PubMed Health⌕ Search

SEARCH · PubMed Health

Results for “Predictive modeling”

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 937 records · Page 52Linked to original sources
PubMed2006

A study of the Gamma hypothesis: predictive modelling of the growth and inhibition of Enterobacter sakazakii.

Although the temperature growth profile of the opportunistic pathogen Enterobacter sakazakii is known, few other environmental factors affecting growth have been analysed. Using a model based on the Gamma hypothesis--that antimicrobial factors in mixtures exert independent effects--a range of weak acids (lactic, acetic, propionic, citric, sorbic and benzoic), pH, salt and temperature and some of their combinations were examined. The weak acids examined inhibited principally with the acid-form of the weak acid, however, benzoic, sorbic and propionic acids also displayed an inhibitory contribution from their respective anionic forms. In all cases pH could be considered an independent inhibiting factor. The minimum pH and maximum salt concentration for growth were calculated to be 3.89 and 9.1% respectively. In combination, there was no suggestion of any interactive effect between them. Studies performed on combinations of Na acetate/pH between 25 and 41 degrees C showed that temperature did not affect the relative inhibitory effects of the weak acid/pH mixtures. The results of this study support the Gamma hypothesis suggesting that there are no synergistic interactions between inhibitory factors and that growth can be predicted from a library of known effects. More importantly to the food industry, the results can be used to design good quality shelf-life challenge tests by reducing the number of studies required.

Acids↗
PubMed2005

[Predictive model for cocaine use in prisons in Rio de Janeiro, Brazil].

OBJECTIVE: To identify predictors of and groups vulnerable to cocaine use in prison. METHODS: We selected 376 inmates with history of cocaine use in prison (cases) and 938 inmates with no history of drug use (controls) serving sentences in the Rio de Janeiro State prison system in 1998. The analysis included exposure variables divided into three hierarchical levels: distal, intermediate, and proximal. We performed bivariate analysis using logistic regression and multivariate analysis using hierarchized regression; results are given in odds ratios. RESULTS: Variables associated with cocaine use in prison in the proximal level were use of alcohol and marijuana and duration of imprisonment in years. The effect of social vulnerability variables (distal level) was intermediated by variables in the next levels. Considering only the distal and intermediate levels, use of marijuana prior to imprisonment (OR=4.50; 95% CI: 3.17-6.41) and offence in order to obtain drugs (OR=2.96; 95% CI: 1.79-4.90) showed the strongest association with the outcome. For every additional year spent in prison, the odds of cocaine use increase by 13% (OR=1.13; 95% CI: 1.06-1.21). CONCLUSIONS: Considering the distal and intermediate levels, use of marijuana prior to imprisonment and perpetration of offence in order to obtain drugs were the variables with greatest predictive value. The final model showed alcohol and marijuana use in prison and duration of imprisonment as important predictors of the outcome. The prison environment appears as a factor stimulating drug use.

Adult↗
PubMedDate not supplied

Expanded health belief model predicts diabetes self-management in college students.

An instrument was designed to determine relationships between constructs of the Expanded Health Belief Model and to identify characteristics of college students who successfully manage their diabetes. The Diabetes College Scale was developed to measure attitudes and behaviors pertinent to diabetes management and college life. It was tested for content validity, test-retest reliability, and internal consistency. Data were collected from college students using a cross-sectional design. Campus health care providers were invited via electronic mail to administer the survey to students with Type I diabetes. Ninety-eight questionnaires were mailed to interested providers, of which 86 (88%) were returned. Mean scores for attitude constructs, seven behaviors, and two outcomes were measured. Twenty-six experts established content validity. Instrument reliability was evaluated using paired t-tests, Cronbach's alpha, and correlation coefficients. Correlation coefficients and stepwise multiple regression analysis evaluated relationships among variables measured. Intention and emotional response were strong predictors of exercise, whereas health importance and intention were predictive of testing blood sugar. Situational factors and emotional response were substantial barriers to optimal diabetes self-care. College health care providers should address these areas in providing services to this population. Additional testing of the instrument is also recommended.

Adolescent↗
PubMed2005

The Gail model predicts breast cancer in women with suspicious radiographic lesions.

BACKGROUND: We sought to evaluate whether a woman's 5-year Gail risk adds to the predictive value of the Breast Imaging Reporting and Data System (BI-RADS) classification for the detection of breast cancer. METHODS: We performed a retrospective review of the BI-RADS classifications and pathology results for all image-guided needle breast biopsy examinations over a 3-year period at our institution. The 5-year Gail risk was calculated for eligible patients. Chi-square analysis was used to compare rates of malignancy based on Gail and BI-RADS scores. RESULTS: A total of 632 image-guided needle biopsy examinations were performed in 609 women. A total of 414 women had suspicious (BI-RADS 4) lesions and underwent 424 biopsy examinations. For this subset, women with a Gail risk of less than 1.7% had 21% malignant results, whereas those with a Gail risk of 1.7% or greater had 42% malignant results (relative risk, 1.94; 95% confidence interval, 1.45-2.66). CONCLUSIONS: The Gail model can stratify further the risk for breast cancer in women with suspicious breast imaging reports.

Adult↗
PubMed2004

Building predictive models for protein tyrosine phosphatase 1B inhibitors based on discriminating structural features by reassembling medicinal chemistry building blocks.

A new approach to predicting the biological activity of small molecule pharmaceutics is demonstrated. Structural features of medicinal chemistry building blocks are used as 2-D molecular descriptors. These descriptors include predefined structural features and macrostructures obtained from a supervised process in which features in the core library are reassembled to provide larger features that strongly differentiate the desired biological response variable. Chemical features derived in this manner can serve as predictor variables for diverse modeling algorithms, and application using partial least squares techniques is demonstrated here. Models are presented for inhibition by benzofuran and benzothiophene biphenyl analogues of protein tyrosine phosphatase 1B (PTP1B), a target for insulin-resistant disease states. Results are compared to models for PTP1B inhibitors available in the literature based on CoMFA-related techniques and 3-D molecular descriptors.

Models, Molecular↗
PubMed2004

Predicting osteoarthritic knee rehabilitation outcome by using a prediction model developed by data mining techniques.

Artificial neural networks (ANN) have been applied to assist in clinical decision-making and prediction. While we consider possible effective treatments for patients with osteoarthritic knee such as Transcutaneous Electrical Nerve Stimulation (TENS), exercise, and TENS with exercise respectively, we have to select a treatment protocol for patients such that they would gain the best improvements according to their clinical conditions. To facilitate this functionality with the existing patient assessment, we hope to apply the ANN programming techniques to develop a computerized prediction system. A preliminary validation was performed to test the validity of the newly developed prediction protocol on knee rehabilitation. We input the key clinical attributes of 62 patients who have undergone the three above-mentioned knee treatments to the protocol. The expected pain improvement of each patient as predicted by the protocol was obtained. Spearman rank-order correlation was used to identify whether there was a significant correlation between the rankings of the observed and expected pain improvement. We found that the Spearman's rho was 0.424, which is statistically significant at p < 0.001. From this preliminary analysis, we are confident that this newly developed prediction protocol will be useful when deciding which treatment regime best suits a patient.

Combined Modality Therapy↗
PubMed2026

Machine learning-based clinical prediction model and multi-omics integration for assessing pancreatic cancer risk in new-onset diabetes.

BACKGROUND: Given that pancreatic cancer (PC) is typically diagnosed at an advanced stage but is often preceded by new-onset diabetes mellitus (NODM), providing a window for early detection, we sought to develop and validate an interpretable machine-learning model integrated with multi-omics profiling to identify early biomarkers of NODM-associated PC. METHODS: In a population-based cohort, individuals with NODM-associated PC and NODM without PC were identified and randomly divided (70:30) into training and validation sets after feature selection. Eight machine learning (ML) classifiers were compared using fivefold cross-validation, and model performance was evaluated in terms of discrimination, calibration, and decision curve&#x2013;based clinical utility. We evaluated interpretability using the Shapley additive explanations (SHAP) analyses. Mechanistically, Olink proteomic profiling and metabolomics were analyzed through clinical classifications and model-defined risk strata. RESULTS: Categorical boosting achieved the best performance in the independent validation set (AUROC&#x2009;=&#x2009;0.844). The NODM cohort was stratified into high- (n&#x2009;=&#x2009;2,362) and low-risk (n&#x2009;=&#x2009;5,030) groups, and internal validation together with SHAP analyses demonstrated consistent model performance and identified clinically interpretable predictors. Proteomic and metabolomic analyses under clinical and risk-based grouping identified 39 overlapping differentially expressed proteins and 145 overlapping metabolites with enriched across 11 shared KEGG pathways. Cross-platform validation highlighted PLTP, CRTAC1, and ITGAV as serum biomarkers with a strong potential for early NODM-PC detection. CONCLUSIONS: We developed an interpretable ML framework centered on NODM enables practical risk stratification for early PC detection by multi-omics and provides a pathway of ML-based triage followed by biomarker confirmation for earlier detection and diagnosis.

Humans↗
PubMed1999

A prediction model for moderate or severe dehydration in children with diarrhoea.

A hospital-based unmatched case-control study (387 cases and 387 controls) was carried out at the Government Medical College Hospital, Nagpur, India, to devise and validate a risk-scoring system for predicting the development of moderate or severe dehydration in children, aged less than five years, with acute watery diarrhoea. On unconditional multiple logistic regression, 12 risk factors--infancy, minority religion, undernutrition, not washing hands by mother before preparation of food, frequency of stools > 8/day, frequency of vomiting > 2/day, measles in previous 6 months, withdrawal of breast-feeding/other feedings, withdrawal of fluids during diarrhoea, not giving oral rehydration solutions (ORS), home available fluids and both during diarrhoea--were significant. Based on regression coefficients, these factors were ascribed statistical weights of 5, 5, 4, 4, 22, 9, 11, 13, 5, 5, 5, and 7 respectively. The receiver-operating characteristic curve suggested a total score of 48 to be the best cut-off for predicting the development of moderate or severe dehydration. At this cut-off, the sensitivity, specificity, positive predictive value, Cohen's kappa, and overall predictive accuracy were 0.81, 0.81, 0.81, 0.61, and 0.86 respectively. If substantiated by further validation, this system can be used for predicting the development of dehydration at the earlier stage, thereby reducing the mortality associated with life-threatening dehydration.

Acute Disease↗
PubMed2000

The Swedish ACCES model: predicting the health economic impact of celecoxib in patients with osteoarthritis or rheumatoid arthritis.

The Arthritis Cost Consequence Evaluation System (ACCES) pharmacoeconomic model was used to evaluate the economic and health impact of the recent introduction of celecoxib for treatment of osteoarthritis (OA) and rheumatoid arthritis (RA) in Sweden. The model demonstrates that use of celecoxib can be expected to reduce the incidence of gastrointestinal adverse events, resource utilization and treatment costs. In a cost-effectiveness analysis, celecoxib demonstrated economic dominance (i.e. improved health at reduced cost) compared with the currently available alternatives for OA, and demonstrated economic dominance against a clinically relevant base-case scenario for RA. In sensitivity analyses, the results were shown to be relatively robust; celecoxib demonstrated economic dominance or favourable cost-effectiveness ratios in all analyses. Based on these data, it can be concluded that the use of celecoxib in Sweden will provide societal benefits by improving health care at reduced cost for patients with OA and RA.

Anti-Inflammatory Agents, Non-Steroidal↗
PubMed2002

Model prediction of treatment planning for dose-fractionated radioimmunotherapy.

BACKGROUND: Clinical trials of radioimmunotherapy (RIT) often use dose fractionation to reduce marrow toxicity. The dosing scheme can be optimized if marrow and tumor cell kinetics following radiation exposure are known. METHODS: A mathematic model of tumor clonogenic cell kinetics was combined with a previously reported marrow cell kinetics model that included marrow stromal cells, progenitor cells, megakaryocytes, and platelets. Reported values for murine tumor and marrow cellular turnover rates and radiosensitivity were used in the model calculation. RESULTS: Given a tolerated level of thrombocytopenia, there is a fractionation scheme in which total radioactive dose administration can be maximized. Isoeffect doses that had different numbers of fractions and total radioactivity, but induced identical platelet nadirs of 20%, were determined. Assuming identical tumor uptake for all dose fractions, six tumor types were examined: early-responding tumors, late-responding tumors, and tumors that lacked a late-responding effect, with either constant or accelerated doubling time. For most tumor types, better tumor control (tumor growth delay and nadir of survival fraction) was predicted for a dosing scheme in which total radioactive dose was maximized. For late-responding tumors with accelerated doubling time, tumor growth delay increased, but the nadir of survival fraction became shallower as the number of fractions increased. CONCLUSIONS: A mathematic model has been developed that allows prediction of the nadir and duration of thrombocytopenia as well as tumor clonogenic cell response to various RIT doses and fractionation schemes. Given a maximum tolerated level of thrombocytopenia, the model can be used to determine a dosing scheme for optimal tumor response.

Abnormalities, Radiation-Induced↗
PubMed2005

Phospho-pivot modeling predicts specific interactions of protein phosphatase-1 with a phospho-inhibitor protein CPI-17.

Phospho-amino acids in proteins are directly associated with phospho-receptor proteins, including protein phosphatases. Here we produced and tested a scheme for docking together interacting phospho-proteins whose monomeric 3D structures were known. The phosphate of calyculin A, an inhibitor for protein phosphatase-1 and 2A (PP1 and PP2A), or phospho-CPI-17, a PP1-specific inhibitor protein, was docked at the active site of PP1. First, a library of 186,624 virtual complexes was generated in silico, by pivoting the phospho-ligand at the phosphorus atom by step every 5 degrees on three rotational axes. These models were then graded for probability according to atomic proximity between two molecules. The predicted structure of PP1 x calyculin A complex fitted to the crystal structure with r.m.s.d. of 0.23 A, providing a validate test of the modeling method. Modeling of PP1 x phospho-CPI-17 complex yielded one converged structure. The segment of CPI-17 around phospho-Thr38 is predicted to fit in the active site of PP1. Positive charges at Arg33/36 of CPI-17 are in close proximity to Glu274 of PP1, where the sequence is unique among Ser/Thr phosphatases. Single mutations of these residues in PP1 reduced the affinity against phospho-CPI-17. Thus, the interface of the PP1 x CPI-17 complex predicted by the phospho-pivot modeling accounts for the specificity of CPI-17 against PP1.

Animals↗
PubMed2004

Quantifying variability in neural responses and its application for the validation of model predictions.

A rate code assumes that a neuron's response is completely characterized by its time-varying mean firing rate. This assumption has successfully described neural responses in many systems. The noise in rate coding neurons can be quantified by the coherence function or the correlation coefficient between the neuron's deterministic time-varying mean rate and noise corrupted single spike trains. Because of the finite data size, the mean rate cannot be known exactly and must be approximated. We introduce novel unbiased estimators for the measures of coherence and correlation which are based on the extrapolation of the signal to noise ratio in the neural response to infinite data size. We then describe the application of these estimates to the validation of the class of stimulus-response models that assume that the mean firing rate captures all the information embedded in the neural response. We explain how these quantifiers can be used to separate response prediction errors that are due to inaccurate model assumptions from errors due to noise inherent in neuronal spike trains.

Action Potentials↗
PubMed2026

CLASPP: A unified model for predicting post-translational modifications.

Post-Translational Modifications (PTMs) are a fundamental mechanism for regulating cellular pathways and increasing the functional diversity of the proteome. Accurately predicting the PTM types that are likely to occur at a given site in the primary sequence is a key challenge in functional proteomics. Existing PTM prediction models predominantly focus on either single PTM types or employ ensemble methods that combine multiple models to predict different PTM types. This fragmentation is largely driven by the vast imbalance in data availability across PTM types, making it difficult to predict multiple PTM types with a single model. To address this limitation, we present the Contrastively Learned Attention-based Stratified PTM Predictor (CLASPP), a unified PTM prediction model. CLASPP addresses imbalance challenges by leveraging unsupervised clustering-based undersampling and a novel contrastive learning framework tailored to PTM data. Additionally, our hierarchical data organization and curation are shown to improve CLASPP's performance by balancing the representation of individual PTM types and provides a standardized dataset to train and validate future model designs. Drawing inspiration from advancements in image and natural language processing, the CLASPP model employs a multi-stage training strategy and a high-quality, curated training dataset to improve PTM prediction performance. To uncover what is learned during the contrastive learning stage, the CLASPP model is shown to distinguish known protein kinase substrate specificity profiles as a form of explainability. Finally, we evaluate the application of CLASPP in predicting PTMs in different model organisms and experimentally validated ubiquitination sites in the understudied DCLK3 kinase. Overall, CLASPP represents a unified model for PTM prediction that addresses key bottlenecks in data imbalance and offers new strategies for biological data curation, thereby improving PTM-type prediction performance across diverse organisms.

Protein Processing, Post-Translational↗
PubMedDate not supplied

Errors between two- and three-dimensional thermal model predictions of hyperthermia treatments.

A simulation program to study the three-dimensional temperature distributions produced by hyperthermia in anatomically realistic inhomogenous tissue models has been developed using the bioheat transfer equation. The anatomical data for the inhomogeneous tissues of the human body are entered on a digitizing tablet from serial computed tomography (CT) scans. Power deposition patterns from various heating modalities must be calculated independently. The program has been used to comparatively evaluate two- and three-dimensional simulations in a series of parametric calculations based on a simple inhomogeneous tissue model for uniform power deposition. The conclusions are that two-dimensional simulations always lead to significant errors at the ends of tumors (up to tens of degrees). However, they can give valid results for the central region of large tumors, but only with tumor blood perfusions greater than approximately 1 kg/m3/s. These conclusions from the geometrically simple model are substantiated by the results obtained using the full three-dimensional model for actual patient anatomical simulations. In summary, three-dimensional simulations will be necessary for accurate patient treatment planning. The effect of the thermal conductivity, used in the models, on the temperature field has also been studied. The results show that using any thermal conductivity value in the range of 0.4 to 0.6 W/m/degrees C sufficiently characterizes most soft tissues, especially in the presence of high blood perfusion. However, bone (thermal conductivity of 1.16 W/m/degrees C) and fat (thermal conductivity of 0.2 W/m/degrees C) do not fit this generalization and significant errors result if soft tissue values are used.

Blood Circulation↗
PubMed2006

Structural correlations and motifs in liquid water at selected temperatures: ab initio and empirical model predictions.

To gain further insight into liquid water's structure and explore the role of different physical forces underlying the interaction between water molecules, the radial and angular structure of water is probed as a function of temperature for a carefully selected set of theoretical models. Simulations are performed with empirical rigid, empirical polarizable, empirical flexible with classical and quantum nuclei, and ab initio models with classical nuclei at 300 and 353 K and quantum nuclei at 300 K. The predicted radial distribution functions, spatial maps, and angular distributions of the neighboring water molecules are consistent with a model of liquid water in which water molecules are tetrahedrally coordinated. In addition, three-dimensional joint distribution functions are introduced and analyzed. By comparison of the functions obtained for hexagonal ice to those of liquid water, several thermally disordered, ice-like cluster structures are identified in the fluid.

Journal Article↗