Diagnostic Aid Tool Research Articles

Staining Pattern of Alcian Blue in Endometrial Cytology: Utility in Distinguishing Grade 1-Endometrial Endometrioid Carcinoma from Endometrial Glandular Stromal Breakdown.

In endometrial cytology, differentiating endometrial glandular stromal breakdown (EGBD) from endometrial endometrioid carcinoma (G1-EEC) is often difficult. In this study, we provided a new focus on chondroitin sulfate (CS), a major substrate component of the endometrial stroma, and assessed the diagnostic utility of Alcian Blue (AB) staining in the differential diagnosis in liquid-based cytological (LBC) samples. LBC specimens from 19 patients with a proliferative endometrium, 36 with EGBD, and 30 with G1-EEC who underwent endometrial cytology were stained with AB (pH 1.0), and their reactivity was observed. In addition, immunocytochemical staining of CS and CD31 was performed for five cases each to evaluate their interrelationship with blood vessels. Regarding the 30 G1-EEC cases, at least one of the three representative staining patterns was observed by AB staining: dot-like, microtubular, and finely branched linear patterns. Moreover, the inner portion of the tubular material observed by AB staining expressed CD31. Conversely, in the 36 EGBD cases, only five metaplastic clusters with irregular protrusions and condensed stromal clusters (CSCs) showed a dot-like positive pattern, and background CSCs did not show reactivity to AB staining in any of the cases. Furthermore, the vascular structure expressing CD31 in cell clusters was also unclear. We demonstrated that AB staining shows different staining patterns in G1-EEC and EGBD, reflecting their different tissue structures. Our data provide new insights into endometrial cell diagnosis changes and demonstrate that AB staining is a potential new diagnostic aid tool for the differentiation of G1-EEC from EGBD.

Automatic left ventricle volume and mass quantification from 2D cine-MRI: Investigating papillary muscle influence

ObjectiveEarly detection of cardiovascular diseases is based on accurate quantification of the left ventricle (LV) function parameters. In this paper, we propose a fully automatic framework for LV volume and mass quantification from 2D-cine MR images already segmented using U-Net. MethodsThe general framework consists of three main steps: Data preparation including automatic LV localization using a convolution neural network (CNN) and application of morphological operations to exclude papillary muscles from the LV cavity. The second step consists in automatically extracting the LV contours using U-Net architecture. Finally, by integrating temporal information which is manifested by a spatial motion of myocytes as a third dimension, we calculated LV volume, LV ejection fraction (LVEF) and left ventricle mass (LVM). Based on these parameters, we detected and quantified cardiac contraction abnormalities using Python software. ResultsCNN was trained with 35 patients and tested on 15 patients from the ACDC database with an accuracy of 99,15 %. U-Net architecture was trained using ACDC database and evaluated using local dataset with a Dice similarity coefficient (DSC) of 99,78 % and a Hausdorff Distance (HD) of 4.468 mm (p < 0,001). Quantification results showed a strong correlation with physiological measures with a Pearson correlation coefficient (PCC) of 0,991 for LV volume, 0.962 for LVEF, 0.98 for stroke volume (SV) and 0.923 for LVM after pillars’ elimination. Clinically, our method allows regional and accurate identification of pathological myocardial segments and can serve as a diagnostic aid tool of cardiac contraction abnormalities. ConclusionExperimental results prove the usefulness of the proposed method for LV volume and function quantification and verify its potential clinical applicability.

Voice acoustics allow classifying autism spectrum disorder with high accuracy

Early identification of children on the autism spectrum is crucial for early intervention with long-term positive effects on symptoms and skills. The need for improved objective autism detection tools is emphasized by the poor diagnostic power in current tools. Here, we aim to evaluate the classification performance of acoustic features of the voice in children with autism spectrum disorder (ASD) with respect to a heterogeneous control group (composed of neurotypical children, children with Developmental Language Disorder [DLD] and children with sensorineural hearing loss with Cochlear Implant [CI]). This retrospective diagnostic study was conducted at the Child Psychiatry Unit of Tours University Hospital (France). A total of 108 children, including 38 diagnosed with ASD (8.5 ± 0.25 years), 24 typically developing (TD; 8.2 ± 0.32 years) and 46 children with atypical development (DLD and CI; 7.9 ± 0.36 years) were enrolled in our studies. The acoustic properties of speech samples produced by children in the context of a nonword repetition task were measured. We used a Monte Carlo cross-validation with an ROC (Receiving Operator Characteristic) supervised k-Means clustering algorithm to develop a classification model that can differentially classify a child with an unknown disorder. We showed that voice acoustics classified autism diagnosis with an overall accuracy of 91% [CI95%, 90.40%-91.65%] against TD children, and of 85% [CI95%, 84.5%–86.6%] against an heterogenous group of non-autistic children. Accuracy reported here with multivariate analysis combined with Monte Carlo cross-validation is higher than in previous studies. Our findings demonstrate that easy-to-measure voice acoustic parameters could be used as a diagnostic aid tool, specific to ASD.

Dual Machine-Learning System to Aid Glaucoma Diagnosis Using Disc and Cup Feature Extraction

Glaucoma is a degenerative disease that affects vision, causing damage to the optic nerve that ends in vision loss. The classic techniques to detect it have undergone a great change since the intrusion of machine learning techniques into the processing of eye fundus images. Several works focus on training a convolutional neural network (CNN) by brute force, while others use segmentation and feature extraction techniques to detect glaucoma. In this work, a diagnostic aid tool to detect glaucoma using eye fundus images is developed, trained and tested. It consists of two subsystems that are independently trained and tested, combining their results to improve glaucoma detection. The first subsystem applies machine learning and segmentation techniques to detect optic disc and cup independently, combine them and extract their physical and positional features. The second one applies transfer learning techniques to a pre-trained CNN to detect glaucoma through the analysis of the complete eye fundus images. The results of both systems are combined to discriminate positive cases of glaucoma and improve final detection. The results show that this system achieves a higher classification rate than previous works. The system also provides information on the basis for the proposed diagnosis suggestion that can help the ophthalmologist to accept or modify it.

Fast fully automatic heart fat segmentation in computed tomography datasets

Heart diseases affect a large part of the world's population. Studies have shown that these diseases are related to cardiac fat. Various medical diagnostic aid systems are developed to reduce these diseases. In this context, this paper presents a new approach to the segmentation of cardiac fat from Computed Tomography (CT) images. The study employs a clustering algorithm called Floor of Log (FoL). The advantage of this method is the significant drop in segmentation time. Support Vector Machine was used to learn the best FoL algorithm parameter as well as mathematical morphology techniques for noise removal. The time to segment cardiac fat on a CT is only 2.01 s on average. In contrast, literature works require more than one hour to perform segmentation. Therefore, this job is one of the fastest to segment an exam completely. The value of the Accuracy metric was 93.45% and Specificity of 95.52%. The proposed approach is automatic and requires less computational effort. With these results, the use of this approach for the segmentation of cardiac fat proves to be efficient, besides having good application times. Therefore, it has the potential to be a medical diagnostic aid tool. Consequently, it is possible to help experts achieve faster and more accurate results.

The Role of Ultrasonography in Patients Referring to the Emergency Department with Acute Abdominal Pain.

Context:Acute abdominal pain is a common clinical problem in emergency and non-emergency cases accounting for 5 to 10% of all referrals to the emergency department. Studies have indicated that these widely differentiated diagnoses are common to these complaints. Considering the high prevalence of this complaint in the patients and the wide range of its differential diagnosis, this review study was designed and evaluated aiming at investigating the causes of acute abdominal pain with a focus on assessing the position of ultrasound as a diagnostic tool in the emergency department.Evidence acquisition:This article was conducted as a narrative review of selected articles from 2005 through 2019. By comparing them, a comprehensive review of ultrasound role was conducted in patients with acute abdominal pain referring to the emergency department.Results:In this review study, we attempted to use the articles of the clinical approach, the required laboratory tests, the disadvantages and advantages of each imaging technique, the differential diagnosis for acute abdominal pain according to the location of the pain, and the position of ultrasound as a diagnostic aid tool. Eventually, the proposed protrusion will be considered in dealing with a patient with acute abdominal pain.Conclusion:Regarding the wide range of causes providing multiple differential diagnosis, as well as the limited time of the health team in the emergency department for diagnostic and therapeutic measures, particularly in time-sensitive clinical conditions, ultrasound offered by emergency medicine specialists as a diagnostic aid is considered to improve the overall diagnosis and treatment of patients, thereby reducing complications.

Software for adult cardiac dynamic through dynamic systems

The normal and abnormal behavior of an adult heart dynamics and its state of evolution towards one of these two states has been characterized successfully in the context of the theory of dynamic systems and probability. The diagnostic methodology of clinical application designed under these two theories has managed to evaluate in an objective and reproducible way the cardiac dynamics from the values of the frequency of the Holter registers. The automation of this methodology through the design of a software that can be docked in any operating system for PC, and contributes as a diagnostic aid tool to generate more timely responses to the patient's clinical condition. Additionally, the values of the probability of these spaces occupied by the attractor, calculated by the Software, allow using an interface that can be consulted by the specialist to evaluate how far a cardiac dynamic is from normality, analyzing in this way the effectiveness of the treatment.

Sistemas dinámicos aplicados a la dinámica cardiaca en 18 horas mediante una ley matemática exponencial

Objetivo: Confirmar la capacidad diagnostica de una ley exponencial de ayuda diagnostica, desarrollada para 21 horas con base en la teoría de sistemas dinámicos junto con la geometría fractal, en evaluaciones realizadas en 18 horas, mediante un estudio de concordancia diagnóstica con respecto al Gold estándar. Materiales y métodos: Se realizó un estudio de 60 dinámicas cardiacas evaluadas en holter y registros electrocardiográficos continuos, de los cuales 15 provienen de sujetos normales y 45 de pacientes con diferentes tipos de patologías cardiacas. Se desarrollaron simulaciones teóricas de la secuencia de las frecuencias cardiacas durante 18 horas, y se construyeron atractores. Se calculó la dimensión fractal de cada atractor y su ocupación espacial en el espacio generalizado de Box-Counting. Se determinó el diagnóstico matemático a partir de la ley y se calculó sensibilidad, especificidad y coeficiente Kappa. Resultados: se encontraron valores para normalidad entre 219 y 373 en la rejilla Kp y entre 49 y 70 para enfermedad aguda, evidenciando que el método permite diferenciar normalidad de enfermedad aguda mediante la ocupación espacial de los atractores valorados desde la ley matemática en 18 horas. Se encontraron valores de sensibilidad y especificidad del 100% y un coeficiente Kappa de 1 al comparar el diagnóstico físico-matemático con el Gold estándar. Conclusión: la ley exponencial de los sistemas dinámicos cardiacos aplicada en 18 horas es útil como herramienta de ayuda diagnóstica, permitiendo cuantificar casos normales, en evolución hacia la enfermedad y en estados agudos.

Home-Based Risk of Falling Assessment Test Using a Closed-Loop Balance Model.

The aim of this study is to improve and facilitate the methods used to assess risk of falling at home among older people through the computation of a risk of falling in real time in daily activities. In order to increase a real time computation of the risk of falling, a closed-loop balance model is proposed and compared with One-Leg Standing Test (OLST). This balance model allows studying the postural response of a person having an unpredictable perturbation. Twenty-nine volunteers participated in this study for evaluating the effectiveness of the proposed system which includes seventeen elder participants: ten healthy elderly ( 68.4 ±5.5 years), seven Parkinson's disease (PD) subjects ( 66.28 ±8.9 years), and twelve healthy young adults ( 28.27 ±3.74 years). Our work suggests that there is a relationship between OLST score and the risk of falling based on center of pressure measurement with four low cost force sensors located inside an instrumented insole, which could be predicted using our suggested closed-loop balance model. For long term monitoring at home, this system could be included in a medical electronic record and could be useful as a diagnostic aid tool.

Parametric imaging for characterizing focal liver lesions in contrast-enhanced ultrasound

The differentiation between benign and malignant focal liver lesions plays an important role in diagnosis of liver disease and therapeutic planning of local or general disease. This differentiation, based on characterization, relies on the observation of the dynamic vascular patterns (DVP) of lesions with respect to adjacent parenchyma, and may be assessed during contrast-enhanced ultrasound imaging after a bolus injection. For instance, hemangiomas (i.e., benign lesions) exhibit hyper-enhanced signatures over time, whereas metastases (i.e., malignant lesions) frequently present hyperenhanced foci during the arterial phase and always become hypo-enhanced afterwards. The objective of this work was to develop a new parametric imaging technique, aimed at mapping the DVP signatures into a single image called a DVP parametric image, conceived as a diagnostic aid tool for characterizing lesion types. The methodology consisted in processing a time sequence of images (DICOM video data) using four consecutive steps: (1) pre-processing combining image motion correction and linearization to derive an echo-power signal, in each pixel, proportional to local contrast agent concentration over time; (2) signal modeling, by means of a curve-fitting optimization, to compute a difference signal in each pixel, as the subtraction of adjacent parenchyma kinetic from the echopower signal; (3) classification of difference signals; and (4) parametric image rendering to represent classified pixels as a support for diagnosis. DVP parametric imaging was the object of a clinical assessment on a total of 146 lesions, imaged using different medical ultrasound systems. The resulting sensitivity and specificity were 97% and 91%, respectively, which compare favorably with scores of 81 to 95% and 80 to 95% reported in medical literature for sensitivity and specificity, respectively.

Prévalence des troubles psychiatriques en médecine générale selon le patient health questionnaire : adéquation avec la détection par le médecin et le traitement prescrit

Psychiatric disorders, mainly depression and anxiety, are frequently encountered in primary care and are a major cause of distress and disability. Nearly half of cases go unnoticed and among those that are recognised, many do not receive adequate treatment. In France, there is limited research concerning the prevalence, detection and management of these conditions in primary care. To estimate the prevalence of psychiatric disorders, overall and for the main psychiatric diagnostic categories, encountered in primary care; to describe general practitioners' (GPs') case identification rate; to examine psychotropic medication prescription according to diagnosis, in a regionally representative sample of GP attenders. GP practicing standard general practice in an urban area of the city of Montpellier and a nearby semi-rural region were recruited to participate. The response rate was 32.8% (n=41). Five additional GP almost exclusively offering homeopathy and acupuncture were recruited nonrandomly for convenience purposes. In each GP surgery, consecutive patients entering the waiting room were invited by a research assistant to participate until 25 patients per GP were recruited. Each participant completed self-report questionnaires in the waiting time, including the patient health questionnaire (PHQ), which yields provisional DSM-IV diagnoses. The GP completed a brief questionnaire during the consultation, giving his/her rating of the severity of any psychiatric disorder present and action taken. The patient response rate was 89.8%. In all, 14.9% of patients reached DSM-IV criteria for major depression or anxiety disorder on the PHQ (9.1% for major depression, 7.5% for panic disorder; 6% for other anxiety disorders). For the subthreshold categories, 7.4% met criteria for other depressive disorders, 11.8% for somatoform disorders and 10.9% for probable alcohol abuse or dependence. 66.3% of patients with DSM-IV diagnoses of major depression or anxiety disorder were identified by the GP as having a psychiatric disorder. The identification rate was 51% for all depressive disorders, anxiety and somatoform disorders. Of patients receiving a prescription for anxiolytic or antidepressant medication on the survey day, 80% were classified as cases of psychiatric disorder by the GP. Only 48.8% met criteria for major depression or anxiety disorder on the PHQ. This study highlights the frequency of psychiatric disorders in a regional study of French general practice. Overall, prevalence rates were similar to those found elsewhere, except for probable alcohol abuse and dependence, which was considerably higher than in the USA PHQ validation study. As in other countries, GP identified roughly half of psychiatric cases. Furthermore, half of patients treated by anxiolytic or antidepressant medication did not meet the diagnostic criteria on the survey day for which these medications have mainly shown their efficacy. This confirms the French paradox of one of the highest psychotropic medication consumption rates in Europe despite many cases of depression remaining untreated. The PHQ could be a rapid and acceptable diagnostic aid tool for French general practice but first needs to be validated against the diagnosis of mental health professionals in this setting.

Editorial SMI 64

Henning Muller, Eusebio Passaretti This special issue of Swiss Medical Informatics (SMI No 64) brings together the best articles submitted to the 21st Congress of the Swiss Society for Medical Informatics (SGMI-SSIM). The congress took place in Sierre (Valais) at the University of Applied Sciences Western Switzerland (HES SO) from 5–6 June 2008, and featured 4 invited presentations, 19 oral scientific presentations and 6 scientific posters. In total, 27 papers were submitted and reviewed by the scientific programme committee on the basis of novelty of approach and technical quality of presentation. From this evaluation process the best eight papers were selected for the present special issue covering a wide range of subjects from the field of medical informatics. Two other papers were added for their practical interest to SGMI-SSIM members, bringing the total up to ten papers. Two articles deal with financial analysis of hospital data [1, 2] and two with image management and storage [3, 4], partly in the context of diagnostic aid. The patient record is traditionally well represented at these conferences, from access models for research [5] to patient identification [6]. Finally, two articles on specific diseases or disease categories are presented [7, 8]. The articles additionally selected describe practical approaches, one to the choice of an integrated electronic patient record at the Inselspital Berne [9], and the other on context-navigated search inside a clinical patient record [10]. In the first article [1] Rodolphe Meyer describes an extensive analysis of data on hospitals to define models measuring the impact of particular information and communication technologies on hospital productivity. This paper also received the award for the best scientific contribution to the conference. Alexandre Gnaegi [2] then describes a project on data mining within attributes of a hospital’s data warehouse in order to estimate income for released but not fully coded patients. The goal is to estimate the income for cases that have left the hospital within a reporting period but have not been fully coded. Off-the-shelf data mining tools have markedly increased the precision of such estimations for the Valais hospital network. Mechthild Uesback [3] describes the introduction of a PACS in Zurich University Hospital from 2004–2007. The results were major space savings and financial gains, with optimisation of workflows engendering a more productive work environment. Adrien Depeursinge then presents a diagnostic aid tool for emergency radiology [4] in the diagnosis of interstitial lung diseases. The tool analyses the texture of the lung tissue in CT images to classify it into healthy and several abnormal tissues. Clinical data are also taken into account since age or environmental factors can significantly change the lung texture properties. Jimison Iavindrasana’s article [5] reports on a framework for data access to a life clinical record with all its security constraints. The context is the EU project AneurIST whose aim is to improve the treatment and understanding of cerebral aneurysms. Tobias Mettler [6] then presents an approach to patient identification and tracking in a processoriented manner. A global view of the identification process across organisations focused on the patient can significantly improve identification. Marc Oertle [7] describes another diagnostic aid tool which targets patients with chronic heart failure and implements evidence-based medicine using information and communication technologies. The goal is standardisation of the care process to reduce variability in treatment. Christina Lovis [8] then outlines another European Union-funded project also targeting a particular group of diseases: nosocomial infections. The goal of this project is to develop new ways of fighting antibiotic resistances of bacteria by analysing large amounts of routine clinical data. The outcome of this project is expected to be IT-biotics, IT technology to fight bacteria. Oliver Handgratiger [9] describes, in the setting of the Inselspital Bern, the process of selecting a new electronic patient record covering all medical specialties and partners in the hospital, and outlines the criteria for selecting a particular solution. The effort to obtain each criterion with its discriminative power is then described. This practical and detailed approach should be useful for other hospitals as well. In the last article of this issue, Ela Bielecki [10] presents Solothurn hospital’s project for Prof. Dr. Henning Muller University of Applied Sciences Sierre & University and Hospitals of Geneva Business Information Systems Institute HES-SO Valais, TechnoArk 3 3960 Sierre, Switzerland henning.mueller@hevs.ch