Sotiris Bersimis

Multivariate Statistical Process Control Charts: An Overview

In this paper we discuss the basic procedures for the implementation of multivariate statistical process control via control charting. Furthermore, we review multivariate extensions for all kinds of univariate control charts, such as multivariate Shewhart-type control charts, multivariate CUSUM control charts and multivariate EWMA control charts. In addition, we review unique procedures for the construction of multivariate control charts, based on multivariate statistical techniques such as principal components analysis (PCA) and partial lest squares (PLS). Finally, we describe the most significant methods for the interpretation of an out-of-control signal.

On the distribution of the total number of run lengths

In the present paper, we study the distribution of a statistic utilizing the runs length of “reasonably long” series of alike elements (success runs) in a sequence of binary trials. More specifically, we are looking at the sum of exact lengths of subsequences (strings) consisting ofk or more consecutive successes (k is a given positive integer). The investigation of the statistic of interest is accomplished by exploiting an appropriate generalization of the Markov chain embedding technique introduced by Fu and Koutras (1994,J. Amer. Statist. Assoc.,89, 1050–1058) and Koutras and Alexandrou (1995,Ann. Inst. Statist. Math.,47, 743–766). In addition, we explore the conditional distribution of the same statistic, given the number of successes and establish statistical tests for the detection of the null hypothesis of randomness versus the alternative hypothesis of systematic clustering of successes in a sequence of binary outcomes.

Comparative antimicrobial susceptibility of biofilm versus planktonic forms of Salmonella enterica strains isolated from children with gastroenteritis

In the present study, 194 Salmonella enterica strains, isolated from infected children and belonging to various serotypes, were investigated for their ability to form biofilms and the biofilm forms of the isolated strains were compared to their corresponding planktonic forms with respect to the antimicrobial susceptibility. For the biofilm-forming strains, the minimum inhibitory concentration for bacterial regrowth (MICBR) from the biofilm of nine clinically applicable antimicrobial agents was determined, and the results were compared to the respective MIC values of the planktonic forms. One hundred and nine S. enterica strains out of 194 (56%) belonging to 13 serotypes were biofilm-forming. The biofilm forms showed increased antimicrobial resistance compared to the planktonic bacteria. The highest resistance rates of the biofilm bacteria were observed with respect to gentamicin (89.9%) and ampicillin (84.4%), and the lowest rates with respect to ciprofloxacin and moxifloxacin (2.8% for both). A remarkable shift of the MICBR50 and MICBR90 toward resistance was observed in the biofilm forms as compared to the respective planktonic forms. The development of new consensus methods for the determination of the antimicrobial susceptibility of biofilm forms seems to be a major research challenge. Further studies are required in order to elucidate the biofilm antimicrobial resistance mechanisms of the bacterial biofilms and their contribution to therapeutic failure in infections with in vitro susceptible bacteria.

Run and Frequency Quota Rules in Process Monitoring and Acceptance Sampling

Motivated by certain models arising in the field of statistical process control and acceptance sampling, we study the waiting-time distribution for the first occurrence of a pattern belonging to a specific family of patterns in a bivariate sequence of trinomial trials. Such a setup can be applied in cases where the final quality of the output of an industrial process is determined by two correlated variables that are used to classify the two measured characteristics as “quite close to target quality,” “of satisfactory quality,” and “far from target quality.” A typical case where this happens is whenever registering the exact value of the characteristic of interest is expensive or difficult (e.g., when the observations come in the form of grouped data, due to the use of m-step gauges). The exact distribution of the waiting time is derived by using a Markov chain-embedding technique, which is then used in order to determine the most appropriate design for the quality-control problems discussed.

A compound control chart for monitoring and controlling high quality processes

In the present article, we propose a new control chart for monitoring high quality processes. More specifically, we suggest declaring the monitored process out of control, by exploiting a compound rule couching on the number of conforming units observed between the (i−1)th and the ith nonconforming item and the number of conforming items observed between the (i−2)th and the ith nonconforming item. Our numerical experimentation demonstrates that the proposed control chart, in most of the cases, exhibits a better (or at least equivalent) performance than its competitors.

Identification and antimicrobial resistance of campylobacter species isolated from animal sources.

Background: Campylobacter spp. are together with Salmonella spp. the leading causes of human bacterial gastroenteritis worldwide. The most commonly isolated species in humans are Campylobacter jejuni and C. coli. The isolation, identification, and antimicrobial resistance of Campylobacter spp. from poultry and raw meat from slaughterhouses, has been investigated for the first time in Greece. During the period from August 2005 to November 2008 a total of 1080 samples were collected: (a) 830 fecal samples from five poultry farms, (b) 150 cecal samples from chicken carcasses in a slaughterhouse, and (c) 100 fecal samples from one pig farm near the region of Attica. The identification of the isolates was performed with conventional (sodium hippurate hydrolysis and commercial identification system (Api CAMPY system, bioMerieux, France), as well as with and molecular methods based on 16S rRNA species specific gene amplification by PCR and subsequent sequence analysis of the PCR products. Results: Sixteen Campylobacter strains were isolated, all collected from the poultry farms. None of the strains was identified as C. jejuni. Antimicrobial susceptibility to six antimicrobials was performed and all the strains were susceptible to ciprofloxacin, amoxicillin–clavulanic acid, and gentamicin. Thirteen out of 14 C. coli were resistant to erythromycin and all C. coli strains were resistant to ampicillin. Conclusion: Our results emphasize the need for a surveillance and monitoring system with respect to the prevalence and antimicrobial resistance of Campylobacter in poultry, as well as for the use of antimicrobials in veterinary medicine in Greece.

Detection of bacteria bearing resistant biofilm forms, by using the universal and specific PCR is still unhelpful in the diagnosis of periprosthetic joint infections

Intraoperative conventional bacteriological cultures were compared with different polymerase chain reaction (PCR) methods in patients with total joint arthroplasties. The isolated bacteria were investigated for biofilm formation, and the biofilm forming strains, in their planktonic and biofilm forms, were further tested for their antimicrobial resistance against several clinically important antimicrobials. Forty four bone and joint samples were included and classified as infected or non-infected according to standard criteria for periprosthetic hip and knee infections. For the bacteriological diagnosis, conventional culture, two types of universal PCR and species specific PCR for three selected pathogens (Staphylococcus aureus, Staphylococcus epidermidis, and Pseudomonas aeruginosa) were applied. Biofilm formation determination was performed by the tissue culture plate method. Antimicrobial susceptibility of the planktonic bacteria was performed by the minimal inhibitory concentration determination and, of the biofilm forms, by the minimal inhibitory concentration for bacterial regrowth from the biofilm. Twenty samples were culture positive, with S. epidermidis, S. aureus, or P. aeruginosa. All PCR methods were very ineffective in detecting only one pathogen. All isolates were biofilm positive and their biofilm forms, were highly resistant. In this study, compared to PCR, culture remains the “gold standard.” The biofilm formation by the causative bacteria and the concomitant manifold increased antimicrobial resistance may explain the clinical failure of treatment in some cases and should be considered in the future for therapeutic planning.

Phase II control charts for autocorrelated processes

Abstract A large amount of SPC procedures are based on the assumption that the process subject to monitoring consists of independent observations. Chemical processes as well as many non-industrial processes exhibit autocorrelation, for which the above-mentioned control procedures are not suitable. This paper proposes a Phase II control procedure for autocorrelated and possibly locally stationary processes. A time-varying autoregressive (AR) model is proposed, which is capable of dealing with the autocorrelation as well as with local non-stationarities of the temporal process. Such non-stationarities are induced by the time-varying nature of the AR coefficients. The model is optimized during Phase I when it is assured that the process is in control and as a result the model describes accurately the process. The Phase II proposed control procedure is based on a comparison of the current time series model with an alternative model, measuring deviations from it. This comparison is carried out using Bayes factors, which help to establish the in-control or out-of-control state of the process in Phase II. Using the threshold rules of the Bayes factors, we propose a binomial-type control procedure for the monitoring of the process. The methodology of this paper is illustrated using two data sets consisting of temperature measurements at two different stages in the manufacturing of a plastic mould.

Serologic markers for HBV, HCV and HIV in immigrants visiting the Athens' polyclinic of 'Doctors of the World - Greece'.

G. Papadakis , N.A. Okoba , C. Nicolaou , F. Boufidou , A. Ioannidis , S. Bersimis , Doctors of the World e Greece, S. Chatzipanagiotou * Greek Delegation of Doctors of the World, Athens, Greece Department of Medical Biopathology, Eginition Hospital, Medical School, University of Athens, Athens, Greece Department of Nursing, Faculty of Human Movement and Quality of Life Sciences, University of Peloponnese, Greece Department of Statistics and Insurance Science, University of Piraeus, Piraeus, Greece

Detection of Biofilm Production of Yersinia enterocolitica Strains Isolated from Infected Children and Comparative Antimicrobial Susceptibility of Biofilm Versus Planktonic Forms

Background and ObjectivesThe ability of Yersinia species to produce biofilms has not been hitherto systematically studied, although there is evidence, that Y. enterocolitica is able to form biofilms on inanimate surfaces. The present study aimed to detect the production of biofilms by 60 clinical strains of Y. enterocolitica and to compare the antimicrobial susceptibility of planktonic versus biofilm-forming bacteria.MethodsY. enterocolitica strains were collected from stool and blood cultures collected from β-thalassaemic children, with gastroenteritis and/or septicemia. The isolated bacterial strains were grouped by biotyping and serotyping and the antimicrobial susceptibility of the planktonic forms was investigated by MIC determination. Biofilm formation was detected by the use of silicone disks and for the biofilm forming strains the minimum inhibitory concentration for bacterial regrowth (MICBR) of 11 clinically important antimicrobials was determined. The presence of the waaE, a gene reported to be related with biofilm formation was investigated in all the strains.ResultsAll of 60 strains were positive for biofilm production by the use of silicone disks. The great majority of the biofilm forms were resistant to all the antimicrobials. In antimicrobial concentrations far higher than the CLSI breakpoints, bacterial regrowth from the biofilms was still possible. None of the strains bore the waaE gene.ConclusionsThese results, indicate that biofilm formation by Y. enterocolitica might be an inherent feature. The presence of biofilms increased dramatically the MICBR in all antimicrobials. The way in which biofilms could contribute to Y. enterocolitica pathogenicity in humans is a matter needing further investigation.