PubMed Health⌕ Search

SEARCH · PubMed Health

Results for “Logistic Models”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 415 records · Page 23Linked to original sources

Pressure inactivation kinetics of phage lambda cI 857.

Inactivation curves of phage lambda cI 857 inactivated by high hydrostatic pressure were obtained at three pressure levels (300, 350, and 400 MPa) in buffered media and ultrahigh-temperature 2% reduced fat milk. Pressurization of phage lambda in buffered media at 300 MPa for 300 min, 350 MPa for 36 min, and 400 MPa for 8 min reduced the titer of phage lambda by 7.5, 6.7, and 7.7 log, respectively. Pressurization of phage lambda in milk at 300 MPa for 400 min, 350 MPa for 80 min, and 400 MPa for 20 min reduced the titer of phage lambda by 5.4, 6.4, and 7.1 log, respectively. Tailing was observed in all inactivation curves, indicating that the linear model was not adequate for describing these curves. Among the three nonlinear models studied, the Weibull and log-logistic models consistently produced best fits to all inactivation curves, and the modified Gompertz model the poorest. Because there were no significant differences in the values of shape factor (n) for suspension medium buffer, we reduced the number of parameters in the Weibull model from two to one by setting n at the mean value. The simplified Weibull model produced a fit comparable to the full model. Additionally, the simplified Weibull model allowed predictions to be made at pressures different from the experimental pressures. Menstruum was found to significantly affect the pressure resistance of phage lambda. Comparison of pressure inactivation of hepatitis A virus and phage lambda indicated that phage lambda is more sensitive to pressure than hepatitis A virus in Dulbecco's modified Eagle medium with 10% fetal bovine sera.

Animals↗

Prediction on lengths of stay in the postanesthesia care unit following general anesthesia: preliminary study of the neural network and logistic regression modelling.

The length of stay in the postanesthesia care unit (PACU) following general anesthesia in adults is an important issue. A model, which can predict the results of PACU stays, could improve the utilization of PACU and operating room resources through a more efficient arrangement. The purpose of study was to compare the performance of neural network to logistic regression analysis using clinical sets of data from adult patients undergoing general anesthesia. An artificial neural network was trained with 409 clinical sets using backward error propagation and validated through independent testing of 183 records. Twenty-two inputs were used to find determinants and to predict categorical values. Logistic regression analysis was performed to provide a comparison. The neural network correctly predicted in 81.4% of situations and identified discriminating variables (intubated state, sex, neuromuscular blocker and intraoperative use of opioid), whereas the figure was 65.0% in logistic regression analysis. We concluded that the neural network could provide a useful predictive model for the optimization of limited resources. The neural network is a new alternative classifying method for developing a predictive paradigm, and it has a higher classifying performance compared to the logistic regression model.

Adult↗

Preoperative risk factors of intraoperative hypothermia in major surgery under general anesthesia.

UNLABELLED: Preoperative factors, such as age and body habitus, affect intraoperative hypothermia during general anesthesia. In a preliminary study, we developed a logistic model to retrospectively evaluate predictors of intraoperative hypothermia in patients who received major surgery. The following factors were selected to develop the model: Z = -15.014 + 0.097 x (Age) + 0.263 x (Height) - 0.323 x (Weight) - 0.055 x (Preoperative systolic blood pressure) - 0.121 x (Preoperative heart rate). By using this model, the probability of hypothermia can be estimated by applying the following formula: Probability = 1/(1 + e(-)(Z)). If an estimated probability of hypothermia was >0.5, the sensibility of prediction was 81.5% and the specificity was 83%. In the second study, the model was applied prospectively to other patients, and the validity of the logistic model was evaluated. The core temperature showed a significant decrease in patients with a probability >0.7, who were predicted to be hypothermic, and their thermoregulatory vasoconstriction threshold also showed a significant decrease, compared with the patients with a probability <==0.3, who were predicted to be normothermic. We concluded that intraoperative hypothermia could be predicted from preoperative characteristics such as age, height, weight, systolic blood pressure, and heart rate. IMPLICATIONS: Increases in age and height and decreases in weight systolic blood pressure and heart rate are major preoperative risk factors of intraoperative hypothermia during major surgery.

Aged↗

Predicting the probability of abortion in dairy cows: a hierarchical Bayesian logistic-survival model using sequential pregnancy data.

Although abortion contributes substantially to poor reproductive health of dairy herds, little is known about the predictability of abortion based on age, previous abortion or gravidity (number of previous pregnancies). A poor understanding of effects of maternal factors on abortion risk exists, in part, because of methodological difficulties related to non-independence of multiple pregnancies of the same cow in analysis of fetal survival data. We prospectively examined sequential pregnancies to investigate relationships between fetal survival and putative dam risk factors for 2991 abortions from 24,706 pregnancies of 13,145 cows in nine California dairy herds. Relative risks and predicted probabilities of abortion (PPA) were estimated using a previously described hierarchical Bayesian logistic-survival model generalized to incorporate longitudinal data of multiple pregnancies from a single cow. The PPA increased with increasing dam age at conception, with increasing number of previous abortions, and if the previous pregnancy was aborted >60 days in gestation. The PPA decreased with increasing gravidity and with increasing number of days open. For cows that aborted, the median time to fetal death decreased slightly as gravidity increased. The study considers several methodological issues faced in epidemiologic investigations of fetal health, including multi-modal hazard functions, extensive censoring and non-independence of multiple pregnancies. The model improves our ability to predict bovine abortion and to characterize fetal survival, which have important applications to herd health management.

Abortion, Veterinary↗

Predictors of psychiatric disorders in liver transplantation candidates: logistic regression models.

This study has two goals. The first goal is to assess the prevalence of psychiatric disorders in orthotopic liver transplantation (OLT) candidates by means of standardized procedures because there has been little research concerning psychiatric problems of potential OLT candidates using standardized instruments. The second goal focuses on identifying predictors of these psychiatric disorders. One hundred sixty-five elective OLT candidates were assessed by our unit. Psychiatric diagnoses were based on the Structured Clinical Interview for the Diagnostic and Statistical Manual of Mental Disorders, Fourth Edition. Patients also were assessed using the Hamilton Depression Rating Scale (HDRS) and the Spielberger Anxiety Index, State and Trait forms (STAI-X1 and STAI-X2). Severity of cirrhosis was assessed by applying Child-Pugh score criteria. Chi-squared and general linear model analysis of variance were used to test the univariate association between patient characteristics and both clinical psychiatric diagnoses and severity of psychiatric diseases. Variables with P less than.10 in univariate analyses were included in multiple regression models. Forty-three percent of patients presented at least one psychiatric diagnosis. Child-Pugh score and previous psychiatric diagnoses were independent significant predictors of depressive disorders. Severity of psychiatric symptoms measured by psychometric scales (HDRS, STAI-X1, and STAI-X2) was associated with Child-Pugh score in the multiple regression model. Our data suggest a high rate of psychiatric disorders, particularly adjustment disorders, in our sample of OLT candidates. Severity of liver disease emerges as the most important variable in predicting severity of psychiatric disorders in these patients.

Adult↗

Investigations using logistic regression models on the effect of the LMA on morphine induced vomiting after tonsillectomy.

The effect of intraoperative airway management on postoperative vomiting after tonsillectomy is unknown. Logistic regression was used in a retrospective study to investigate the effect of the laryngeal mask airway (LMA) on a morphine dose-vomiting response curve. Charts were reviewed in 351 children in whom the airway was managed with either a LMA (n=177) or a tracheal tube (n=174). A mean perioperative morphine dose of 0.10 mg.kg(-1) (SD 0.09) was used in 248 children and a further 103 children were given no opioid. One hundred and eighteen of these 248 children vomited (47.6%) compared to 14 of 103 children given no morphine (13.6%). The probability of vomiting was related to morphine dose using logistic regression with both a linear and an E(max) model. Both the calibration (Hosmer-Lemishow goodness of fit chi-squared test lambda(2), P=0.81) and discrimination (area under the receiver operating characteristic plot, AUC ROC=0.67) of the E(max) model were better than the linear model (lambda(2), P=0.49; AUC ROC=0.64). Pharmacodynamic parameter estimates for the Emax model were P(0) (the baseline probability of vomiting) 0.139, P(max) (the maximal probability of vomiting due to morphine) 0.96, ED(50) (morphine dose that induces an effect equivalent to 50% of the logit P(max)) 0.09 mg.kg-1. The probability of vomiting was 50% after morphine 0.125 mg.kg-1. The use of the LMA had no effect on this dose-response curve. A covariate analysis investigating propofol for induction or isoflurane for the intraoperative maintenance of anaesthesia, however, showed that both drugs shifted the curve to the right. The probability of vomiting was 50% after morphine 0.17 mg.kg(-1) and 0.21 mg.kg(-1) for the isoflurane and propofol use curves, respectively. The concomitant use of propofol and isoflurane, but not the use of the LMA, decreases the probability of vomiting due to morphine.

Adolescent↗

A program for logistic prediction modelling.

A computer program has been developed that can be used for analysing a binary outcome variable and a set of regressors of type interval with a logistic (i.e. nonlinear) model.

Biometry↗

Is metabolic syndrome a discrete entity in the general population? Evidence from the Caerphilly and Speedwell population studies.

OBJECTIVE: To examine the clinical and epidemiological utility of the concepts of metabolic syndrome and insulin resistance syndrome in two prospective cohort studies of white men. METHODS: Men aged 45-63 years were screened for evidence of ischaemic heart disease (IHD) between 1979 and 1982 and followed up at regular intervals thereafter. Non-fatal coronary events were validated from hospital records and fatal coronary events from death certificates. RESULTS: Analysis of serum insulin concentrations in non-diabetic individuals measured at entry to the study showed no independent contribution to the prediction of subsequent IHD at 10 year follow up. Blood glucose concentrations, however, showed a small independent contribution in the combined cohort in the upper fifth of the distribution. Three different models of metabolic syndrome among non-diabetic individuals were defined based on tertiles, medians, and clusters. The predictive value of each model was assessed using logistic regression before and after adjustment for conventional and metabolic risk factors. After adjustment the odds were non-significant and close to unity. CONCLUSIONS: This study did not detect any complex relation among the five variables defining metabolic syndrome; the excess risk seems to be no greater than can be explained by individual effects of the defining variables in a multiple logistic model.

Blood Glucose↗

Comparison and cross-validation of simple and multiple logistic regression models to predict USMLE step 1 performance.

BACKGROUND: Early identification of students who may have difficulty with the United States Medical Licensing Examination-Step 1 examination is important for medical schools and students. Numerous models that predict Step 1 performance have been identified, but few of these models have been cross-validated. PURPOSE: To cross-validate different prediction models of Step 1 performance. METHODS: The development sample was 686 students from a Midwestern medical school. The cross-validation sample was 147 different students. Logistic regression was used to develop the multiple model and Year 1 grade point average (GPA) and Year 2 Fall GPA were used as the simple models. Receiver Operating Characteristic graphs were used to select optimal cutoffs for each model. Kappa coefficients were used to determine level of agreement, and sensitivity and specificity were used to assess classification accuracy. RESULTS: The Year 1 GPA model had relatively poor agreement with actual Step 1 performance, but the other models evidenced fair agreement. The multiple and Year 1 GPA models demonstrated statistically significant loss of classification accuracy on cross-validation, whereas the Year 2 Fall GPA model did not. CONCLUSIONS: Cross-validation is necessary to determine the generalizability and overall utility of prediction models.

Education, Medical↗

Estimating treatment efficacy over time: a logistic regression model for binary longitudinal outcomes.

This paper presents a case study in longitudinal data analysis where the goal is to estimate the efficacy of a new drug for treatment of a severe chronic constipation. Data consist of long sequences of binary outcomes (relief/no relief) on each of a large number of patients randomized to treatment (low and high dose) or placebo. Data characteristics indicate: (1) the treatment effects vary non-linearly with time; (2) there is substantial heterogeneity across subjects in their responses to treatment; and (3) there is a high proportion of subjects who never experience any relief (the non-responders). To overcome these challenges, we develop a hierarchical model for binary longitudinal data with a mixture distribution on the probability of response to account for the high frequency of non-responders. While the model is specified conditionally on subject-specific latent variables, we also draw inferences on key population-average parameters for the assessment of the treatments' efficacy in a population. In addition we employ a model-checking method to compare the goodness-of-fit for our model against simpler modelling approaches for aggregated counts, such as the zero-inflated Poisson and zero-inflated negative binomial models. We estimate subject-specific and population-average rate ratios of relief for the treatment with respect to the placebo as functions of time (RR(t)), and compare them with the rate ratios estimated from the models for aggregated counts. We find that: (1) the treatment is effective with respect to the placebo with higher efficacy at the beginning of the study; (2) the estimated rate ratios from the models for aggregated counts appear to be similar to the average across time of the population-average rate ratios estimated under our model; and (3) model-checking suggests that the hierarchical and zero-inflated negative binomial model fit the data best. If we are mainly interested to establish the overall efficacy (or safety) of a new drug, it is appropriate to aggregate the longitudinal data over time and analyse the count data by use of standard statistical methods. However, the models for aggregated counts cannot capture time trend of treatment such as the initial treatment benefit or the development of tolerance during the early stage of the treatment which may be important information to physicians to predict the treatment effects for their patients.

Biometry↗

[Interferon treatment of chronic hepatitis C--assessment of predictive factors to the effect of interferon treatment using multivariate analysis with the logistic regression model].

We treated 156 chronic hepatitis C patients with alpha-interferon (IFN) and assessed the response rate and the predictive factors to the effect of IFN treatment. Complete response (CR) rate was 39.1%, and CR with serum HCV-RNA disappearance rate was 29%. CR to IFN treatment was dependent on HCV serotype and serum HCV-RNA. Patients of serotype II and low serum HCV-RNA were effective to IFN treatment.

Adult↗

A comparison of goodness of fit tests for the logistic GEE model.

Generalized estimating equations have become a popular regression method for analysing clustered binary data. Methods to assess the goodness of fit of the fitted models have recently been developed. However, evaluations and comparisons of these methods are limited. We discuss these methods and develop two additional statistics to evaluate goodness of fit. We evaluate the performance of each of the statistics with respect to type I error rates and power in a simulation study. Guidance is provided regarding appropriate use of the statistics under various scenarios.

Biometry↗

Detection of occult metastatic lymph nodes in the neck with gray-scale and power Doppler US.

PURPOSE: To determine the most accurate criterion for predicting malignancy of small cervical lymph nodes with gray-scale ultrasound (GSUS) and power Doppler ultrasound (PDUS). MATERIAL AND METHODS: Findings of 69 pathologically verified cervical nodes (38 benign, 31 malignant) in 57 patients without wide echogenic hilum on GSUS that measured less than 10 mm in minimal axial diameter were prospectively studied. Minimal and maximal axial diameters, ratios of minimal to maximal axial diameters, and presence or absence of calcification or necrosis of the nodes were assessed. On PDUS, vascularity in the node was classified into 4 pattern groups. A logistic model was used to evaluate the significant factors for predicting malignancy. RESULTS: The logistic model revealed that the minimal axial diameter and vascularity patterns were the only significant factors for malignancy. Using the minimal axial diameter, a node larger than 8 mm showed the highest accuracy (73%) with 45% sensitivity and 93% specificity. Of the vascularity patterns, spotted or peripheral pattern had the highest accuracy (80%) with 61% sensitivity and 93% specificity. A combined criterion of the minimal axial diameter larger than 8 mm and spotted or peripheral pattern increased the accuracy to 82% and sensitivity to 77% but specificity decreased to 86%. CONCLUSION: A combined criterion of minimal axial diameter and vascular patterns was most accurate for diagnosing occult metastatic lymph nodes in the neck.

Adult↗

Logistic transmission modeling for the simulated data of GAW10 problem 2.

A recently developed nonparametric method is a generalization of the transmission disequilibrium test across all alleles of a locus. This approach has been applied to Problem 2 of GAW10 and has been extended to explore the combined contribution of neighboring loci for chromosomes 1, 5, and 8. When applied to the chromosome 5 data of the first replicate of the nuclear pedigrees from Problem 2 of GAW10, the data show that four of the 25 loci obtain a probability less than 0.05. However, when combined models composed of each potentially significant marker (p < 0.05) and its nearest neighbors are considered, the combined contributions of G14 and G15 are the most significant (p = 0.007). Consequently, the region near G14 and G15 is identified as the best candidate region in chromosome 5 for linkage to the common disease.

Case-Control Studies↗

Use of a hierarchical logistic regression model to determine the impact of war injuries on clinical pregnancy rates in patients undergoing intracytoplasmic sperm injection.

OBJECTIVE: To determine the effects of war injuries, including spinal cord injuries, poisoning, and other injuries, on clinical pregnancy rates in infertile couples undergoing intracytoplasmic sperm injection (ICSI) and to compare the results with infertile couples who were not victims of the war. DESIGN: Retrospective study. SETTING: A large, national clinic in Tehran, Iran. PATIENT(S): Six hundred sixty-seven couples undergoing ICSI. INTERVENTION(S): Database analysis. MAIN OUTCOME MEASURE(S): Ongoing clinical pregnancy. RESULT(S): War victims with spinal cord injuries and those who had been poisoned had the same pregnancy rates as did infertile couples who were not victims of the war. The predictive model shows that the more embryos that are transferred, the more the chances for clinical pregnancies; in addition, the more cycles a couple undergoes, the fewer are the chances for clinical pregnancy in an additional cycle. Finally, younger females have more chances for clinical pregnancy than do older ones. CONCLUSION(S): Intracytoplasmic sperm injection is an appropriate option for the treatment of infertile war victim couples, especially for couples suffering from spinal cord injuries and poisoning.

Adult↗

Hospice usage by minorities in the last year of life: results from the National Mortality Followback Survey.

OBJECTIVES: To examine racial/ethnic variations in rates of hospice use in a national cohort and to identify individual characteristics associated with hospice use. DESIGN: Secondary analysis of the 1993 National Mortality Followback Survey (NMFS), a nationally obtained sample using death certificates and interviews with relatives (proxy respondents) to provide mortality, social, and economic data and information about healthcare utilization in the last year of life for 23,000 deceased individuals. SETTING: Hospice care. PARTICIPANTS: Individuals aged 15 and older who died in 1993. Subjects were included in this analysis if they died of nontraumatic causes (N = 11,291). MEASUREMENTS: Hospice use was dichotomized by proxy responses indicating use or nonuse of home or inpatient hospice services. The percentage of individuals using hospice services in the last year of life was calculated. RESULTS: Unadjusted bivariate results found that African Americans were less likely to use hospice than whites (odds ratio (OR) = 0.59; P <.001) and that those without a living will (LW) (OR = 0.23; P <.001) and without a cancer diagnosis (OR = 0.28; P <.001) were less likely to use hospice. The negative relationship between African Americans and hospice use was unaffected when controlled for sex, education, marital status, existence of a LW, income, and access to health care. Logistic models revealed that presence of a LW diminished the negative relationship between African Americans and hospice use, but the latter remained significant (OR = 0.83; P =.033). A subanalysis of subjects aged 55 and older showed a significant interaction between access to care and race/ethnicity with respect to hospice use (P =.044). Inclusion of income in this multivariable logistic model attenuated the relationship between African-American race/ethnicity and hospice use (OR = 0.77), and the difference between whites and African Americans became only marginally statistically significant (P =.060). CONCLUSION: In the 1993 NMFS, hospice use was negatively associated with African-American race/ethnicity independent of income and access to healthcare. The relationship is not independent of age, insurance type, or history of stroke. For subjects aged 55 and older, access to healthcare may be an important confounder of the negative relationship between African-American race/ethnicity and hospice use. Consistent with previous studies, this analysis found that African Americans were less likely to use LWs than whites. The reduced importance of African-American race/ethnicity on hospice use with the inclusion of presence of a LW in logistic models suggests that similar cultural processes may shape differences between African Americans and whites in advance care planning and hospice use.

Adolescent↗

Independent predictors of recurrence of chronic subdural hematoma: results of multivariate analysis performed using a logistic regression model.

OBJECT: The authors attempted to determine independent predictors that contribute to the recurrence of chronic subdural hematoma (CSDH). METHODS: A total of 105 consecutive patients who underwent surgery for CSDH were included in this study. Eleven patients underwent a repeated operation because the CSDH recurred. Univariate and multivariate analyses were performed to assess the relationships among various variables and CSDH recurrence. Finally, four variables were found to be independently associated with the recurrence of CSDH: 1) absence of a multiplicity of hematoma cavities on CT scans; 2) presence of a history of seizure; 3) width of the hematoma; and 4) absence of a history of diabetes mellitus (DM). CONCLUSIONS: As previously reported, the width of the hematoma is related to the incidence of CSDH recurrence. In this study, the lack of a multiplicity of hematoma cavities was the favorite predictor of CSDH recurrence. In addition, histories of seizure and no past DM are closely related to the incidence of CSDH recurrence.

Adult↗

Iron stores and coronary artery disease: a clinical application of a method to incorporate measurement error of the exposure in a logistic regression model.

Rates of coronary artery disease (CAD) increase sharply after menopause. We examined the hypotheses that high iron stores, as measured by plasma ferritin levels, are a risk factor for CAD and that the increase in iron stores after menopause is at least in part responsible for the rise in CAD in women. We also investigated measurement error of plasma ferritin using a Bayesian conditional independence model and incorporated it into the estimation of the odds ratio (OR) for males. Cases had >/=1 coronary artery stenosis >/=70%. Controls had no visible coronary lesions on angiography. The median plasma ferritin level was 48 mg/L (interquartile range: 28 to 86) among 244 cases and 45 mg/l (24 to 85) among 140 controls. The multivariate analyses among females, males, and females and males combined did not support an association between plasma ferritin levels and CAD (OR for one unit change in log ferritin 1.01, 95% CI 0.71-1.44, OR 0.95, 95% CI 0.66-1.37 and OR 0.95, 95% CI 0.75-1.21, respectively). Accounting for the measurement error of ferritin in males slightly improved the precision of the estimate of the OR but did not unmask an association (OR: 0.94, 95% CI 0.69-1.30). We conclude that high ferritin levels before or after menopause are not associated with CAD. Measurement error might be considered in situations where a one-time measurement is assumed to be representative of long-term exposure.

Aged↗