PubMed Health⌕ Search

Biomedical subjects

Byron J Gajewski

Publications and source records attributed to Byron J Gajewski.

16 recordsLinked to original sources
PubMed2006

Non-normal path analysis in the presence of measurement error and missing data: a Bayesian analysis of nursing homes' structure and outcomes.

Path analytic models are useful tools in quantitative nursing research. They allow researchers to hypothesize causal inferential paths and test the significance of these paths both directly and indirectly through a mediating variable. A standard statistical method in the path analysis literature is to treat the variables as having a normal distribution and to estimate paths using several least squares regression equations. The parameters corresponding to the direct paths have point and interval estimates based on normal distribution theory. Indirect paths are a product of the direct path from the independent variable to the mediating variable and the direct path of the mediating variable to the dependent variable. However, in the case of non-normal distributions, the point and interval estimates of the indirect path become much more difficult to estimate. We address the issue of calculating indirect point and interval estimates in the case of non-normally distributed data. Our substantive application is a nursing home research problem in which the variables in the path analysis of interest involve variables with normal, Bernoulli, or Poisson distributions. Additionally, one of the Poisson variables is observed with error. This paper addresses estimating point and interval estimation of indirect paths for variables with non-normal distributions in the presence of missing data and measurement error. We handle these difficulties from a fully Bayesian point of view. We present our substantive path analysis motivated from a nursing home structure, process, and outcomes model. Our results focus on the impact job turnover in the nursing homes has on nursing home outcomes.

Data Interpretation, Statistical↗
PubMed2006

Bayesian sample size calculations in phase II clinical trials using a mixture of informative priors.

A number of researchers have discussed phase II clinical trials from a Bayesian perspective. A recent article by Mayo and Gajewski focuses on sample size calculations, which they determine by specifying an informative prior distribution and then calculating a posterior probability that the true response will exceed a prespecified target. In this article, we extend these sample size calculations to include a mixture of informative prior distributions. The mixture comes from several sources of information. For example consider information from two (or more) clinicians. The first clinician is pessimistic about the drug and the second clinician is optimistic. We tabulate the results for sample size design using the fact that the simple mixture of Betas is a conjugate family for the Beta- Binomial model. We discuss the theoretical framework for these types of Bayesian designs and show that the Bayesian designs in this paper approximate this theoretical framework.

Algorithms↗
PubMed2006

Inter-rater reliability of nursing home surveys: a Bayesian latent class approach.

In the U.S., federal and state governments perform routine inspections of nursing homes. Results of the inspections allow government to generate fines for findings of non-compliance as well as allow consumers to rank facilities. The purpose of this study is to investigate the inter-rater reliability of the nursing home survey process. In general, the survey data involves 191 binary deficiency variables interpreted as 'deficient' or 'non-deficient'. To reduce the dimensionality of the problem, our proposed method involves two steps. First, we reduce the deficiency categories to sub-categories using previous nursing home studies. Second, looking at the State of Kansas specifically, we take the deficiency data from 1 year, and use Bayesian latent class analysis (LCA) to collapse the sub-categories to a binary variable. We evaluate inter-rater agreement using deficiency data from two separate survey teams on one facility, a matched-pair design. We evaluate the agreement of the two raters on binary data using the weights from the LCA. This allows a two-by-two contingency analysis using a Bayesian beta-binomial model. We elicit informative prior distributions from the nursing home providers. Together, with the experimental data, this provides a posterior distribution of the kappa agreement of the raters for nursing home deficiency citation data.

Bayes Theorem↗
PubMed2006

Reliability of the nursing home survey process: a simultaneous survey approach.

PURPOSE: We designed this study to examine the reliability of the nursing home survey process in the state of Kansas using regular and simultaneous survey teams. In particular, the study examined how two survey teams exposed to the same information at the same time differed in their interpretations. DESIGN AND METHODS: The protocol for simultaneous surveys consists of having one in-region and one out-of-region team survey a facility together. RESULTS: The regular and simultaneous survey teams generally agreed about the number of deficiencies. The intraclass correlation coefficient was 0.87 for total deficiencies and 0.76 for deficiencies with scores of G or higher. But in a substantial number of instances the teams did not agree about the scope and severity of the deficiency or about what regulation the nursing home had breached. IMPLICATIONS: The survey process is reliable when assessing aggregate results, but it is only moderately reliable when examining individual citations. Stakeholders (i.e., consumers, policy makers, nursing home administrators) should be aware of the limitations of the survey process. It needs to be modified to reduce variability.

Data Collection↗
PubMed2006

Unit type differences in RN workgroup job satisfaction.

Using cross-sectional data from the 2004 National Database of Nursing Quality Indicators (NDNQI) RN Satisfaction Survey, differences in RN workgroup job satisfaction were examined among 10 unit types--medical-surgical, step-down, critical care, pediatric, maternal-newborn, psychiatric, emergency department, rehabilitation, surgical services, and outpatient clinics and labs. The national sample included RN workgroups in 2,900 patient care units (55,516 RNs; 206 hospitals in 44 states). Workgroup satisfaction across all unit types was moderate. RN workgroups in pediatric units were the most satisfied, whereas those in surgical services and emergency department unit types were least satisfied. A consistent finding across all unit types was high satisfaction with the specific domains of nurse-to-nurse interaction, professional status, and professional development versus much lower satisfaction with task, decision making, and pay. Findings can be used to inform and develop investigations that examine specific aspects of the work environment for RN workgroups in various unit types.

Data Collection↗
PubMed2006

Some statistical issues in microarray gene expression data.

In this paper we discuss some of the statistical issues that should be considered when conducting experiments involving microarray gene expression data. We discuss statistical issues related to preprocessing the data as well as the analysis of the data. Analysis of the data is discussed in three contexts: class comparison, class prediction and class discovery. We also review the methods used in two studies that are using microarray gene expression to assess the effect of exposure to radiofrequency (RF) fields on gene expression. Our intent is to provide a guide for radiation researchers when conducting studies involving microarray gene expression data.

Artifacts↗
PubMed2004

A log-normal distribution model of the effect of bacteria and ear fenestration on hearing loss: a Bayesian approach.

Chronic ear infection is a potentially life-threatening illness that medical doctors typically treat with ear surgery. Despite the success of this treatment, complications can occur due to bacteria infection. Surgeons believe that this infection causes the patient to have clinically significant hearing damage. In order to understand such complications, surgeons must quantify the effect of bacteria, their toxins and ear surgery on hearing loss. To this end, the other two authors of this paper performed two experiments on guinea pigs to measure hearing thresholds following a bacterial infection and surgery of the inner ear. The response variable in these experiments is hearing thresholds measured in decibels (dB). The problem in analysing such experiments is that the hearing threshold observations often suffer from missing data and censoring mechanisms of various types. Additionally, the distribution of hearing thresholds has heavy tails and is peaked. In order to account for the above statistical issues, we present a Bayesian method with a location-shifted log-normal distribution. The method accounts for the uncertainty in the data collection mechanism and the parameters associated with a location-shifted log-normal distribution. We refer to one of the parameters as the "location-shift" parameter. The Bayesian approach provides a posterior distribution of the location-shift parameter that we compare with values estimated in previously published studies. The immediate goal of our proposed method was to quantify the effects of ear surgery and bacteria infection on hearing loss. Thus, we present the merits of the method in the form of a case study, and report posterior distributions of mean hearing loss, probability of clinically significant hearing loss and relative risk. The results show that surgeon 2, using the surgical procedure "oval window", poses a greater than 40 per cent chance of a 15dB hearing loss regardless of injection of bacteria or not. However, surgeon 1, using the surgical procedure "semicircular canal", does not pose a significantly greater than 40 per cent chance of a 15dB hearing loss unless there is a Pseudomonas aeruginosa-induced infection.

Aged↗
PubMed2004

Bayesian sample size calculations in phase II clinical trials using informative conjugate priors.

A number of researchers have discussed phase II clinical trials from a Bayesian perspective. A recent article by Tan and Machin focuses on sample size calculations, which they determine by specifying a diffuse prior distribution and then calculating a posterior probability that the true response will exceed a prespecified target. In this article, we extend these sample size calculations to include informative prior distributions using various strategies that allow researchers with both optimistic and pessimistic priors direct involvement in the sample size decision making. We select the informative priors via multiple methods determined by the mean, median or mode of the conjugate prior. These cases can result in varying sample sizes.

Bayes Theorem↗
PubMed2004

Hearing loss with semicircular canal fistula in exotoxin A-deficient Pseudomonas otitis media.

OBJECTIVE: The study goal was to compare the severity of hearing loss with semicircular canal injury in the presence of otitis media (OM) due to an exotoxin A-producing strain of Pseudomonas aeruginosa (PA+) and an exotoxin A-deficient daughter strain (PA-). METHODS: PA+ or PA- was injected bilaterally into guinea pig ears. Three days later, unilateral lateral semicircular canal transection was performed. Hearing was tested before and after transection. RESULTS: PA OM was induced in all injected ears. Significant elevation of click and 12-kHz thresholds (P < 0.0001) were encountered in PA+-infected ears. No significant threshold elevations were encountered in PA--infected ears. CONCLUSION: Hearing loss resulting from canal injury in the presence of Pseudomonas OM may be mediated by exotoxin A. SIGNIFICANCE: Treatment to neutralize the effects of exotoxin A may minimize the risk of hearing loss with canal fistula in chronic OM.

ADP Ribose Transferases↗
PubMed2004

Hearing loss with semicircular canal transection and Pseudomonas aeruginosa otitis media.

OBJECTIVE: To determine if Pseudomonas aeruginosa (PA) otitis media (OM) increases the risk of sensorineural hearing loss (SNHL) with semicircular canal transection in the guinea pig model. METHODS: PA was injected transtympanically into both middle ears of pigmented guinea pigs. Saline-injected animals served as controls. Two to 4 days after injection, one horizontal semicircular canal was transected and sealed. Hearing was tested using electrocochleography before and after transection. RESULTS: PA-OM was induced in all PA-injected ears. Five days after semicircular canal transection, click-evoked thresholds were significantly elevated in ears with PA-OM (P = 0.00009) but not in saline-injected ears (P = 0.398). CONCLUSION: Violation of the inner ear in the presence of PA-OM is associated with increased risk of SNHL in the guinea pig. SIGNIFICANCE: Factors unique to PA infection may be responsible for SNHL with labyrinthine injury in humans with chronic otitis media.

Animals↗
PubMed2003

Hearing loss with stapedotomy in otitis media.

OBJECTIVE: Stapes fixation is often found in patients with either active or inactive otitis media (OM). Stapedotomy is generally not performed in ears with OM because of the potential risk of sensorineural hearing loss (SNHL). Recent studies have demonstrated that the inner ear may be fenestrated in the presence of OM without significantly increased risk of SNHL. The goal of this study was to determine if stapedotomy in the presence of OM significantly increases the incidence of postoperative SNHL. METHODS: Streptococcus pneumoniae or Pseudomonas aeruginosa was injected bilaterally into the middle ears of guinea pigs (n = 18 and 16, respectively). A control group (n = 14) was injected with saline solution. Two days postinjection, a unilateral stapedotomy was performed. Auditory thresholds were evaluated by electrocochleography before and after stapedotomy. RESULTS: Bacterial OM was induced in all ears injected with pneumococci and pseudomonas. Auditory thresholds increased in all ears treated with stapedotomy. Stapedotomy performed in the presence of pseudomonas OM resulted in significantly greater SNHL than in control or pneumococcal ears (P = 0.0055). Hearing thresholds were not significantly different between pneumococcal OM and control ears treated with stapedotomy. CONCLUSION: Stapedotomy in the presence of pseudomonas OM, but not pneumococcal OM, significantly increases the risk of SNHL in the guinea pig model. SIGNIFICANCE: Stapedotomy should be avoided in patients with active OM, particularly in the presence of pseudomonas.

Animals↗
PubMed2003

Hyperbaric compression in the guinea pig with perilymph fistula.

OBJECTIVE: The study goal was to evaluate the effects of hyperbaric therapy on the auditory and vestibular function of guinea pigs compromised by perilymph fistula (PLF). METHODS: Twenty-four pigmented guinea pigs underwent induction of bilateral eustachian tube dysfunction before the creation of a unilateral PLF. Half of the animals were randomly assigned to receive immediate hyperbaric compression treatment of 4 "dives" each. Hearing was tested electrocochleographically, and signs of vestibulopathy were recorded before and after compression. RESULTS: After accounting for the effects of PLF, compression was not associated with significant hearing loss (P = 0.5411). Vestibulopathy was seen only in ears with PLF, and its incidence was similar for compression and noncompression groups. CONCLUSION: Hyperbaric compression does not compromise auditory or vestibular function in guinea pig ears with experimental PLF. SIGNIFICANCE: Our observations support the relative safety of recompression in patients with PLF.

Animals↗
PubMed2003

Incidence of venous thromboembolic events among nursing home residents.

Chronic care facility stay has been shown to be an independent risk factor for venous thromboembolism. Review of the literature, however, reveals a paucity of data addressing the issue of venous thromboembolism in nursing home residents. The purpose of this study was to determine the incidence of venous thromboembolic events among nursing home residents. A retrospective cohort study was derived from data compiled in the State of Kansas Minimum Data Set (MDS) for nursing home residents from July 1, 1997 to July 1, 1998. A total of 18,661 residents (median age, 85 years, 74% female, 95% white) satisfied the study criteria. The outcome measures of the primary endpoint-development of a venous thromboembolic event (VTE)-were obtained from the MDS quarterly health assessments and the Medicare ICD-9 codes. We determined the incidence of VTE among nursing home residents as 1.30 events per 100 person-years of observation.

Aged↗
PubMedDate not supplied

Caudal septoplasty for treatment of septal deviation: aesthetic and functional correction of the nasal base.

OBJECTIVES: To describe our technique in the treatment of significant caudal septal deviation; to evaluate the effectiveness of our technique of caudal septoplasty in the treatment of caudal septal deviations. DESIGN: Retrospective review of cases taken from a database of more than 2000 patients who underwent rhinoplasty performed by 1 surgeon in a private facial plastic surgery practice. RESULTS: Medical charts were reviewed to determine the rate of preoperative nasal obstruction in 59 (95%) of 62 patients as well as nasal obstruction postoperatively 11 (17%) of 62 (P < .001). Photographs were reviewed to determine the severity of caudal deviation and the postoperative result. By photographic evaluation, we found that all but 3 patients had significant improvement in their postoperative appearance. Twenty-six patients had no evidence of residual asymmetry. The rate of revision was 5 (8%) of 62 patients. CONCLUSIONS: The caudal septoplasty technique is effective, relatively easy to perform, and shows long-term reliability in correcting caudal septal deviation. In properly selected patients, the technique is effective in improving cosmesis and nasal airflow.

Esthetics↗
PubMedDate not supplied

A systematically tested intervention for managing reactive depression.

BACKGROUND: Patients and family caregivers repeatedly experience reactive depression that leads to medication errors, mismanagement of chronic disease, and poor self-care. These problems place them at high-risk for malnutrition, infection, heart diseases, and psychiatric sequelae. OBJECTIVES: A secondary data analysis compared findings across a series of studies to evaluate the acceptability, effectiveness, and cost of a therapeutic writing intervention to reduce reactive depression, a common and frequently recurring adverse symptom. METHODS: Secondary analysis of data from the series of studies was conducted. Data came from patients requiring lifelong, daily central intravenous catheter infusion of home total parenteral nutrition necessitated by nonmalignant bowel disease and their family caregivers who assist with this complex home care. Variables combined across the studies were pre- and postintervention scores from the Center for Epidemiological Studies-Depression Scale (CES-D), the number of weeks patients wrote in their diaries (adherence), and the written content in the diaries. Content analysis was used to analyze written data. The intervention materials and nurses' time spent were averaged across studies to determine costs. RESULTS: The weighted average baseline CES-D scores across studies for patients (17.94) and caregivers (15.75) showed the presence of depression. After journal writing had been used for an average of 10.4 weeks across studies, the effect sizes of the between (d =.27) and within (d =.65) patient group scores indicated moderate to large improvement in depression. Themes from written diaries showed that missing out on activities, financial worries, strain related to the severe illness, and the complexity of home care were related to depression across the studies. CONCLUSIONS: The intervention was acceptable to participants, effective for managing reactive depression, and low in cost. The next steps will address testing for the longitudinal effects of the intervention.

Adult↗