PubMed Health⌕ Search

SEARCH · PubMed Health

Results for “Prediction model”

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 55 records · Page 3Linked to original sources
PubMed2006

Thermodynamic modeling of activity coefficient and prediction of solubility: Part 1. Predictive models.

A new activity coefficient model was developed from excess Gibbs free energy in the form G(ex) = cA(a) x(1)(b)...x(n)(b). The constants of the proposed model were considered to be function of solute and solvent dielectric constants, Hildebrand solubility parameters and specific volumes of solute and solvent molecules. The proposed model obeys the Gibbs-Duhem condition for activity coefficient models. To generalize the model and make it as a purely predictive model without any adjustable parameters, its constants were found using the experimental activity coefficient and physical properties of 20 vapor-liquid systems. The predictive capability of the proposed model was tested by calculating the activity coefficients of 41 binary vapor-liquid equilibrium systems and showed good agreement with the experimental data in comparison with two other predictive models, the UNIFAC and Hildebrand models. The only data used for the prediction of activity coefficients, were dielectric constants, Hildebrand solubility parameters, and specific volumes of the solute and solvent molecules. Furthermore, the proposed model was used to predict the activity coefficient of an organic compound, stearic acid, whose physical properties were available in methanol and 2-butanone. The predicted activity coefficient along with the thermal properties of the stearic acid were used to calculate the solubility of stearic acid in these two solvents and resulted in a better agreement with the experimental data compared to the UNIFAC and Hildebrand predictive models.

Butanones↗
PubMed2002

An independently derived and validated predictive model for selecting patients with myocardial infarction who are likely to benefit from tissue plasminogen activator compared with streptokinase.

BACKGROUND: In the Global Utilization of Streptokinase and tPA for Occluded coronary arteries (GUSTO) trial, patients with myocardial infarction who were treated with tissue plasminogen activator (tPA) had a 6.3% 30-day mortality, compared with a mortality of 7.3% among those treated with streptokinase, despite a greater risk of intracranial hemorrhage with tPA. However, in part because of its higher cost, tPA has not been adopted universally. METHODS: Using an independently developed model, we predicted the benefits of tPA therapy in the 24,146 patients in the GUSTO trial and compared these predictions with the actual benefits of tPA, after classifying patients by their risks of mortality and intracranial hemorrhage. We also performed a "patient-specific" cost-effectiveness analysis among different strata of expected benefit of tPA. RESULTS: Our model predicted that among patients with myocardial infarction, 61% of the benefit of tPA use in reducing mortality accrued to only 25% of patients; treating half of patients could capture 85% of the benefit. Including the risk of intracranial hemorrhage, our model predicted that treating half the GUSTO patients with tPA and the others with streptokinase would yield similar outcomes as treating all patients with tPA, because the additional risk of intracranial hemorrhage exceeded the expected benefit in some patients. When patients were stratified into quartiles of risk, the observed outcomes in the GUSTO patients corresponded well with these predicted results. The estimated cost-effectiveness of tPA was sensitive to patient characteristics. CONCLUSION: For selected patients, use of tPA yields substantially better outcomes than streptokinase, and use of the less expensive agent is difficult to justify. For many patients, however, tPA is unlikely to provide any additional benefit and, in some patients, it may even cause net harm.

Adult↗
PubMed2005

The accuracy of outcome prediction models for childhood-onset epilepsy.

PURPOSE: Two large prospective cohort studies of childhood epilepsy (Nova Scotia and the Netherlands) each developed a statistical model to predict long-term outcome. We sought to evaluate the accuracy of a prognostic model based on the two studies combined. METHODS: Analyses with classification tree models and stepwise logistic regression produced predictive models for the combined dataset and the two separate cohorts. The resulting models were then externally validated on the opposite cohort. Remission was defined as no longer receiving daily medication for any length of time at the end of follow-up. RESULTS: The combined cohorts yielded 1,055 evaluable patients. At the end of follow-up (>or=5 years in >96%), 622 (59%) were in remission. By using the combined data, the classification tree model and the logistic regression model predicted the outcome correctly in approximately 70%. The classification tree model split the data on epilepsy type and age at first seizure. Predictors in the logistic regression model were: seizure number before treatment, age at first seizure, absence seizures, epilepsy types of symptomatic generalized and symptomatic partial, preexisting neurologic signs, intelligence, and the combination of febrile seizures and cryptogenic partial epilepsy. When the prediction models from each cohort were cross-validated on the opposite cohort, the outcome was predicted slightly less accurately than did the model from the combined data. CONCLUSIONS: Based on currently available clinical and EEG variables, predicting the outcome of childhood epilepsy may be difficult and appears to be incorrect in about one of every three patients.

Age of Onset↗
PubMed1993

Predictive modelling of hydroxyapatite-polyethylene composite.

A predictive model for hydroxyapatite-reinforced polyethylene composite has been developed using the finite element analysis method. The simulation is based on the analysis of a representative cell. Results for the complete material can be derived using a spatial statistical material model. Predicted values of Young's modulus are found to be in reasonable agreement with experimentally measured values over a wide range of hydroxyapatite volume fraction. The predictive model can be used to investigate the micromechanical behaviour of the material. This investigation leads to significant elucidation of the failure processes for this material.

Biocompatible Materials↗
PubMed2006

Prediction models for insulin resistance in girls with premature adrenarche. The premature adrenarche insulin resistance score: PAIR score.

AIM: The purpose of this study was to develop an accurate regression model to predict insulin resistance in girls with premature adrenarche. METHODS: The insulin sensitivity index was calculated from the frequently sampled intravenous glucose tolerance test with tolbutamide. Thirty-five prepubertal girls (23 Caribbean-Hispanic and 12 African-American; mean age 6.8 years) were studied. The insulin sensitivity index was compared to birth weight, body mass index (BMI), the presence of acanthosis nigricans (AN), insulin-like growth factor 1, insulin-like growth factor binding protein 1, sex hormone binding globulin, lipid profile, and adrenocorticotropic hormone stimulated androgens. RESULTS: The best prediction models included birth weight, BMI, and AN (model 1: R(2) = 0.78) and BMI, AN, and serum 17-OH pregnenolone (model 2: R(2) = 0.76). When viewed as screening tests, a cutoff value <5.5 (premature adrenarche insulin resistance score) in both equations showed a sensitivity of 100% and a specificity of 85%. CONCLUSION: Born small for gestational age, premature adrenarche, obesity, AN, and higher serum 17-OH pregnenolone levels may confer negative, but independent, health risks.

Acanthosis Nigricans↗
PubMed2003

Predictive model for the combined effect of temperature, sodium lactate, and sodium diacetate on the heat resistance of Listeria monocytogenes in beef.

The effects of heating temperature (60 to 73.9 degrees C), sodium lactate (NaL; 0.0 to 4.8% [wt/wt]), and/or sodium diacetate (SDA; 0.0 to 0.25% [wt/wt]) and of the interactions of these factors on the heat resistance of a five-strain mixture of Listeria monocytogenes in 75% lean ground beef were examined. Thermal death times for L. monocytogenes in filtered stomacher bags in a circulating water bath were determined. The recovery medium was tryptic soy agar supplemented with 0.6% yeast extract and 1% sodium pyruvate. Decimal reduction times (D-values) were calculated by fitting a survival model to the data with a curve-fitting program. The D-values were analyzed by second-order response surface regression for temperature, NaL level, and SDA level. The D-values observed for beef with no NaL or SDA at 60, 65, 71.1, and 73.9 degrees C were 4.67, 0.72, 0.17, and 0.04 min, respectively. The addition of 4.8% NaL to beef increased heat resistance at all temperatures, with D-values ranging from 14.3 min at 60 degrees C to 0.13 min at 73.9 degrees C. Sodium diacetate interacted with NaL, thereby reducing the protective effect of NaL and rendering L. monocytogenes in beef less resistant to heat. A mathematical model describing the combined effect of temperature, NaL level, and SDA level on the thermal inactivation of L. monocytogenes was developed. This model can predict D-values for any combination of temperature, NaL level, and SDA level that is within the range of those tested. This predictive model will have substantial practical importance to processors of cooked meat, allowing them to vary their thermal treatments of ready-to-eat meat products in a safe manner.

Animals↗
PubMed2002

Using Monte Carlo techniques to judge model prediction accuracy: validation of the pesticide root zone model 3.12.

Individuals from the Federal Insecticide, Fungicide, and Rodenticide Act (FIFRA) Environmental Model Validation Task Force (FEMVTF) Statistics Committee periodically met to discuss the mechanism for conducting an uncertainty analysis of Version 3.12 of the pesticide root zone model (PRZM 3.12) and to identify those model input parameters that most contribute to model prediction error. This activity was part of a larger project evaluating PRZM 3.12. The goal of the uncertainty analysis was to compare site-specific model predictions and field measurements using the variability in each as a basis of comparison. Monte Carlo analysis was used as an integral tool for judging the model's ability to predict accurately. The model was judged on how well it predicts measured values, taking into account the uncertainty in the model predictions. Monte Carlo analysis provides the tool for inferring model prediction uncertainty. We argue that this is a fairer test of the model than a simple one-to-one comparison between predictions and measurements. Because models are known to be imperfect predictors prior to running the model, the inaccuracy in model predictions should be considered when models are judged for their predictive ability. Otherwise, complex models can easily fail a validation test. Few complex models, such as PRZM 3.12, would pass a typical model validation exercise. This paper describes the approaches to the validation of PRZM 3.12 used by the committee and discusses issues in sampling distribution selection and appropriate statistics for interpreting the model validation results.

Forecasting↗
PubMed1993

Predictive model for impaction of lower third molars.

The study was carried out to create and test a model for predicting impaction of lower third molars on the basis of radiographic findings at age 20 years. Fifty-six initially unerupted lower third molars were followed up for 6 years. Five radiographic findings in panoramic tomograms at age 20 were taken as variables. Clinical status at age 26 was taken as response. The radiographic features studied were angulation of tooth, development of root, state of impaction, depth in bone, and relation of the tooth to the ramus of the mandible and the second molar. With the use of logistic regression, univariate and bivariate analyses, and clustering techniques, a decision tree was constructed that indicated accuracies of prediction on the basis of single variables or pairs of variables. The most important predictor was the type of impaction. The model predictions and test teeth findings were in agreement in 94% of instances. It was concluded that the model is suitable for predicting lower third molar impaction at age 20.

Adult↗
PubMed2003

Performance of a glucose fed periodic anaerobic baffled reactor under increasing organic loading conditions: 2. Model prediction.

A model was developed for the anaerobic digestion of a glucose-based medium in an innovative high-rate reactor, the periodic anaerobic baffled reactor (PABR). The model considers each PABR compartment as two variable volume interacting sections, of constant total volume, one with high solids and one with low solids concentration, with the gas and liquid flows influencing the material flows between the two sections. For the simulation of glucose degradation, the biomass was divided into acidogenic, acetogenic and methanogenic groups of microorganisms. The kinetic part of the model accounted for possible inhibition of acidogenesis, acetogenesis and methanogenesis by volatile fatty acids. The model succeeded in predicting the reactor performance upon step increases in the organic loading rate.

Bioreactors↗
PubMed1994

Evaluation of muscle force prediction models of the lumbar trunk using surface electromyography.

Optimization-based models for prediction of muscle forces in the lumbar region of the torso are used to estimate the forces acting on spinal motion segments, especially for asymmetric tasks. The objectives of this study were to determine (a) which of four torso model formulations best predicted the electromyographic data, (b) the difference in muscular contribution to spinal compression force for the four models, and (c) the effect of using the lowest possible muscle stress bound in the model formulation. An approach for the investigation of competing optimization model formulations was developed and was illustrated with electromyographic data from static asymmetric loading conditions. This method is based on (a) the choice of experimental conditions in which models predict decidedly different muscle forces, and (b) the ability to ensure that the experimental conditions are such that the minimum number of assumptions about the force-electromyogram relationship must be made in order to choose between competing model predictions. Of the four models analyzed, only the formulation with an objective function that was the sum of cubed muscle stresses predicted the electromyographic data acceptably. The muscular contribution to spinal compression force predicted by these models differed by as much as 160% for some experimental conditions. The use of the lowest possible muscle stress bound does not appear to predict muscle forces that are in agreement with electromyographic data.

Adult↗
PubMed2006

Early prediction of mortality in isolated head injury patients: a new predictive model.

BACKGROUND: To construct a predictive model of survival in isolated head injury patients, on the basis of easily available parameters that are independent risk factors for survival outcome. METHODS: Trauma registry-based study of head injury patients who had no other major extracranial injuries and were not hypotensive at admission. A predictive model of probability of death was constructed using discriminant analysis, on the basis of admission Glasgow Coma Scale (GCS) score, head Abbreviated Injury Score (AIS), age, and mechanism of injury. RESULTS: The study included 7,191 patients with head trauma. The overall correct classification rate of the proposed predictive model was 94.2% as compared with 89.0% of the admission GCS score (p < 0.05) and 92.8% of the head AIS (p < 0.05). The correct classification rate of the predictive model developed for the severe head trauma (GCS score 4-8) patients was 79.9%, as compared with 72.6% using the admission GCS score alone or 75.1% (p < 0.05). A one-page, easy to use table summarizing the predicted mortality on the basis of GCS score, head AIS, mechanism of injury, and age was developed. CONCLUSIONS: The proposed model has a significantly better predictive power, especially in severe head trauma, than the extensively used GCS and head AIS. A simple table on the probability of death of a particular patient based on admission GCS score, head AIS, mechanism of injury and age of patient can provide instant information.

Abbreviated Injury Scale↗
PubMed2026

Enterocutaneous Fistula-Associated Sepsis and Mortality: Development and Validation of a Multimodal Artificial Intelligence Prediction Model.

BACKGROUND: Predicting enterocutaneous fistula (ECF)-associated sepsis and mortality poses significant challenges in digital health care due to the disease's complexity and heterogeneous clinical manifestations. Current approaches that rely on single-modal data or traditional scoring systems often fail to capture the intricate immune-inflammatory dynamics and multisystem involvement in patients with ECF. OBJECTIVE: This study aims to develop an artificial intelligence (AI)-driven multimodal fusion model integrating clinical, imaging, and transcriptomic data for early prediction of ECF-associated sepsis and 28-day mortality, addressing the limitations of conventional single-dimensional models. METHODS: This study leveraged publicly available datasets (Medical Information Mart for Intensive Care III [MIMIC-III], electronic Intensive Care Unit [eICU], and The Cancer Genome Atlas) to construct a multimodal framework. Clinical parameters were processed using Extreme Gradient Boosting, abdominal imaging features were extracted via convolutional neural networks, and transcriptomic profiles were analyzed with variational autoencoders. A Transformer-based fusion network was employed for joint prediction and validated through cross-validation and external testing. Key features were identified using Shapley Additive Explanations and Local Interpretable Model-Agnostic Explanations interpretability algorithms, while immune regulatory mechanisms were explored via weighted gene co-expression network analysis. RESULTS: The multimodal model achieved an area under the curve (AUC) of 0.89 for predicting sepsis and 28-day mortality, outperforming unimodal models (clinical-only model, AUC 0.72, and imaging-only model, AUC 0.78). Critical predictors included Sequential Organ Failure Assessment score, lactate levels, intra-abdominal free fluid on imaging, and immunoregulatory genes (programmed death-ligand 1 [PD-L1] and indoleamine 2,3-dioxygenase 1 [IDO1]). Mechanistic analysis revealed distinct immune reprogramming in patients with sepsis, characterized by increased regulatory T cells and M2 macrophages, along with downregulated cluster of differentiation 8+ (CD8+) T cells. CONCLUSIONS: This multimodal AI model offers an innovative digital solution in medical informatics, enabling precise early risk stratification for ECF-associated sepsis. By integrating multisource data and providing interpretable insights into immune-inflammatory pathways, the model enhances health care quality for patients with ECF and paves the way for personalized intervention strategies.

Humans↗
PubMed2001

Feature mining and predictive model construction from severe trauma patient's data.

In management of severe trauma patients, trauma surgeons need to decide which patients are eligible for damage control. Such decision may be supported by utilizing models that predict the patient's outcome. The study described in this paper investigates the possibility to construct patient outcome prediction models from retrospective patient's data at the end of initial damage control surgery by using feature mining and machine learning techniques. As the data used comprises rather excessive number of features, special attention was paid to the problem of selecting only the most relevant features. We show that a small subset of features may carry enough information to construct reasonably accurate prognostic models. Furthermore, the techniques used in our study identified two factors, namely the pH value when admitted to ICU and the worst partial active thromboplastin time, to be of highest importance for prediction. This finding is pathophysiologically reasonable and represents two of three major problems with severe trauma patients, metabolic acidosis, hypothermia, and coagulopathy.

Algorithms↗
PubMed2004

Conversion rates in laparoscopic colorectal surgery: a predictive model with, 1253 patients.

BACKGROUND: This study aimed all develop a mathematical model for predicting the conversion rate for patients undergoing laparoscopic colorectal surgery. METHOD: This descriptive single-center study used routinely collected clinical data from 1,253 patients undergoing laparoscopic surgery between November 1991 and April 2003. A two-level hierarchical regression model was used to identify patient, surgeon, and procedure-related factors associated with conversion of laparoscopic to open surgery. The model was internally validated and tested using measures of discrimination and calibration. Exclusion criteria for laparoscopic colectomy included a body mass greater than 50, lesion diameter exceeding 15 cm, and multiple prior major laparotomies (exclusive of appendectomy, hysterectomy, and cholecystectomy). RESULTS: The average conversion rate for the study population was 10.0% (95% confidence interval [CI], 8.3-11.7%). The independent predictors of conversion of laparoscopic to open surgery were the body mass index (odds ratio [OR], 2.1 per 10 Americans Society of Anesthesiology units increase), (ASA) grade 3 or 4, 1 or 2 (OR, 3.2, 5.8), type of resection (low rectal, left colorectal, right colonic vs small/other bowel procedures; OR, 8.82, 4.76, 2.98), presence of intraoperative abscess (OR, 3.60) or fistula (OR, 4.73), and surgeon seniority (junior vs senior staff OR, 1.56). The model offered adequate discrimination (area under receiver operator characteristic curve, 0.74) and excellent agreement (p = 0.384) between observed and model-predicted conversion rates (range of calibration, 3-32% conversion rate). CONCLUSIONS: Laparoscopic conversion rates are dependent on a multitude of factors that require appropriate adjustment for case mix before comparisons are made between or within centers. The Cleveland Clinic Foundation (CCF) laparoscopic conversion rate model is a simple additive score that can be used in everyday practice to evaluate outcomes for laparoscopic colorectal surgery.

Adolescent↗
PubMed1996

Indices for performance evaluation of predictive models in food microbiology.

Two complementary measures are proposed as simple indices of the performance of models in predictive food microbiology. The indices assess the level of confidence one can have in the predictions of the model and whether the model displays any bias which could lead to 'fail-dangerous' predictions. The use of the indices is demonstrated using data collated from independent and published literature. This analysis supports previous reports that evaluation of predictive models by comparison to published microbial growth rate data may be inappropriate because of limitations in that data. The indices may fail to reveal some forms of systematic deviation between observed and predicted behaviour. It is concluded, however, that the indices provide an objective and readily interpreted summary of model performance and may serve as a first step towards the development of an objective and useful definition of the term 'validated model' in predictive food microbiology.

Evaluation Studies as Topic↗
PubMed2002

Predictive models and the effectiveness of strategies for improving outpatient follow-up under managed care.

OBJECTIVES: This study tested the accuracy of models for predicting rehospitalization in a managed behavioral health organization and tested the effectiveness of different care management strategies for enhancing outpatient treatment follow-up. METHODS: In a controlled study, patients with an inpatient mental health or substance use admission received one of three types of care management, distinguished by the level of care managers' involvement in discharge planning and postdischarge outreach: usual (N=31), enhanced (N=94), and intensive (N=74). The groups were compared with each other and with a cohort admitted in the year before the study that received usual care management (N=192) to determine whether differences existed in time to outpatient follow-up, amount of postdischarge care, and rehospitalization at 30, 60, and 180 days. RESULTS: No differences between groups were found. The majority of patients (69 percent) received outpatient care within 30 days of discharge. Prediction models using logistic regression suggested that the number of clinical and sociodemographic risk factors identified by care managers was related to the rate of rehospitalization at 60 and 180 days. Patients authorized to receive intermediate care (partial hospitalization or residential care) and those who failed to attend intermediate care if it was authorized were more likely than other patients to be rehospitalized at 30, 60, and 180 days. CONCLUSIONS: Outpatient follow-up after psychiatric hospitalization did not improve with increasingly intensive discharge planning and outreach. Improvement in prediction of risk of rehospitalization may increase opportunities to provide intensive interventions for difficult-to-engage patients.

Adult↗