Frequent Episode Research Articles

A survey of episode mining

AbstractEpisode 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.This article is categorized under: Algorithmic Development > Spatial and Temporal Data Mining Algorithmic Development > Association Rules Technologies > Association Rules

Early Cytomegalovirus Reactivation in Renal Recipients Is Associated with High Levels of B Cell Maturation Antigen Transcript Expression Prior to Transplantation.

Cytomegalovirus (CMV) infection is the most frequent infection episode in kidney transplant (KT) recipients. Reactivation usually occurs in the first three months after transplantation and is associated with higher cellular and/or antibody-mediated rejection rates and poorer graft performance. CMV induces the expression of BAFF (B-cell-activating factor, a cytokine involved in the homeostasis of B cells), which communicates signals for survival and growth to B cells and virus-specific plasma cells via the R-BAFF (BAFF receptor), TACI (the calcium modulator, the cyclophilin ligand interactor), and BCMA (B cell maturation antigen) receptors. These molecules of the BAFF system have also been suggested as biomarkers for the development of alloantibodies and graft dysfunction. This prospective study included 30 CMV-IgG seropositive KT recipients. The expression levels of the genes BAFF-R, transmembrane activator and CAML interactor (TACI), and B cell maturation antigen (BCMA) in peripheral blood leukocytes (PBL) pre-KT were determined using qPCR. qPCR was also used to monitor CMV reactivation in the first three months following KT. The remainder of the KT recipients were classified as CMV- reactivation, and those with more than 500 copies/mL in at least one sample were classified as CMV+ reactivation. There were no discernible variations in the BAFF-R and TACI transcript expression levels. In the CMV+ group, we examined the relationship between the transcript levels and peak viremia. Peak viremia levels and BCMA transcript levels showed a strong correlation. BAFF-R and TACI expressions showed no measurable differences. In patients with early CMV reactivation, high BCMA receptor expression was associated with increased plasmablast, lymphocyte B cell class-switched levels (LBCS), and viral load. Our findings demonstrate that pre-KT BCMA transcript levels increased in KT recipients with early CMV reactivation. These transcript levels positively correlate with peak viremia and weakly with plasmablast and LBCS levels in PBLs.

Avapritinib for the Treatment of Indolent Systemic Mastocytosis

Indolent systemic mastocytosis (ISM) is a disorder characterized by an accumulation of mast cells in subdermal tissue that leads to exaggerated immune response after release of mast cells mediators. Routinely administered treatments include H1 and H2 receptor antagonists, mast cell stabilizers, corticosteroids, and more recently anti-IgE antibody therapies. Our case presentation explores the treatment of indolent mastocytosis with avapritinib, an antineoplastic, after routine treatment options failed.A 64-year-old female with history of obesity presented to a community-based Allergy/Immunology clinic with chief complaints of recurrent throat tightness, fatigue, headaches, brain fog. She was found to have high tryptase levels which remained persistently elevated from 46 to 55 (include units) over 13-month span. Physical exam was grossly unremarkable.Bone marrow biopsy showed mast cell aggregates highly suspicious for ISM. PCR for KIT (D816V) mutation was positive. Initial treatment included fexofenadine 180 mg and famotidine 20 mg both twice daily. Overall, she had less frequent episode of throat tightness over 9 months, but itchiness, fatigue, brain fog persisted. Monthlyomalizumab 300 mg was added on but was eventually discontinued to lack of benefit. She was referred to a tertiary center where avapritinib 25 mg daily was started. Four months after initiation, occurrences of throat tightness, stomach cramps, and vomiting resolved, and came off all other therapies for mastocytosis. Eight months after avapritinib initiation tryptase had decreased to 19.Avapritinib is a selective kinase inhibitor used to avoid resistance in patients undergoing chemotherapy with indications in those with advanced systemic mastocytosis and neoplastic complications. The mechanism of action of avapritinib includes inhibition of KIT and PDGFRA mutations. Treatment in our patient resulted in the successful symptomatic treatment of indolent systemic mastocytosis targeting KIT (D816V). This case demonstrates a new treatment which may improve the quality of life of individuals with ISM.

PS-C27-4: CONTROLLED RESISTANT HYPERTENSION FOLLOWING A SUCCESSFUL RENAL ARTERY STENTING: A RARE CASE REPORT IN A DEVELOPING COUNTRY

Introduction: Renal artery stenosis is among the etiologies of secondary hypertension in which the diagnosis and therapy are difficult. We report a case of a patient suffered from uncontrollable hypertension with frequent episode of malignant hypertension, treated with renal artery stenting. Case Description: A 36-year-old female visited cardiovascular policlinic on a routine control for her hypertension. Having diagnosed with hypertension for two years, he had several episodes of malignant hypertension. At the beginning of her treatment, she was prescribed an angiotensin-converting-enzyme inhibitor yet her pressure was not only uncontrolled but also worsen. By the visit, she was medicated using two alpha-2-adrenergic agonists, a loop diuretic, a beta-blocker, a calcium-channel blocker, an angiotensin-receptor blocker, and an aldosterone-receptor antagonist without any satisfactory outcome on her blood pressure status. She had a blood pressure of 196/130 mmHg with tachycardia of 112 times/minute. We found cardiomegaly on physical examination which proven by chest x-ray. Echocardiography indicated hypertensive heart disease. Screening for secondary hypertension, including laboratory tests (complete blood count, potassium, sodium, creatinine, fasting glucose, fasting lipid profile, urinalysis, thyroid stimulating hormone, 24H urinary free cortisol) suggested normal results. Renal ultrasound and doppler were also conducted and showed a suspicion of right renal artery stenosis. Therefore, angiography of the renal artery was conducted for diagnostic and therapy when indicated. The angiography suggested a normal left renal artery while the right artery had a 95% stenosis on the proximal part. An intravascular ultrasound-guided percutaneous transluminal angioplasty on her right renal artery was conducted and two vascular stents were implanted. The patient showed a remarkable development following her decreasing blood pressure on follow-up. After 1 week, her blood pressure is now controllable on a single antihypertensive and antiplatelet therapy. Conclusion: The diagnosis and management of a patient with resistant hypertension might be challenging, particularly in the setting of a developing country. Renal artery angiography, among other examination, might be crucial in the diagnosis sequence, yet was not always readily available. We present a case in which diagnosis of renal artery stenosis was made followed by a definite treatment resulting in a remarkable hypertension control. An identifiable etiology is the key to a proper and the best treatment option for the patient.

Mining Frequent Serial Positioning Episode Rules with Forward and Backward Search Technique from Event Sequences

Abstract A large event sequence can generate episode rules that are patterns which help to identify the possible dependencies existing among event types. Frequent episodes occurring in a simple sequence of events are commonly used for mining the episodes from a sequential database. Mining serial positioning episode rules (MSPER) using a fixed-gap episode occurrence suffers from unsatisfied scalability with complex sequences to test whether an episode occurs in a sequence. Large number of redundant nodes was generated in the MSPER-trie-based data structure. In this paper, forward and backward search algorithm (FBSA) is proposed here to detect minimal occurrences of frequent peak episodes. An extensive correlation of parameter settings and the generating procedure of fixed-gap episodes are carried out. To generate a fixed-gap episode and estimate the variance that decides the parameter selection in event sequences, Spearman’s correlation coefficient is used for verifying the sequence of occurrences of the episodes. MFSPER with FBSA is developed to eliminate the frequent sequence scans and redundant event sets. The MFSPER–FBSA stores the minimal occurrences of frequent peak episodes from the event sequences. The experimental evaluation on benchmark datasets shows that the proposed technique outperforms the existing methods with respect to memory, execution time, recall and precision.

Differentially private frequent episode mining over event streams

Frequent episode mining is a wide range framework of data mining from sequential data with many applications, which is a totally short-ordered collection of event-types and unearths temporal correlations without information loss over event streams. While offering substantial benefits, directly releasing frequent episodes to the public will enormously threaten the individual’s privacy. However, there is little work so far concentrating on privately frequent episode mining. In this paper, we investigate the privacy problem in mining frequent episodes from event streams due to continuous releases in successive windows and propose a real-time differentially private frequent episode mining algorithm over event streams to avoid the privacy leakage with ω-event privacy guarantee. To obtain private frequent episodes, we propose a sample-based perturbation approach, which improves the accuracy of selecting frequent episodes based on sampling databases. To reduce the privately mining time and avoid repeatedly privacy budget allocation to coincident window of adjacent releases as much as possible, we present an incremental perturbation approach according to the judgment in dissimilarity calculation mechanism. Meanwhile, in order to protect data collected from any ω successive timestamps over event streams, we employ an adaptive ω-event privacy mechanism on the basis of the dynamicity of episodes. Finally, experimental results on real-world datasets demonstrate the effectiveness and efficiency of our algorithm.

Mining serial positioning episode rules by natural exponent inertia weight based swallow swarm optimization algorithm with constraint based event sequences

The Frequent Episode Mining (FEM) is a challenging framework to identify frequent episodes from a sequence database. In a sequence, an ordered collection of events defines an episode, and frequent episodes are only considered by the earlier studies. Also, it doesn’t support for the serial based episode rule mining. In this work, the episode rules are mined with precise and serial based rule mining considering the temporal factor, so that, the occurrence time of the consequent is specified in contrast to the traditional episode rule mining. The proposed work has a larger number of candidates and specific time constraints to generate the fixed-gap episodes, and mining such episodes from whole sequence where the time span between any two events is a constant which is utilized to improve the proposed framework’s performance. In order to improve the efficiency, an Optimal Fixed-gap Episode Occurrence (OFEO) is performed using the Natural Exponent Inertia Weight based Swallow Swarm Optimization (NEIWSSO) algorithm. The temporal constraints significantly evaluate the effectiveness of episode mining, and a noticeable advantage of the present work is to generate optimal fixed-gap episodes for better prediction. The effective use of memory consumption and performance enhancement is achieved by developing new trie-based data structure for Mining Serial Positioning Episode Rules (MSPER) using a pruning method. The position of frequent events is updated in the precise-positioning episode rule trie instead of frequent events to reduce the memory space. The benchmark datasets Retail, Kosarak, and MSNBC is used to evaluate the proposed algorithm’s efficiency. Eventually, it is found that it outperforms the existing techniques with respect to memory consumption and execution time. On an average, the proposed algorithm achieves 28 times lesser execution time and consumes 45.5% less memory space for the highest minimum support value on the Retail dataset compared to existing methods.

Impact of duration of untreated illness in bipolar I disorder (manic episodes) on clinical outcome, socioecnomic burden in Egyptian population

IntroductionBipolar disorder (BD) is a serious and chronic mental illness that may result in disability. We evaluated effect of the duration of untreated of bipolar (DUB) (manic episodes) on clinical outcomes, including episode severity, residual symptoms, duration of hospitalization, and suicide attempts, and on socioeconomic status of patients. MethodsA total of 216 participants who had bipolar I disorder (manic state) recruited from November 2017–December 2019 from an inpatient psychiatric unit. Patients divided into 2 groups based on DUB: Group A, with DUB < 4 months; and Group B, with DUB ≥4 months. All participants had evaluation for demographic and clinical features, Socioeconomic scale, Young mania rating scale (YMRS) at admission and discharge. ResultsGroup A participants were more often male, urban residents, married, literate and educated, professionally employed. Group A had a younger age of onset, less duration of illness, less frequency of episode, less suicide attempts, less duration in hospital, high mean of socioeconomic, lower mean of YMRS at admission and discharge in compared to Group B. ConclusionA longer DUB (manic episodes)was associated with negative clinical outcomes (more frequent episode, more symptoms severity, longer hospital admission, more suicide severity, more residual symptoms) and low socioeconomic state of patients with BDI (manic episodes).

Prevalence of Root Stumps of Permanent Teeth in Pediatric Patients

Tooth loss is the terminal event in the life of a tooth and is a frequent episode in individuals who are uncared and have neglected oral hygiene. Tooth loss has various ill effects on an individual such as impairment of masticatory function, bad phonetics, unpleasant aesthetics, TMJ disorders, psychological issues, social withdrawal which results from decrease in confidence level. It is evident that caries and periodontitis are the most common causes for tooth loss with caries being the commonest between them. Neglected oral health may result in caries progression, which will lead to formation of root stumps. The aim of the study is to find the prevalence and incidence of root stumps of permanent teeth in pediatric patients. The study was performed under a university setting where the data of patients with root stumps of permanent teeth was collected by reviewing patients records and analysing the data of 86000 patients. The collected data was compiled, reviewed, tabulated and entered in SPSS software for statistical analysis. The study shows that only 2% were extractions of root stumps of permanent teeth. Extraction of root stumps of permanent teeth were more prevalent in patients of 9 and 11 years of age (34%) with a female predilection with most common teeth being the maxillary second premolar (22.2%). This study indicates the negligence of parents regarding the oral health of the children and provides insight on parents’ care towards the oral health of the child. Preventive measures such as topical fluoride application and usage of denial fissure sealants should be encouraged to prevent caries. Thus, the preservation of the natural dentition should be the ultimate goal of the dental professionals.

An Interrupted Time Series Analysis of the Dissemination of a Sickle Cell Vaso-Occlusive Episode Treatment Algorithm and a Case Management Referral Form for Individuals With Sickle Cell Disease in the Emergency Department

BackgroundSickle cell disease is associated with frequent vaso-occlusive episode and emergency department visits. Our group developed (1) a vaso-occlusive episode treatment algorithm based on the National Heart, Lung, and Blood Institute recommendations, and (2) a case management referral form to identify social behavioral health needs of patients with sickle cell disease in the emergency department. The aims of this project were to (1) disseminate the vaso-occlusive episode algorithm and case management referral form, and (2) to evaluate the individual provider-reported awareness, use, and preferred method of access to each tool among emergency department providers in North Carolina. MethodsAn interrupted time series analysis was used to study the impact that an educational effort had on the awareness of a sickle cell vaso-occlusive episode treatment algorithm and a case management referral form. A targeted list was developed to identify the providers working in emergency departments with the largest number of sickle cell disease patient visits. In-service education was provided to targeted emergency departments in North Carolina over a period of 3 years. The vaso-occlusive episode algorithm and case management referral form were put up on the websites of professional organizations. Surveys were provided to emergency department providers at these targeted emergency departments with a baseline and post dissemination at 20 and 32 months for assessing the provider awareness, use, and preferred method of access of the tools. Additional feedback could be given by the participants through telephone interviews. Descriptive statistics were obtained, and content analysis was performed on interviews. ResultsWe received survey responses for the following periods: baseline (T1, n = 190), post dissemination at 20 (T2, n = 142), and 32 months (T3, n = 93). Awareness of the tools was between 42% (baseline) and 41% (post dissemination at T2, T3) for the vaso-occlusive episodes algorithm and 25% (baseline) and 29% (post dissemination at T2, T3) for the case management referral form. However, use of these tools was found to be low as only 19% of the emergency department providers used the vaso-occlusive episode algorithm at T1 and 13% T2, while 5% of emergency department providers used the case management referral form at T1 and 6% at T2. With further education about the tools, an increase in the usage of the tools was observed T3, which was 29% for the vaso-occlusive episodes algorithm and 9% for the case management referral form. Lack of incorporation of the decision support tools into emergency department processes was observed to be an overarching barrier to dissemination of the tools identified in interviews (n = 8). ConclusionsThis study can be used to inform future strategies on dissemination of evidence-based tools to emergency department providers.

Evaluation of Health Care Disparities for Individuals with Intellectual and Developmental Disabilities in Ohio.

The purpose of the study was to determine the acute and long term services and supports (LTSS) utilization, cost of health care and disparities in access of care for individuals with Intellectual and Developmental Disabilities (IDD). Individuals with IDD on a waiver (receiving Medicaid-funded LTSS in community settings) compared to non-IDD individuals on a waiver control group were compared using Ohio Medicaid claims data from calendar year 2013. Results found the IDD Waiver population had lower utilization rates for emergency department visits, hospital admissions, and hospital readmissions within 30days compared to the Non-IDD Waiver population and lower PMPM expenditures across all medical service categories except pharmacy. However, the IDD Waiver population possessed greater PMPM costs for LTSS and therefore greater overall costs of care. Furthermore, 94% of IDD Waiver individuals had an episode of care for neurological conditions, with the second most frequent episode of care being for mental health services. The two most frequent episodes of care for individuals in the Non-IDD Waiver group were for conditions related to treatment (medical/surgical) and musculoskeletal conditions. The goal of this research was to investigate the health care needs of individuals with IDD that may vary from other long term care populations. The differences in health care needs for individuals with IDD require health systems and care management that is tailored to the sub-population, with an emphasis on treatment for neurological and mental health conditions. The typical focus of care management efforts on reducing unnecessary utilization of hospital services may be less relevant to the IDD Waiver population. The results of this study will be used to make recommendations regarding the unique health care needs of individuals with IDD.

Multi-Source Data Stream Online Frequent Episode Mining

Online frequent episode mining is more complicated than the traditional static frequent episode mining due to the continuous, unbounded and time-varying data stream. Especially in the multiple data streams, online frequent episode mining is more difficult than the single-source stream, due to the concurrency, global clock loss, and uncertainty of delay caused by the distributed environment. To cope with these problems, we propose a new algorithm. Firstly, the data stream with “happen-before” relationship among multiple sources is combined on the global data lattice. Next, the traversal on global data lattice generates effective parallel and serial candidate data streams, which guarantee the accuracy of subsequent mining and reduce the number of global sequences during searching process. Then, we use the frequent episode tree to detect the expanding online serial episodes and parallel episodes. Finally, we verify the effectiveness and efficiency of the proposed methods through extensive experiments.

Large-Scale Frequent Episode Mining from Complex Event Sequences with Hierarchies

Frequent Episode Mining (FEM), which aims at mining frequent sub-sequences from a single long event sequence, is one of the essential building blocks for the sequence mining research field. Existing studies about FEM suffer from unsatisfied scalability when faced with complex sequences as it is an NP-complete problem for testing whether an episode occurs in a sequence. In this article, we propose a scalable, distributed framework to support FEM on “big” event sequences. As a rule of thumb, “big” illustrates an event sequence is either very long or with masses of simultaneous events. Meanwhile, the events in this article are arranged in a predefined hierarchy. It derives some abstractive events that can form episodes that may not directly appear in the input sequence. Specifically, we devise an event-centered and hierarchy-aware partitioning strategy to allocate events from different levels of the hierarchy into local processes. We then present an efficient special-purpose algorithm to improve the local mining performance. We also extend our framework to support maximal and closed episode mining in the context of event hierarchy, and to the best of our knowledge, we are the first attempt to define and discover hierarchy-aware maximal and closed episodes. We implement the proposed framework on Apache Spark and conduct experiments on both synthetic and real-world datasets. Experimental results demonstrate the efficiency and scalability of the proposed approach and show that we can find practical patterns when taking event hierarchies into account.

Discovering frequent chain episodes

Frequent episode discovery is a popular framework in temporal data mining with many applications. An episode is a partially ordered set of nodes with each node associated with an event-type. The episodes literature has seen different notions of frequency and a variety of associated discovery algorithms under these different frequencies when the associated partial order is total (serial episode) or trivial (parallel episode). Recently an apriori-based discovery algorithm for mining episodes where the associated partial order has no restriction but the node to event-type association is one–one (general injective episodes) was proposed based on the non-overlapped frequency measure. This work pointed out that frequency alone is not a sufficient indicator of interestingness in the context of episodes with general partial orders and introduced a new measure of interestingness called bidirectional evidence (BE) to address this issue. This algorithm discovers episodes by incorporating both frequency and BE thresholds in the level-wise procedure. In this paper, we extend this BE-based algorithm to a much larger class of episodes that we call chain episodes. This class encompasses all serial and parallel episodes (injective or otherwise) and also many other non-injective episodes with unrestricted partial orders. We first discuss how the BE measure can be generalized to chain episodes and prove the monotonicity property it satisfies in this general context. We then describe our candidate generation step (with correctness proofs) which nicely exploits this new monotonicity property. We further describe the frequency counting (with correctness proofs) and BE computation steps for chain episodes. The experimental results demonstrate the effectiveness of our algorithms.

Effectiveness of Child to Child Programme on Knowledge Regarding Management of Minor Ailments among School Children

Background: Suffering from minor ailments is the most frequent episode in childhood experiences. A productive and energetic population cannot grow from unhealthy children who are chronically affected by repeated minor ailments. th Method: An evaluative study using one group pretest posttest design was conducted among 30 school children of 9 class in a selected school of Udupi taluk, Karnataka to assess the knowledge of school children regarding the management of minor ailments and to evaluate the effectiveness of structured teaching programme on knowledge regarding management of minor ailments. Results: Majority of children 17 (56 .7 %) had average knowledge in the pretest and only 4(13.3%) children had poor knowledge. There was a significant difference between the mean pretest and posttest knowledge scores on management of minor ailments among school children which indicated that the structured teaching programme on management of minor ailments was found to be effective(t= 9.702, P<0.05). Conclusion: The study concluded that the teaching programme was effective in bringing the desired changes in the knowledge of the school children.

Клинические особенности биполярного аффективного расстройства у госпитализированных больных позднего возраста

Background: as a result of global population aging the amount of aged patients with bipolar disorder (BD) is gradually growing both with the disease onset in the first half of life and with disease onset after 60 years. Aim of the study was to observe clinical features and course of BD in elderly. Material and methods: continuous sample of bipolar in-patients of geriatric clinical units of MHRC aged 60 and older (n = 146) in 2014–2017 were included to comparative study. According to the aim and tasks of the study the patients were divided into 3 groups depending on the age of BD onset: with early-onset BD (0–49 years), new onset in the involution period (50–59 years) and with late-onset BD (60 years and older). All of the patients were examined by psychopathological, clinical and psychometrical method (Hamilton Depression Rating Scale — HAM-D, Hamilton Anxiety Rating Scale — HARS, Young Mania Rating Scale — YMRS, Mini-Mental State Examination — MMSE and Montreal Cognitive Assessment — MoCA). Results: early-onset BD (0–49 years) occurred in 92 patients (63%), new-onset BD in involution period (50–59 years) — in 35 cases (24%), late-onset BD (60 years and older) — in 19 patients included to the study (13%). Early-onset BD was more common in men, while new onset in the involution period — in women. Late-onset BD occurred in men and women with equal frequency. In the majority of patients BD started with depressive episode. Mixed affective episodes showed to be more common as a first BD episode with the increase of disease onset age. Age features of clinical course of affective episodes, cognitive functioningand premorbid characteristics of enrolled patients were viewed and discussed in the study. Early-onset BD leads to more frequent affective episode formation in elderly up to rapid cycling forms, while late-onset BD leads to more prolonged clinical course of affective episodes in comparison with early-onset BD. Premorbid features occur more often in patients with disease onset in thefirst half of life than in patients with late-onset BD. Cognitive functioning of all observed patients stay under age norm during intermission. Conclusion: BD can have its onset at every age, even after 60 years, though in the majority of patients BD onsets before 50 years. Due to ageing, regardless to the age of disease onset depressions and manias in all elderly patients get age-related patterns, mixed affective states become more common.

Do children with neurological disabilities use more inpatient resources: an observational study

BackgroundAdvances in healthcare have improved the survival of children with neurological disabilities (ND). Studies in the US have shown that children with ND use a substantial proportion of resources in children’s hospitals, however, little research has been conducted in the UK. We aimed to test the hypothesis that children with neurological disabilities use more inpatient resources than children without neurological disabilities, and to quantify any significant differences in resource use.MethodsA retrospective observational study was conducted, looking at the number of hospital admissions, total inpatient days and the reason for admissions for paediatric inpatients from January 1st to March 31st 2015. Inpatients were assigned into one of three groups: children without ND, children with one ND, and children with more than one ND.ResultsThe sample population included 942 inpatients (mean age 6y 6mo). Children with at least one ND accounted for 15.3% of the inpatients, 17.7% of total hospital inpatient admission episodes, and 27.8% of the total inpatients days. Neurological disability had a statistically significant effect on total hospital admissions (p < 0.001). Neurological disability also had a statistically significant effect on total inpatient days (p < 0.001). Neurological disability increased the length of inpatient stay across medicine, specialties, and surgery.ConclusionsChildren with ND had more frequent hospital admission episode and longer inpatient stays. We identified a smaller group within this population, with arguably more complex neurological disabilities, children with more than one ND. This group had the highest number of admissions and longest inpatient stays. More frequent hospital admissions and longer inpatient stays may place children with ND at greater risk of the adverse effects of hospitalisations. We recommend further investigations looking at each the effects of the different categories of ND on inpatient resource use, and repeat of this study at a national level and over a longer period of time.

Sequential Behavior Pattern Discovery with Frequent Episode Mining and Wireless Sensor Network

By recognizing patterns in occupants' daily activities, building systems are able to optimize and personalize services. Established technologies are available for data collection and pattern mining, but they all share the drawback that the methodology used for data collection tends to be ill suited for pattern recognition. For this research, we developed a bespoke WSN and combined it with a compact data format for frequent episode mining to overcome this obstacle. The proposed framework has been evaluated with both synthetic data from a smart home simulator and with real data from a self-organizing WSN in a student's home. We are able to demonstrate that the framework is capable of discovering sequential patterns in heterogeneous sensor data. With corresponding scenarios, patterns in daily activities can be deduced. The framework is self-contained, scalable, and energy-efficient, and is thus applicable in multiple building system settings.

Discovering utility-based episode rules in complex event sequences

Mining high utility episode rules in complex event sequences has emerged as an important topic in data mining because the utility-based episode rules generated may provide important insights that facilitate decision making for expert and intelligent systems. Although one may employ previous methods in this research area to indirectly construct utility-based episode rules, they typically lack efficiency and effectiveness for real-world applications. In this paper, we develop a novel methodology to directly generate high utility episode rules during the mining process, which is the first work addressing the issue of utility-based episode rule mining. Our goal is to simultaneously resolve the difficulty of the previous reported methods for frequent episode mining and utility-based episode mining. An algorithm called UBER-Mine (Utility-Based Episode Rules) and a structure named UR-Tree (Utility Rule Tree) are proposed to mine efficiently the complete set of high utility episode rules in complex event sequences. In short, UBER-Mine is based on an extended downward closure property, which can efficiently discover utility-based episode rules. On the other hand, UR-Tree can maintain important event information without producing candidate episodes to further accelerate the mining process. Results on both real and synthetic datasets show that UBER-Mine with UR-Tree has good scalability on large datasets and runs faster than the basic UBER-Mine and the current best high utility episode mining algorithm over 100 times. Furthermore, by proposing a high-utility episode-rule model called IV-UBER (InVestment by Utility-Based Episode Rules), we further demonstrate the effectiveness of our method for mining high utility-based episode rules on a real-world application for stock investment. The experimental results show that our proposed IV-UBER method outperforms several state-of-the-art algorithms in terms of both precision and annualized return for investment.

The risk factors associated with severe wheeze episode in preschool children

Ozet Abstract Amac: Okul oncesi yas grubunda agir hisilti atagi ile iliskili risk faktorlerini belirlemektir. Yontem: Ocak 2013 ile Haziran 2013 tarihleri arasinda Inonu Universitesi Turgut Ozal Tip Merkezi Cocuk Alerji ve Astim poliklinigi ile Cocuk Acil poliklinigine, tekrarlayan agir hisilti atagi ile basvuran alti yasindan kucuk hastalarin dosyalari geriye donuk olarak incelendi. Bulgular: Alti aylik surede her iki poliklinige (cocuk alerji ve cocuk acil) 70 cocuk agir hisilti atagi ile basvurmustu. Calismaya, karsilastirma yapabilmek icin ayni yasta hafif hisilti atagi ile basvuran 72 cocuk hasta da dahil edildi. Agir hisilti atak tanisi konulan olgularin 49 (%68,1)’u erkek idi ve ortanca yasi 30 ay (6-60) idi. Hastalarin ilk gecirdikleri atak yasinin ortancasi 6 ay (1-60), son bir yil icerisindeki atak sayisinin ortancasi 5 (1-10) ve son bir yilda sistemik steroid gerektiren atak sayisinin ortancasi 2 (1-10) idi. Modifiye astim prediktif indeks hastalarin 27 (%38,1)’sinde pozitifti ve 29 hastada (%41,4) hisilti coklu tetiklenen hisilti fenotipindeydi. Agir hisilti atagi erkek cinsiyette (p=0,004) ve pasif sigara maruziyeti olan cocuklarda (p=0,011) daha fazlaydi. Ayrica son 1 yilda atak sikligi (p=0,029) ve sistemik steroid gerektiren atak sayisi da (p=0,001) agir hisilti atagi ile basvuran hastalarda daha fazlaydi. Sonuc: Agir hisilti atagi erkek cinsiyette, pasif sigara maruziyeti olan cocuklarda, son bir yilda hisilti ataklari sik olan ve sistemik steroid gerektiren hastalarda daha fazla gorulmektedir. Bu nedenle hisiltisi olan cocuklarin son 1 yildaki hisilti oykuleri detayli bir sekilde sorgulanmali ve sigara maruziyeti onlenmelidir. Objective: To determine the risk factors which associated with severe wheeze episode in preschool children Method: Between January 2013 and June 2013, the files of the patients, who were seen as severe wheeze episode and under 6 years old at the time of application, were analyzed retrospectively in the pediatric allergy and pediatric emergency department of Inonu University Turgut Ozal Medical Center Results: During the six month period, 70 children applied to two clinics (pediatric allergy and pediatric emergency) due to severe wheeze episode. Seventy-two children who applied with mild wheeze episode were included in the study to compare with severe wheeze episode. Forty-nine patients (68.1%) who were diagnosed with severe wheeze episode were male and the median age was 30 (6-60) months. The median age of first wheeze episode was 6 (160) months, median episode of wheeze number in the previous year was 5 (1-10) and median episode of wheeze required systemic steroid in the previous year was 2 (1-10). Modified Asthma Predictive Index was positive in 27 patients (38.1%) and wheeze was the multiple-trigger phenotype in 29 patients (41.1%). Severe wheeze episode was more in male gender (p=0.004) and in children who exposure to passive smoking (p=0.011). Also, frequency of wheeze episode (p=0.029) and required systemic steroid (p=0.001) in previous year were more in the patients with severe wheeze episode Conclusion: Severe wheeze episode were seen more in the patient who were male gender, exposure to passive smoking, have frequent wheeze episode and require systemic steroid in previous year. Therefore detailed previous year history of wheeze should be questioned in the patient who have wheeze and exposure of passive smoking should be prevented