Home About us Contact
|
Home About us Contact | ||
|
|
||
semi-Markov Model (semi-markov + model)
Selected AbstractsOnline pattern recognition based on a generalized hidden Markov model for intraoperative vital sign monitoringINTERNATIONAL JOURNAL OF ADAPTIVE CONTROL AND SIGNAL PROCESSING, Issue 5 2010Ping Yang Abstract The trend patterns of vital signs provide significant insight into the interpretation of intraoperative physiological measurements. We have modeled the trend signal of a vital sign parameter as a generalized hidden Markov model (also known as a hidden semi-Markov model). This model treats a time series as a sequence of predefined patterns and describes the transition between these patterns as a first-order Markov process and the intra-segmental variations as different dynamic linear systems. Based on this model, a switching Kalman smoother combines a Bayesian inference process with a fixed-point Kalman smoother in order to estimate the unconditional true signal values and generates the probability of occurrence for each pattern online. The probabilities of pattern transitions are tested against a threshold to detect change points. A second-order generalized pseudo-Bayesian algorithm is used to summarize the state propagation over time and reduces the computational overhead. The memory complexity is reduced using linked tables. The algorithm was tested on 30 simulated signals and 10 non-invasive-mean-blood-pressure trend signals collected at a local hospital. In the simulated test, the algorithm achieved a high accuracy of signal estimation and pattern recognition. In the test on clinical data, the change directions of 45 trend segments, out of the 54 segments annotated by an expert, were correctly detected with the best performing threshold, and with the introduction of only 8 false-positive detections. The proposed method can detect the changes of trend patterns in a time series online, while generating quantitative evaluation of the significance of detection. This method is promising for physiological monitoring as the method not only generates early alerts, but also summarizes the temporal contextual information for a high-level decision support system. Copyright © 2009 John Wiley & Sons, Ltd. [source] Comparison of the metabolic and economic consequences of long-term treatment of schizophrenia using ziprasidone, olanzapine, quetiapine and risperidone in Canada: a cost-effectiveness analysisJOURNAL OF EVALUATION IN CLINICAL PRACTICE, Issue 4 2010Roger S. McIntyre MD FRCPC Abstract Rationale, aims and objectives, Second-generation antipsychotic agents have varying propensities to cause weight gain, elevated lipid levels and associated long-term complications. This study evaluates the cost-effectiveness of four second-generation antipsychotic agents used in Canada for the treatment of schizophrenia (ziprasidone, olanzapine, quetiapine, risperidone) with a focus on their long-term metabolic consequences. Method, Using data from the Clinical Antipsychotic Trials of Intervention Effectiveness Study, a semi-Markov model was developed to predict the incidence and associated costs of type 2 diabetes, cardiovascular complications (e.g. angina, myocardial infarction, stroke, cardiovascular disease death), and acute psychiatric hospitalizations in patients with chronic schizophrenia treated over 5 years. Incremental costs per quality-adjusted life year (QALY) gained were calculated from the perspective of the Canadian provincial ministries of health. Scenario and probabilistic sensitivity analyses were performed. Results, The total average cost of treatment with ziprasidone was $25 301 versus $28 563 with olanzapine, $26 233 with quetiapine and $21 831 with risperidone. Ziprasidone had the lowest predicted number of type 2 diabetes cases and cardiovascular disease events, and the highest QALY gains. Patients receiving quetiapine had the highest predicted number of hospitalizations. Ziprasidone was less costly and resulted in more QALYs compared with olanzapine and quetiapine. Compared with risperidone, ziprasidone was more costly and had higher QALYs, with an incremental cost per QALY gained of $218 060. Conclusion, Compared with olanzapine and quetiapine, ziprasidone produced savings to the health care system. Although ziprasidone generated incremental expenditures versus risperidone, it resulted in more QALYs. Based on this analysis, ziprasidone treatment possesses cost and therapeutic advantages compared with olanzapine and quetiapine. [source] Stochastic modeling of usage patterns in a web-based information systemJOURNAL OF THE AMERICAN SOCIETY FOR INFORMATION SCIENCE AND TECHNOLOGY, Issue 7 2002Hui-Min Chen Users move from one state (or task) to another in an information system's labyrinth as they try to accomplish their work, and the amount of time they spend in each state varies. This article uses continuous-time stochastic models, mainly based on semi-Markov chains, to derive user state transition patterns (both in rates and in probabilities) in a Web-based information system. The methodology was demonstrated with 126,925 search sessions drawn from the transaction logs of the University of California's MELVYL® library catalog system (www.melvyl.ucop.edu). First, user sessions were categorized into six groups based on their similar use of the system. Second, by using a three-layer hierarchical taxonomy of the system Web pages, user sessions in each usage group were transformed into a sequence of states. All the usage groups but one have third-order sequential dependency in state transitions. The sole exception has fourth-order sequential dependency. The transition rates as well as transition probabilities of the semi-Markov model provide a background for interpreting user behavior probabilistically, at various levels of detail. Finally, the differences in derived usage patterns between usage groups were tested statistically. The test results showed that different groups have distinct patterns of system use. Knowledge of the extent of sequential dependency is beneficial because it allows one to predict a user's next move in a search space based on the past moves that have been made. It can also be used to help customize the design of the user interface to the system to facilitate interaction. The group CL6 labeled "knowledgeable and sophisticated usage" and the group CL7 labeled "unsophisticated usage" both had third-order sequential dependency and had the same most-frequently occurring search pattern: screen display, record display, screen display, and record display. The group CL8 called "highly interactive use with good search results" had fourth-order sequential dependency, and its most frequently occurring pattern was the same as CL6 and CL7 with one more screen display action added. The group CL13, called "known-item searching" had third-order sequential dependency, and its most frequently occurring pattern was index access, search with retrievals, screen display, and record display. Group CL14 called "help intensive searching," and CL18 called "relatively unsuccessful" both had third-order sequential dependency, and for both groups the most frequently occurring pattern was index access, search without retrievals, index access, and again, search without retrievals. [source] A semi-Markov model for binary longitudinal responses subject to misclassificationTHE CANADIAN JOURNAL OF STATISTICS, Issue 3 2001Rhonda J. Rosychuk Abstract The authors propose a two-state continuous-time semi-Markov model for an unobservable alternating binary process. Another process is observed at discrete time points that may misclassify the true state of the process of interest. To estimate the model's parameters, the authors propose a minimum Pearson chi-square type estimating approach based on approximated joint probabilities when the true process is in equilibrium. Three consecutive observations are required to have sufficient degrees of freedom to perform estimation. The methodology is demonstrated on parasitic infection data with exponential and gamma sojourn time distributions. Un modèle semi-markovien pour données longitudinales binaires sujettes à des erreurs de classification Les auteures proposent un modèle semi-markovien à temps continu et à deux états pour un processus binaire alternant non-observable. Un processus auxiliaire observé en temps discret renseigne toutefois de façon imparfaite quant à l'état réel du processus d'intér,t. Pour estimer les paramètres du modèle, les auteures proposent la minimisation d'un critère de type khi-deux de Pearson en s'appuyant sur une approximation des probabilités conjointes du processus en équilibre. Trois observations consécutives fournissent suffisamment de degrés de liberté aux fins d'estimation. La méthodologie est illustrée au moyen de données sur une infection parasitaire avec temps de séjour exponentiel et gamma. [source] A semi-Markov model of disease recurrence in insured dogsAPPLIED STOCHASTIC MODELS IN BUSINESS AND INDUSTRY, Issue 5 2007Xikui Wang Abstract We use a semi-Markov model to analyse the stochastic dynamics of disease occurrence of dogs insured in Canada from 1990 to 1999, and the probability pattern of death from illness. After statistically justifying the use of a stochastic model, we demonstrate that a stationary first-order semi-Markov process is appropriate for analysing the available data set. The probability transition function is estimated and its stationarity is tested statistically. Homogeneity of the semi-Markov model with respect to important covariates (such as geographic location, insurance plan, breed and age) is also statistically examined. We conclude with discussions and implications of our results in veterinary contents. Copyright © 2007 John Wiley & Sons, Ltd. [source] Driving forces behind increasing cardiovascular drug utilization: a dynamic pharmacoepidemiological modelBRITISH JOURNAL OF CLINICAL PHARMACOLOGY, Issue 6 2008Helle Wallach Kildemoes WHAT IS ALREADY KNOWN ABOUT THIS SUBJECT , Several studies indicate that switch to more expensive drugs and increasing treatment intensity, rather than population ageing have been responsible for rising drug expenditures during the 1990s. , Little is known about the driving forces behind the increasing treatment intensity with cardiovascular drugs. WHAT THIS STUDY ADDS , This study provides a new pharmacoepidemiological method to analyse drug utilization trends, applying dispensing data at the individual level. , The suggested semi-Markov model allows for quantification of the influence of changing incidence, discontinuation and user mortality on rising treatment prevalence. , Increasing treatment incidence was the main driver behind rising treatment prevalence for most cardiovascular drug categories. , Whereas declining discontinuation drove some of the growth, declining mortality among drug users had little influence. AIMS To investigate the driving forces behind increasing utilization of cardiovascular drugs. METHODS Using register data, all Danish residents as of 1 January 1996 were followed until 2006. Cohort members were censored at death or emigration. Cardiovascular drug utilization on the individual level was traced, applying registered out-of-hospital dispensing. The impact of population ageing on cardiovascular drug utilization was investigated using standardized intensities and prevalences. Based on a three-state (untreated, treated and dead) semi-Markov model, we explored to what extent increasing treatment prevalence was driven by changing incidence, discontinuation and mortality. Expected treatment prevalences were modelled, applying stratum-specific cohort prevalence in 1996 along with incidence, discontinuation and drug user mortality either throughout 1996,2004 or at fixed 1996 levels. RESULTS Treatment prevalence (ages ,20 years) with cardiovascular drugs increased by 39% during 1996,2005 from 192.4 to 256.9 per 1000 inhabitants (95% confidence interval 256.5, 257.3). Treatment intensity grew by 109% from 272 to 569 defined daily doses 1000,1 day,1. Population ,middle-ageing' accounted for 11.5 and 20.3%, respectively. Increasing treatment incidence was the main driver of the rising treatment prevalence in most drug categories. Declining discontinuation drove some of the growth, declining drug user mortality less. Even with fixed incidence in the model, treatment prevalence continued to increase. CONCLUSIONS Age-related increases in treatment intensity and prevalence, rather than population ageing, drove the increasing treatment intensity with cardiovascular drugs. Increasing treatment prevalence in subgroups was primarily caused by increasing incidence. Due to pharmacoepidemiological disequilibrium, treatment prevalence will continue to grow even with unchanged incidence. [source] | |||||||||||||