Search results for: diagnostic test accuracy

Authors: Ananda Perera

Abstract:

Computer-Assisted Medical Evaluation of Symptoms (CAMEOS) is a medical expert system designed to help General Practices (GPs) make an accurate diagnosis. CAMEOS comprises a knowledge base, user input, inference engine, reasoning module, and output statement. The knowledge base was developed by the author. User input is an Html file. The physician user collects data in the consultation. Data is sent to the inference engine at servers. CAMEOS uses set theory to simulate diagnostic reasoning. The program output is a list of differential diagnoses, the most probable diagnosis, and the diagnostic reasoning.

Keywords: CDSS, computerized decision support systems, expert systems, general practice, diagnosis, diagnostic systems, primary care diagnostic system, artificial intelligence in medicine

Procedia PDF Downloads 127

Authors: Pegah Safavi, Mehdi Zehtabian, Mohammad Amin Mosleh-Shirazi

Abstract:

Cancer is one of the leading causes of death in the world. Radiation therapy is one of the main choices for cancer treatment. Intensity-modulated radiation therapy is a new type of radiation therapy technique available for vital structures such as the parathyroid glands. It is very important to check the accuracy of the delivered IMRT treatment because any mistake may lead to more complications for the patient. This paper describes an experiment to determine the accuracy of a dose measured by EBT3 film. To test this method, the EBT3 film on the head and neck of the Rando phantom was irradiated by an IMRT device and the irradiation was repeated twice. Finally, the dose designed by the irradiation system was compared with the dose measured by the EBT3 film. Using this criterion, the accuracy of the EBT3 film was evaluated. When using this criterion, a 95% agreement was reached between the planned treatment and the measured values.

Keywords: EBT3, phantom, accuracy, cancer, IMRT

Procedia PDF Downloads 118

Authors: Sabrina Azzi, Michal Iglewski, Véronique Nabelsi

Abstract:

Diagnosis error problem is frequent and one of the most important safety problems today. One of the main objectives of our work is to propose an ontological representation that takes into account the diagnostic criteria in order to improve the diagnostic. We choose pneumonia disease since it is one of the frequent diseases affected by diagnosis errors and have harmful effects on patients. To achieve our aim, we use a semi-automated method to integrate diverse knowledge sources that include publically available pneumonia disease guidelines from international repositories, biomedical ontologies and electronic health records. We follow the principles of the Open Biomedical Ontologies (OBO) Foundry. The resulting ontology covers symptoms and signs, all the types of pneumonia, antecedents, pathogens, and diagnostic testing. The first evaluation results show that most of the terms are covered by the ontology. This work is still in progress and represents a first and major step toward a development of a diagnosis decision support system for pneumonia.

Keywords: Clinical decision support system, Diagnostic errors, Ontology, Pneumonia

Procedia PDF Downloads 159

Authors: Wassim Katerji, Mercedes Farjas, Carmen Morillo

Abstract:

Terrain-Based Analysis results in derived products from an input DEM and these products are needed to perform various analyses. To efficiently use these products in decision-making, their accuracies must be estimated systematically. This paper proposes a procedure to assess the accuracy of these derived products, by calculating the accuracy of the slope dataset and its significance, taking as an input the accuracy of the DEM. Based on the output of previously published research on modeling the relative accuracy of a DEM, specifically ASTER and SRTM DEMs with Lebanon coverage as the area of study, analysis have showed that ASTER has a low significance in the majority of the area where only 2% of the modeled terrain has 50% or more significance. On the other hand, SRTM showed a better significance, where 37% of the modeled terrain has 50% or more significance. Statistical analysis deduced that the accuracy of the slope dataset, calculated on a cell-by-cell basis, is highly correlated to the accuracy of the input DEM. However, this correlation becomes lower between the slope accuracy and the slope significance, whereas it becomes much higher between the modeled slope and the slope significance.

Keywords: terrain-based analysis, slope, accuracy assessment, Digital Elevation Model (DEM)

Procedia PDF Downloads 420

Authors: Yashaswini Channabasavegowda, Hema Nagaraj

Abstract:

Aim: The current study aims at discovering word-class deficits concerning the noun-verb ratio in confrontation naming, picture description, and picture-word matching tasks. A total of ten persons with aphasia (PWA) and ten age-matched neurotypical individuals (NTI) were recruited for the study. The research includes both behavioural and objective measures to assess the word class deficits in PWA. Objective: The main objective of the research is to identify word class deficits seen in persons with aphasia, using various speech eliciting tasks. Method: The study was conducted in the L1 of the participants, considered to be Kannada. Action naming test and Boston naming test adapted to the Kannada version are administered to the participants; also, a picture description task is carried out. Picture-word matching task was carried out using e-prime software (version 2) to measure the accuracy and reaction time with respect to identification verbs and nouns. The stimulus was presented through auditory and visual modes. Data were analysed to identify errors noticed in the naming of nouns versus verbs, with respect to the Boston naming test and action naming test and also usage of nouns and verbs in the picture description task. Reaction time and accuracy for picture-word matching were extracted from the software. Results: PWA showed a significant difference in sentence structure compared to age-matched NTI. Also, PWA showed impairment in syntactic measures in the picture description task, with fewer correct grammatical sentences and fewer correct usage of verbs and nouns, and they produced a greater proportion of nouns compared to verbs. PWA had poorer accuracy and lesser reaction time in the picture-word matching task compared to NTI, and accuracy was higher for nouns compared to verbs in PWA. The deficits were noticed irrespective of the cause leading to aphasia.

Keywords: nouns, verbs, aphasia, naming, description

Procedia PDF Downloads 76

Authors: Kumar Kanudkuri, A. Sandhya

Abstract:

Typically, in a MRI clinical setting, there are several protocols run, each indicated for a specific anatomy and disease condition. However, these protocols or parameters within them can change over time due to changes to the recommendations by the physician groups or updates in the software or by the availability of new technologies. Most of the time, the changes are performed by the MRI technologist to account for either time, coverage, physiological, or Specific Absorbtion Rate (SAR ) reasons. However, giving properly guidelines to MRI technologist is important so that they do not change the parameters that negatively impact the image quality. Typically a standard American College of Radiology (ACR) MRI phantom is used for Quality Control (QC) in order to guarantee that the primary objectives of MRI are met. The visual evaluation of quality depends on the operator/reviewer and might change amongst operators as well as for the same operator at various times. Therefore, overcoming these constraints is essential for a more impartial evaluation of quality. This makes quantitative estimation of image quality (IQ) metrics for MRI quality control is very important. So in order to solve this problem, we proposed that there is a need for a robust, open-source, and automated MRI image control tool. The Designed and developed an automatic analysis tool for measuring MRI image quality (IQ) metrics like Signal to Noise Ratio (SNR), Signal to Noise Ratio Uniformity (SNRU), Visual Information Fidelity (VIF), Feature Similarity (FSIM), Gray level co-occurrence matrix (GLCM), slice thickness accuracy, slice position accuracy, High contrast spatial resolution) provided good accuracy assessment. A standardized quality report has generated that incorporates metrics that impact diagnostic quality.

Keywords: ACR MRI phantom, MRI image quality metrics, SNRU, VIF, FSIM, GLCM, slice thickness accuracy, slice position accuracy

Procedia PDF Downloads 134

Authors: Alyona Gencheva

Abstract:

The most common way to study diagnostic results is using specialized programs at a stationary workplace. Magnetic Resonance Imaging is presented in a two-dimensional (2D) format, and Computed Tomography sometimes looks like a three-dimensional (3D) model that can be interacted with. The main idea of the research is to compare ways of displaying diagnostic results in virtual reality that can help a surgeon during or before an operation in augmented reality. During the experiment, the medical staff examined liver vessels in the abdominal area and heart boundaries. The search time and detection accuracy were measured on black-and-white and coloured scans. Usability testing in virtual reality shows convenient ways of interaction like hand input, voice activation, displaying risk to the patient, and the required number of scans. The results of the experiment will be used in the new C# program based on Magic Leap technology.

Keywords: augmented reality, computed tomography, magic leap, magnetic resonance imaging, usability testing, VTE risk

Procedia PDF Downloads 80

Authors: Kathrina Aseanne Acapulco-Gomez, Shayne Julieane Morales, Tzar Francis Verame

Abstract:

Mean platelet volume (MPV) is the most accurate measure of the size of platelets and is routinely measured by most automated hematological analyzers. Several studies have shown associations between MPV and cardiovascular risks and outcomes. Although its measurement may provide useful data, MPV remains to be a diagnostic tool that is yet to be included in routine clinical decision making. The aim of this systematic review and meta-analysis is to determine summary estimates of the diagnostic accuracy of mean platelet volume for the diagnosis of myocardial infarction among adult patients with angina and/or its equivalents in terms of sensitivity, specificity, diagnostic odds ratio, and likelihood ratios, and to determine the difference of the mean MPV values between those with MI and those in the non-MI controls. The primary search was done through search in electronic databases PubMed, Cochrane Review CENTRAL, HERDIN (Health Research and Development Information Network), Google Scholar, Philippine Journal of Pathology, and Philippine College of Physicians Philippine Journal of Internal Medicine. The reference list of original reports was also searched. Cross-sectional, cohort, and case-control articles studying the diagnostic performance of mean platelet volume in the diagnosis of acute myocardial infarction in adult patients were included in the study. Studies were included if: (1) CBC was taken upon presentation to the ER or upon admission (within 24 hours of symptom onset); (2) myocardial infarction was diagnosed with serum markers, ECG, or according to accepted guidelines by the Cardiology societies (American Heart Association (AHA), American College of Cardiology (ACC), European Society of Cardiology (ESC); and, (3) if outcomes were measured as significant difference AND/OR sensitivity and specificity. The authors independently screened for inclusion of all the identified potential studies as a result of the search. Eligible studies were appraised using well-defined criteria. Any disagreement between the reviewers was resolved through discussion and consensus. The overall mean MPV value of those with MI (9.702 fl; 95% CI 9.07 – 10.33) was higher than in those of the non-MI control group (8.85 fl; 95% CI 8.23 – 9.46). Interpretation of the calculated t-value of 2.0827 showed that there was a significant difference in the mean MPV values of those with MI and those of the non-MI controls. The summary sensitivity (Se) and specificity (Sp) for MPV were 0.66 (95% CI; 0.59 - 0.73) and 0.60 (95% CI; 0.43 – 0.75), respectively. The pooled diagnostic odds ratio (DOR) was 2.92 (95% CI; 1.90 – 4.50). The positive likelihood ratio of MPV in the diagnosis of myocardial infarction was 1.65 (95% CI; 1.20 – 22.27), and the negative likelihood ratio was 0.56 (95% CI; 0.50 – 0.64). The intended role for MPV in the diagnostic pathway of myocardial infarction would perhaps be best as a triage tool. With a DOR of 2.92, MPV values can discriminate between those who have MI and those without. For a patient with angina presenting with elevated MPV values, it is 1.65 times more likely that he has MI. Thus, it is implied that the decision to treat a patient with angina or its equivalents as a case of MI could be supported by an elevated MPV value.

Keywords: mean platelet volume, MPV, myocardial infarction, angina, chest pain

Procedia PDF Downloads 50

Authors: Hyun-Woo Cho

Abstract:

Continuous monitoring of industrial plants is one of necessary tasks when it comes to ensuring high-quality final products. In terms of monitoring and diagnosis, it is quite critical and important to detect some incipient abnormal events of manufacturing processes in order to improve safety and reliability of operations involved and to reduce related losses. In this work a new multivariate statistical online diagnostic method is presented using a case study. For building some reference models an empirical discriminant model is constructed based on various past operation runs. When a fault is detected on-line, an on-line diagnostic module is initiated. Finally, the status of the current operating conditions is compared with the reference model to make a diagnostic decision. The performance of the presented framework is evaluated using a dataset from complex industrial processes. It has been shown that the proposed diagnostic method outperforms other techniques especially in terms of incipient detection of any faults occurred.

Keywords: data mining, empirical model, on-line diagnostics, process fault, process monitoring

Procedia PDF Downloads 366

Authors: Shanza Akram, Sameen Toor, Heba Harb Abu Alkass, Zainab Abdulsalam Altaha, Sara Taha Abdulla, Saleem Imran

Abstract:

Acute pulmonary embolism (PE) is a common disease and can be fatal. The clinical presentation is variable and nonspecific, making accurate diagnosis difficult. Testing patients with suspected acute PE has increased dramatically. However, the overuse of some tests, particularly CT and D-dimer measurement, may not improve care while potentially leading to patient harm and unnecessary expense. CTPA is the investigation of choice for PE. Its easy availability, accuracy and ability to provide alternative diagnosis has lowered the threshold for performing it, resulting in its overuse. Guidelines have recommended the use of clinical pretest probability tools such as ‘Wells score’ to assess risk of suspected PE. Unfortunately, implementation of guidelines in clinical practice is inconsistent. This has led to low risk patients being subjected to unnecessary imaging, exposure to radiation and possible contrast related complications. Aim: To study the diagnostic yield of CT PA, clinical pretest probability of patients according to wells score and to determine whether or not there was an overuse of CTPA in our service. Methods: CT scans done on patients with suspected P.E in our hospital from 1st January 2014 to 31st December 2014 were retrospectively reviewed. Medical records were reviewed to study demographics, clinical presentation, final diagnosis, and to establish if Wells score and D-Dimer were used correctly in predicting the probability of PE and the need for subsequent CTPA. Results: 100 patients (51male) underwent CT PA in the time period. Mean age was 57 years (24-91 years). Majority of patients presented with shortness of breath (52%). Other presenting symptoms included chest pain 34%, palpitations 6%, collapse 5% and haemoptysis 5%. D Dimer test was done in 69%. Overall Wells score was low (<2) in 28 %, moderate (>2 - < 6) in 47% and high (> 6) in 15% of patients. Wells score was documented in medical notes of only 20% patients. PE was confirmed in 12% (8 male) patients. 4 had bilateral PE’s. In high-risk group (Wells > 6) (n=15), there were 5 diagnosed PEs. In moderate risk group (Wells >2 - < 6) (n=47), there were 6 and in low risk group (Wells <2) (n=28), one case of PE was confirmed. CT scans negative for PE showed pleural effusion in 30, Consolidation in 20, atelactasis in 15 and pulmonary nodule in 4 patients. 31 scans were completely normal. Conclusion: Yield of CT for pulmonary embolism was low in our cohort at 12%. A significant number of our patients who underwent CT PA had low Wells score. This suggests that CT PA is over utilized in our institution. Wells score was poorly documented in medical notes. CT-PA was able to detect alternative pulmonary abnormalities explaining the patient's clinical presentation. CT-PA requires concomitant pretest clinical probability assessment to be an effective diagnostic tool for confirming or excluding PE. . Clinicians should use validated clinical prediction rules to estimate pretest probability in patients in whom acute PE is being considered. Combining Wells scores with clinical and laboratory assessment may reduce the need for CTPA.

Keywords: CT PA, D dimer, pulmonary embolism, wells score

Procedia PDF Downloads 192

Authors: Abdel Hadi N. Ebraheim, Eman Azomi, Nefisa A. Fahmy

Abstract:

This paper designs and implements a computer-aided system (CAS) to help detect and diagnose liver cirrhosis in patients with Chronic Hepatitis C. Our system reduces the required features (tests) the patient is asked to do to tests to their minimal best most informative subset of tests, with a diagnostic accuracy above 99%, and hence saving both time and costs. We use the Support Vector Machine (SVM) with cross-validation, a Multilayer Perceptron Neural Network (MLP), and a Generalized Regression Neural Network (GRNN) that employs a base of radial functions for functional approximation, as classifiers. Our system is tested on 199 subjects, of them 99 Chronic Hepatitis C.The subjects were selected from among the outpatient clinic in National Herpetology and Tropical Medicine Research Institute (NHTMRI).

Keywords: liver cirrhosis, artificial neural network, support vector machine, multi-layer perceptron, classification, accuracy

Procedia PDF Downloads 420

Authors: Naohiro Nakamura

Abstract:

Analysis methods to accurately estimate the behavior of buildings when earthquakes occur is very important for improving the seismic safety of such buildings. Recently, the use of damping devices has increased significantly and there is a particular need to appropriately evaluate the behavior of buildings with such devices during earthquakes in the design stage. At present, however, the accuracy of the analysis evaluations is not sufficient. One reason is that the accuracy of current analysis methods has not been appropriately verified because there is very limited data on the behavior of actual buildings during earthquakes. Many types of shaking table test of large structures are performed at the '3-Dimensional Full-Scale Earthquake Testing Facility' (nicknamed 'E-Defense') operated by the National Research Institute of Earth Science and Disaster Prevention (NIED). In this study, simulations using 3- dimensional analysis models were conducted on shaking table test of a 5-story steel-frame structure with dampers. The results of the analysis correspond favorably to the test results announced afterward by the committee. However, the suitability of the parameters and models used in the analysis and the influence they had on the responses remain unclear. Hence, we conducted additional analysis and studies on these models and parameters. In this paper, outlines of the test are shown and the utilized analysis model is explained. Next, the analysis results are compared with the test results. Then, the additional analyses, concerning with the hysteresis curve of the dampers and the beam-end stiffness of the frame, are investigated.

Keywords: three-dimensional analysis, E-defense, full-scale experimen, vibration control damper

Procedia PDF Downloads 160

Authors: Gurukiran Veerapur, Nytik Birudavolu, Seetharam U. N., Chandravva Hebbi, R. Praneeth Reddy

Abstract:

This work presents a robust approach for the recognition of characters in Telugu and Kannada, two South Indian scripts with structural similarities in characters. To recognize the characters exhaustive datasets are required, but there are only a few publicly available datasets. As a result, we decided to create a dataset for one language (source language),train the model with it, and then test it with the target language.Telugu is the target language in this work, whereas Kannada is the source language. The suggested method makes use of Canny edge features to increase character identification accuracy on pictures with noise and different lighting. A dataset of 45,150 images containing printed Kannada characters was created. The Nudi software was used to automatically generate printed Kannada characters with different writing styles and variations. Manual labelling was employed to ensure the accuracy of the character labels. The deep learning models like CNN (Convolutional Neural Network) and Visual Attention neural network (VAN) are used to experiment with the dataset. A Visual Attention neural network (VAN) architecture was adopted, incorporating additional channels for Canny edge features as the results obtained were good with this approach. The model's accuracy on the combined Telugu and Kannada test dataset was an outstanding 97.3%. Performance was better with Canny edge characteristics applied than with a model that solely used the original grayscale images. The accuracy of the model was found to be 80.11% for Telugu characters and 98.01% for Kannada words when it was tested with these languages. This model, which makes use of cutting-edge machine learning techniques, shows excellent accuracy when identifying and categorizing characters from these scripts.

Keywords: base characters, modifiers, guninthalu, aksharas, vattakshara, VAN

Procedia PDF Downloads 22

Authors: Francis Zerd, Brian E. Moore, Atuganile E. Malango, Patrick W. Hosokawa, Kevin O. Lillehei, Laurence Lemery Mchome, D. Ryan Ormond

Abstract:

Introduction: Since neuropathologic diagnosis in the developing world is hampered by limitations in technical infrastructure, trained laboratory personnel, and subspecialty-trained pathologists, the use of telepathology for diagnostic support, second-opinion consultations, and ongoing training holds promise as a means of addressing these challenges. This research aims to assess the utility of static teleneuropathology in improving neuropathologic diagnoses in low- and middle-income countries. Methods: Consecutive neurosurgical biopsy and resection specimens obtained at Muhimbili National Hospital in Tanzania between July 1, 2018, and June 30, 2019, were selected for retrospective, blinded static-image neuropathologic review followed by on-site review by an expert neuropathologist. Results: A total of 75 neuropathologic cases were reviewed. The agreement of static images and on-site glass diagnosis was 71% with strict criteria and 88% with less stringent criteria. This represents an overall improvement in diagnostic accuracy from 36% by general pathologists to 71% by a neuropathologist using static telepathology (or 76% to 88% with less stringent criteria). Conclusions: Telepathology offers a suitable means of providing diagnostic support, second-opinion consultations, and ongoing training to pathologists practicing in resource-limited countries. Moreover, static digital teleneuropathology is an uncomplicated, cost-effective, and reliable way to achieve these goals.

Keywords: neuropathology, resource-limited settings, static image, Tanzania, teleneuropathology

Procedia PDF Downloads 81

Authors: Yan-Lin Liu, Cheng-Ting Shih, Jay Wu

Abstract:

Tablet devices have been introduced into the medical environment in recent years. The performance of display can be varied based on the use of different hardware specifications and types of display technologies. Therefore, the differences between tablet devices and medical diagnostic LCDs have to be verified to ensure that image quality is not jeopardized for clinical diagnosis in a picture archiving and communication system (PACS). In this study, a set of randomized object test patterns (ROTPs) were developed, which included randomly located spheres in abdominal CT images. Five radiologists were asked to independently review the CT images on different generations of iPads and a diagnostic monochrome medical LCD monitor. Receiver operating characteristic (ROC) analysis was performed by using a five-point rating scale, and the average area under curve (AUC) and average reading time (ART) were calculated. The AUC values for the second generation iPad, iPad mini, iPad Air, and monochrome medical monitor were 0.712, 0.717, 0.725, and 0.740, respectively. The differences between iPads were not significant. The ARTs were 177 min and 127 min for iPad mini and medical LCD monitor, respectively. A significant difference appeared (p = 0.04). The results show that the iPads were slightly inferior to the monochrome medical LCD monitor. However, tablet devices possess advantages in portability and versatility, which can improve the convenience of rapid diagnosis and teleradiology. With advances in display technology, the applicability of tablet devices and mobile devices may be more diversified in PACS.

Keywords: tablet devices, PACS, receiver operating characteristic, LCD monitor

Procedia PDF Downloads 452

Authors: K. Hinde, R. Bookun, P. Tran

Abstract:

Percutaneous CT guided biopsies provide a fast, minimally invasive, cost effective and safe method for obtaining tissue for histopathology and culture. Standards for diagnostic yield vary depending on whether the tissue is being obtained for histopathology or culture. We present a retrospective audit from Western Health in Melbourne Australia over a 12-month period which aimed to determine the diagnostic yield, technical success and complication rate for CT guided bone biopsies and identify factors affecting these results. The digital imaging storage program (Synapse Picture Archiving and Communication System – Fujifilm Australia) was analysed with key word searches from October 2015 to October 2016. Nineteen CT guided bone biopsies were performed during this time. The most common referring unit was oncology, work up imaging included CT, MRI, bone scan and PET scan. The complication rate was 0%, overall diagnostic yield was 74% with a technical success of 95%. When performing biopsies for histologic analysis diagnostic yield was 85% and when performing biopsies for bacterial culture diagnostic yield was 60%. There was no significant relationship identified between size of lesion, distance of lesion to skin, lesion appearance on CT, the number of samples taken or gauge of needle to diagnostic yield or technical success. CT guided bone biopsy at Western Health meets the standard reported at other major clinical centres for technical success and safety. It is a useful investigation in identification of primary malignancy in distal bone metastases.

Keywords: bone biopsy, computed tomography, core biopsy, histopathology

Procedia PDF Downloads 175

Authors: Emiliano Lustrissimi, Bonifacio Bianco, Sebastiano Caravaggi, Antonio Rosato

Abstract:

A mathematical model has been developed to optimize the design of an end-of-production-line (EOL) for testing and validating the performance and functionality of newly manufactured electric motors (EMs) for electric vehicles. The model has been developed to predict the behaviour of EOL test benches and EMs under various boundary conditions, eliminating the need for extensive physical testing, with the main target of reducing the corresponding power consumption. The maximum performance to be guaranteed by the EMs according to the carmaker specifications is taken as inputs. Then, the required performance of each main EOL test bench component is calculated and the corresponding systems available on the market are selected based on manufacturers’ catalogues. According to the model outputs, an EOL test bench has been designed for testing a low-power (about 22 kW) EM. The performance of the designed EOL test bench has been measured and used to validate the proposed model to assess both the consistency of the constraints as well as the accuracy of predictions in terms of electric demands. The comparison between experimental and predicted data exhibited a reasonable agreement, allowing to demonstrate that, despite some discrepancies, the model gives an accurate representation of the EOL test benches' performance.

Keywords: electric motors, electric vehicles, end-of-production-line test bench, mathematical model, field tests

Procedia PDF Downloads 3

Authors: Ethan James

Abstract:

Over one billion people worldwide suffer from some level of vision loss or blindness as a result of progressive retinal diseases. Many patients, particularly in developing areas, are incorrectly diagnosed or undiagnosed whatsoever due to unconventional diagnostic tools and screening methods. Artificial intelligence (AI) based on deep learning (DL) convolutional neural networks (CNN) have recently gained a high interest in ophthalmology for its computer-imaging diagnosis, disease prognosis, and risk assessment. Optical coherence tomography (OCT) is a popular imaging technique used to capture high-resolution cross-sections of retinas. In ophthalmology, DL has been applied to fundus photographs, optical coherence tomography, and visual fields, achieving robust classification performance in the detection of various retinal diseases including macular degeneration, diabetic retinopathy, and retinitis pigmentosa. However, there is no complete diagnostic model to analyze these retinal images that provide a diagnostic accuracy above 90%. Thus, the purpose of this project was to develop an AI model that utilizes machine learning techniques to automatically diagnose specific retinal diseases from OCT scans. The algorithm consists of neural network architecture that was trained from a dataset of over 20,000 real-world OCT images to train the robust model to utilize residual neural networks with cyclic pooling. This DL model can ultimately aid ophthalmologists in diagnosing patients with these retinal diseases more quickly and more accurately, therefore facilitating earlier treatment, which results in improved post-treatment outcomes.

Keywords: artificial intelligence, deep learning, imaging, medical devices, ophthalmic devices, ophthalmology, retina

Procedia PDF Downloads 146

Authors: Dua Hişam, Serhat İkizoğlu

Abstract:

Identifying the problem behind balance disorder is one of the most interesting topics in the medical literature. This study has considerably enhanced the development of artificial intelligence (AI) algorithms applying multiple machine learning (ML) models to sensory data on gait collected from humans to classify between normal people and those suffering from Vestibular System (VS) problems. Although AI is widely utilized as a diagnostic tool in medicine, AI models have not been used to perform feature extraction and identify VS disorders through training on raw data. In this study, three machine learning (ML) models, the Random Forest Classifier (RF), Extreme Gradient Boosting (XGB), and K-Nearest Neighbor (KNN), have been trained to detect VS disorder, and the performance comparison of the algorithms has been made using accuracy, recall, precision, and f1-score. With an accuracy of 95.28 %, Random Forest Classifier (RF) was the most accurate model.

Keywords: vestibular disorder, machine learning, random forest classifier, k-nearest neighbor, extreme gradient boosting

Procedia PDF Downloads 42

Authors: Joseph George, Anne Kotteswara Roa

Abstract:

Skin disease is one of the most common and popular kinds of health issues faced by people nowadays. Skin cancer (SC) is one among them, and its detection relies on the skin biopsy outputs and the expertise of the doctors, but it consumes more time and some inaccurate results. At the early stage, skin cancer detection is a challenging task, and it easily spreads to the whole body and leads to an increase in the mortality rate. Skin cancer is curable when it is detected at an early stage. In order to classify correct and accurate skin cancer, the critical task is skin cancer identification and classification, and it is more based on the cancer disease features such as shape, size, color, symmetry and etc. More similar characteristics are present in many skin diseases; hence it makes it a challenging issue to select important features from a skin cancer dataset images. Hence, the skin cancer diagnostic accuracy is improved by requiring an automated skin cancer detection and classification framework; thereby, the human expert’s scarcity is handled. Recently, the deep learning techniques like Convolutional neural network (CNN), Deep belief neural network (DBN), Artificial neural network (ANN), Recurrent neural network (RNN), and Long and short term memory (LSTM) have been widely used for the identification and classification of skin cancers. This survey reviews different DL techniques for skin cancer identification and classification. The performance metrics such as precision, recall, accuracy, sensitivity, specificity, and F-measures are used to evaluate the effectiveness of SC identification using DL techniques. By using these DL techniques, the classification accuracy increases along with the mitigation of computational complexities and time consumption.

Keywords: skin cancer, deep learning, performance measures, accuracy, datasets

Procedia PDF Downloads 95

Authors: Dmitriy Babenko, Sergey Yegorov, Ilya Korshukov, Aidana Sultanbekova, Valentina Barkhanskaya, Tatiana Bashirova, Yerzhan Zhunusov, Yevgeniya Li, Viktoriya Parakhina, Svetlana Kolesnichenko, Yeldar Baiken, Aruzhan Pralieva, Zhibek Zhumadilova, Matthew S. Miller, Gonzalo H. Hortelano, Anar Turmuhambetova, Antonella E. Chesca, Irina Kadyrova

Abstract:

Introduction: The rapidly evolving COVID-19 pandemic, along with the re-emergence of pathogens causing acute respiratory infections (ARI), has necessitated the development of novel diagnostic tools to differentiate various causes of ARI. MALDI-MS, due to its wide usage and affordability, has been proposed as a potential instrument for diagnosing SARS-CoV-2 versus non-SARS-CoV-2 ARI. The aim of this study was to investigate the potential of MALDI-MS in conjunction with a machine learning model to accurately distinguish between symptomatic infections caused by SARS-CoV-2 and non-SARS-CoV-2 during both the early and later phases of the pandemic. Furthermore, this study aimed to analyze mass spectrometry (MS) data obtained from nasal swabs of healthy individuals. Methods: We gathered mass spectra from 252 samples, comprising 108 SARS-CoV-2-positive samples obtained in 2020 (Covid 2020), 7 SARS-CoV- 2-positive samples obtained in 2023 (Covid 2023), 71 samples from symptomatic individuals without SARS-CoV-2 (Control non-Covid ARVI), and 66 samples from healthy individuals (Control healthy). All the samples were subjected to RT-PCR testing. For data analysis, we employed the caret R package to train and test seven machine-learning algorithms: C5.0, KNN, NB, RF, SVM-L, SVM-R, and XGBoost. We conducted a training process using a five-fold (outer) nested repeated (five times) ten-fold (inner) cross-validation with a randomized stratified splitting approach. Results: In this study, we utilized the Covid 2020 dataset as a case group and the non-Covid ARVI dataset as a control group to train and test various machine learning (ML) models. Among these models, XGBoost and SVM-R demonstrated the highest performance, with accuracy values of 0.97 [0.93, 0.97] and 0.95 [0.95; 0.97], specificity values of 0.86 [0.71; 0.93] and 0.86 [0.79; 0.87], and sensitivity values of 0.984 [0.984; 1.000] and 1.000 [0.968; 1.000], respectively. When examining the Covid 2023 dataset, the Naive Bayes model achieved the highest classification accuracy of 43%, while XGBoost and SVM-R achieved accuracies of 14%. For the healthy control dataset, the accuracy of the models ranged from 0.27 [0.24; 0.32] for k-nearest neighbors to 0.44 [0.41; 0.45] for the Support Vector Machine with a radial basis function kernel. Conclusion: Therefore, ML models trained on MALDI MS of nasopharyngeal swabs obtained from patients with Covid during the initial phase of the pandemic, as well as symptomatic non-Covid individuals, showed excellent classification performance, which aligns with the results of previous studies. However, when applied to swabs from healthy individuals and a limited sample of patients with Covid in the late phase of the pandemic, ML models exhibited lower classification accuracy.

Keywords: SARS-CoV-2, MALDI-TOF MS, ML models, nasopharyngeal swabs, classification

Procedia PDF Downloads 72

Authors: Amira Ben Rabeh, Faouzi Benzarti, Hamid Amiri, Mouna Bouaziz

Abstract:

Alzheimer is a disease that affects the brain. It causes degeneration of nerve cells (neurons) and in particular cells involved in memory and intellectual functions. Early diagnosis of Alzheimer Diseases (AD) raises ethical questions, since there is, at present, no cure to offer to patients and medicines from therapeutic trials appear to slow the progression of the disease as moderate, accompanying side effects sometimes severe. In this context, analysis of medical images became, for clinical applications, an essential tool because it provides effective assistance both at diagnosis therapeutic follow-up. Computer Assisted Diagnostic systems (CAD) is one of the possible solutions to efficiently manage these images. In our work; we proposed an application to detect Alzheimer’s diseases. For detecting the disease in early stage we used the three sections: frontal to extract the Hippocampus (H), Sagittal to analysis the Corpus Callosum (CC) and axial to work with the variation features of the Cortex(C). Our method of classification is based on Support Vector Machine (SVM). The proposed system yields a 90.66% accuracy in the early diagnosis of the AD.

Keywords: Alzheimer Diseases (AD), Computer Assisted Diagnostic(CAD), hippocampus, Corpus Callosum (CC), cortex, Support Vector Machine (SVM)

Procedia PDF Downloads 342

Authors: Jian-Jun Shu

Abstract:

The statistical properties of CRMs are explored by estimating similar-word set occurrence distribution. It is observed that CRMs tend to have a fat-tail distribution for similar-word set occurrence. Thus, the fat-tail test with two fatness coefficients is proposed to distinguish CRMs from non-CRMs, especially from exons. For the first fatness coefficient, the separation accuracy between CRMs and exons is increased as compared with the existing content-based CRM prediction method – fluffy-tail test. For the second fatness coefficient, the computing time is reduced as compared with fluffy-tail test, making it very suitable for long sequences and large data-base analysis in the post-genome time. Moreover, these indexes may be used to predict the CRMs which have not yet been observed experimentally. This can serve as a valuable filtering process for experiment.

Keywords: statistical approach, transcription factor binding sites, cis-regulatory modules, DNA sequences

Procedia PDF Downloads 264

Authors: J. B. Sharma, Vivek Kakkar, Sunesh Kumar, K. K. Roy, Rajesh Kumari, Kavita Pandey, Smriti Hari

Abstract:

Background: Stress urinary incontinence (SUI) is a common problem affecting the quality of life of women. Methods: It is a prospective study conducted over 40 women of SUI by endovaginal ultrasound on rest and Valsalva preoperatively and six months postoperatively for levator hiatus, pubovisceral thickness, urethral length, and bladder neck position. A 24-hour pad test was also performed on all women at the same time for grading of SUI. Treatment given was medical in 4 (10%), Burch colposuspension in 18 (45%), and tension-free obturator tape in 18 (45%). Results: Mean age, parity, and body mass index in the study were 41.60 years, 2.73, and 24.2 kg/m², respectively. All 40 (100%) patients had SUI, with the mean duration of symptoms being 4.04 years. On the 24-hour pad test, mild SUI was in 4 (10%), moderate SUI in 33 (82.5%), and severe SUI in 3 (7.5%), with mean preoperative 24-hour pad test being 36.69 gm which significantly reduced to 9.79 gm postoperatively (p 0.001). There was a significant change in levator hiatus and pubovisceral thickness with the treatment of SUI. Overall urethral length increased, but there was a significant decrease in urethral length on Valsalva after the treatment (0.40 versus 0.28 cm, p 0.04) and a significant reduction in bladder neck descent after Valsalva after treatment (0.41 cm versus 0.27 cm, p 0.001). Conclusion: Endovaginal ultrasound and 24-hour pad test are useful diagnostic modalities for SUI diagnosis and to see the impact of treatment.

Keywords: stress urinary incontinence, endovaginal ultrasound, 24-hours pad test, pubovisceral muscle thickness

Procedia PDF Downloads 57

Authors: Rose Shayeghi, Pejman Hosseinioun

Abstract:

The Multiple Intelligences theory characterizes human intelligence as a multifaceted entity that exists in all human beings with varying degrees. The most important contribution of this theory to the field of English Language Teaching (ELT) is its role in identifying individual differences and designing more learner-centered programs. The present study aims at investigating the relationship between different elements of multiple intelligence and grammar scores. To this end, 63 female Iranian EFL learner selected from among intermediate students participated in the study. The instruments employed were a Nelson English language test, Michigan Grammar Test, and Teele Inventory for Multiple Intelligences (TIMI). The results of Pearson Product-Moment Correlation revealed a significant positive correlation between grammatical accuracy and linguistic as well as interpersonal intelligence. The results of Stepwise Multiple Regression indicated that linguistic intelligence contributed to the prediction of grammatical accuracy.

Keywords: multiple intelligence, grammar, ELT, EFL, TIMI

Procedia PDF Downloads 460

Authors: Amer A. Hasan, Mehri Igci, Ersin Borazan, Rozhgar A. Khailany, Emine Bayraktar, Ahmet Arslan

Abstract:

Gastric cancer (GC) has high morbidity and fatality rate in various countries and is still one of the most frequent and deadly diseases. Novel mitogenic and motogenic Gastrokine1 (GKN1) and Gastrokine 2 (GKN2) genes that are highly expressed in the normal stomach epithelium and plays an important role in maintaining the integrity and homeostasis of stomach mucosal epithelial cells. Significant loss of copy number and mRNA transcript of GKN1 and GKN2 gene expression were frequently observed in all types of gastric cancer. In this study, 47 paired samples that were grouped according to the types of gastric cancer and the clinical characteristics of the patients, including gender and average of age were investigated with gene expression analysis and mutation screening by monetering RT-PCR, SSCP and nucleotide sequencing techniques. Both GKN1 and GKN2 genes were observed significantly reduced found by (Wilcoxon signed rank test; p<0.05). As a result of gene screening, no mutation (no different genotype) was detected. It is considered that gene mutations are not the cause of inactivation of gastrokines. In conclusion, the mRNA expression level of GKN1 and GKN2 genes statistically was decreased regardless the gender, age or cancer type of patients. Reduced of gastrokine genes seems to occur at the initial steps of cancer development. In order to understand the investigation between gastric cancer and diagnostic biomarker; further analysis is necessary.

Keywords: gastric cancer, diagnostic biomarker, nucleotide sequencing, semi-quantitative RT-PCR

Procedia PDF Downloads 449

Authors: Salam N. Abdo, Orien L. Tulp, George P. Einstein

Abstract:

The purpose of this exploratory study was to gather the insights into psoriasis etiology, treatment, and patient experience, for developing psoriasis and psoriatic arthritis diagnostic test. Data collection methods consisted of a comprehensive meta-analysis of relevant studies and psoriasis patient survey. Established meta-analysis guidelines were used for the selection and qualitative comparative analysis of psoriasis and psoriatic arthritis research studies. Only studies that clearly discussed psoriasis etiology, treatment, and patient experience were reviewed and analyzed, to establish a qualitative data base for the study. Using the insights gained from meta-analysis, an existing psoriasis patient survey was modified and administered to collect additional data as well as triangulate the results. The hypothesis is that specific types of psoriatic disease have specific etiology and pathophysiologic pattern. The following etiology categories were identified: bacterial, environmental/microbial, genetic, immune, infectious, trauma/stress, and viral. Additional results, obtained from meta-analysis and confirmed by patient survey, were the common age of onset (early to mid-20s) and type of psoriasis (plaque; mild; symmetrical; scalp, chest, and extremities, specifically elbows and knees). Almost 70% of patients reported no prescription drug use due to severe side effects and prohibitive cost. These results will guide the development of psoriasis and psoriatic arthritis diagnostic test. The significant number of medical publications classified psoriatic arthritis disease as inflammatory of an unknown etiology. Thus numerous meta-analyses struggle to report any meaningful conclusions since no definitive results have been reported to date. Therefore, return to the basics is an essential step to any future meaningful results. To date, medical literature supports the fact that psoriatic disease in its current classification could be misidentifying subcategories, which in turn hinders the success of studies conducted to date. Moreover, there has been an enormous commercial support to pursue various immune-modulation therapies, thus following a narrow hypothesis/mechanism of action that is yet to yield resolution of disease state. Recurrence and complications may be considered unacceptable in a significant number of these studies. The aim of the ongoing study is to focus on a narrow subgroup of patient population, as identified by this exploratory study via meta-analysis and patient survey, and conduct an exhaustive work up, aiming at mechanism of action and causality before proposing a cure or therapeutic modality. Remission in psoriasis has been achieved and documented in medical literature, such as immune-modulation, phototherapy, various over-the-counter agents, including salts and tar. However, there is no psoriasis and psoriatic arthritis diagnostic test to date, to guide the diagnosis and treatment of this debilitating and, thus far, incurable disease. Because psoriasis affects approximately 2% of population, the results of this study may affect the treatment and improve the quality of life of a significant number of psoriasis patients, potentially millions of patients in the United States alone and many more millions worldwide.

Keywords: biologics, early diagnosis, etiology, immune disease, immune modulation therapy, inflammation skin disorder, phototherapy, plaque psoriasis, psoriasis, psoriasis classification, psoriasis disease marker, psoriasis diagnostic test, psoriasis marker, psoriasis mechanism of action, psoriasis treatment, psoriatic arthritis, psoriatic disease, psoriatic disease marker, psoriatic patient experience, psoriatic patient quality of life, remission, salt therapy, targeted immune therapy

Procedia PDF Downloads 95

Authors: Vadanasundari Vedarethinam, Kun Qian

Abstract:

The metabolic analysis is more distal over proteomics and genomics engaging in clinics and needs rationally distinct techniques, designed materials, and device for clinical diagnosis. Conventional techniques such as spectroscopic techniques, biochemical analyzers, and electrochemical have been used for metabolic diagnosis. Currently, there are four major challenges including (I) long-term process in sample pretreatment; (II) difficulties in direct metabolic analysis of biosamples due to complexity (III) low molecular weight metabolite detection with accuracy and (IV) construction of diagnostic tools by materials and device-based platforms for real case application in biomedical applications. Development of chips with nanomaterial is promising to address these critical issues. Mass spectroscopy (MS) has displayed high sensitivity and accuracy, throughput, reproducibility, and resolution for molecular analysis. Particularly laser desorption/ ionization mass spectrometry (LDI MS) combined with devices affords desirable speed for mass measurement in seconds and high sensitivity with low cost towards large scale uses. We developed a plasmonic chip for clinical metabolic fingerprinting as a hot carrier in LDI MS by series of chips with gold nanoshells on the surface through controlled particle synthesis, dip-coating, and gold sputtering for mass production. We integrated the optimized chip with microarrays for laboratory automation and nanoscaled experiments, which afforded direct high-performance metabolic fingerprinting by LDI MS using 500 nL of serum, urine, cerebrospinal fluids (CSF) and exosomes. Further, we demonstrated on-chip direct in-vitro metabolic diagnosis of early-stage lung cancer patients using serum and exosomes without any pretreatment or purifications. To our best knowledge, this work initiates a bionanotechnology based platform for advanced metabolic analysis toward large-scale diagnostic use.

Keywords: plasmonic chip, metabolic fingerprinting, LDI MS, in-vitro diagnostics

Procedia PDF Downloads 136

Authors: Wisam H. Benamer, Ehab A. Elfallah, Mohamed A. Elshaari, Farag A. Elshaari

Abstract:

A challenge for laboratories is to provide bacterial identification and antibiotic sensitivity results within a short time. Hence, advancement in the required technology is desirable to improve timing, accuracy and quality. Even with the current advances in methods used for both phenotypic and genotypic identification of bacteria the need is there to develop method(s) that enhance the outcome of bacteriology laboratories in accuracy and time. The hypothesis introduced here is based on the assumption that the chromosome of any bacteria contains unique sequences that can be used for its identification and typing. The outcome of a pilot study designed to test this hypothesis is reported in this manuscript. Methods: The complete chromosome sequences of several bacterial species were downloaded to use as search targets for unique sequences. Visual basic and SQL server (2014) were used to generate a complete set of 18-base long primers, a process started with reverse translation of randomly chosen 6 amino acids to limit the number of the generated primers. In addition, the software used to scan the downloaded chromosomes using the generated primers for similarities was designed, and the resulting hits were classified according to the number of similar chromosomal sequences, i.e., unique or otherwise. Results: All primers that had identical/similar sequences in the selected genome sequence(s) were classified according to the number of hits in the chromosomes search. Those that were identical to a single site on a single bacterial chromosome were referred to as unique. On the other hand, most generated primers sequences were identical to multiple sites on a single or multiple chromosomes. Following scanning, the generated primers were classified based on ability to differentiate between medically important bacterial and the initial results looks promising. Conclusion: A simple strategy that started by generating primers was introduced; the primers were used to screen bacterial genomes for match. Primer(s) that were uniquely identical to specific DNA sequence on a specific bacterial chromosome were selected. The identified unique sequence can be used in different molecular diagnostic techniques, possibly to identify bacteria. In addition, a single primer that can identify multiple sites in a single chromosome can be exploited for region or genome identification. Although genomes sequences draft of isolates of organism DNA enable high throughput primer design using alignment strategy, and this enhances diagnostic performance in comparison to traditional molecular assays. In this method the generated primers can be used to identify an organism before the draft sequence is completed. In addition, the generated primers can be used to build a bank for easy access of the primers that can be used to identify bacteria.

Keywords: bacteria chromosome, bacterial identification, sequence, primer generation

Procedia PDF Downloads 164

Authors: Ulrich Wake, Eniman Syamsuddin

Abstract:

The model for camera model identificaiton is trained using pretrained model ResNet43 and ResNet50. The dataset consists of 500 photos of each phone. Dataset is divided into 1280 photos for training, 320 photos for validation and 400 photos for testing. The model is trained using One Cycle Policy Method and tested using Test-Time Augmentation. Furthermore, the model is trained for 50 epoch using regularization such as drop out and early stopping. The result is 90% accuracy for validation set and above 85% for Test-Time Augmentation using ResNet50. Every model is also trained by slightly updating the pretrained model’s weights

Keywords: ​ One Cycle Policy, ResNet34, ResNet50, Test-Time Agumentation

Procedia PDF Downloads 168