SEARCH · PubMed Health

Results for “predictive modelling”

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

PubMed2026

ToxiVerse: chemical bioprofiling, toxicity data sharing and customizable predictive modeling.

MOTIVATION: Chemical toxicity assessment is critical for drug development and environmental safety. Computational models have emerged as a promising alternative to animal testing and now play a significant role in efficiently evaluating new chemicals. To address the urgent need for user-friendly machine learning tools in computational toxicology, we developed ToxiVerse, a public web-based platform. RESULTS: ToxiVerse provides automatic chemical bioprofiling, curated toxicity datasets, and a predictive modeling interface designed for researchers who lack programming expertise. The platform comprises three integrated modules: (i) Bioprofiler, which provides chemical descriptors by combining chemical-bioactivity data from PubChem assays with a machine learning-based data gap-filling procedure; (ii) Database, which hosts ∼50 000 curated chemicals covering diverse toxicity endpoints; and (iii) Cheminformatics, which enables dataset upload, chemical curation, and automatic generation of quantitative structure-activity relationship models for toxicity prediction. AVAILABILITY: The tool is accessible at www.toxiverse.com, and source code is available at https://github.com/zhu-research-group/toxiverse.

Quantitative Structure-Activity Relationship↗

PubMed2025

Genetic mapping and predictive modeling of paralog synthetic lethality.

Paralogs are abundant in the human genome and thought to be a primary source of synthetic lethality, yet the vast paralogome remains largely uncharacterized. A digenic screen of 36,648 paralogous pairs in the human genome revealed that synthetic lethalities were infrequent and varied in penetrance in different tumor backgrounds. We hypothesized that the variable penetrance of synthetic lethalities resulted from complex polygenic interactions with different cellular contexts. A machine learning classifier of a subset of paralog pairs tested across 49 cancer models revealed that endogenous perturbations in related pathways predicted paralog synthetic lethality. Further, predictive modeling of paralog synthetic lethality showed that the strength of synthetic lethal interactions was largely due to the overlap and essentiality of the protein-protein interaction networks shared by the paralog pairs. Collectively, this study tested 36,648 digenic paralog interactions and delineated the key feature classes that underlie the heterogeneity of paralog synthetic lethalities.

Humans↗

PubMed1992

A comparative investigation of hepatic clearance models: predictions of metabolite formation and elimination.

Liver clearance models serve to improve our understanding of the relationships between the physiological determinants and hepatic clearance and predict changes in the disposition of substrates when homeostasis of the organ is perturbed. Their ability to describe metabolism was presently extended to the sequential formation and elimination of primary (M1), secondary (M2), and tertiary (M3) metabolites during a single passage of drug (P) across the liver, under steady state and first-order conditions. The well-stirred model is distinct from other models in that metabolite formation and elimination is independent of enzymic distributions, the number of steps involved in metabolite formation, and the intrinsic clearances of the precursors. This model predicts that the extraction ratio of a formed primary metabolite derived from drug (E[M1, P]) is identical to that for the preformed primary metabolite (E[M1]), and that the extraction ratios of a secondary metabolite derived from drug (E[M2, P]) and primary metabolite (E[M2, M1]) or preformed secondary metabolite (E[M2]) are identical. For the more physiologically acceptable, parallel-tube and dispersion models, metabolite sequential elimination is highly influenced by the intrinsic clearances of the precursors and the enzymic distributions that mediate removal of precursor species and the metabolites. Furthermore, the extent of sequential metabolism recedes as the number of steps involved for metabolite formation increases. These models predict that E[M1, P] less than E[M1], and E[M2, P] less than E[M2, M1] less than E[M2], with the magnitude of the changes being less for the dispersion model than for the parallel-tube model. Competing pathways that divert substrate from entering the sequential pathway were found to exert only minimal influence on the sequential pathway.

Liver↗

PubMed1991

Mathematical analysis of perifusion data: models predicting elution concentration.

System models are constructed and analyzed for combined convective flow and for dispersion in distorting concentrations of a chemical signal as it passes through a packed column. We derive general analytical solutions for these models. The results have applications to analyses such as in biological experiments involving hormonal stimulation of perifused cells, elution chromatography, adsorption columns, and studies of groundwater flow. The models reveal that the column distorts an incoming signal (such as a change in solute concentration in the flowing liquid) at the inlet. This distortion is greatest at low values of the Peclet number of the flow and is small at larger values. We explore the effects of the approximations inherent in the mathematical models of the system. Specification of the boundary conditions of the problem are shown to be particularly important. With the use of incorrect models, it is possible to obtain accurate interpolations to data obtained from perfusion experiments. However, the parameters derived (in particular the dispersion constant and the peak concentration of a solute concentration pulse) may be considerably in error. This may lead to errors when these parameter estimates are used to predict results in other experimental situations.

Animals↗

PubMed2025

A prediction model for metachronous colorectal cancer: development and validation.

BACKGROUND: Being able to estimate the risk of metachronous disease in a patient with colorectal cancer (CRC) could enable risk-appropriate surveillance. The aim of this study was to develop a risk-prediction model to estimate individual 10-year risk of metachronous disease following a CRC diagnosis. METHODS: A population-based cohort of patients with CRC was recruited soon after diagnosis between 1997 and 2012 from the United States, Canada, and Australia. Cox regression with the least absolute shrinkage and selection operator penalization was used to identify factors that predicted the risk of a new primary CRC diagnosed at least 1 year after the initial CRC diagnosis. Potential predictors included demography, anthropometry, lifestyle factors, comorbidities, personal and family cancer history, medication use, age at diagnosis, and pathological features of the first CRC. Internal validation through bootstrapping was used to evaluate the discrimination and calibration. RESULTS: We included 6085 CRC cases; 138 (2.3%) of these cases were diagnosed with metachronous disease over a median of 12 years (IQR = 5-17 years). Metachronous CRC risk was predicted by body mass index; smoking status; level of physical activity; family history of cancer and synchronous CRC; stage, grade, histological type, and DNA mismatch repair status; and age at diagnosis of the first CRC. The model was valid with a C statistic of 0.65 (95% CI = 0.63 to 0.68) and a calibration slope of 0.873 (SD = 0.087). CONCLUSIONS: Metachronous CRC can be predicted with reasonable accuracy using a prediction model that consists of clinical variables collected as part of routine practice.

Humans↗

PubMed1989

Individual outcome prediction models for intensive care units.

Prognostic criteria based on static analysis of group statistics do not help much in decisions to withhold or withdraw therapy from intensive care unit (ICU) patients too ill to benefit, since they do not provide adequate information on the features that distinguish non-survivors from survivors. A predictive model which uses dynamic analysis of severity scores based on physiological variables is presented here along with the results of tests of the model in 831 ICU patients. 109 patients were correctly predicted to die by the model. Of 722 whose prediction was outcome unknown, 181 died. Thus, the odds for prediction of death among non-survivors were 0.376. Since there were no false predictions of death, the estimated chance of a false prediction was 0.0055.

Bayes Theorem↗

PubMed1992

Structure and parameterization of pharmacokinetic models: their impact on model predictions.

There has been an increasing interest in physiologically based pharmacokinetic (PBPK) models in the area of risk assessment. The use of these models raises two important issues: (1) How good are PBPK models for predicting experimental kinetic data? (2) How is the variability in the model output affected by the number of parameters and the structure of the model? To examine these issues, we compared a five-compartment PBPK model, a three-compartment PBPK model, and nonphysiological compartmental models of benzene pharmacokinetics. Monte Carlo simulations were used to take into account the variability of the parameters. The models were fitted to three sets of experimental data and a hypothetical experiment was simulated with each model to provide a uniform basis for comparison. Two main results are presented: (1) the difference is larger between the predictions of the same model fitted to different data sets than between the predictions of different models fitted to the dame data; and (2) the type of data used to fit the model has a larger effect on the variability of the predictions than the type of model and the number of parameters.

Animals↗

PubMed1991

A predictive model for DNA recognition by the herpes simplex virus protein ICP4.

The herpes simplex virus (HSV) type 1 immediate early protein ICP4 is an essential regulatory enzyme that binds DNA directly in order to stimulate or repress gene expression. The degree of transaction is related to the locations and affinities of the ICP4 binding sites. A number of binding sites have been identified; some sites showed obvious homology to one another, and these were called consensus ICP4 binding sites. Other binding sites did not appear to be related, and these were termed non-consensus sites. We hypothesized, however, that a single model could describe all ICP4 binding sites, given the appropriate characterizations of sites. We performed statistical analyses on a set of ICP4 binding sites and found that the bases important for defining binding were located within a 13 base region. Missing contact analyses on several high-affinity binding sites revealed the same 13 base region as important for critical protein-DNA contacts. From these data we derived the consensus sequence RTCGTCNNYNYSG, where R is purine, Y is pyrimidine, S is C or G, and N is any base. In addition, we found that a better profile for ICP4 binding sites involves use of a matrix of base proportions from the binding site data; sites are analyzed by calculating the Matrix Mean score. We show that this Matrix Mean model could accurately predict the locations of novel ICP4 binding sites. Finally, we analyzed the entire HSV-1 genome for potential ICP4 binding sites and speculate about what these results suggest for the role of ICP4 in viral gene regulation.

Amino Acid Sequence↗

PubMed1991

Effects of cannabidiol in animal models predictive of antipsychotic activity.

The effects of cannabidiol (CBD) were compared to those produced by haloperidol in rats submitted to experimental models predictive of antipsychotic activity. Several doses of CBD (15-480 mg/kg) and haloperidol (0.062-1.0 mg/kg) were tested in each model. First, CBD increased the effective doses 50% (or) ED50 of apomorphine for induction of the sniffing and biting stereotyped behaviors. In addition, both CBD and haloperidol reduced the occurrence of stereotyped biting induced by apomorphine (6.4 mg/kg), increased plasma prolactin levels and produced palpebral ptosis, as compared to control solutions. However, CBD did not induce catalepsy even at the highest doses, in contrast to haloperidol. Such a pharmacological profile is compatible with that of an "atypical" antipsychotic agent, though the mechanism of action is uncertain and may not be identical to that of the dopamine antagonists.

Animals↗

PubMed1987

A predictive model for determining asbestos concentrations for fibers less than five micrometers in length.

The controversy of whether small asbestos fibers are biologically significant has not been resolved. The present standard method for evaluating asbestos fiber concentrations in workroom air excludes fibers less than 5 micron long even though it has been shown that small fiber concentrations dominate in a dust cloud. This research project was conducted to develop a mathematical model whereby one could predict small (less than 5 micron length) asbestos fiber concentration based on the fiber count concentration determined by phase contrast microscope analysis. Dry chrysotile asbestos was aerosolized into a chamber and sampled by membrane filtration. Segments from each filter were analyzed by both the NIOSH technique using phase contrast microscopy (PCM) and scanning electron microscopy (SEM) at 2000 X for fiber concentrations. A linear relationship was found to exist between the natural logarithm of the SEM-determined concentration and the natural logarithm of the PCM-determined concentration (r = 0.852). Using these data, a mathematical model was developed to predict SEM concentrations based on PCM counts. This model may have application in retrospective epidemiological studies for estimating small fiber exposure levels to determine if small fibers play a role in disease production. The greatest utility would be in those retrospective studies where the only exposure information available is based on PCM counts.

Air Pollutants↗

PubMed1991

A comparison of static and dynamic characteristics between rectus eye muscle and linear muscle model predictions.

The characteristics of a muscle model are analyzed using rectus eye muscle parameter values and compared to rectus eye muscle data. The muscle is modeled as a viscoelastic parallel combination connected to a parallel combination of active state tension generator, viscosity element, and length tension elastic element. Each of the elements is linear and their existence is supported with physiological evidence. The static and dynamic properties of the muscle model are compared to rectus eye muscle data. The length-tension characteristics of the model are in good agreement with the data within the operating region of the muscle. With the muscle model incorporated into a lever system to match the isotonic experiment paradigm, simulation results for this linear system yield a nonlinear force-velocity curve. Moreover, the family of force-velocity curves generated with different stimulus rates reported in the literature match the predictions of the model without parametric changes. The results of this paper are important in studies involving the oculomotor plant and oculomotor neural networks. Additionally, these results may be applicable to other muscles.

Isometric Contraction↗

PubMed1990

The development of a model for predicting infants at high risk of sudden infant death syndrome in Tasmania.

A statutory 'Notification of Birth' form, containing obstetric and perinatal information, has been routinely collected for Tasmanian deliveries since 1974. For the period 1980 to 1984, birth notification data was collected for over 99% of Tasmanian deliveries. This data was examined for the 130 cases of sudden infant death syndrome (SIDS) that occurred from 1980 to 1984 and for 610 controls. It was then used to construct an at-birth scoring system to predict infants at higher risk of SIDS in the postneonatal period. A predictive model of the relative risk of SIDS was developed by fitting a binomial/logistic generalised linear model to the binary 1980-1984 case control data with birth variables used as predictors. The final predictive model contained five variables (maternal age, infant sex, birth weight, month of birth and feeding practice) and had a sensitivity of 62% and specificity of 73%. The model was then tested on independent birth cohorts from 1985 and 1986 and found to have a sensitivity of 47% and specificity of 77%. The risk of SIDS in the group of infants classified as high risk was 7.9 per 1000 live births and in the group at low risk it was 2.5 per 1000 live births. In addition, the model predicted 74% of neonatal deaths occurring during these 2 years. This compares well with other predictive models developed elsewhere. The predictive model will be used to identify infants at high risk for SIDS in a prospective cohort study.

Cohort Studies↗

PubMed1990

A predictive model for vapor concentration in a nose-only inhalation chamber.

A unique nose-only inhalation chamber was designed and constructed to deliver uniform concentrations of gas, vapor, and aerosol contaminants to mice. This research investigated the fluid dynamics of a vaporous contaminant in the vertical flow chamber. The vapor was introduced by allowing the liquid phase of the contaminant to evaporate freely into the chamber interior. A contaminant mass transfer model was developed to predict concentrations generated by the system. The mathematical model of the system used clean airflow, liquid surface area, thickness of the stagnant air layer covering the liquid, system pressure, contaminant diffusion coefficient, and contaminant vapor pressure to compute the vapor concentration delivered to exposure ports. The equation was verified by placing various containers of methyl isobutyl ketone in the chamber and determining with a photospectrometer the resulting equilibrium concentrations. Vapor pressure, diffusion coefficient, and system pressure were held constant while airflow, surface area, and stagnant air layer thickness were varied systematically within the chamber. The resulting empirical data points were compared to the curves predicted by the theoretical model. Empirical concentrations fell within 0 to 48% of the theoretical values, showing that the equation can be used to choose values for airflow, surface area, and stagnant air layer thickness that will result in chamber concentrations in close proximity to the target concentration. If an exact concentration is essential, parameters may be individually adjusted to converge on the target concentration.

Animals↗

PubMed1989

A psychosociomedical prediction model of response to treatment by chronically disabled workers with low-back pain.

There has been much interest in identifying variables that can predict which individuals are susceptible to developing chronic low-back pain. There currently are a number of studies that are evaluating primary predictors (which uninjured workers are likely to develop chronic low-back pain) and secondary predictors (which workers with acute episodes will develop chronic pain). The present study reports the first results from a large-scale investigation of tertiary predictors. Specifically, it addresses the issue of what psychosociomedical variables are predictive of success/failure in response to a comprehensive Functional Restoration treatment program by workers who are chronically disabled with low-back pain. Three stages were involved in the development of this prediction model. First, a group of treatment and research professionals who had extensive experience in the area of chronic low-back pain identified an array of 42 variables, from a larger pool of quantified physical, psychosocial, and medical parameters rated to be important with this patient population.(ABSTRACT TRUNCATED AT 250 WORDS)

Adult↗

PubMed1976

A simplified in vitro classification for prognosis in adult acute leukemia: the application of in vitro results in remission-predictive models.

Previous classification in vitro of adult acute leukemia incorporating morphology has been complex and difficult to understand. We have devised a simplified classification based solely on leuekemic proliferation in vitro. Seventy-six patients with adult acute leukemia previously untreated were included in this study and received identical chemotherapy. Three groups were recognized. The complete remission rate was 76% in the 21 patients with no leukemic growth in vitro (Group 1), 75% in 36 patients with leukemic cell growth but aggregates of 20 cells or less (Group 2), and only 21% in the 15 patients with aggregates of greater than 20 (Group 3). There was a highly significant difference in complete remission rates between Group 3 and the other two groups (p less than 0.001). Linear logistic regression analysis demonstrated the independence of the growth in vitro from other prognostic variables. A predictive model utilizing the in vitro result more accurately predicted for remission, both retrospectively and prospectively, than a model constructed with presently known prognostic parameters. The cause of death in failures suggested that this system detects resistance to the chemotherapy.

Acute Disease↗

PubMed1990

The health belief model: predicting compliance and dropout in cardiac rehabilitation.

We investigated the health belief model and the health locus of control constructs as predictors of group membership (compliers or dropouts) with cardiac rehabilitation and whether they added predictive utility to routinely assessed patient demographics and health behaviors. Questionnaires were completed on entry into the study by 120 patients with coronary artery disease, and by the end of the 6 month program there were 58 compliers and 62 dropouts. Discriminant function analyses were carried out to determine prediction of group membership. The health belief model predicted group membership 64.6% of the time, explaining 5.2% of the variance. Demographics, health behaviors, and health belief model factors accounted for 21.1% of the variance between compliers and total dropouts with group membership correctly predicted 74.4% of the time; avoidable and unavoidable dropout was correctly predicted 84.2% of the time with 56.9% of the variance explained. Health locus of control did not distinguish between compliers and dropouts. The addition of the health belief model provided additional information about compliance with cardiac rehabilitation beyond that explained by demographic and health behavior variables alone, particularly when predicting avoidable/unavoidable dropout.

Attitude to Health↗

PubMed1991

Drug resistance-reversal strategies: comparison of experimental data with model predictions.

We previously developed a mathematical model to describe the emergence and dynamic growth of a drug-resistant subpopulation in a tumor. In the present study, our objective was to test the model's ability to mimic two strategies for reversal of drug resistance. We present data from one in vitro cell proliferation assay with drug-resistant LS174T human colon carcinoma variants and one in vivo assay of survival after treatment of female (C57BL/6 x DBA/2)F1 mice inoculated with doxorubicin-resistant P388/ADR leukemia cells. The in vitro assay examined the effects of inhibiting the biosynthesis of glutathione in cells resistant to alkylating agents or cisplatin. The in vivo assay compared the effects on cell survival of low-level continuous infusion versus high-intensity bolus dosing, with or without coadministration of the drug efflux pump blocker verapamil. Results in vitro and in vivo were comparable for qualitative accuracy and predictability to results with the model. Both the in vitro study and the model showed that, for resistant cells with high levels of glutathione, short-term cell survival was dose dependent and that even high doses of drug did not eliminate all of these cells. Addition of an inhibitor of glutathione biosynthesis did, however, augment elimination of the resistant cells. Resistant cells with low levels of glutathione could be eliminated with high drug doses or coadministration of drug and a glutathione synthesis inhibitor. In vivo, coadministration of doxorubicin with verapamil increased animal survival when either continuous infusion or bolus dosing regimens were used. The effectiveness of the blocker is crucial; when a partially (50%) effective blocker is used, continuous infusion achieves better elimination of resistant cells, but a completely (100%) effective blocker is efficacious in both dosing scenarios. Careful interpretation of these findings is necessary because the pharmacokinetics of drug in the small populations of cells in the model are not easily extrapolated to those in large tumors. This model may be useful in determining resistance mechanisms, their levels of effectiveness, and concentrations of compounds required at target sites to overcome them.

Animals↗

PubMed1990

Return to work after stroke: development of a predictive model.

Seventy-nine stroke patients who underwent a vocationally oriented, comprehensive, inpatient stroke rehabilitation program were followed up to evaluate their return to work. At follow-up, 49% had returned to work a mean of 3.1 months after rehabilitation discharge. Factors associated with success and with failure of vocational rehabilitation were then identified, and a predictive model was developed. There were positive associations between return to work and Barthel Index on admission (p = 0.0002) and discharge (p = 0.0015). Negative associations were found between return to work and aphasia (p = 0.0009), rehabilitation length of stay (p less than 0.0001), and prior alcohol consumption (p = 0.03). A step-wise multiple regression model explained 42% of the variance in return to work. Those most likely to return to work were not aphasic; they had shorter rehabilitation lengths of stay and higher Barthel Index scores on discharge; and they were lighter consumers of alcoholic beverages before their strokes. In conclusion, a set of factors predictive of return to work in younger stroke patients was identified, including, most notably, a strong negative association with aphasia and an intriguing negative association with prior alcohol consumption.

Adult↗