Reflections on Partial Least Squares Path Modeling

The purpose of the present article is to take stock of a recent exchange in Organizational Research Methods between critics (Rönkkö & Evermann, 2013) and proponents (Henseler et al., 2014) of partial least squares path modeling (PLS-PM). The two target articles were centered around six principal issues, namely whether PLS-PM: (1) can be truly characterized as a technique for structural equation modeling (SEM); (2) is able to correct for measurement error; (3) can be used to validate measurement models; (4) accommodates small sample sizes; (5) is able to provide null hypothesis tests for path coefficients; and (6) can be employed in an exploratory, model-building fashion. We summarize and elaborate further on the key arguments underlying the exchange, drawing from the broader methodological and statistical literature in order to offer additional thoughts concerning the utility of PLS-PM and ways in which the technique might be improved. We conclude with recommendations as to whether and how PLS-PM serves as a viable contender to SEM approaches for estimating and evaluating theoretical models.

A comparative study on inter and intralaboratory reproducibility of renin measurement with a conventional enzymatic method and a new chemiluminescent assay of immunoreactive renin.

BACKGROUND: The activity of the renin-angiotensin system is usually evaluated as plasma renin activity (PRA, ngAI/ml per h) but the reproducibility of this enzymatic assay is notoriously scarce. We compared the inter and intralaboratory reproducibilities of PRA with those of a new automated chemiluminescent assay, which allows the direct quantification of immunoreactive renin [chemiluminescent immunoreactive renin (CLIR), microU/ml]. METHODS: Aliquots from six pool plasmas of patients with very low to very high PRA levels were measured in 12 centres with both the enzymatic and the direct assays. The same methods were applied to three control plasma preparations with known renin content. RESULTS: In pool plasmas, mean PRA values ranged from 0.14 +/- 0.08 to 18.9 +/- 4.1 ngAI/ml per h, whereas those of CLIR ranged from 4.2 +/- 1.7 to 436 +/- 47 microU/ml. In control plasmas, mean values of PRA and of CLIR were always within the expected range. Overall, there was a significant correlation between the two methods (r = 0.73, P < 0.01). Similar correlations were found in plasmas subdivided in those with low, intermediate and high PRA. However, the coefficients of variation among laboratories found for PRA were always higher than those of CLIR, ranging from 59.4 to 17.1% for PRA, and from 41.0 to 10.7% for CLIR (P < 0.01). Also, the mean intralaboratory variability was higher for PRA than for CLIR, being respectively, 8.5 and 4.5% (P < 0.01). CONCLUSION: The measurement of renin with the chemiluminescent method is a reliable alternative to PRA, having the advantage of a superior inter and intralaboratory reproducibility.

Inequality measurement for ordered response health data

When health status is an ordered response variable, Allison and Foster (2004)postulate that a distribution Q exhibits more inequality than a distribution P if Q is obtained from P via a sequence of median preserving spreads. This paper introduces a parametric family of inequality indices which are founded on the Allison and Foster ordering. [Authors]

The value of intraoperative ultrasound in oblique corpectomy for cervical spondylotic myelopathy and ossified posterior longitudinal ligament.

Intraoperative ultrasound (IOUS) has been described to be useful during central corpectomy for compressive cervical myelopathy. This study aimed at documenting the utility of IOUS in oblique cervical corpectomy (OCC). Prospective data from 24 patients undergoing OCC for cervical spondylotic myelopathy and ossified posterior longitudinal ligament (OPLL) were collected. Patients had a preoperative cervical spine magnetic resonance (MR) image, IOUS and a postoperative cervical CT scan. Retrospective data from 16 historical controls that underwent OCC without IOUS were analysed to compare the incidence of residual compression between the two groups. IOUS identified the vertebral artery in all cases, detected residual cord compression in six (27%) and missed compression in two cases (9%). In another two cases with OPLL, IOUS was sub-optimal due to shadowing. IOUS measurement of the corpectomy width correlated well with these measurements on the postoperative CT. The extent of cord expansion noted on IOUS after decompression showed no correlation with immediate or 6-month postoperative neurological recovery. No significant difference in residual compression was noted in the retrospective and prospective groups of the study. Craniocaudal spinal cord motion was noted after the completion of the corpectomy. IOUS is an inexpensive and simple real-time imaging modality that may be used during OCC for cervical spondylotic myelopathy. It is helpful in identifying the vertebral artery and determining the trajectory of approach, however, it has limited utility in patients with OPLL due to artifacts from residual ossification.

A New Approach for the Carbon Monoxide (CO) Exposure Diagnosis: Measurement of Total CO in Human Blood Versus Carboxyhemoglobin (HbCO).

The aim of the study is to present the application of a headspace-gas chromatography-mass spectrometry (HS-GC-MS) method for the determination of the carbon monoxide (CO) blood concentration and to compare it with carboxyhemoglobin (HbCO) saturation. In postmortem cases, the HbCO measured by spectrophotometry frequently leads to inaccurate results due to inadequate samples or analyses. The true role of CO intoxication in the death of a person could be misclassified. The estimation of HbCO from HS-GC-MS CO measurements provides helpful information by determining the total CO levels (CO linked to hemoglobin (HbCO) and CO dissociated from hemoglobin). The CO concentrations were converted in HbCO saturation levels to define cutoff blood CO values. CO limits were defined as less than 1 μmol/mL for living persons, less than 1.5 μmol/mL for dead persons without CO exposure, and greater than 3 μmol/mL for dead persons with clear CO poisoning.

Accuracy profile validation of a new analytical method for propane measurement using headspace-gas chromatography-mass spectrometry

Propane can be responsible for several types of lethal intoxication and explosions. Quantifying it would be very helpful to determine in some cases the cause of death. Some gas chromatography-mass spectrometry (GC-MS) methods of propane measurements do already exist. The main drawback of these GC-MS methods described in the literature is the absence of a specific propane internal standard necessary for accurate quantitative analysis. The main outcome of the following study was to provide an innovative Headspace-GC-MS method (HS-GC-MS) applicable to the routine determination of propane concentration in forensic toxicology laboratories. To date, no stable isotope of propane is commercially available. The development of an in situ generation of standards is thus presented. An internal-labeled standard gas (C3DH7) is generated in situ by the stoichiometric formation of propane by the reaction of deuterated water (D2O) with Grignard reagent propylmagnesium chloride (C3H7MgCl). The method aims to use this internal standard to quantify propane concentrations and, therefore, to obtain precise measurements. Consequently, a complete validation with an accuracy profile according to two different guidelines, the French Society of Pharmaceutical Sciences and Techniques (SFSTP) and the Gesellschaft für toxikologische und Forensische Chemie (GTFCh), is presented.

Analytical interference of 4-hydroxy-3-methoxymethamphetamine with the measurement of plasma free normetanephrine by ultra-high pressure liquid chromatography-tandem mass spectrometry.

OBJECTIVES: The diagnosis of pheochromocytoma relies on the measurement of plasma free metanephrines assay whose reliability has been considerably improved by ultra-high pressure liquid chromatography tandem mass spectrometry (UHPLC-MS/MS). Here we report an analytical interference occurring between 4-hydroxy-3-methoxymethamphetamine (HMMA), a metabolite of 3,4-methylenedioxymethamphetamine (MDMA, "Ecstasy"), and normetanephrine (NMN) since they share a common pharmacophore resulting in the same product ion after fragmentation. DESIGN AND METHODS: Synthetic HMMA was spiked into plasma samples containing various concentrations of NMN and the intensity of the interference was determined by UPLC-MS/MS before and after improvement of the analytical method. RESULTS: Using a careful adjustment of chromatographic conditions including the change of the UPLC analytical column, we were able to distinguish both compounds. HMMA interference for NMN determination should be seriously considered since MDMA activates the sympathetic nervous system and if confounded with NMN may lead to false-positive tests when performing a differential diagnostic of pheochromocytoma.

Cell-mediated immunity to predict cytomegalovirus disease in high-risk solid organ transplant recipients.

Late-onset cytomegalovirus (CMV) disease commonly occurs after discontinuation of antiviral prophylaxis. We determined the utility of testing CD8+ T-cell response against CMV as a predictor of late-onset CMV disease after a standard course of antiviral prophylaxis. Transplant patients at high-risk for CMV disease were enrolled. CD8+ T-cell-mediated immunity (CMI) was tested using the QuantiFERON-CMV assay at baseline, 1, 2 and 3 months posttransplant by measurement of interferon-gamma response to whole blood stimulation with a 21-peptide pool. The primary outcome was the ability of CMI testing to predict CMV disease in the first 6 months posttransplant. There were 108 evaluable patients (D+/R+ n = 39; D-/R+ n = 34; D+/R- n = 35) of whom 18 (16.7%) developed symptomatic CMV disease. At the end of prophylaxis, CMI was detectable in 38/108 (35.2%) patients (cutoff 0.1 IU/mL interferon-gamma). CMV disease occurred in 2/38 (5.3%) patients with a detectable interferon-gamma response versus 16/70 (22.9%) patients with a negative response; p = 0.038. In the subgroup of D+/R- patients, CMV disease occurred in 1/10 (10.0%) patients with a detectable interferon-gamma response (cutoff 0.1 IU/mL) versus 10/25 (40.0%) patients with a negative CMI, p = 0.12. Monitoring of CMI may be useful for predicting late-onset CMV disease.

Measurement of the mechanical power of walking by satellite positioning system (GPS).

PURPOSE: This descriptive article illustrates the application of Global Positioning System (GPS) professional receivers in the field of locomotion studies. The technological challenge was to assess the external mechanical work in outdoor walking. METHODS: Five subjects walked five times during 5 min on an athletic track at different imposed stride frequency (from 70-130 steps x min(-1)). A differential GPS system (carrier phase analysis) measured the variation of the position of the trunk at 5 Hz. A portable indirect calorimeter recorded breath-by-breath energy expenditure. RESULTS: For a walking speed of 1.05 +/- 0.11 m x s(-1), the vertical lift of the trunk (43 +/- 14 mm) induced a power of 46.0 +/- 20.4 W. The average speed variation per step (0.15 +/- 0.03 m x s(-1)) produced a kinetic power of 16.9 +/- 7.2 W. As compared with commonly admitted values, the energy exchange (recovery) between the two energy components was low (39.1 +/- 10.0%), which induced an overestimated mechanical power (38.9 +/- 18.3 W or 0.60 W x kg(-1) body mass) and a high net mechanical efficiency (26.9 +/- 5.8%). CONCLUSION: We assumed that the cause of the overestimation was an unwanted oscillation of the GPS antenna. It is concluded that GPS (in phase mode) is now able to record small body movements during human locomotion, and constitutes a promising tool for gait analysis of outdoor unrestrained walking. However, the design of the receiver and the antenna must be adapted to human experiments and a thorough validation study remains to be conducted.

Measurement of β-tryptase in postmortem serum in cardiac deaths. [Measurement of beta-tryptase in postmortem serum in cardiac deaths]

Mast cells are well known for their role in hypersensitivity reactions. However, there is increasing evidence that they might also participate in both developing and weakening atherosclerotic plaques, potentially causing plaque instability. Some clinical studies have therefore postulated the existence of relationships between blood β-tryptase levels and acute coronary syndromes. In this study, we investigated postmortem serum β-tryptase levels in a series of 90 autopsy cases with various degrees of coronary atherosclerosis that had undergone medico-legal investigations. β-tryptase concentrations in these cases were compared to levels observed in 6 fatal anaphylaxis cases following contrast material administration. Postmortem serum β-tryptase concentrations in the anaphylactic deaths ranged from 146 to 979 ng/ml. In 9 out of 90 cases of cardiac deaths, β-tryptase levels were higher than clinical reference values of 11.4 ng/ml and ranged from 21 to 65 ng/ml. These results indicate that increased postmortem serum β-tryptase levels can be observed, though not systematically, in cardiac deaths with varying degrees of coronary atherosclerosis disease, thereby suggesting that mast cell activation in this disease cannot be ascertained by postmortem serum β-tryptase measurements.

The Europeanisation of the measurement of diversity in education: a soft instrument of public policy

Faced with an increasing number of data and rankings, the author questions the roles of the different groups of actors who were originally involved in questioning the use of statistical indicators as a means of addressing issues of access to higher education. The comparison and nature of these international (UNESCO, OECD, EUROSTAT) and national (Germany, England, France, Switzerland) indicators in matters of inequalities of access to higher education question the tension between the discourses and the indicators they generate, and their recording at the national level. Who says what and with what consequences? What range of actors are involved in this process? What kind of power relations forms them? The author discusses how the issue of inequalities of access to higher education got on to the agendas of European organisations, identifies the policies that were defined, and sets them against an array of indicators, showing the discrepancy between the discourses and what the indicators reveal, the gap between the recommendations and the available tools. Why is there such a contrast? What are the mechanisms at work? Is it a technical or a political problem? What does this discrepancy reveal as far as national specificities within the construction of social inequalities are concerned?

Inequality measurement for ordered response health data

Because self-reported health status [SRHS] is an ordered response variable, inequality measurement for SRHS data requires a numerical scale for converting individual responses into a summary statistic. The choice of scale is however problematic, since small variations in the numerical scale may reverse the ordering of a given pair of distributions of SRHS data in relation to conventional inequality indices such as the variance. This paper introduces a parametric family of inequality indices, founded on an inequality ordering proposed by Allison and Foster [Allison, R.A., Foster, J., 2004. Measuring health inequalities using qualitative data. Journal of Health Economics 23, 505-524], which satisfy a suitable invariance property with respect to the choice of numerical scale. Several key members of the parametric family are also derived, and an empirical application using data from the Swiss Health Survey illustrates the proposed methodology. [Authors]

Characterization of cerebral glucose dynamics in vivo with a four-state conformational model of transport at the blood-brain barrier.

Determination of brain glucose transport kinetics in vivo at steady-state typically does not allow distinguishing apparent maximum transport rate (T(max)) from cerebral consumption rate. Using a four-state conformational model of glucose transport, we show that simultaneous dynamic measurement of brain and plasma glucose concentrations provide enough information for independent and reliable determination of the two rates. In addition, although dynamic glucose homeostasis can be described with a reversible Michaelis-Menten model, which is implicit to the large iso-inhibition constant (K(ii)) relative to physiological brain glucose content, we found that the apparent affinity constant (K(t)) was better determined with the four-state conformational model of glucose transport than with any of the other models tested. Furthermore, we confirmed the utility of the present method to determine glucose transport and consumption by analysing the modulation of both glucose transport and consumption by anaesthesia conditions that modify cerebral activity. In particular, deep thiopental anaesthesia caused a significant reduction of both T(max) and cerebral metabolic rate for glucose consumption. In conclusion, dynamic measurement of brain glucose in vivo in function of plasma glucose allows robust determination of both glucose uptake and consumption kinetics.

Computer Aided Detection and measurement of peripheral artery disease.

Computer-Aided Tomography Angiography (CTA) images are the standard for assessing Peripheral artery disease (PAD). This paper presents a Computer Aided Detection (CAD) and Computer Aided Measurement (CAM) system for PAD. The CAD stage detects the arterial network using a 3D region growing method and a fast 3D morphology operation. The CAM stage aims to accurately measure the artery diameters from the detected vessel centerline, compensating for the partial volume effect using Expectation Maximization (EM) and a Markov Random field (MRF). The system has been evaluated on phantom data and also applied to fifteen (15) CTA datasets, where the detection accuracy of stenosis was 88% and the measurement accuracy was with an 8% error.

Dépistage du cancer de la prostate: utilité, buts et perspectives en 2010 [Prostate cancer screening: utility, goals and perspectives in 2010].

According to recent results of a sub-group of 20,000 patients from the ERSPC study, prostate cancer screening significantly increases disease specific survival for men with a life expectancy of 15 years. However presently, only 20% of prostate biopsies lead to the diagnosis of cancer. This low yield may be increased by using new tools on their way to validation, such as the blood and urinary markers p2-PSA and PCA3, so as MRI and tridimensional computerized echography. Finally, the tumours detected must be managed with subtlety, since a third of them are not overtly aggressive clinically. Hence, a significant proportion of such tumours may not need immediate curative intent treatment, and can be followed up in an active surveillance protocol.