SEARCH · Search PubMed

Results for “Predictive”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

SourceResearch connectionFrom yearThrough year

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

At least 1,207 records · Page 67Linked to original sources

PubMedDate not supplied

Toward prediction of class II mouse major histocompatibility complex peptide binding affinity: in silico bioinformatic evaluation using partial least squares, a robust multivariate statistical technique.

The accurate identification of T-cell epitopes remains a principal goal of bioinformatics within immunology. As the immunogenicity of peptide epitopes is dependent on their binding to major histocompatibility complex (MHC) molecules, the prediction of binding affinity is a prerequisite to the reliable prediction of epitopes. The iterative self-consistent (ISC) partial-least-squares (PLS)-based additive method is a recently developed bioinformatic approach for predicting class II peptide-MHC binding affinity. The ISC-PLS method overcomes many of the conceptual difficulties inherent in the prediction of class II peptide-MHC affinity, such as the binding of a mixed population of peptide lengths due to the open-ended class II binding site. The method has applications in both the accurate prediction of class II epitopes and the manipulation of affinity for heteroclitic and competitor peptides. The method is applied here to six class II mouse alleles (I-Ab, I-Ad, I-Ak, I-As, I-Ed, and I-Ek) and included peptides up to 25 amino acids in length. A series of regression equations highlighting the quantitative contributions of individual amino acids at each peptide position was established. The initial model for each allele exhibited only moderate predictivity. Once the set of selected peptide subsequences had converged, the final models exhibited a satisfactory predictive power. Convergence was reached between the 4th and 17th iterations, and the leave-one-out cross-validation statistical terms--q2, SEP, and NC--ranged between 0.732 and 0.925, 0.418 and 0.816, and 1 and 6, respectively. The non-cross-validated statistical terms r2 and SEE ranged between 0.98 and 0.995 and 0.089 and 0.180, respectively. The peptides used in this study are available from the AntiJen database (http://www.jenner.ac.uk/AntiJen). The PLS method is available commercially in the SYBYL molecular modeling software package. The resulting models, which can be used for accurate T-cell epitope prediction, will be made freely available online (http://www.jenner.ac.uk/MHCPred).

Animals↗

PubMed2002

Comparison of measured and predicted environmental PCB concentrations using simple compartmental models.

The use of models to represent biological, chemical, and physical processes that govern the fate and transport of environmental contaminants is an enduring feature of risk assessments. Data collection is costly and time-consuming. Measuring future conditions is impossible regardless of the resources available. For these reasons, rarely do analysts have sufficient empirical data for estimating risks in a population of interest across the desired dimensions of space and time. The appropriate level of complexity, detail, and resource investment in a modeling exercise should be established by the intended use of the results generated and by the expected performance of the available modeling options. At one end of the spectrum, the concentration of a contaminant in an environmental medium may be estimated quickly and inexpensively using an intermedia partition coefficient or simple steady state compartmental model. In contrast, a complex dynamic model requiring vast stores of input data, computer power, and run time may be used to estimate concentration. However, because models are generally used when data are scarce or nonexistent, our ability to assess the accuracy and precision of various model options is often limited. The research presented below exploits a relatively unusual opportunity to compare concentration measurements of polychlorinated biphenyls (PCBs) for multiple environmental media with predictions from simple compartmental fate and transport models using two-dimensional Monte Carlo analysis. Simple compartmental models are found to predict measurements quite well overall, although decisions about the treatment of variability and autocorrelation in the airborne load of contaminant with season, weather system, and location influence their performance. The models are assessed at two sites near New Bedford Harbor in Massachusetts, one characterized by higher and more variable contaminant concentrations, while the other is a comparison or "background" site. The difference between model performance in the two locations illustrates some characteristics of situations in which simple models are most appropriate. Under background conditions of relatively low and consistent contaminant levels, a two compartment model generates excellent predictions of the sum of PCB congener concentration in soil based on air concentration. Under more contaminated or more variable conditions, model results are less predictive; however, most fall within an order of magnitude of the data. A comparison of model performance for predicting concentration of the sum of PCB congeners vs for predictions of individual PCB congeners is also pursued. Individual congener concentrations in soil tend to be slightly overpredicted for lighter weight congeners, i.e., those more characteristic of the New Bedford Harbor region, while levels of heavier congeners tend to be underpredicted in circumstances where air concentrations are relatively low. A three compartment model representing air, soil, and plant matter is found to predict levels of PCBs in edible produce within about an order of magnitude of those measured, under the conditions considered. This work demonstrates the relevance and usefulness of results from simple and easily implemented models for fate and transport predictions.

Decision Making↗

PubMed2006

A hybrid mixture discriminant analysis-random forest computational model for the prediction of volume of distribution of drugs in human.

A computational approach is described that can predict the VD(ss) of new compounds in humans, with an accuracy of within 2-fold of the actual value. A dataset of VD values for 384 drugs in humans was used to train a hybrid mixture discriminant analysis-random forest (MDA-RF) model using 31 computed descriptors. Descriptors included terms describing lipophilicity, ionization, molecular volume, and various molecular fragments. For a test set of 23 proprietary compounds not used in model construction, the geometric mean fold-error (GMFE) was 1.78-fold (+/-11.4%). The model was also tested using a leave-class out approach wherein subsets of drugs based on therapeutic class were removed from the training set of 384, the model was recast, and the VD(ss) values for each of the subsets were predicted. GMFE values ranged from 1.46 to 2.94-fold, depending on the subset. Finally, for an additional set of 74 compounds, VD(ss) predictions made using the computational model were compared to predictions made using previously described methods dependent on animal pharmacokinetic data. Computational VD(ss) predictions were, on average, 2.13-fold different from the VD(ss) predictions from animal data. The computational model described can predict human VD(ss) with an accuracy comparable to predictions requiring substantially greater effort and can be applied in place of animal experimentation.

Algorithms↗

PubMed1999

Predicting binding affinities of protein ligands from three-dimensional models: application to peptide binding to class I major histocompatibility proteins.

A simple and fast free energy scoring function (Fresno) has been developed to predict the binding free energy of peptides to class I major histocompatibility (MHC) proteins. It differs from existing scoring functions mainly by the explicit treatment of ligand desolvation and of unfavorable protein-ligand contacts. Thus, it may be particularly useful in predicting binding affinities from three-dimensional models of protein-ligand complexes. The Fresno function was independently calibrated for two different training sets: (a) five HLA-A0201-peptide structures, which had been determined by X-ray crystallography, and (b) three-dimensional models of 37 H-2K(k)-peptide structures, which had been obtained by knowledge-based homology modeling. For both training sets, a good cross-validated fit to experimental binding free energies was obtained with predictive errors of 3-3.5 kJ/mol. As expected, lipophilic interactions were found to contribute the most to HLA-A0201-peptide interactions, whereas H-bonding predominates in H-2K(k) recognition. Both cross-validated models were afterward used to predict the binding affinity of a test set of 26 peptides to HLA-A0204 (an HLA allele closely related to HLA-A0201) and of a series of 16 peptides to H-2K(k). Predictions were more accurate for HLA-A2-binding peptides as the training set had been built from experimentally determined structures. The average error in predicting the binding free energy of the test peptides was 3.1 kJ/mol. For the homology model-derived equation, the average error in predicting the binding free energy of peptides to K(k) was significantly higher (5.4 kJ/mol) but still very acceptable. The present scoring function is thus able to predict with a good accuracy binding free energies from three-dimensional models, at the condition that the backbone coordinates of the MHC-bound peptide have first been determined with an accuracy of about 1-1.5 A. Furthermore, it may be easily recalibrated for any protein-ligand complex.

Crystallography, X-Ray↗

PubMed2000

Use of artificial neural networks to predict drug dissolution profiles and evaluation of network performance using similarity factor.

PURPOSE: To use artificial neural networks for predicting dissolution profiles of matrix-controlled release theophylline pellet preparation, and to evaluate the network performance by comparing the predicted dissolution profiles with those obtained from physical experiments using similarity factor. METHODS: The Multi-Layered Perceptron (MLP) neural network was used to predict the dissolution profiles of theophylline pellets containing different ratios of microcrystalline cellulose (MCC) and glyceryl monostearate (GMS). The concepts of leave-one-out as well as a time-point by time-point estimation basis were used to predict the rate of drug release for each matrix ratio. All the data were used for training, except for one set which was selected to compare with the predicted output. The closeness between the predicted and the reference dissolution profiles was investigated using similarity factor (f2). RESULTS: The f2 values were all above 60, indicating that the predicted dissolution profiles were closely similar to the dissolution profiles obtained from physical experiments. CONCLUSION: The MLP network could be used as a model for predicting the dissolution profiles of matrix-controlled release theophylline pellet preparation in product development.

Cellulose↗

PubMed2000

Influence of stereoselective pharmacokinetics in the development and predictability of an IVIVC for the enantiomers of metoprolol tartrate.

PURPOSE: To investigate the ability of an IVIVC developed with a racemate drug as well as each enantiomer in predicting the in vivo enantiomer drug performance. METHODS: Dissolution of metoprolol extended release tablets with different release characteristics (e.g., fast (F), moderate (M), and slow (S)) was performed using USP Apparatus I, pH 1.2, 50 rpm. Metoprolol racemate tablets (S, M, and F, 100 mg) and 50 mg oral solution were administered to healthy volunteers, blood samples were collected over 24 (solution) and 48 (tablet) hours and assayed. IVIVC models developed were: (1) Racemate-fraction of drug dissolved (FRD) vs Racemate-fraction of drug absorbed (FRA), (2) R-FRD vs R-FRA, and (3) S-FRD vs S-FRA for combinations of formulations (S/M/F, S/M, S/F, and M/F). Enantiomer Cmax and AUC prediction errors (PEs) were estimated for model evaluation after convolution of in vivo release rates. RESULTS: The R-IVIVC and S-IVIVC accurately predicted the R- and S-metoprolol pharmacokinetic profiles, respectively. The averaged prediction errors (PE) for the enantiomer Cmax and AUC were less than 10% for S/M/F, M/F, and S/F IVIVC models. Racemate-IVIVC (M/F) was able to predict S-enantiomer with an average %PE of 2.52 for S-Cmax and 4.3 for S-AUC. However, the racemate-IVIVC was unable to predict the R-enantiomer pharmacokinetic profile. CONCLUSIONS: Metoprolol racemate data cannot be used to accurately predict R-enantiomer drug concentrations. However, the racemate data was predictive of the active stereoisomer.

Adult↗

PubMed1980

Attention, unpredictability, and reports of physical symptoms: eliminating the benefits of predictability.

Sometimes unpredictable aversive events have more adverse consequences than predictable aversive events and sometimes not. Three experiments were conducted to test an attentional explanation of the inconsistent effects of unpredictability. This explanation suggests that unpredictable events exert a deleterious influence because more attention is typically directed to them. If there were no difference in the amount of attention directed to unpredictable and predictable events, however, there should be no difference in their effects. The validity of these notions was assessed by applying them to one previously established finding from the unpredictability literature--the finding that exposure to unpredictable noise leads to reports of more severe physical symptoms than does exposure to predictable noise. In Experiment 1, subjects performed a reaction time task while they listened to loud bursts of either predictable or unpredictable noise. As expected, reaction times were slower when the noise was unpredictable than when it was not. This finding suggests that more attention had been directed to the unpredictable than the predictable noise. In Experiments 2 and 3, subjects were exposed to either predictable or unpredictable noise and were either instructed to attend to the noise or given no special instructions. In both cases, subjects not instructed to attend to the noise reported more severe symptoms when the noise was unpredictable than when it was not, thus replicating the previous finding. Of greater interest, however, was the fact that equating the amount of attention directed to the unpredictable and predictable noise (by asking subjects to attend to the noise) eliminated the apparent benefits of predictability. The discussion of the findings centers on their theoretical and practical significance.

Acoustic Stimulation↗

PubMed2001

Prediction of energy expenditure in a whole body indirect calorimeter at both low and high levels of physical activity.

OBJECTIVES: In studies that involve the use of a room calorimeter, 24 h energy intake is often larger than 24 h energy expenditure (24 h EE) because of a decrease in activity energy expenditure due to the confined space. This positive energy balance can have large consequences for the interpretation of substrate balances. The objective of this study was to develop a method for predicting an individual's 24 h EE in a room calorimeter at both low (1.4xRMR) and high (1.8xRMR) levels of physical activity. METHODS: Two methods are presented that predict an individual's 24 h EE in a metabolic chamber. The first method was based on three components: (1) a 30 min measurement of resting metabolic rate (RMR) using a ventilated hood system; (2) measurement of exercise energy expenditure during 10 min of treadmill walking; and (3) estimation of free-living energy expenditure using a tri-axial motion sensor. Using these measurements we calculated the amount of treadmill time needed for each individual in order to obtain a total 24 h EE at either a low (1.4xRMR) or a high (1.8xRMR) level of physical activity. We also developed a method to predict total 24 h EE during the chamber stay by using the energy expenditure values for the different levels of activity as measured during the hours already spent in the chamber. This would provide us with a tool to adjust the exercise time and/or energy intake during the chamber stay. RESULTS: Method 1: there was no significant difference in expected and measured 24 h EE under either low (9.35+/-0.56 vs 9.51+/-0.47 MJ/day; measured vs predicted) or high activity conditions (13.41+/-0.74 vs 13.97+/-0.78 MJ/day; measured vs predicted). Method 2: the developed algorithm predicted 24 h EE for 97.6+/-4.0% of the final value at 3 h into the test day, and for 98.6+/-3.7% at 7 h into the test day. CONCLUSION: Both methods provide accurate prediction of energy expenditure in a room calorimeter at both high and low levels of physical activity. It equally shows that it is possible to accurately predict total 24 h EE from energy expenditure values obtained at 3 and 7 h into the study.

Adaptation, Physiological↗

PubMedDate not supplied

Proton magnetic resonance spectroscopy improves outcome prediction in perinatal CNS insults.

OBJECTIVE: Prediction of neurologic outcome is difficult in neonates with acute nervous system injury. Previous studies using proton magnetic resonance spectroscopy ((1)H-MRS) have been used to predict short-term neurologic outcome in neonates with a variety of neurologic insults. We were interested in determining the effectiveness of combining clinical evaluation and spectroscopy obtained at the time of injury in predicting neurologic outcome at 24 months. STUDY DESIGN: We studied 33 neonates with acute central nervous system injury, 5.8+/-3.7 days of injury, owing to hypoxic-ischemic encephalopathy. Neonates were assessed using clinical variables (initial arterial pH, initial blood glucose, Sarnat score, electroencephalography) and spectroscopy (NAA/Cho, NAA/Cre, Cho/Cre, and lactate). Neonates were divided into two outcome groups: good/moderate and poor. Differences between the groups were assessed using chi(2) and t-test analyses. We analyzed the best predictors of outcome using discriminant analysis and calculated sensitivity, specificity, positive, and negative predictive values for each variable independently and in combination. RESULTS: There were significant differences between the good/moderate and poor outcome for the Sarnat score, EEG, lactate, and NAA/Cho. Spectroscopy combined with clinical variables improved sensitivity, but not specificity for predicting outcome. The presence of lactate had the best individual predictive value. Combination of the clinical with the MRS variables had the highest predictive value. CONCLUSION: Proton magnetic resonance spectroscopy done early after injury improves the ability to predict neurologic outcome at 24 months of age.

Aspartic Acid↗

PubMed2004

Combined use of physicochemical data and small-molecule crystallographic contact propensities to predict interactions in protein binding sites.

Knowledge-based methods are a good alternative to force-field-based methods for the analysis of sites of interaction in protein binding cavities. Both the Protein Data Bank (PDB) and the Cambridge Structural Database (CSD) offer a good amount of data on non-covalent interactions. Although different from protein-derived data, small-molecule crystal data from the CSD are worth looking at as they provide a much more abundant and diverse set of intermolecular contacts. CSD data, when properly corrected by use of octanol-water pi values, can be used to predict the type of ligand chemical group most likely to occupy a given position within a protein binding site. Comparison with observed positions of ligand groups shows that the success rates of these predictions vary from 23% to 84%. Often, the group predicted to be most preferred at a given position is similar but not identical to the observed ligand group; if these are considered successes, prediction success rates range from 71% to 94%. Using PDB data, the corresponding rates are 16% to 79%, and 61% to 96%. Specificity of prediction of NH groups is somewhat better when using PDB interaction data, but results of prediction of hydrophobic groups seem worse than those obtained with CSD data. We have analysed the importance of data selection by applying different filters to eliminate unwanted interactions from our knowledge-base. The presence of certain types of interactions can be undesirable if they are unrepresentative of biological situations (contact to solvent molecules in small-molecule crystal structures, secondary crystallographic contacts) or if they are likely to add noise to the data without conveying much new information (long-distance contacts, sparsely-populated data sets). The elimination of solvent contacts was found to have no effect on the prediction of ligand groups in our test set. Both secondary-contact filtering and noise filtering were found to have a clear beneficial effect on predictive ability.

Binding Sites↗

PubMed2003

Greater than predicted decrease in energy expenditure during exercise after body weight loss in obese men.

This study was performed retrospectively to investigate whether exercise energy expenditure (EE) measured during a standardized treadmill protocol (4.5 km/h at 0% grade) falls below predicted values after body weight loss in obese men. A reference equation was established to predict net exercise EE in a control sample of 83 obese individuals (27 kg/m(2)< or = body mass index <45 kg/m(2)), using age, fat mass and fat-free mass as independent variables. This equation was then used to predict net exercise EE in another group of 11 obese men before and after a 15-week drug-based weight loss programme that was coupled with energy restriction [-2929 kJ/day (-700 kcal/day)]. Body weight and body composition were determined by hydrodensitometry. Net exercise EE, insulin, leptin, 3,3',5-tri-iodothyronine and free thyroxine were measured after an overnight fast at baseline and 2-4 weeks after the end of the programme, when subjects were weight stable. Body weight was significantly reduced (-11%; P <0.01) at the end of the weight loss programme. At baseline, measured net exercise EE was similar to that predicted from the regression equation [19.6 and 19.8 kJ/min (4.69 and 4.74 kcal/min) respectively; not significant]. However, after the end of the intervention, measured net exercise EE was significantly below the predicted value [15.5 and 17.3 kJ/min (3.71 and 4.14 kcal/min) respectively; P <0.01]. The difference between the predicted and the measured fall in net exercise EE was significantly associated with changes in leptin concentration ( r =0.79, P <0.01), even after correction for changes in fat mass and insulin. These observations suggest that net exercise EE falls below predicted values after body weight loss. In addition, this greater than predicted decrease in net exercise EE was associated with changes in leptin.

Adult↗

PubMed1998

The use of tooth thickness in predicting intermaxillary tooth-size discrepancies.

Intermaxillary tooth-size discrepancies can be assessed using a diagnostic setup or predicted using a mathematical formula, such as the Bolton analysis. However, variations in tooth thickness may produce inaccuracies in the Bolton analysis ratio. To date, no method for incorporating tooth thickness into discrepancy prediction has been proposed. The purpose of this study was to design and test a new method of predicting anterior tooth-size discrepancy that takes into account tooth thickness and width. Forty-four positioner setup models were set to ideal overbite (2.5 mm) and occlusion (Class I canine relationship). Interproximal gaps between the maxillary or mandibular central incisors were allowed in order to optimize tip and torque. The mesiodistal width of all anterior teeth and the labiolingual thickness of the maxillary incisors were measured on these idealized setups to the nearest 0.1 mm. Actual intermaxillary anterior ratios were then calculated. A new method of prediction was developed by assuming a linear relationship between tooth thickness and ideal intermaxillary ratio. Errors in Bolton's method were compared with the new method. The results showed wide variations in mesiodistal tooth widths, tooth thicknesses, and intermaxillary anterior ratios in orthodontically treated patients. The correlation coefficient between the intermaxillary ratio and tooth thickness was r = 0.68 when tooth thickness was < 2.75 mm, and r = 0.28 when tooth thickness was > or = 2.75 mm. The mean absolute errors in predicting the actual intermaxillary ideal ratio was 1.29 +/- 0.81 for Bolton's ratio and 0.84 +/- 0.46 for the new prediction formula. These new formulas were better than Bolton's ratio in predicting tooth-size discrepancies (p = 0.003). Tooth thickness combined with mesiodistal width may be useful in predicting intermaxillary tooth-size discrepancies.

Algorithms↗

PubMed1999

Prediction of the international normalized ratio and maintenance dose during the initiation of warfarin therapy.

AIMS: A pharmacokinetic/pharmacodynamic model, with Bayesian parameter estimation, was used to retrospectively predict the daily International Normalized Ratios (INRs) and the maintenance doses during the initiation of warfarin therapy in 74 inpatients. METHODS: INRs and maintenance doses predicted by the model were compared with the actual INRs and the eventual maintenance dose. Cases with drugs or medical conditions interacting with warfarin or receiving concurrent heparin therapy were not excluded. As the study was retrospective, model predictions of the maintenance dose were not those that were administered. Mean prediction error (MPE) and percentage absolute prediction errors (PAPE) were used to assess the model predictions. RESULTS: INR MPE ranged from -0.07 to 0.06 and median PAPE from 10% to 20%. Dose MPE ranged from -0.7 to 0.17 mg and median PAPE from 16.7% to 37.5%. Accurate and precise dose predictions were obtained after 3 or more INR feedback's. CONCLUSIONS: This study shows that the model can accurately predict daily INRs and the maintenance dose in this sample of cases. The model can be incorporated into computer decision-support systems for warfarin therapy and may lead to improvement in the initiation of warfarin therapy.

Adult↗

PubMed1997

Applicants to medical school: the value of predicted school leaving grades.

Among school leavers applying to study medicine in the United Kingdom a majority offer General Certificate of Education, Advanced Level (A-level) examinations as part of the assessment of academic ability. At the time of application, up to 9 months before completing A-level studies, schools are requested to predict the final grades likely to be achieved by the applicant. A total of 5054 A-level predictions from 1661 applicants to a single medical school were compared with the results achieved. Predicted and achieved grades were both high with 93% of predicted grades being A or B. Over half the predictions were correct, with 41% of predictions above achieved grades and only 7% below achieved grade. Independent and selective schools predicted higher grades than comprehensive schools and sixth form colleges, and their pupils were more likely to achieve the entrance requirements. A-level predictions for medical school applicants are a strong predictor of achievement and should continue to be regarded as a useful part of the selection process.

Adolescent↗

PubMed2001

Spirometric lung volumes in the adult Pacific Islander population: comparison with predicted values in a European population.

OBJECTIVE: Prediction equations for spirometric lung volumes have been developed mainly in Europe and North America and may not be relevant to Pacific Islanders. This study was undertaken to determine whether currently available prediction equations adequately describe spirometric lung volumes in the asymptomatic adult Pacific Islander population. METHODOLOGY: Healthy asymptomatic Pacific Island adults aged 15-70 years were recruited. Pulmonary function was measured in the laboratory at Green Lane Hospital, Auckland, New Zealand, in accordance with American Thoracic Society standards. Measured results were compared with predicted values derived from four sets of prediction equations relevant to, or currently used in, New Zealand. RESULTS: A total of 101 volunteers took part in the study; mean age 28 years (range 18-66 years), 39% male, body mass index = 32 (range 22-54). For forced expiratory volume in 1 s (FEV1) and forced vital capacity (FVC), when measured values were compared with reference values, the slopes of the regression lines were not significantly different from 1 and the intercepts were not significantly different from zero. Prediction equations derived for African-Americans did not provide a better fit than the prediction equations for Caucasians. Predictions were improved when ideal rather than actual bodyweight was used. CONCLUSION: Respiratory parameters (FEV1 and FVC) in healthy asymptomatic adult Pacific Islanders in New Zealand are adequately described by currently available prediction equations and no adjustment for ethnicity is required.

Adolescent↗

PubMed2003

Predicting disease outcome of non-invasive transitional cell carcinoma of the urinary bladder using an artificial neural network model: results of patient follow-up for 15 years or longer.

BACKGROUND: Patients with non-invasive (Ta/T1) transitional cell carcinoma (TCC) of the urinary bladder are often observed without progression in the long-term follow-up period, although many of them experience recurrence of disease. It is difficult to accurately predict the disease outcome of each patient with Ta/T1 TCC using conventional prognostic criteria. In this study, we examined the usefulness of artificial neural networks (ANNs) to predict the long-term disease outcome of patients with TCC of the urinary bladder. METHODS: A retrospective, prognostic study of 90 patients with Ta/T1 TCC of the urinary bladder, diagnosed by transurethral resection of the bladder tumor between April 1981 and March 1985, and then followed up for 15 years or longer, was carried out. Data were analyzed using the Bayesian network tool of SPSS Neural Connection 2.1. The input neural data consisted of tumor stage, grade, tumor number, age, gender, tumor architecture and estimates of mean nuclear volume. The data set was randomly divided into 68 training and 22 testing examples for the prediction of disease progression and tumor recurrence within 15 years. RESULTS: During 15 years follow-up, tumor recurrence was noted in 42/90 (47%) Ta/T1 tumors. The ANN model could not predict tumor recurrence. Conversely, disease progression was noted in 17/90 (19%) Ta/T1 tumors, and, in the test set, 4/22 (18%) Ta/T1 tumors underwent disease progression. The sensitivity of the ANN model to predict progression was 100% (specificity 67%; positive predictive value 40%; negative predictive value 100%). Patients who were judged to have a favorable prognosis using ANN analysis did not progress within the 15-year follow-up period. CONCLUSION: The results of the ANN study indicate that long-term progression-free survival of patients with non-invasive TCC of the urinary bladder can be precisely predicted. A favorable prognosis using ANNs would be one of the exclusion criteria for immediate or future total cystectomy.

Adult↗

PubMed1991

The use of fetal echocardiography for predicting intrapartum fetal heart rate patterns in the post-term pregnancy.

One of the shortcomings of antepartum testing in the post-term pregnancy is that it does not identify the majority of fetuses who develop abnormal intrapartum fetal heart rate changes. The purpose of this study was to determine whether antenatal cardiovascular evaluation could aid in the identification of post-term fetuses at risk for intrapartum heart rate abnormalities. Seventy-five patients with a gestational age greater than 41 weeks underwent a non-stress test, amniotic fluid index and real-time assessment of the heart for the presence or absence of a pericardial effusion. M-mode measurements of the right ventricular inner dimension (RVID), left ventricular inner dimension (LVID), biventricular outer dimension (BVOD) and Doppler velocimetry of the umbilical artery (S/D) were performed. Group I (n = 32) had normal intrapartum heart rate tracings. Group II (n = 20) had abnormal intrapartum fetal heart rate tracings but did not undergo emergency delivery. Group III (n = 23) had abnormal intrapartum fetal heart rate tracings but underwent emergency delivery. When comparing Group I with Group II, the latter had significant differences for abnormal RVID, RVID/LVID ratio, and pericardial effusion. When comparing Groups I and III, there were significant differences for RVID, RVID/LVID ratio, pericardial effusion, BVOD, LVID and amniotic fluid index. Neither the non-stress test nor S/D predicted abnormal intrapartum fetal heart rate patterns. For prediction of abnormal intrapartum heart rate patterns, the sensitivities of the RVID (0.79), LVID (0.33), RVID/LVID ratio (0.72) and BVOD (0.63) were 1.7-4 times greater than the non-stress test (0.19) and the sensitivities of the RVID, RVID/LVID ratio and BVOD were 2 times greater than the amniotic fluid index (0.28). The positive (0.50-0.86) and negative (0.42-0.68) predictive values were similar for all groups. To predict emergency delivery associated with abnormal heart rate tracings, the sensitivities of the RVID (0.83), RVID/LVID ratio (0.70) and BVOD (0.65) were 2.5-3 times greater than the non-stress test (0.26) and 1.5 times greater than the amniotic fluid index (0.39). The positive (0.36-0.56) and negative (0.70-0.86) predictive values were similar. The presence of pericardial effusion had a higher sensitivity than the non-stress test and amniotic fluid index for predicting abnormal intrapartum heart rate patterns but not emergency delivery. Doppler velocimetry of the umbilical artery had a lower sensitivity than the non-stress test and amniotic fluid index for predicting intrapartum heart rate patterns as well as identifying the fetus needing emergency delivery. The results of this study would suggest that there is initially dilatation of the right ventricle which may be associated with abnormal intrapartum fetal heart rate patterns. However, when the left ventricle dilates, leading to cardiomegaly, there is a greater incidence of abnormal intrapartum fetal heart rate changes and associated emergency delivery. The amniotic fluid index appears to be a later finding for predicting abnormal intrapartum fetal heart rate changes.

Journal Article↗

PubMed2000

A cell-kinetic model of CD34+ cell mobilization and harvest: development of a predictive algorithm for CD34+ cell yield in PBPC collections.

BACKGROUND: Mobilization and homing of PBPCs are still poorly understood. Thus, a sufficient algorithm for the prediction of PBPC yield in apheresis procedures does not yet exist. STUDY DESIGN AND METHODS: The decline of CD34+ cells in the peripheral blood during apheresis and their simultaneous increase in the collection bag were determined in a prospective study of 18 consecutive apheresis procedures. A cell-kinetic, four-compartment model describing these changes was developed. Retrospective data from 136 apheresis procedures served to further improve this model. A predictive algorithm for the yield was developed that considered the sex, weight, and height of the patient, the number of CD34+ cells in peripheral blood before apheresis, the inlet flow, and the duration of the apheresis. The accuracy of this algorithm was evaluated by comparison of the predicted and the observed yields of CD34+ cells in 105 prospective autologous and 148 retrospective allogeneic apheresis procedures. RESULTS: The correlation between predicted and observed yields was good for the autologous and allogeneic groups with a correlation coefficient (r) of 0.8979 and 0.8311 (p<0.0001), respectively. The regression is described by the equations log (measured value [m]) = 1.0118 + 0.8595 x log (predicted value [p]) for the autologous and log (m) = 2.226 + 0.7559 x log (p) for the allogeneic group. The respective equations for the zero-point regression are log (m) = 1.014 x log (p) and log (m) = 1.026 x log (p). The probability that the measured value was 90 percent or more of the predicted value was 83.8 percent for the autologous and 90.5 percent for the allogeneic apheresis procedures. CONCLUSION: The predictive accuracy of the algorithm and the slope of the zero-point regression curve were higher for allogeneic than autologous PBPC collections. The predictive algorithm may be a useful tool in PBPC harvest, enabling the adaptation of the size of the apheresis to the needs of each patient.

Algorithms↗