Interobserver reliability of classification and characterization of proximal humeral fractures: a comparison of two and three-dimensional CT

Interobserver reliability for the classification of proximal humeral fractures is limited. The aim of this study was to test the null hypothesis that interobserver reliability of the AO classification of proximal humeral fractures, the preferred treatment, and fracture characteristics is the same for two-dimensional (2-D) and three-dimensional (3-D) computed tomography (CT). Members of the Science of Variation Group--fully trained practicing orthopaedic and trauma surgeons from around the world--were randomized to evaluate radiographs and either 2-D CT or 3-D CT images of fifteen proximal humeral fractures via a web-based survey and respond to the following four questions: (1) Is the greater tuberosity displaced? (2) Is the humeral head split? (3) Is the arterial supply compromised? (4) Is the glenohumeral joint dislocated? They also classified the fracture according to the AO system and indicated their preferred treatment of the fracture (operative or nonoperative). Agreement among observers was assessed with use of the multirater kappa (κ) measure. Interobserver reliability of the AO classification, fracture characteristics, and preferred treatment generally ranged from "slight" to "fair." A few small but statistically significant differences were found. Observers randomized to the 2-D CT group had slightly but significantly better agreement on displacement of the greater tuberosity (κ = 0.35 compared with 0.30, p < 0.001) and on the AO classification (κ = 0.18 compared with 0.17, p = 0.018). A subgroup analysis of the AO classification results revealed that shoulder and elbow surgeons, orthopaedic trauma surgeons, and surgeons in the United States had slightly greater reliability on 2-D CT, whereas surgeons in practice for ten years or less and surgeons from other subspecialties had slightly greater reliability on 3-D CT. Proximal humeral fracture classifications may be helpful conceptually, but they have poor interobserver reliability even when 3-D rather than 2-D CT is utilized. This may contribute to the similarly poor interobserver reliability that was observed for selection of the treatment for proximal humeral fractures. The lack of a reliable classification confounds efforts to compare the outcomes of treatment methods among different clinical trials and reports.

Relationship between Clinical Macular Changes and Retinal Function in Age-Related Macular Degeneration

Purpose

Towards a classification of biomarkers of neuropsychiatric disease: from encompass to compass

There is currently considerable imprecision in the nosology of biomarkers used in the study of neuropsychiatric disease. The neuropsychiatric field lags behind others such as oncology, wherein, rather than using 'biomarker' as a blanket term for a diverse range of clinical phenomena, biomarkers have been actively classified into separate categories, including prognostic and predictive tests. A similar taxonomy is proposed for neuropsychiatric diseases in which the core biology remains relatively unknown. This paper divides potential biomarkers into those of (1) risk, (2) diagnosis/trait, (3) state or acuity, (4) stage, (5) treatment response and (6) prognosis, and provides illustrative exemplars. Of course, biomarkers rely on available technology and, as we learn more about the neurobiological correlates of neuropsychiatric disorders, we will realize that the classification of biomarkers across these six categories can change, and some markers may fit into more than one category.Molecular Psychiatry advance online publication, 28 October 2014; doi:10.1038/mp.2014.139.

Breast cancer prognosis risk estimation using integrated gene expression and clinical data

Novel prognostic markers are needed so newly diagnosed breast cancer patients do not undergo any unnecessary therapy. Various microarray gene expression datasets based studies have generated gene signatures to predict the prognosis outcomes, while ignoring the large amount of information contained in established clinical markers. Nevertheless, small sample sizes in individual microarray datasets remain a bottleneck in generating robust gene signatures that show limited predictive power. The aim of this study is to achieve high classification accuracy for the good prognosis group and then achieve high classification accuracy for the poor prognosis group.

Depression and suicidal behavior in adolescents : a multi-informant and multi-methods approach to diagnostic classification

Informant discrepancies have been reported between parent and adolescent measures of depressive disorders and suicidality. We aimed to examine the concordance between adolescent and parent ratings of depressive disorder using both clinical interview and questionnaire measures and assess multi-informant and multi-method approaches to classification.

Stable feature selection for clinical prediction: Exploiting ICD tree structure using Tree-Lasso

Modern healthcare is getting reshaped by growing Electronic Medical Records (EMR). Recently, these records have been shown of great value towards building clinical prediction models. In EMR data, patients' diseases and hospital interventions are captured through a set of diagnoses and procedures codes. These codes are usually represented in a tree form (e.g. ICD-10 tree) and the codes within a tree branch may be highly correlated. These codes can be used as features to build a prediction model and an appropriate feature selection can inform a clinician about important risk factors for a disease. Traditional feature selection methods (e.g. Information Gain, T-test, etc.) consider each variable independently and usually end up having a long feature list. Recently, Lasso and related l1-penalty based feature selection methods have become popular due to their joint feature selection property. However, Lasso is known to have problems of selecting one feature of many correlated features randomly. This hinders the clinicians to arrive at a stable feature set, which is crucial for clinical decision making process. In this paper, we solve this problem by using a recently proposed Tree-Lasso model. Since, the stability behavior of Tree-Lasso is not well understood, we study the stability behavior of Tree-Lasso and compare it with other feature selection methods. Using a synthetic and two real-world datasets (Cancer and Acute Myocardial Infarction), we show that Tree-Lasso based feature selection is significantly more stable than Lasso and comparable to other methods e.g. Information Gain, ReliefF and T-test. We further show that, using different types of classifiers such as logistic regression, naive Bayes, support vector machines, decision trees and Random Forest, the classification performance of Tree-Lasso is comparable to Lasso and better than other methods. Our result has implications in identifying stable risk factors for many healthcare problems and therefore can potentially assist clinical decision making for accurate medical prognosis.

A novel aggregate gene selection method for microarray data classification

This paper introduces a novel method for gene selection based on a modification of analytic hierarchy process (AHP). The modified AHP (MAHP) is able to deal with quantitative factors that are statistics of five individual gene ranking methods: two-sample t-test, entropy test, receiver operating characteristic curve, Wilcoxon test, and signal to noise ratio. The most prominent discriminant genes serve as inputs to a range of classifiers including linear discriminant analysis, k-nearest neighbors, probabilistic neural network, support vector machine, and multilayer perceptron. Gene subsets selected by MAHP are compared with those of four competing approaches: information gain, symmetrical uncertainty, Bhattacharyya distance and ReliefF. Four benchmark microarray datasets: diffuse large B-cell lymphoma, leukemia cancer, prostate and colon are utilized for experiments. As the number of samples in microarray data datasets are limited, the leave one out cross validation strategy is applied rather than the traditional cross validation. Experimental results demonstrate the significant dominance of the proposed MAHP against the competing methods in terms of both accuracy and stability. With a benefit of inexpensive computational cost, MAHP is useful for cancer diagnosis using DNA gene expression profiles in the real clinical practice.

Hidden Markov models for cancer classification using gene expression profiles

This paper introduces an approach to cancer classification through gene expression profiles by designing supervised learning hidden Markov models (HMMs). Gene expression of each tumor type is modelled by an HMM, which maximizes the likelihood of the data. Prominent discriminant genes are selected by a novel method based on a modification of the analytic hierarchy process (AHP). Unlike conventional AHP, the modified AHP allows to process quantitative factors that are ranking outcomes of individual gene selection methods including t-test, entropy, receiver operating characteristic curve, Wilcoxon test and signal to noise ratio. The modified AHP aggregates ranking results of individual gene selection methods to form stable and robust gene subsets. Experimental results demonstrate the performance dominance of the HMM approach against six comparable classifiers. Results also show that gene subsets generated by modified AHP lead to greater accuracy and stability compared to competing gene selection methods, i.e. information gain, symmetrical uncertainty, Bhattacharyya distance, and ReliefF. The modified AHP improves the classification performance not only of the HMM but also of all other classifiers. Accordingly, the proposed combination between the modified AHP and HMM is a powerful tool for cancer classification and useful as a real clinical decision support system for medical practitioners.

Mass spectrometry cancer data classification using wavelets and genetic algorithm

This paper introduces a hybrid feature extraction method applied to mass spectrometry (MS) data for cancer classification. Haar wavelets are employed to transform MS data into orthogonal wavelet coefficients. The most prominent discriminant wavelets are then selected by genetic algorithm (GA) to form feature sets. The combination of wavelets and GA yields highly distinct feature sets that serve as inputs to classification algorithms. Experimental results show the robustness and significant dominance of the wavelet-GA against competitive methods. The proposed method therefore can be applied to cancer classification models that are useful as real clinical decision support systems for medical practitioners.

Study protocol: the registrar clinical encounters in training (ReCEnT) study

Background
Patient encounters are the core learning activity of Australian general practice (family practice) training. Exposure to patient demographics and presentations may vary from one general practice registrar (vocational trainee) to another. This can affect comprehensiveness of training. Currently, there is no mechanism to systematically capture the content of GP registrar consultations. The aim of the Registrar Clinical Encounters in Training (ReCEnT) study is to document longitudinally the nature and associations of consultation-based clinical and educational experiences of general practice registrars.
Methods/design
This is an ongoing prospective multi-site cohort study of general practice registrars’ consultations, entailing paper-based recording of consultation data. The study setting is general practices affiliated with three geographically-based Australian general practice regional training providers. Registrars record details of 60 consecutive consultations. Data collected includes registrar demographics, details of the consultation, patient demographics, reasons for encounter and problems managed. Problems managed are coded with the International Classification of Primary Care (second edition) classification system. Additionally, registrars record educational factors related to the encounter. The study will follow the clinical exposure of each registrar six-monthly over the 18 months to two years (full-time equivalent) of their general practice training program.
Conclusions
The study will provide data on a range of factors (patient, registrar and consultation factors). This data will be used to inform a range of educational decisions as well as being used to answer educational research questions. We plan to use ReCEnT as a formative assessment tool for registrars and help identify and address educational needs. The study will facilitate program evaluation by the participating training providers and thus improve articulation of educational programs with practice experience. From the research point of view it will address an evidence gap – the in-practice clinical and educational experience of general practice trainees, determinants of these experiences, and the determinants of registrars’ patterns of practice (for example, prescribing practice) over the course of their training.

A sociodemographic, clinical study of patients with venous ulcer

Background Venous ulcer is the most serious consequence of chronic venous insufficiency and is responsible for almost 70% of chronic leg ulcers. The main purpose of this research was to describe social, demographic and clinical characteristics of patients with venous ulcers and to identify some professional repercussions of this pathology.Subjects and methods We evaluated patients with a clinical picture compatible with venous ulcer. The sociodemographic characteristics of the patients, and the clinical characteristics and professional repercussions of the pathology were studied. We used the ankle-brachial index to identify associated arterial disease. The body mass index (BMI) was used for the classification of the nutritional condition of the patients.Results A total of 120 patients were included in the study (90 females and 30 males; 80.8% White; 44.2% > 60 years old). Ninety-one per cent of the patients had been in education for less than 4 years, and 89.7% were on the poverty line. Thirty-five per cent were retired, 2.5% were receiving government help due to disease and 4.2% were unemployed. About 16% of patients were out of work due to the disease, and 49.2% presented some degree of disability in terms of work tasks. The ulcer area was less than 30 cm(2) in 69.1% of patients. The first ulcer episode occurred in 13.4 years on average, and 64.2% of patients had recurrent episodes. Females presented on average 5.65 pregnancies, and 75.4% of patients were overweight.Conclusion Venous ulcer occurred mainly in the low-income population, who presented with little formal education. Generally, the ulcers were present for a long time and were recurrent, with repercussions for the capabilities of patients to work.

Critical analysis of the international classification of headache disorders diagnostic criteria (ICHD I-1988) and (ICHD II-2004), for migraine in children and adolescents

The present study analyzed the (ICHD I-1988) and ( ICHD II-2004) diagnostic criteria in children and adolescents. Our population consisted of 496 patients of the Headache Outpatient Ward for Children and Adolescents retrospectively studied from 1992 to 2002. Individuals were classified according to three diagnostic groups: Intuitive Clinical Diagnosis ( Gold Standard), ICHD I-1988 and ICHD II-2004. They were statistically compared using the variables: Sensitivity ( S), Specificity (Sp), Positive Predictive Value (PPV), Negative Predictive Value (NPV). When ICHD I-1988 was used, the sensitivity of migraine without and with aura was 21% and 27%, respectively, whereas in ICHD II-2004 it changed to 53% and 71% without affecting specificity. As a conclusion, the current classification criteria ( ICHD II-2004) showed greater sensitivity and high specificity for migraine than ICHD I-1988, although it improved migraine diagnosis in children and adolescents, the sensitivity remains poor.

Traumatic subdural hygromas: Proposed pathogenesis based classification

Background: Traumatic subdural hygroma (TSHy) is an accumulation of cerebrospinal fluid (CSF) in the subdural space after head injury. It appears to be relatively common, but its onset time and natural history are not well defined. Considered a benign epiphenomenon of trauma, the pathogenesis of TSHy is still unclear and many questions remain unanswered. This study adds to the information on TSHy, and proposes a classification based on pathogenesis.Methods: Thirty-four consecutive adult patients with TSHy were analyzed for clinical evolution and serial CT scan, during a period of several months. TSHy diagnosis was based on published CT scan criteria of hypodense subdural collection after trauma, without enhancement and neomembrane, with a minimum distance of 3 mm between the skull and brain. Ventricle size was analyzed by calculating the bicaudate index (BCI). For comparison, the BCI was measured from CT scan at three moments: admission, at time of TSHy diagnosis, and from last CT scan.Results: There were 34 patients, aged between 16 and 85 years (mean 40), half of them were below 40 years. Road traffic crashes were the main cause of head injury. The mean time for hygroma diagnosis was 9 days. Twenty-one patients (61.8%) underwent conservative treatment for TSHy and 13 (38.2%), surgical treatment. TSHy are early lesions and can be detected in the first 24 hours after trauma, usually as small subdural effusion (SSEff). Based on clinical and CT scan findings, we divided the 34 patients into 3 groups, (Ia and Ib) without evident mass effect and (II) with evident mass effect. Group Ia includes patients without ventricle dilation; Ib, patients with associated ventricle dilations.Conclusions: SSEff detected in the first 24 hours posttrauma in our series evolved into TSHy suggesting that this is an early lesion; all THSy were divided in three groups according to the pathophysiologic mechanism. These three groups probably represent a continuum of CSF absorption impairment. Group la represents what most authors consider a simple hygroma, with no impairment on CSF absorption. Group Ib represent the external hydrocephalus form with various degrees of CSF imbalance, and group II were the cases presenting marked mass effect.