Chow–Liu trees are sufficient predictive models for reproducing key features of functional networks of periictal EEG time-series

Seizure freedom in patients suffering from pharmacoresistant epilepsies is still not achieved in 20–30% of all cases. Hence, current therapies need to be improved, based on a more complete understanding of ictogenesis. In this respect, the analysis of functional networks derived from intracranial electroencephalographic (iEEG) data has recently become a standard tool. Functional networks however are purely descriptive models and thus are conceptually unable to predict fundamental features of iEEG time-series, e.g., in the context of therapeutical brain stimulation. In this paper we present some first steps towards overcoming the limitations of functional network analysis, by showing that its results are implied by a simple predictive model of time-sliced iEEG time-series. More specifically, we learn distinct graphical models (so called Chow–Liu (CL) trees) as models for the spatial dependencies between iEEG signals. Bayesian inference is then applied to the CL trees, allowing for an analytic derivation/prediction of functional networks, based on thresholding of the absolute value Pearson correlation coefficient (CC) matrix. Using various measures, the thus obtained networks are then compared to those which were derived in the classical way from the empirical CC-matrix. In the high threshold limit we find (a) an excellent agreement between the two networks and (b) key features of periictal networks as they have previously been reported in the literature. Apart from functional networks, both matrices are also compared element-wise, showing that the CL approach leads to a sparse representation, by setting small correlations to values close to zero while preserving the larger ones. Overall, this paper shows the validity of CL-trees as simple, spatially predictive models for periictal iEEG data. Moreover, we suggest straightforward generalizations of the CL-approach for modeling also the temporal features of iEEG signals.

TIME SERIES ANALYSIS AS INPUT FOR PREDICTIVE MODELING: PREDICTING CARDIAC ARREST IN A PEDIATRIC INTENSIVE CARE UNIT

The first manuscript, entitled "Time-Series Analysis as Input for Clinical Predictive Modeling: Modeling Cardiac Arrest in a Pediatric ICU" lays out the theoretical background for the project. There are several core concepts presented in this paper. First, traditional multivariate models (where each variable is represented by only one value) provide single point-in-time snapshots of patient status: they are incapable of characterizing deterioration. Since deterioration is consistently identified as a precursor to cardiac arrests, we maintain that the traditional multivariate paradigm is insufficient for predicting arrests. We identify time series analysis as a method capable of characterizing deterioration in an objective, mathematical fashion, and describe how to build a general foundation for predictive modeling using time series analysis results as latent variables. Building a solid foundation for any given modeling task involves addressing a number of issues during the design phase. These include selecting the proper candidate features on which to base the model, and selecting the most appropriate tool to measure them. We also identified several unique design issues that are introduced when time series data elements are added to the set of candidate features. One such issue is in defining the duration and resolution of time series elements required to sufficiently characterize the time series phenomena being considered as candidate features for the predictive model. Once the duration and resolution are established, there must also be explicit mathematical or statistical operations that produce the time series analysis result to be used as a latent candidate feature. In synthesizing the comprehensive framework for building a predictive model based on time series data elements, we identified at least four classes of data that can be used in the model design. The first two classes are shared with traditional multivariate models: multivariate data and clinical latent features. Multivariate data is represented by the standard one value per variable paradigm and is widely employed in a host of clinical models and tools. These are often represented by a number present in a given cell of a table. Clinical latent features derived, rather than directly measured, data elements that more accurately represent a particular clinical phenomenon than any of the directly measured data elements in isolation. The second two classes are unique to the time series data elements. The first of these is the raw data elements. These are represented by multiple values per variable, and constitute the measured observations that are typically available to end users when they review time series data. These are often represented as dots on a graph. The final class of data results from performing time series analysis. This class of data represents the fundamental concept on which our hypothesis is based. The specific statistical or mathematical operations are up to the modeler to determine, but we generally recommend that a variety of analyses be performed in order to maximize the likelihood that a representation of the time series data elements is produced that is able to distinguish between two or more classes of outcomes. The second manuscript, entitled "Building Clinical Prediction Models Using Time Series Data: Modeling Cardiac Arrest in a Pediatric ICU" provides a detailed description, start to finish, of the methods required to prepare the data, build, and validate a predictive model that uses the time series data elements determined in the first paper. One of the fundamental tenets of the second paper is that manual implementations of time series based models are unfeasible due to the relatively large number of data elements and the complexity of preprocessing that must occur before data can be presented to the model. Each of the seventeen steps is analyzed from the perspective of how it may be automated, when necessary. We identify the general objectives and available strategies of each of the steps, and we present our rationale for choosing a specific strategy for each step in the case of predicting cardiac arrest in a pediatric intensive care unit. Another issue brought to light by the second paper is that the individual steps required to use time series data for predictive modeling are more numerous and more complex than those used for modeling with traditional multivariate data. Even after complexities attributable to the design phase (addressed in our first paper) have been accounted for, the management and manipulation of the time series elements (the preprocessing steps in particular) are issues that are not present in a traditional multivariate modeling paradigm. In our methods, we present the issues that arise from the time series data elements: defining a reference time; imputing and reducing time series data in order to conform to a predefined structure that was specified during the design phase; and normalizing variable families rather than individual variable instances. The final manuscript, entitled: "Using Time-Series Analysis to Predict Cardiac Arrest in a Pediatric Intensive Care Unit" presents the results that were obtained by applying the theoretical construct and its associated methods (detailed in the first two papers) to the case of cardiac arrest prediction in a pediatric intensive care unit. Our results showed that utilizing the trend analysis from the time series data elements reduced the number of classification errors by 73%. The area under the Receiver Operating Characteristic curve increased from a baseline of 87% to 98% by including the trend analysis. In addition to the performance measures, we were also able to demonstrate that adding raw time series data elements without their associated trend analyses improved classification accuracy as compared to the baseline multivariate model, but diminished classification accuracy as compared to when just the trend analysis features were added (ie, without adding the raw time series data elements). We believe this phenomenon was largely attributable to overfitting, which is known to increase as the ratio of candidate features to class examples rises. Furthermore, although we employed several feature reduction strategies to counteract the overfitting problem, they failed to improve the performance beyond that which was achieved by exclusion of the raw time series elements. Finally, our data demonstrated that pulse oximetry and systolic blood pressure readings tend to start diminishing about 10-20 minutes before an arrest, whereas heart rates tend to diminish rapidly less than 5 minutes before an arrest.

Inappropriate imaging utilization in Texas: Geographic variation and predictive factors

Objective::Describe and understand regional differences and associated multilevel factors (patient, provider and regional) to inappropriate utilization of advance imaging tests in the privately insured population of Texas. Methods: We analyzed Blue Cross Blue Shield of Texas claims dataset to study the advance imaging utilization during 2008-2010 in the PPO/PPO+ plans. We used three of CMS "Hospital Outpatient Quality Reporting" imaging efficiency measures. These included ordering MRI for low back pain without prior conservative management (OP-8) and utilization of combined with and without contrast abdominal CT (OP-10) and thorax CT (OP-11). Means and variation by hospital referral regions (HRR) in Texas were measured and a multilevel logistic regression for being a provider with high values for any the three OP measures was used in the analysis. We also analyzed OP-8 at the individual level. A multilevel logistic regression was used to identify predictive factors for having an inappropriate MRI for low back pain. Results: Mean OP-8 for Texas providers was 37.89%, OP-10 was 29.94% and OP-11 was 9.24%. Variation was higher for CT measure. And certain HRRs were consistently above the mean. Hospital providers had higher odds of high OP-8 values (OP-8: OR, 1.34; CI, 1.12-1.60) but had smaller odds of having high OP-10 and OP-11 values (OP-10: OR, 0.15; CI, 0.12-0.18; OP-11: OR, 0.43; CI, 0.34-0.53). Providers with the highest volume of imaging studies performed, were less likely to have high OP-8 measures (OP-8: OR, 0.58; CI, 0.48-0.70) but more likely to perform combined thoracic CT scans (OP-11: OR, 1.62; CI, 1.34-1.95). Males had higher odds of inappropriate MRI (OR, 1.21; CI, 1.16-1.26). Pattern of care in the six months prior to the MRI event was significantly associated with having an inappropriate MRI. Conclusion::We identified a significant variation in advance imaging utilization across Texas. Type of facility was associated with measure performance, but the associations differ according to the type of study. Last, certain individual characteristics such as gender, age and pattern of care were found to be predictors of inappropriate MRIs.^

Predictive regression equations and clinical uses of peripheral pulse timing characteristics in children

Studies have shown that increased arterial stiffening can be an indication of cardiovascular diseases like hypertension. In clinical practice, this can be detected by measuring the blood pressure (BP) using a sphygmomanometer but it cannot be used for prolonged monitoring. It has been established that pulse wave velocity (PWV) is a direct measure of arterial stiffening but its usefulness is hampered by the absence of non-invasive techniques to estimate it. Pulse transit time (PTT) is a simple and non-invasive method derived from PWV. However, limited knowledge of PTT in children is found in the present literature. The aims of this study are to identify independent variables that confound PTT measure and describe PTT regression equations for healthy children. Therefore, PTT reference values are formulated for future pathological studies. Fifty-five Caucasian children (39 male) aged 8.4 +/- 2.3 yr (range 5-12 yr) were recruited. Predictive equations for PTT were obtained by multiple regressions with age, vascular path length, BP indexes and heart rate. These derived equations were compared in their PWV equivalent against two previously reported equations and significant agreement was obtained (p < 0.05). Findings herein also suggested that PTT can be useful as a continuous surrogate BP monitor in children.

On the hydrophobicity of peptides:comparing empirical predictions of peptide log P values

Peptides are of great therapeutic potential as vaccines and drugs. Knowledge of physicochemical descriptors, including the partition coefficient logP, is useful for the development of predictive Quantitative Structure-Activity Relationships (QSARs). We have investigated the accuracy of available programs for the prediction of logP values for peptides with known experimental values obtained from the literature. Eight prediction programs were tested, of which seven programs were fragment-based methods: XLogP, LogKow, PLogP, ACDLogP, AlogP, Interactive Analysis's LogP and MlogP; and one program used a whole molecule approach: QikProp. The predictive accuracy of the programs was assessed using r(2) values, with ALogP being the most effective (r( 2) = 0.822) and MLogP the least (r(2) = 0.090). We also examined three distinct types of peptide structure: blocked, unblocked, and cyclic. For each study (all peptides, blocked, unblocked and cyclic peptides) the performance of programs rated from best to worse is as follows: all peptides - ALogP, QikProp, PLogP, XLogP, IALogP, LogKow, ACDLogP, and MlogP; blocked peptides - PLogP, XLogP, ACDLogP, IALogP, LogKow, QikProp, ALogP, and MLogP; unblocked peptides - QikProp, IALogP, ALogP, ACDLogP, MLogP, XLogP, LogKow and PLogP; cyclic peptides - LogKow, ALogP, XLogP, MLogP, QikProp, ACDLogP, IALogP. In summary, all programs gave better predictions for blocked peptides, while, in general, logP values for cyclic peptides were under-predicted and those of unblocked peptides were over-predicted.

Növelhető-e a csőd-előrejelző modellek előre jelző képessége az új klasszifikációs módszerek nélkül? (Can the predictive capacity of bankruptcy forecasting models be increased without new classification methods?)

A Bázel–2. tőkeegyezmény bevezetését követően a bankok és hitelintézetek Magyarországon is megkezdték saját belső minősítő rendszereik felépítését, melyek karbantartása és fejlesztése folyamatos feladat. A szerző arra a kérdésre keres választ, hogy lehetséges-e a csőd-előrejelző modellek előre jelző képességét növelni a hagyományos matematikai-statisztikai módszerek alkalmazásával oly módon, hogy a modellekbe a pénzügyi mutatószámok időbeli változásának mértékét is beépítjük. Az empirikus kutatási eredmények arra engednek következtetni, hogy a hazai vállalkozások pénzügyi mutatószámainak időbeli alakulása fontos információt hordoz a vállalkozás jövőbeli fizetőképességéről, mivel azok felhasználása jelentősen növeli a csődmodellek előre jelző képességét. A szerző azt is megvizsgálja, hogy javítja-e a megfigyelések szélsőségesen magas vagy alacsony értékeinek modellezés előtti korrekciója a modellek klasszifikációs teljesítményét. ______ Banks and lenders in Hungary also began, after the introduction of the Basel 2 capital agreement, to build up their internal rating systems, whose maintenance and development are a continuing task. The author explores whether it is possible to increase the predictive capacity of business-failure forecasting models by traditional mathematical-cum-statistical means in such a way that they incorporate the measure of change in the financial indicators over time. Empirical findings suggest that the temporal development of the financial indicators of firms in Hungary carries important information about future ability to pay, since the predictive capacity of bankruptcy forecasting models is greatly increased by using such indicators. The author also examines whether the classification performance of the models can be improved by correcting for extremely high or low values before modelling.

Searching for Predictive Subgroups

Thesis (Ph.D.)--University of Washington, 2016-08

Multiple Imputation of missing values in exploratory factor analysis of multidimensional scales: estimating latent trait scores

ABSTRACT Researchers frequently have to analyze scales in which some participants have failed to respond to some items. In this paper we focus on the exploratory factor analysis of multidimensional scales (i.e., scales that consist of a number of subscales) where each subscale is made up of a number of Likert-type items, and the aim of the analysis is to estimate participants' scores on the corresponding latent traits. We propose a new approach to deal with missing responses in such a situation that is based on (1) multiple imputation of non-responses and (2) simultaneous rotation of the imputed datasets. We applied the approach in a real dataset where missing responses were artificially introduced following a real pattern of non-responses, and a simulation study based on artificial datasets. The results show that our approach (specifically, Hot-Deck multiple imputation followed of Consensus Promin rotation) was able to successfully compute factor score estimates even for participants that have missing data.

Towards a predictive model of Ca²⁺ puffs

We investigate key characteristics of Ca²⁺ puffs in deterministic and stochastic frameworks that all incorporate the cellular morphology of IP[subscript]3 receptor channel clusters. In a first step, we numerically study Ca²⁺ liberation in a three dimensional representation of a cluster environment with reaction-diffusion dynamics in both the cytosol and the lumen. These simulations reveal that Ca²⁺ concentrations at a releasing cluster range from 80 µM to 170 µM and equilibrate almost instantaneously on the time scale of the release duration. These highly elevated Ca²⁺ concentrations eliminate Ca²⁺ oscillations in a deterministic model of an IP[subscript]3R channel cluster at physiological parameter values as revealed by a linear stability analysis. The reason lies in the saturation of all feedback processes in the IP[subscript]3R gating dynamics, so that only fluctuations can restore experimentally observed Ca²⁺ oscillations. In this spirit, we derive master equations that allow us to analytically quantify the onset of Ca²⁺ puffs and hence the stochastic time scale of intracellular Ca²⁺ dynamics. Moving up the spatial scale, we suggest to formulate cellular dynamics in terms of waiting time distribution functions. This approach prevents the state space explosion that is typical for the description of cellular dynamics based on channel states and still contains information on molecular fluctuations. We illustrate this method by studying global Ca²⁺ oscillations.

Predictive Value Of Phase I Trials For Safety In Later Trials And Final Approved Dose: Analysis Of 61 Approved Cancer Drugs.

Phase I trials use a small number of patients to define a maximum tolerated dose (MTD) and the safety of new agents. We compared data from phase I and registration trials to determine whether early trials predicted later safety and final dose. We searched the U.S. Food and Drug Administration (FDA) website for drugs approved in nonpediatric cancers (January 1990-October 2012). The recommended phase II dose (R2PD) and toxicities from phase I were compared with doses and safety in later trials. In 62 of 85 (73%) matched trials, the dose from the later trial was within 20% of the RP2D. In a multivariable analysis, phase I trials of targeted agents were less predictive of the final approved dose (OR, 0.2 for adopting ± 20% of the RP2D for targeted vs. other classes; P = 0.025). Of the 530 clinically relevant toxicities in later trials, 70% (n = 374) were described in phase I. A significant relationship (P = 0.0032) between increasing the number of patients in phase I (up to 60) and the ability to describe future clinically relevant toxicities was observed. Among 28,505 patients in later trials, the death rate that was related to drug was 1.41%. In conclusion, dosing based on phase I trials was associated with a low toxicity-related death rate in later trials. The ability to predict relevant toxicities correlates with the number of patients on the initial phase I trial. The final dose approved was within 20% of the RP2D in 73% of assessed trials.

Volumetric Capnography For The Evaluation Of Chronic Airways Diseases.

Obstructive lung diseases of different etiologies present with progressive peripheral airway involvement. The peripheral airways, known as the silent lung zone, are not adequately evaluated with conventional function tests. The principle of gas washout has been used to detect pulmonary ventilation inhomogeneity and to estimate the location of the underlying disease process. Volumetric capnography (VC) analyzes the pattern of CO2 elimination as a function of expired volume. To measure normalized phase 3 slopes with VC in patients with non-cystic fibrosis bronchiectasis (NCB) and in bronchitic patients with chronic obstructive pulmonary disease (COPD) in order to compare the slopes obtained for the groups. NCB and severe COPD were enrolled sequentially from an outpatient clinic (Hospital of the State University of Campinas). A control group was established for the NCB group, paired by sex and age. All subjects performed spirometry, VC, and the 6-Minute Walk Test (6MWT). Two comparisons were made: NCB group versus its control group, and NCB group versus COPD group. The project was approved by the ethical committee of the institution. Statistical tests used were Wilcoxon or Student's t-test; P<0.05 was considered to be a statistically significant difference. Concerning the NCB group (N=20) versus the control group (N=20), significant differences were found in body mass index and in several functional variables (spirometric, VC, 6MWT) with worse results observed in the NCB group. In the comparison between the COPD group (N=20) versus the NCB group, although patients with COPD had worse spirometric and 6MWT values, the capnographic variables mean phase 2 slope (Slp2), mean phase 3 slope normalized by the mean expiratory volume, or mean phase 3 slope normalized by the end-tidal CO2 concentration were similar. These findings may indicate that the gas elimination curves are not sensitive enough to monitor the severity of structural abnormalities. The role of normalized phase 3 slope may be worth exploring as a more sensitive index of small airway disease, even though it may not be equally sensitive in discriminating the severity of the alterations.

[balloon Laryngoplasty For Acquired Subglottic Stenosis In Children: Predictive Factors For Success].

The treatment of subglottic stenosis in children remains a challenge for the otorhinolaryngologist, and may involve both endoscopic and open surgery. To report the experience of two tertiary facilities in the treatment of acquired subglottic stenosis in children with balloon laryngoplasty, and to identify predictive factors for success of the technique and its complications. Descriptive, prospective study of children diagnosed with acquired subglottic stenosis and submitted to balloon laryngoplasty as primary treatment. Balloon laryngoplasty was performed in 37 children with an average age of 22.5 months; 24 presented chronic subglottic stenosis and 13 acute subglottic stenosis. Success rates were 100% for acute subglottic stenosis and 32% for chronic subglottic stenosis. Success was significantly associated with acute stenosis, initial grade of stenosis, children of a smaller age, and the absence of tracheostomy. Transitory dysphagia was the only complication observed in three children. Balloon laryngoplasty may be considered the first line of treatment for acquired subglottic stenosis. In acute cases, the success rate is 100%, and although the results are less promising in chronic cases, complications are not significant and the possibility of open surgery remains without prejudice.

Reference Values For High-density Lipoprotein Particle Size And Volume By Dynamic Light Scattering In A Brazilian Population Sample And Their Relationships With Metabolic Parameters.

Current data indicate that the size of high-density lipoprotein (HDL) may be considered an important marker for cardiovascular disease risk. We established reference values of mean HDL size and volume in an asymptomatic representative Brazilian population sample (n=590) and their associations with metabolic parameters by gender. Size and volume were determined in HDL isolated from plasma by polyethyleneglycol precipitation of apoB-containing lipoproteins and measured using the dynamic light scattering (DLS) technique. Although the gender and age distributions agreed with other studies, the mean HDL size reference value was slightly lower than in some other populations. Both HDL size and volume were influenced by gender and varied according to age. HDL size was associated with age and HDL-C (total population); non- white ethnicity and CETP inversely (females); HDL-C and PLTP mass (males). On the other hand, HDL volume was determined only by HDL-C (total population and in both genders) and by PLTP mass (males). The reference values for mean HDL size and volume using the DLS technique were established in an asymptomatic and representative Brazilian population sample, as well as their related metabolic factors. HDL-C was a major determinant of HDL size and volume, which were differently modulated in females and in males.

Desenhos de estruturas químicas correlacionam-se com propriedades biológicas: MIA-QSAR

Descriptors in multivariate image analysis applied to quantitative structure-activity relationship (MIA-QSAR) are pixels of bidimensional images of chemical structures (drawings), which were used to model the trichomonicidal activities of a series of benzimidazole derivatives. The MIA-QSAR model showed good predictive ability, with r², q² and r val. ext.² of 0.853, 0.519 and 0.778, respectively, which are comparable to the best values obtained by CoMFA e CoMSIA for the same series. A MIA-based analysis was also performed by using images of alphabetic letters with the corresponding numeric ordering as dependent variables, but no correlation was found, supporting that MIA-QSAR is not arbitrary.

Estimativa de bem-estar de frango de corte em função da concentração de amônia e grau de luminosidade no galpão de produção

Brazil is an important poultry meat export country, and large parts of its destination are countries with specific rearing restrictions related to broiler s welfare. One of the aerial pollutants mostly found in high concentrations in closed poultry housing environment is ammonia. There are evidences that broilers welfare may be compromised by the continuous exposition to this pollutant in rearing housing. This research aimed to estimate broilers welfare reared under specific thermal environmental attributes and bird s density, as function of the ammonia concentration and light intensity inside the housing environment using the Fuzzy Theory. Results showed that the best welfare value (0.89 in the scale: 0-1) approximately 90% of the ideal was found in the conditions that associated the ideal thermal environment, with bird s density between 13-15 birds m-2, with values of the ammonia concentration in the environment below 5 ppm, and light intensity near 1 lx. Using the predictive method it was possible to estimate broilers welfare with relation to the ammonia concentration and light intensity in the housing.