PICADAR: a diagnostic predictive tool for primary ciliary dyskinesia.

Symptoms of primary ciliary dyskinesia (PCD) are nonspecific and guidance on whom to refer for testing is limited. Diagnostic tests for PCD are highly specialised, requiring expensive equipment and experienced PCD scientists. This study aims to develop a practical clinical diagnostic tool to identify patients requiring testing.Patients consecutively referred for testing were studied. Information readily obtained from patient history was correlated with diagnostic outcome. Using logistic regression, the predictive performance of the best model was tested by receiver operating characteristic curve analyses. The model was simplified into a practical tool (PICADAR) and externally validated in a second diagnostic centre.Of 641 referrals with a definitive diagnostic outcome, 75 (12%) were positive. PICADAR applies to patients with persistent wet cough and has seven predictive parameters: full-term gestation, neonatal chest symptoms, neonatal intensive care admittance, chronic rhinitis, ear symptoms, situs inversus and congenital cardiac defect. Sensitivity and specificity of the tool were 0.90 and 0.75 for a cut-off score of 5 points. Area under the curve for the internally and externally validated tool was 0.91 and 0.87, respectively.PICADAR represents a simple diagnostic clinical prediction rule with good accuracy and validity, ready for testing in respiratory centres referring to PCD centres.

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.

Data quality in trauma transfusion studies and the impact of missing data on predicting massive transfusion

Maximizing data quality may be especially difficult in trauma-related clinical research. Strategies are needed to improve data quality and assess the impact of data quality on clinical predictive models. This study had two objectives. The first was to compare missing data between two multi-center trauma transfusion studies: a retrospective study (RS) using medical chart data with minimal data quality review and the PRospective Observational Multi-center Major Trauma Transfusion (PROMMTT) study with standardized quality assurance. The second objective was to assess the impact of missing data on clinical prediction algorithms by evaluating blood transfusion prediction models using PROMMTT data. RS (2005-06) and PROMMTT (2009-10) investigated trauma patients receiving ≥ 1 unit of red blood cells (RBC) from ten Level I trauma centers. Missing data were compared for 33 variables collected in both studies using mixed effects logistic regression (including random intercepts for study site). Massive transfusion (MT) patients received ≥ 10 RBC units within 24h of admission. Correct classification percentages for three MT prediction models were evaluated using complete case analysis and multiple imputation based on the multivariate normal distribution. A sensitivity analysis for missing data was conducted to estimate the upper and lower bounds of correct classification using assumptions about missing data under best and worst case scenarios. Most variables (17/33=52%) had <1% missing data in RS and PROMMTT. Of the remaining variables, 50% demonstrated less missingness in PROMMTT, 25% had less missingness in RS, and 25% were similar between studies. Missing percentages for MT prediction variables in PROMMTT ranged from 2.2% (heart rate) to 45% (respiratory rate). For variables missing >1%, study site was associated with missingness (all p≤0.021). Survival time predicted missingness for 50% of RS and 60% of PROMMTT variables. MT models complete case proportions ranged from 41% to 88%. Complete case analysis and multiple imputation demonstrated similar correct classification results. Sensitivity analysis upper-lower bound ranges for the three MT models were 59-63%, 36-46%, and 46-58%. Prospective collection of ten-fold more variables with data quality assurance reduced overall missing data. Study site and patient survival were associated with missingness, suggesting that data were not missing completely at random, and complete case analysis may lead to biased results. Evaluating clinical prediction model accuracy may be misleading in the presence of missing data, especially with many predictor variables. The proposed sensitivity analysis estimating correct classification under upper (best case scenario)/lower (worst case scenario) bounds may be more informative than multiple imputation, which provided results similar to complete case analysis.^

Reliability measures for local nodes assessment in classification trees

Most of the modem developments with classification trees are aimed at improving their predictive capacity. This article considers a curiously neglected aspect of classification trees, namely the reliability of predictions that come from a given classification tree. In the sense that a node of a tree represents a point in the predictor space in the limit, the aim of this article is the development of localized assessment of the reliability of prediction rules. A classification tree may be used either to provide a probability forecast, where for each node the membership probabilities for each class constitutes the prediction, or a true classification where each new observation is predictively assigned to a unique class. Correspondingly, two types of reliability measure will be derived-namely, prediction reliability and classification reliability. We use bootstrapping methods as the main tool to construct these measures. We also provide a suite of graphical displays by which they may be easily appreciated. In addition to providing some estimate of the reliability of specific forecasts of each type, these measures can also be used to guide future data collection to improve the effectiveness of the tree model. The motivating example we give has a binary response, namely the presence or absence of a species of Eucalypt, Eucalyptus cloeziana, at a given sampling location in response to a suite of environmental covariates, (although the methods are not restricted to binary response data).

Evaluating statistical and machine learning methods to predict risk of in-hospital child mortality in Uganda

Thesis (Master's)--University of Washington, 2016-08

CURB-65 and other markers of illness severity in community-acquired pneumonia among HIV-positive patients

Introduction: As the relative burden of community-acquired bacterial pneumonia among HIV-positive patients increases, adequate prediction of case severity on presentation is crucial. We sought to determine what characteristics measurable on presentation are predictive of worse outcomes. Methods: We studied all admissions for community-acquired bacterial pneumonia over 1 year at a tertiary centre. Patient demographics, comorbidities, HIV-specific markers and CURB-65 scores on Emergency Department presentation were reviewed. Outcomes of interest included mortality, bacteraemia, intensive care unit admission and orotracheal intubation. Results: A total of 396 patients were included, 49 HIV positive and 347 HIV negative. Mean CURB-65 score was 1.3 for HIV-positive and 2.2 for HIV-negative patients (p<0.0001), its predictive value for mortality being maintained in both groups (p¼0.03 and p<0.001, respectively). Adjusting for CURB-65 scores, HIV infection by itself was only associated with bacteraemia (adjusted odds ratio 7.1 CI 95% [2.6–19.5]). Patients with<200 CD4 cells/mL presented similar CURB- 65 adjusted mortality (adjusted odds ratio 1.7 CI 95% [0.2–15.2]), but higher risk of intensive care unit admission (adjusted odds ratio 5.7 CI 95% [1.5–22.0]) and orotracheal intubation (adjusted odds ratio 9.1 CI 95% [2.2–37.1]), compared to HIV-negative patients. These two associations were not observed in the>200 CD4 cells/mL subgroup (adjusted odds ratio 2.2 CI 95% [0.7–7.6] and adjusted odds ratio 0.8 CI 95% [0.1–6.5] respectively). Antiretroviral therapy and viral load suppression were not associated with different outcomes (p>0.05). Conclusions: High CURB-65 scores and CD4 counts<200 cells/mL were both associated with worse outcomes. Severity assessment scales and CD4 counts may both be helpful in predicting severity in HIV-positive patients presenting with community-acquired bacterial pneumonia.

Ultrasonido a la cabecera del paciente, una herramienta diagnóstica de disección aórtica en el departamento de emergencias

El síndrome aórtico agudo puede presentarse como un cuadro clínico característico de una emergencia vascular, o por el contrario de una forma completamente atípica, donde el diagnóstico reta al médico de emergencias, llevando a errores fatales al pasar por alto el diagnóstico de esta entidad. Con el objetivo de mostrar la utilidad del ultrasonido realizado a la cabecera del paciente en el diagnóstico de disección aórtica, se describen 9 casos de pacientes que ingresaron al departamento de emergencias y que fueron diagnosticados con síndrome aórtico agudo, gracias a la valoración ultrasonográfica inicial realizada por residentes y Especialistas en Medicina de Emergencias en un hospital de Bogotá D.C., Colombia. Este reporte de casos muestra que el ultrasonido a la cabecera del paciente, es un método diagnóstico no invasivo, accesible y útil para la detección temprana de esta patología en los servicios de emergencias.

Trials, tricks and transparency: how disclosure rules affect clinical knowledge

Scandals of selective reporting of clinical trial results by pharmaceutical firms have underlined the need for more transparency in clinical trials. We provide a theoretical framework which reproduces incentives for selective reporting and yields three key implications concerning regulation. First, a compulsory clinical trial registry complemented through a voluntary clinical trial results database can implement full transparency (the existence of all trials as well as their results is known). Second, full transparency comes at a price. It has a deterrence effect on the incentives to conduct clinical trials, as it reduces the firms'gains from trials. Third, in principle, a voluntary clinical trial results database without a compulsory registry is a superior regulatory tool; but we provide some qualified support for additional compulsory registries when medical decision-makers cannot anticipate correctly the drug companies' decisions whether to conduct trials. Keywords: pharmaceutical firms, strategic information transmission, clinical trials, registries, results databases, scientific knowledge JEL classification: D72, I18, L15

The use of clinical risk factors enhances the performance of BMD in the prediction of hip and osteoporotic fractures in men and women.

SUMMARY: BMD and clinical risk factors predict hip and other osteoporotic fractures. The combination of clinical risk factors and BMD provide higher specificity and sensitivity than either alone. INTRODUCTION AND HYPOTHESES: To develop a risk assessment tool based on clinical risk factors (CRFs) with and without BMD. METHODS: Nine population-based studies were studied in which BMD and CRFs were documented at baseline. Poisson regression models were developed for hip fracture and other osteoporotic fractures, with and without hip BMD. Fracture risk was expressed as gradient of risk (GR, risk ratio/SD change in risk score). RESULTS: CRFs alone predicted hip fracture with a GR of 2.1/SD at the age of 50 years and decreased with age. The use of BMD alone provided a higher GR (3.7/SD), and was improved further with the combined use of CRFs and BMD (4.2/SD). For other osteoporotic fractures, the GRs were lower than for hip fracture. The GR with CRFs alone was 1.4/SD at the age of 50 years, similar to that provided by BMD (GR = 1.4/SD) and was not markedly increased by the combination (GR = 1.4/SD). The performance characteristics of clinical risk factors with and without BMD were validated in eleven independent population-based cohorts. CONCLUSIONS: The models developed provide the basis for the integrated use of validated clinical risk factors in men and women to aid in fracture risk prediction.

La cohorte OstéoLaus: évaluation des outils de routine clinique pour la prédiction de la fracture ostéoporotique [OsteoLaus: prediction of osteoporotic fractures by clinical risk factors and DXA, IVA and TBS].

OsteoLaus is a cohort of 1400 women 50 to 80 years living in Lausanne, Switzerland. Clinical risk factors for osteoporosis, bone ultrasound of the heel, lumbar spine and hip bone mineral density (BMD), assessment of vertebral fracture by DXA, and microarchitecture evaluation by TBS (Trabecular Bone Score) will be recorded. TBS is a new parameter obtained after a re-analysis of a DXA exam. TBS is correlated with parameters of microarchitecture. His reproducibility is good. TBS give an added diagnostic value to BMD, and predict osteoporotic fracture (partially) independently to BMD. The position of TBS in clinical routine in complement to BMD and clinical risk factors will be evaluated in the OsteoLaus cohort.

Prediction of clinical response after renal angioplasty: respective value of renal Doppler sonography and scintigraphy.

OBJECTIVE: The goal of our study was to compare Doppler sonography and renal scintigraphy as tools for predicting the therapeutic response in patients after undergoing renal angioplasty. SUBJECTS AND METHODS. Seventy-four hypertensive patients underwent clinical examination, Doppler sonography, and renal scintigraphy before and after receiving captopril in preparation for renal revascularization. The patients were evaluated for the status of hypertension 3 months after the procedure. The predictive values of the findings of clinical examination, Doppler sonography, renal scintigraphy, and angiography were assessed. RESULTS: For prediction of a favorable therapeutic outcome, abnormal results from renal scintigraphy before and after captopril administration had a sensitivity of 58% and specificity of 57%. Findings of Doppler sonography had a sensitivity of 68% and specificity of 50% before captopril administration and a sensitivity of 81% and specificity of 32% after captopril administration. Significant predictors of a cure or reduction of hypertension after revascularization were low unilateral (p = 0.014) and bilateral resistive (p = 0.016) indexes on Doppler sonography before (p = 0.009) and after (p = 0.028) captopril administration. On multivariate analysis, the best predictors were a unilateral resistive index of less than 0.65 (odds ratio [OR] = 3.7) after captopril administration and a kidney longer than 93 mm (OR = 7.8). The two best combined criteria to predict the favorable therapeutic outcome were a bilateral resistive index of less than 0.75 before captopril administration combined with a unilateral resistive index of less than 0.70 after captopril administration (sensitivity, 76%; specificity, 58%) or a bilateral resistive index of less than 0.75 before captopril administration and a kidney measuring longer than 90 mm (sensitivity, 81%; specificity, 50%). CONCLUSION: Measurements of kidney length and unilateral and bilateral resistive indexes before and after captopril administration were useful in predicting the outcome after renal angioplasty. Renal scintigraphy had no significant predictive value.

Validated prediction of clinical outcome in sarcomas and multiple types of cancer on the basis of a gene expression signature related to genome complexity.

Sarcomas are heterogeneous and aggressive mesenchymal tumors. Histological grading has so far been the best predictor for metastasis-free survival, but it has several limitations, such as moderate reproducibility and poor prognostic value for some histological types. To improve patient grading, we performed genomic and expression profiling in a training set of 183 sarcomas and established a prognostic gene expression signature, complexity index in sarcomas (CINSARC), composed of 67 genes related to mitosis and chromosome management. In a multivariate analysis, CINSARC predicts metastasis outcome in the training set and in an independent 127 sarcomas validation set. It is superior to the Fédération Francaise des Centres de Lutte Contre le Cancer grading system in determining metastatic outcome for sarcoma patients. Furthermore, it also predicts outcome for gastrointestinal stromal tumors (GISTs), breast carcinomas and lymphomas. Application of the signature will permit more selective use of adjuvant therapies for people with sarcomas, leading to decreased iatrogenic morbidity and improved outcomes for such individuals.

New prognostic factors and calculators for outcome prediction in patients with recurrent glioblastoma: A pooled analysis of EORTC Brain Tumour Group phase I and II clinical trials.

BACKGROUND: Prognostic models have been developed to predict survival of patients with newly diagnosed glioblastoma (GBM). To improve predictions, models should be updated with information at the recurrence. We performed a pooled analysis of European Organization for Research and Treatment of Cancer (EORTC) trials on recurrent glioblastoma to validate existing clinical prognostic factors, identify new markers, and derive new predictions for overall survival (OS) and progression free survival (PFS).¦METHODS: Data from 300 patients with recurrent GBM recruited in eight phase I or II trials conducted by the EORTC Brain Tumour Group were used to evaluate patient's age, sex, World Health Organisation (WHO) performance status (PS), presence of neurological deficits, disease history, use of steroids or anti-epileptics and disease characteristics to predict PFS and OS. Prognostic calculators were developed in patients initially treated by chemoradiation with temozolomide.¦RESULTS: Poor PS and more than one target lesion had a significant negative prognostic impact for both PFS and OS. Patients with large tumours measured by the maximum diameter of the largest lesion (⩾42mm) and treated with steroids at baseline had shorter OS. Tumours with predominant frontal location had better survival. Age and sex did not show independent prognostic values for PFS or OS.¦CONCLUSIONS: This analysis confirms performance status but not age as a major prognostic factor for PFS and OS in recurrent GBM. Patients with multiple and large lesions have an increased risk of death. With these data prognostic calculators with confidence intervals for both medians and fixed time probabilities of survival were derived.