temporalized, and the data distribution is not stable. Facing the development trend of long-grouped-heavy-duty train captains, if the braking analysis of the train by temporal data mining of small groups can be used for predictive analysis, it will make innovative progress in the entire train braking field. This paper focuses on combining latest technology such as machine learning, transfer learning and lifelong learning to construct the first predictive analysis research framework in the field of train braking systems. Based on the principle of train braking process and temporal data collected from intelligent experiment platform, a baseline has firstly been built to solve fixed-grouped and multi-grouped temporal prediction problems. Then a predictive algorithm for model verification and update for lifelong learning is established to automatically update model parameters over time. Finally, relying on the parameter transfer in transfer learning, a multi-grouped temporal data prediction analysis is performed. Through comparing the training results of the “pre-trained” model on the general domain, the “tuned” model on both general domain and the target domain, and the “target only” model on the target domain separately, multi-domain tuning results show their applicable scope and transfer conditions. In summary, this work can contribute to intelligently upgrading the semi-physical intelligent test platform for long-grouped-heavy-duty trains.

In this paper, we address the problem of the spatiotemporal data mining in the field of the road conditions estimation. We demonstrate that road condition estimation can be defined as a problem of dynamic discovering of different classes of road profile during training phase. We focus on the road profile classification from time series data collected by a low-cost inertial sensor embedded into smartphone devices. Data used in this work are composed of three datasets which treat real asphalt pavement problems. The first, called Asphalt-obstacle, address the identification problem of obstacles in the pavement where data are collected. The second, called Asphalt pavement-type, aims at identifying three types of pavements namely flexible pavement, cobblestone street and dirt roads. The third and final dataset, called Asphalt pavement-regularity, treat the pavement quality effect on the driver comfortability. In order to estimate the road conditions, we conduct an evaluation of four spatiotemporal algorithms which combine concepts from machine learning and data-driven. With uniform parameters setting and on-line implementation property, we find that Markov spatiotemporal dynamic model achieve the best average classification accuracy of 90.5%±0.01 in 4-class Asphalt obstacles, 84%±0.006 in 3-class Asphalt pavement-type and 94.9%±0.005 in 2-class Asphalt pavement-regularity. [ABSTRACT FROM AUTHOR]

With the rapid increase of information generated from all kinds of sources, temporal big data mining in business area has been paid more and more attention recently. A novel data mining algorithm for mining temporal association is proposed. Mining temporal association can not only provide better predictability for customer behaviour but also help organisations with better strategies and marketing decisions. To compare the proposed algorithm, two methods to mine temporal association are presented. One is improved based on a traditional mining algorithm, Apriori. The other is based on an Index-Tree. Moreover, the proposed method is extended to mine temporal association in multi-dimensional space. The experimental results show that the Index-Tree method outperforms the Apriori-modified method in all cases.

In the machine learning area, when rare events occur, the problem is treated simply as an outlier or anomaly detection; however, all strategies are applied when the events have already occurred. In this work, rare events correspond to events with a very low probability of occurrence, significant impact after they occur, difficult detection, and little predictability. The detection and alarm of these events are only possible if previous and predictable changes have been observed in the measurable variables, still with low probability but may herald the appearance of a rare event. In this work, these previous changes are called extreme outliers. We propose a multivariate method for detecting and describing the changes in the sensor system due to extreme events that may precede a rare event. We use long-tail probability density distributions to observe the low-probability events and to define the magnitudes of the sensor signal that can determine the presence of extreme outliers. After detection, the method uses unsupervised and supervised learning to describe the changes in the monitored system. The results show the method's effectiveness in detecting and describing changes in time series for different scenarios and criticality levels that precede extreme outliers or rare events. The approach allows the development of alerts according to the level of criticality the sensor system achieves. The proposed method can help in decision-making to reduce the impact of this class of events in critical industrial environments. • We detect extreme outliers in systems monitored by time series. • We use the Theory of Extreme Values to predict the occurrence of extreme outliers. • We describe the changes that occur in the system after extreme outliers occur. • We apply supervised and unsupervised learning to interpret changes that occurred. • Proposal of a workflow for detecting and describing anomalies that occurred. [ABSTRACT FROM AUTHOR]

A temporal model describes processes as a sequence of observable events characterised by distinguishable actions in time. Conformance checking allows these models to determine whether any sequence of temporally ordered and fully-observable events complies with their prescriptions. The latter aspect leads to Explainable and Trustworthy AI, as we can immediately assess the flaws in the recorded behaviours while suggesting any possible way to amend the wrongdoings. Recent findings on conformance checking and temporal learning lead to an interest in temporal models beyond the usual business process management community, thus including other domain areas such as Cyber Security, Industry 4.0, and e-Health. As current technologies for accessing this are purely formal and not ready for the real world returning large data volumes, the need to improve existing conformance checking and temporal model mining algorithms to make Explainable and Trustworthy AI more efficient and competitive is increasingly pressing. To effectively meet such demands, this paper offers KnoBAB, a novel business process management system for efficient Conformance Checking computations performed on top of a customised relational model. This architecture was implemented from scratch after following common practices in the design of relational database management systems. After defining our proposed temporal algebra for temporal queries (xtLTLf), we show that this can express existing temporal languages over finite and non-empty traces such as LTLf. This paper also proposes a parallelisation strategy for such queries, thus reducing conformance checking into an embarrassingly parallel problem leading to super-linear speed up. This paper also presents how a single xtLTLf operator (or even entire sub-expressions) might be efficiently implemented via different algorithms, thus paving the way to future algorithmic improvements. Finally, our benchmarks highlight that our proposed implementation of xtLTLf (KnoBAB) outperforms state-of-the-art conformance checking software running on LTLf logic.

Abstract Background Birthweight is an important indicator during the fetal development process to protect the maternal and infant safety. However, birthweight is difficult to be directly measured, and is usually roughly estimated by the empirical formulas according to the experience of the doctors in clinical practice. Methods This study attempts to combine multiple electronic medical records with the B-ultrasonic examination of pregnant women to construct a hybrid birth weight predicting classifier based on long short-term memory (LSTM) networks. The clinical data were collected from 5,759 Chinese pregnant women who have given birth, with more than 57,000 obstetric electronic medical records. We evaluated the prediction by the mean relative error (MRE) and the accuracy rate of different machine learning classifiers at different predicting periods for first delivery and multiple deliveries. Additionally, we evaluated the classification accuracies of different classifiers respectively for the Small-for-Gestational-age (SGA), Large-for-Gestational-Age (LGA) and Appropriate-for-Gestational-Age (AGA) groups. Results The results show that the accuracy rate of the prediction model using Convolutional Neuron Networks (CNN), Random Forest (RF), Linear-Regression, Support Vector Regression (SVR), Back Propagation Neural Network(BPNN), and the proposed hybrid-LSTM at the 40th pregnancy week for first delivery were 0.498, 0.662, 0.670, 0.680, 0.705 and 0.793, respectively. Among the groups of less than 39th pregnancy week, the 39th pregnancy week and more than 40th week, the hybrid-LSTM model obtained the best accuracy and almost the least MRE compared with those of machine learning models. Not surprisingly, all the machine learning models performed better than the empirical formula. In the SGA, LGA and AGA group experiments, the average accuracy by the empirical formula, logistic regression (LR), BPNN, CNN, RF and Hybrid-LSTM were 0.780, 0.855, 0.890, 0.906, 0.916 and 0.933, respectively. Conclusions The results of this study are helpful for the birthweight prediction and development of guidelines for clinical delivery treatments. It is also useful for the implementation of a decision support system using the temporal machine learning prediction model, as it can assist the clinicians to make correct decisions during the obstetric examinations and remind pregnant women to manage their weight.

The information technology revolution, especially with the adoption of the Internet of Things, longitudinal data in many domains become more available and accessible for secondary analysis. Such data provide meaningful opportunities to understand process in many domains along time, but also challenges. A main challenge is the heterogeneity of the temporal variables due to the different types of data, whether a measurement or an event, and type of samplings: fixed or irregular. Other variables can be also events that may or not have duration. In this review, we discuss the various types of temporal data, and the various relevant analysis methods. Starting with fixed frequency variables, with forecasting and time series methods, and proceeding with sequential data, and sequential patterns mining, and time intervals mining for events having various time duration. Also the use of various deep learning based architectures for temporal data is discussed. The challenge of heterogeneous multivariate temporal data analysis and discuss various options to deal with it, focusing on an increasingly used option of transforming the data into symbolic time intervals through temporal abstraction and the use of time intervals related patterns discovery for temporal knowledge discovery, clustering, classification prediction, and more. Finally, we discuss the overview of the field, and areas in which more studies and contributions are needed. This article is categorized under:Algorithmic Development > Spatial and Temporal Data Mining [ABSTRACT FROM AUTHOR]

Background: Birthweight is an important indicator during the fetal development process to protect the maternal and infant safety. However, birthweight is difficult to be directly measured, and is usually roughly estimated by the empirical formulas according to the experience of the doctors in clinical practice.Methods: This study attempts to combine multiple electronic medical records with the B-ultrasonic examination of pregnant women to construct a hybrid birth weight predicting classifier based on long short-term memory (LSTM) networks. The clinical data were collected from 5,759 Chinese pregnant women who have given birth, with more than 57,000 obstetric electronic medical records. We evaluated the prediction by the mean relative error (MRE) and the accuracy rate of different machine learning classifiers at different predicting periods for first delivery and multiple deliveries. Additionally, we evaluated the classification accuracies of different classifiers respectively for the Small-for-Gestational-age (SGA), Large-for-Gestational-Age (LGA) and Appropriate-for-Gestational-Age (AGA) groups.Results: The results show that the accuracy rate of the prediction model using Convolutional Neuron Networks (CNN), Random Forest (RF), Linear-Regression, Support Vector Regression (SVR), Back Propagation Neural Network(BPNN), and the proposed hybrid-LSTM at the 40th pregnancy week for first delivery were 0.498, 0.662, 0.670, 0.680, 0.705 and 0.793, respectively. Among the groups of less than 39th pregnancy week, the 39th pregnancy week and more than 40th week, the hybrid-LSTM model obtained the best accuracy and almost the least MRE compared with those of machine learning models. Not surprisingly, all the machine learning models performed better than the empirical formula. In the SGA, LGA and AGA group experiments, the average accuracy by the empirical formula, logistic regression (LR), BPNN, CNN, RF and Hybrid-LSTM were 0.780, 0.855, 0.890, 0.906, 0.916 and 0.933, respectively.Conclusions: The results of this study are helpful for the birthweight prediction and development of guidelines for clinical delivery treatments. It is also useful for the implementation of a decision support system using the temporal machine learning prediction model, as it can assist the clinicians to make correct decisions during the obstetric examinations and remind pregnant women to manage their weight. [ABSTRACT FROM AUTHOR]

In this study, we implemented a hybrid approach, incorporating temporal data mining, machine learning, and process mining for modeling and predicting the course of treatment of Intensive Care Unit (ICU) patients. We used process mining algorithms to construct models of management of ICU patients. Then, we extracted the decision points from the mined models and used temporal data mining of the periods preceding the decision points to create temporal-pattern features. We trained classifiers to predict the next actions expected for each point. The methodology was evaluated on medical ICU data from the hypokalemia and hypoglycemia domains. The study's contributions include the representation of medical treatment trajectories of ICU patients using process models, and the integration of Temporal Data Mining and Machine Learning with Process Mining, to predict the next therapeutic actions in the ICU.

A new layer of complexity, constituted of networks of information token recurrence, has been identified in socio-technical systems such as the Wikipedia online community and the Zooniverse citizen science platform. The identification of this complexity reveals that our current understanding of the actual structure of those systems, and consequently the structure of the entire World Wide Web, is incomplete, which raises novel questions for data science research but also from the perspective of social epistemology. Here we establish the principled foundations and practical advantages of analyzing information diffusion within and across Web systems with Transcendental Information Cascades, and outline resulting directions for future study in the area of socio-technical systems. We also suggest that Transcendental Information Cascades may be applicable to any kind of time-evolving system that can be observed using digital technologies, and that the structures found in such systems comprise properties common to all naturally occurring complex systems. [ABSTRACT FROM AUTHOR]

In recent years, the use of frequent temporal patterns as features for classification has increasingly been used and investigated. In this process, commonly frequent patterns are mined from each class separately. Then the patterns are unified, and feature selection methods may be employed, which are given to induce a classifier. However, this approach is very time consuming since the mining of each class separately takes time. In this paper, we introduce the Saraswati suite that can modify a temporal patterns discovery algorithm into a predictive temporal patterns discovery algorithm, which we demonstrate on Time Intervals Related Patterns. The suite enables predictive patterns to be favored in runtime, while mining both classes simultaneously to discover these patterns. This is through the use of a novel stopping criteria that we call the Saraswati selection criteria and strategies suite. Since the selection criteria are based on the patterns' metrics, such as their frequency in each class or their reoccurrence, and more, it is explainable to domain experts, rather than as a score as happens with common feature selection measures. We modified an existing time intervals related patterns discovery algorithm according to the Saraswati suite, and evaluated it rigorously against the current approach on six real-life datasets. Our results show that the Saraswati-based algorithm is much faster than discovery of the entire set of frequent patterns, and the selection criteria are more effective than existing state-of-the-art feature selection methods when the discovered predictive patterns are used for classification. Additionally, the selection of the patterns is explainable in the domain expert's terminology based on several meaningful metrics. [ABSTRACT FROM AUTHOR]

Pharmacovigilance consists in monitoring and preventing the occurrence of adverse drug reactions. This activity can be time-consuming because it requires the collection of both patient and medication information. In this paper, we present two visualization and data mining applications to make this task easier for the practitioner. These tools have been developed and tested using the biomedical data warehouse eHOP (Hospital Biomedical Data Warehouse) of the Rennes University Hospital Centre. The first application is a tool to visualize the patient electronic health record in the form of a timeline. All patient data is collected and displayed chronologically. The usability test of the timeline has been very positive (SUS score: 82.5) and the tool is now available for practitioners in their daily practice. The second application is a tool to visualize and search the sequences of a patient cohort. The visual interface allow user to quickly visualize sequences. A query builder allows user to search for sequences in relation with a reference sequence, such as a prescription sequence followed by an abnormal biological value. The sequences are then visually aligned with this reference sequence and ranked by similarity. The GSP (Generalized Sequential Pattern) and Apriori algorithms allow us to display a summary of the sequences list by searching for common sequences and associations. The tool was tested on a use case which consisted in detection of inappropriate drug administration. Compared to a random order, we showed this ranking system saved the practitioner time in this task (to analyze one sequence, 3.49 ± 3.54 vs. 2.26 ± 2.86 s, p = 0.0003). These two visualization and data mining applications will help the daily practice of pharmacovigilance.