Bharat Rao

Development and External Validation of Prognostic Model for 2-Year Survival of Non–Small-Cell Lung Cancer Patients Treated With Chemoradiotherapy

PURPOSEnRadiotherapy, combined with chemotherapy, is the treatment of choice for a large group of non-small-cell lung cancer (NSCLC) patients. Recent developments in the treatment of these patients have led to improved survival. However, the clinical TNM stage is highly inaccurate for the prediction of survival, and alternatives are lacking. The objective of this study was to develop and validate a prediction model for survival of NSCLC patients, treated with chemoradiotherapy.nnnPATIENTS AND METHODSnThe clinical data from 377 consecutive inoperable NSCLC patients, Stage I-IIIB, treated radically with chemoradiotherapy were collected. A prognostic model for 2-year survival was developed, using 2-norm support vector machines. The performance of the model was expressed as the area under the curve of the receiver operating characteristic and assessed using leave-one-out cross-validation, as well as two external data sets.nnnRESULTSnThe final multivariate model consisted of gender, World Health Organization performance status, forced expiratory volume in 1 s, number of positive lymph node stations, and gross tumor volume. The area under the curve, assessed by leave-one-out cross-validation, was 0.74, and application of the model to the external data sets yielded an area under the curve of 0.75 and 0.76. A high- and low-risk group could be clearly identified using a risk score based on the model.nnnCONCLUSIONnThe multivariate model performed very well and was able to accurately predict the 2-year survival of NSCLC patients treated with chemoradiotherapy. The model could support clinicians in the treatment decision-making process.

The importance of patient characteristics for the prediction of radiation-induced lung toxicity

PURPOSEnExtensive research has led to the identification of numerous dosimetric parameters as well as patient characteristics, associated with lung toxicity, but their clinical usefulness remains largely unknown. We investigated the predictive value of patient characteristics in combination with established dosimetric parameters.nnnPATIENTS AND METHODSnData from 438 lung cancer patients treated with (chemo)radiation were used. Lung toxicity was scored using the Common Toxicity Criteria version 3.0. A multivariate model as well as two single parameter models, including either V(20) or MLD, was built. Performance of the models was expressed as the AUC (Area Under the Curve).nnnRESULTSnThe mean MLD was 13.5 Gy (SD 4.5 Gy), while the mean V(20) was 21.0% (SD 7.3%). Univariate models with V(20) or MLD both yielded an AUC of 0.47. The final multivariate model, which included WHO-performance status, smoking status, forced expiratory volume (FEV(1)), age and MLD, yielded an AUC of 0.62 (95% CI: 0.55-0.69).nnnCONCLUSIONSnWithin the range of radiation doses used in our clinic, dosimetric parameters play a less important role than patient characteristics for the prediction of lung toxicity. Future research should focus more on patient-related factors, as opposed to dosimetric parameters, in order to identify patients at high risk for developing radiation-induced lung toxicity more accurately.

Development and Validation of a Prognostic Model Using Blood Biomarker Information for Prediction of Survival of Non-Small-Cell Lung Cancer Patients Treated With Combined Chemotherapy and Radiation or Radiotherapy Alone (NCT00181519, NCT00573040, and NCT00572325).

PURPOSEnCurrently, prediction of survival for non-small-cell lung cancer patients treated with (chemo)radiotherapy is mainly based on clinical factors. The hypothesis of this prospective study was that blood biomarkers related to hypoxia, inflammation, and tumor load would have an added prognostic value for predicting survival.nnnMETHODS AND MATERIALSnClinical data and blood samples were collected prospectively (NCT00181519, NCT00573040, and NCT00572325) from 106 inoperable non-small-cell lung cancer patients (Stages I-IIIB), treated with curative intent with radiotherapy alone or combined with chemotherapy. Blood biomarkers, including lactate dehydrogenase, C-reactive protein, osteopontin, carbonic anhydrase IX, interleukin (IL) 6, IL-8, carcinoembryonic antigen (CEA), and cytokeratin fragment 21-1, were measured. A multivariate model, built on a large patient population (N = 322) and externally validated, was used as a baseline model. An extended model was created by selecting additional biomarkers. The models performance was expressed as the area under the curve (AUC) of the receiver operating characteristic and assessed by use of leave-one-out cross validation as well as a validation cohort (n = 52).nnnRESULTSnThe baseline model consisted of gender, World Health Organization performance status, forced expiratory volume, number of positive lymph node stations, and gross tumor volume and yielded an AUC of 0.72. The extended model included two additional blood biomarkers (CEA and IL-6) and resulted in a leave-one-out AUC of 0.81. The performance of the extended model was significantly better than the clinical model (p = 0.004). The AUC on the validation cohort was 0.66 and 0.76, respectively.nnnCONCLUSIONSnThe performance of the prognostic model for survival improved markedly by adding two blood biomarkers: CEA and IL-6.

Subgroup Discovery for Test Selection: A Novel Approach and Its Application to Breast Cancer Diagnosis

We propose a new approach to test selection based on the discovery of subgroups of patients sharing the same optimal test, and present its application to breast cancer diagnosis. Subgroups are defined in terms of background information about the patient. We automatically determine the best t subgroups a patient belongs to, and decide for the test proposed by their majority. We introduce the concept of prediction quality to measure how accurate the test outcome is regarding the disease status. The quality of a subgroup is then the best mean prediction quality of its members (choosing the same test for all). Incorporating the quality computation in the search heuristic enables a significant reduction of the search space. In experiments on breast cancer diagnosis data we showed that it is faster than the baseline algorithm APRIORI-SD while preserving its accuracy.

A new, accurate predictive model for incident hypertension.

Objective: Data mining represents an alternative approach to identify new predictors of multifactorial diseases. This work aimed at building an accurate predictive model for incident hypertension using data mining procedures. Methods: The primary study population consisted of 1605 normotensive individuals aged 20–79 years with 5-year follow-up from the population-based study, that is the Study of Health in Pomerania (SHIP). The initial set was randomly split into a training and a testing set. We used a probabilistic graphical model applying a Bayesian network to create a predictive model for incident hypertension and compared the predictive performance with the established Framingham risk score for hypertension. Finally, the model was validated in 2887 participants from INTER99, a Danish community-based intervention study. Results: In the training set of SHIP data, the Bayesian network used a small subset of relevant baseline features including age, mean arterial pressure, rs16998073, serum glucose and urinary albumin concentrations. Furthermore, we detected relevant interactions between age and serum glucose as well as between rs16998073 and urinary albumin concentrations [area under the receiver operating characteristic (AUC 0.76)]. The model was confirmed in the SHIP validation set (AUC 0.78) and externally replicated in INTER99 (AUC 0.77). Compared to the established Framingham risk score for hypertension, the predictive performance of the new model was similar in the SHIP validation set and moderately better in INTER99. Conclusion: Data mining procedures identified a predictive model for incident hypertension, which included innovative and easy-to-measure variables. The findings promise great applicability in screening settings and clinical practice.

Fast semi-supervised SVM classifiers using a priori metric information

This paper describes a support vector machine-based (SVM) parametric optimization method for semi-supervised classification, called LIAM (for linear hyperplane classifier with a priori metric information). Our method takes advantage of similarity information to leverage the unlabelled data in training SVMs. In addition to the smoothness constraints in existing semi-supervised methods, LIAM incorporates local class similarity constraints, that we empirically show, improved the accuracies in the presence of a few labelled points. We present and discuss a general convex mathematical-programming-based formulation to solve the inductive semi-supervised problem; i.e. our proposed algorithm directly classifies test samples not present when training. This general formulation results in different variants depending on the choice of the norms that are used in the objective function. For example, when using the 1-norm the proposed formulation becomes a linear programming problem that has the advantage of generating sparse solutions depending on a minimal set of the original features (feature selection). On the other hand, one of the proposed formulations results in an unconstrained quadratic problem for which solutions can be obtained by solving a simple system of linear equations, resulting in a fast competitive alternative to state-of-the-art semi-supervised algorithms. Our experiments on public benchmarks indicate that LIAM is at least one order of magnitude faster and at least as or more accurate (in most of the cases) than other state-of-the-art semi-supervised classification methods.

Sparse classifiers for Automated HeartWall Motion Abnormality Detection

Coronary Heart Disease is the single leading cause of death world-wide, with lack of early diagnosis being a key contributory factor. This disease can be diagnosed by measuring and scoring regional motion of the heart wall in echocardiography images of the left ventricle (LV) of the heart. We describe a completely automated and robust technique that detects diseased hearts based on automatic detection and tracking of the endocardium and epicardium of the LV. We describe a novel feature selection technique based on mathematical programming that results in a robust hyperplane-based classifier. The classifier depends only on a small subset of numerical feature extracted from dualcontours tracked through time. We verify the robustness of our system on echocardiograms collected in routine clinical practice at one hospital, both with the standard crossvalidation analysis, and then on a held-out set of completely unseen echocardiography images.

Federated ontology search for the medical domain

In this paper we describe a novel methodology for retrieving and combining information from multiple ontologies for the medical domain. In the last decades the number and diversity of available ontologies for the medical domain has grown considerably. The variety and number of such resources available makes the cost to integrate them into an application incremental, often prohibitive for exploratory prototyping, and discouraging for larger-scale integration. Cross-ontology localized merging is proposed as a way to allow for a flexible and scalable solution. This approach also indicates a low maintenance cost and high reusability for different application types within the medical domain

Introduction to the special section on clinical data mining

Mining clinical data is a fast-evolving field, ranging from mining patient data of a particular type (e.g., images, genomics) to mining the increased amount of mixed-format information (databases, free text, images, labs, etc) in electronic health records (EHR), to selecting, extracting and synthesizing relevant knowledge from large medical corpuses, to the promise of personalized medicine where therapy and prevention are tailored to smaller and smaller patient subpopulations, down to the individual patient. Clinical data mining can be a key asset in driving vast systemic improvements in healthcare, leading to improved patient outcomes and reduced healthcare costs. In this report we briefly survey the latest advancements in this field, and introduce four selected articles that cover both state-of-the-art data mining techniques for clinical data and discuss emerging clinical data mining applications.

WE‐EF‐210‐01: Advances in Coherent Image Formation and Volume Imaging in Ultrasound

Recent advances in ultrasound-related technologies have had a significant impact on enhancing image quality as well as offering new approaches for quantitative ultrasonic imaging and therapeutic applications. The presentations associated with this session will provide an overview of advances in ultrasoundnimage formation, the development of using nanoparticles for therapeuticnultrasound applications, as well as approaches for assessing the intrinsic viscoelastic properties of tissue and methods for monitoring tissue response to therapy.nLearning Objectives:n1.xa0nDevelop a general understanding of new technologies associated with enhanced ultrasoundnimage formation and volume imaging.n2.xa0nDevelop an understanding of new ultrasound-based technologies for quantitative assessment of intrinsic tissue properties.n3.xa0nDevelop an understanding of novel approaches for ultrasound-mediated non-invasive therapeutic applications.nDr. Rao is an employee of Siemens Ultrasound