Conventional Diagnostic Methods Research Articles

Machine learning techniques for diagnosis of rare diseases from medical images

Introduction/Background: Rare diseases are life-threatening or chronically debilitating conditions that affect a small percentage of the population. Early and accurate diagnosis of rare diseases is challenging due to their complexity and limited understanding. Conventional diagnostic methods are often inadequate, time-consuming, and expensive. Machine learning (ML) has emerged as a promising technique for the analysis of medical images to support the diagnosis of various diseases including rare disorders. ML algorithms can learn complex patterns from large medical imaging datasets to aid clinicians in disease diagnosis, prognosis, and detection of complications. Materials and Methods: A structured search was conducted in electronic databases, including PubMed, Scopus, Web of Science, and Google Scholar to identify peer-reviewed articles published between 2013 to 2023 related to ML-based diagnosis of rare diseases from medical images. A total of 187 articles were identified after removing duplicates. The titles and abstracts of retrieved articles were screened to determine their relevance based on the research objective. Finally, 51 full-text articles were selected for the final review. The key data extracted from selected studies included diseases, imaging modalities, ML algorithms, performance metrics, datasets, and limitations. Results: Most studies evaluated deep learning-based ML techniques, with convolutional neural networks (CNN) being the most applied algorithm. CNNs were mainly used to classify rare diseases based on specific imaging features in X-rays, CT, and MRI scans. Diseases frequently investigated included cardiovascular, neurological, and rare genetic disorders. Publicly available datasets such as Deep Lesion, MSD, and ChestX-ray14 were commonly utilized. Most studies reported high classification accuracy ranging from 80-95% on test datasets. However, limited generalizability due to small private datasets and lack of external validation were limitations. Discussion: The results demonstrate the potential of deep learning for the image-based diagnosis of rare diseases. Features learned from large imaging data sets enabled CNNs to distinguish subtle abnormalities. Hybrid models combining CNNs with other techniques like recurrent neural networks further improved performance. Overall, ML showed promise as a decision support tool. However, more multi-center validation studies are needed using larger and diverse datasets before clinical adoption. Standardization of performance metrics and reporting is also required to establish reliability and generalizability. Conclusion: This comprehensive review provided insights into ongoing research applying ML to medical images for rare disease diagnosis. While initial results are encouraging, further work is still necessary before ML can be reliably used in clinical decision making. Larger collaborative efforts and open-source datasets are needed to advance the field. Standardization of ML frameworks can also promote reproducible research and comparison of different methodologies.

Cough2COVID-19 detection using an enhanced multi layer ensemble deep learning framework and CoughFeatureRanker

In response to the pressing requirement for precise and easily accessible COVID-19 detection methods, we present the Cough2COVID-19 framework, which is cost-effective, non-intrusive, and widely accessible. The conventional diagnostic methods, notably the PCR test, are encumbered by limitations such as cost and invasiveness. Consequently, the exploration of alternative solutions has gained momentum. Our innovative approach employs a multi-layer ensemble deep learning (MLEDL) framework that capitalizes on cough audio signals to achieve heightened efficiency in COVID-19 detection. This study introduces the Cough2COVID-19 framework, effectively addressing these challenges through AI-driven analysis. Additionally, this study proposed the CoughFeatureRanker algorithm, which delves into the robustness of pivotal features embedded within cough audios. The CoughFeatureRanker algorithm selects the most prominent features based on their optimal discriminatory performance from 15 features to detect COVID-19. The effectiveness of the CoughFeatureRanker algorithm within the ensemble framework is scrutinized, confirming its favorable influence on the accuracy of COVID-19 detection. The Cough2COVID-19 (MLEDL) framework achieves remarkable outcomes in COVID-19 detection through cough audio signals, boasting a specificity of 98%, sensitivity of 97%, accuracy of 98%, and an AUC score of 0.981. Our framework asserts its supremacy in precise non-invasive screening through an exhaustive comparison with cutting-edge methodologies. This groundbreaking innovation holds the potential to enhance urban resilience by transforming disease diagnosis, offering a significant approach to curtailing transmission risks and facilitating timely interventions in the ongoing battle against the pandemic.

Implantable Intraocular Fluorescence Sensor for Visualized Monitoring of Alzheimer's Disease

AbstractWith an increase in the older individuals, the global incidence of Alzheimer's disease (AD) is increasing. Early diagnosis of AD necessitates long‐term monitoring; however, conventional diagnostic methods such as positron emission tomography (PET) and magnetic resonance imaging (MRI) are unsuitable for frequent use because of infrastructure limitations. The eye, connected to the brain via the optic nerve, offers a potential window for monitoring neurodegenerative diseases. This study presents a novel system for continuous intraocular monitoring using a fluorescent aptamer‐conjugated intraocular lens (FAIOL). FAIOL emits fluorescent signals in the presence of beta‐secretase‐1 (BACE1), an enzyme associated with amyloid beta 1–42 production. These signals can be analyzed using mobile phone applications. In vitro, experiments demonstrates that FAIOL responded to BACE1 by detecting low concentrations of the target molecule over extended periods. Ex vivo tests using porcine eyeballs shows an increase in the fluorescence signal intensity by more than 8% within 5 h in the presence of BACE1. The integrated image analysis program reduces sensor noise and provides numerical signal values, facilitating a straightforward interpretation. FAIOL holds significant potential as an innovative platform for the early diagnosis and long‐term monitoring of AD and promises improved patient outcomes through timely intervention and ongoing surveillance.

Rapid Molecular Diagnostics in Vulvovaginal Candidosis.

Vulvovaginal candidosis (VVC) is a common condition among women, with current diagnostic methods relying on clinical evaluation and laboratory testing. These traditional methods are often limited by the need for specialized training, variable performance, and lengthy diagnostic processes, leading to delayed treatment and inappropriate antifungal use. This review evaluates the efficacy of molecular diagnostic tools for VVC and provides guidance on their application in clinical practice. A literature search was conducted using PubMed to identify studies evaluating rapid diagnostic tests specifically for vulvovaginal Candida isolates. Inclusion criteria focused on studies utilizing molecular diagnostics for the detection of Candida species in VVC. Articles discussing non-vaginal Candida infections, non-English studies, and animal or in vitro research were excluded. Twenty-three studies met the inclusion criteria, predominantly evaluating nucleid acid amplification tests/polymerase chain reaction (NAAT/PCR) assays and DNA probes. PCR/NAAT assays demonstrated high sensitivity and specificity (>86%) for VVC diagnosis, outperforming conventional diagnostic methods. Comparatively, DNA probes, while simpler, exhibited lower sensitivity. The included studies were mostly observational, with only one randomized controlled trial. Emerging diagnostic technologies, including artificial intelligence and integrated testing models, show promise for improving diagnostic precision and clinical outcomes. Molecular diagnostics offer a significant improvement in VVC management, though traditional methods remain valuable in resource-limited settings.

Evaluating CD1a Immunohistochemistry for Tegumentary Leishmaniasis Diagnosis in the New World: A Focus on Colombia.

Leishmaniasis, a chronic vector-borne disease caused by parasites of the genus Leishmania, presents diagnostic challenges. Conventional diagnostic methods struggle with accurate visualization of these parasites. Immunostaining with CD1a has demonstrated effectiveness in visualizing Leishmania parasites, particularly in the Old World. However, the application of CD1a immunostaining in Colombian leishmaniasis remains unexplored. To determine the utility of CD1a as an immunomarker in detecting chronic forms of tegumentary leishmaniasis. This proof-of-concept study involved 48 paraffin-embedded samples categorized into 3 groups: moderate-to-high parasite load (n = 15), low load (n = 15), and chronic granulomatous inflammation (n = 13); 5 samples diagnosed with cutaneous histoplasmosis. These samples were stained with the immunomarker CD1a clone EP3622 for comparative analysis. In addition, CD1a immunohistochemistry was compared with 18S rDNA qPCR and hematoxylin-eosin staining to evaluate its performance in relation to these established methods. CD1a immunohistochemistry was positive in 46.51% of the samples evaluated. This immunomarker showed lower sensitivity and negative predictive value than 18S rDNA qPCR and hematoxylin-eosin staining; specificity and negative predictive value were consistent. ROC indicated inferior discrimination for leishmaniasis compared with 18 s rDNA qPCR and hematoxylin-eosin staining. Immunohistochemistry for CD1a could be a diagnostic support in the detection of chronic forms of tegumentary leishmaniasis.

PCR- and wash-free detection of serum miRNA via signaling probe hybridization.

Detection of microRNAs (miRNAs) in the serum is an effective liquid biopsy technique for cancer diagnosis. However, conventional diagnostic methods are time-consuming and complex. Therefore, in this study, we established a signaling probe-based DNA microarray system for miRNA detection. PCR, fluorescence labeling, and washing are not necessary for signaling probes. Four probes were designed using different miRNAs as diagnostic cancer markers. The developed system is useful for various miRNAs, regardless of their target lengths (18-26-mer) and GC content (36%-89%). Here, all the assays were performed within 40 min. Overall, our signaling probe-based DNA hybridization system facilitates the simple and rapid detection of serum miRNAs without the need for gene amplification, fluorescence labeling and washing.

Pulp Vitality Diagnosis by Means of an Optical Pulp Scanning Device.

This study aimed to evaluate the diagnostic accuracy of an Optical Pulp Scanning (OPS) device. A total of 421 teeth from 107 emergency patients were investigated. Pulp vitality was assessed using conventional diagnostic methods (ConvDia), cold pulp testing (CPT), and a final diagnosis (FinDia) based on the pulp chamber contents (PCCs) of teeth requiring endodontic treatment (EmeTe). Following ConvDia, OPS screening was performed, endodontic access was prepared, and the FinDia was established. The specificity, sensitivity, as well as positive and negative predictive values of ConvDia, CPT, and FinDia were calculated against the OPS results. The null hypothesis stated that specificity and sensitivity would be equal to or lower than 90% and 80%, respectively. OPS sensitivity was 66.2% and 72.2% (EmeTe) for ConvDia, 66.2% and 69.8% (EmeTe) for CPT, and 76.9% for FinDia. Specificity was 26.4% and 25.5% (EmeTe) for ConvDia, 26.9% and 21.7% (EmeTe) for CPT, and 31.5% for FinDia. These results suggest that, at its current stage of development, the OPS device does not provide an acceptable level of diagnostic accuracy, particularly in vital teeth.

Amplification-free detection of Ascochyta blight in chickpea using a simple molecular beacon assay

Ascochyta blight is a major biotic stress that limits chickpea production globally. Fungicide application remains one of the effective control measures for the endemic spread. Due to the serious threat that synthetic fungicides pose to crop quality, early diagnosis of the pathogen is imperative. Whilst there have previously been several conventional lab-based diagnostic methods developed for early detection of Ascochyta rabiei, they require long assay times, specialised equipment and facilities, and trained personnel to process the samples. To overcome this challenge, a rapid amplification-free detection assay using a molecular beacon probe was developed. The method consists of a simple assembly assay that accurately detects pathogen within 30 min. The developed assay is species-specific and has a similar sensitivity level as conventional amplification-based methods. Although it is still a lab-based technique, considering the simplicity of the assay, it has a great potential to be developed further as a reliable in-field diagnostic device for early detection and quantification of fungal pathogen spores.

The Microbiome and Atopic Dermatitis

: The microbiome consists of a collection of microorganisms, their genetic material, and their interactions within a specific biological environment. Atopic dermatitis is a complex, long-lasting inflammatory skin condition that causes dryness and itchiness. It is often associated with other conditions like allergic rhino conjunctivitis and asthma. Contemporary methods that do not require culturing have been developed to identify microorganisms and their genetic makeup, which can have both positive and negative effects on their host. There are indications that microorganisms in the gut and on the skin could potentially influence the progression of atopic dermatitis. Although antiseptic treatments have been used for many years, conventional diagnostic methods and genomics are now beginning to help us understand that targeted interventions for imbalanced microbial communities might eventually be incorporated into a comprehensive therapeutic approach.

Utilizing Multi-layer Perceptron for Esophageal Cancer Classification Through Machine Learning Methods

Aims This research paper aims to check the effectiveness of a variety of machine learning models in classifying esophageal cancer through MRI scans. The current study encompasses Convolutional Neural Network (CNN), K-Nearest Neighbor (KNN), Recurrent Neural Network (RNN), and Visual Geometry Group 16 (VGG16), among others which are elaborated in this paper. This paper aims to identify the most accurate model to facilitate increased, improved diagnostic accuracy to revolutionize early detection methods for this dreadful disease. The ultimate goal is, therefore, to improve the clinical practice performance and its results with advanced machine learning techniques in medical diagnosis. Background Esophageal cancer poses a critical problem for medical oncologists since its pathology is quite complex, and the death rate is exceptionally high. Proper early detection is essential for effective treatment and improved survival. The results are positive, but the conventional diagnostic methods are not sensitive and have low specificity. Recent progress in machine learning methods brings a new possibility to high sensitivity and specificity in the diagnosis. This paper explores the potentiality of different machine-learning models in classifying esophageal cancer through MRI scans to complement the constraints of the traditional diagnostics approach. Objective This study is aimed at verifying whether CNN, KNN, RNN, and VGG16, amongst other advanced machine learning models, are effective in correctly classifying esophageal cancer from MRI scans. This review aims at establishing the diagnostic accuracy of all these models, with the best among all. It plays a role in developing early detection mechanisms that increase patient outcome confidence in the clinical setting. Methods This study applies the approach of comparative analysis by using four unique machine learning models to classify esophageal cancer from MRI scans. This was made possible through the intensive training and validation of the model using a standardized set of MRI data. The model’s effectiveness was assessed using performance evaluation metrics, which included accuracy, precision, recall, and F1 score. Results In classifying esophageal cancers from MRI scans, the current study found VGG16 to be an adequate model, with a high accuracy of 96.66%. CNN took the second position, with an accuracy of 94.5%, showing efficient results for spatial pattern recognition. The model of KNN and RNN also showed commendable performance, with accuracies of 91.44% and 88.97%, respectively, portraying their strengths in proximity-based learning and handling sequential data. These findings underline the potential to add significant value to the processes of esophageal cancer diagnosis using machine learning models. Conclusion The study concluded that machine learning techniques, mainly VGG16 and CNN, had a high potential for escalated diagnostic precision in classifying esophageal cancer from MRI imaging. VGG16 showed great accuracy, while CNN displayed advanced spatial detection, followed by KNN and RNN. Thus, the results set new opportunities for introducing advanced computational models to the clinics, which might transform strategies for early detection to improve patient-centered outcomes in oncology.

NEURO DEEP FUZZY GENETIC ALGORITHM APPROACH FOR CLASSIFICATION AND DETECTION OF BRAIN TUMOR FROM LARGE DATASETS

Brain tumors represent one of the most critical and life-threatening diseases. Early detection and accurate classification are essential for effective treatment planning and survival rate improvement. With the exponential growth of medical data, particularly in imaging and diagnostic datasets, traditional algorithms face limitations in handling large-scale, high-dimensional data efficiently. Conventional machine learning and diagnostic methods often struggle with classification accuracy, computational complexity, and overfitting in large, noisy datasets. Addressing these issues is crucial for the development of robust diagnostic tools capable of handling real-world clinical data. This paper presents a novel hybrid approach combining Neural Networks, Deep Learning, Fuzzy Logic, and Genetic Algorithms, termed Neuro Deep Fuzzy Genetic Algorithm (NDFGA), for the classification and detection of brain tumors from large datasets. Neural Networks and Deep Learning architectures are leveraged for feature extraction and hierarchical learning. Fuzzy Logic improves interpretability and manages uncertainty in medical data, while Genetic Algorithms optimize feature selection and model parameters. This hybrid method is designed to maximize classification accuracy while minimizing false positives and computational overhead. The proposed approach was tested on a large brain tumor dataset comprising over 10,000 MRI scans. The NDFGA approach demonstrated superior performance compared to standalone methods. It achieved a classification accuracy of 97.8%, a sensitivity of 96.5%, and a specificity of 98.1%. The model also showed improved robustness in handling large datasets, reducing false positives by 12% and computational time by 15% compared to traditional methods. This hybrid model presents a scalable and efficient solution for brain tumor detection, especially in clinical environments.

Leveraging photosensitive and thermally stable luminescent Ba2ZnWO6:Eu3+, M+ (M+= Na, K , and Li) nanophosphor for targeted non-invasive and stain-free visualization of cracked tooth syndrome

The cracked tooth syndrome poses a significant challenge in dentistry, thereafter untreated cases often lead to severe complications, such as pulpitis or complete tooth fracture, ultimately contributing to tooth loss. However, the conventional diagnostic methods to visualize microcracks in the tooth suffer from severe drawbacks, such as inaccurate cold stimulation, discomfort with probing, impractical staining techniques, and difficulty in distinguishing harmless craze lines from pathological cracks. To address this challenge, for the first time, we are proposing a novel approach by utilizing luminescent Ba2ZnWO6:Eu3+ (3 mol %), K+ (1 wt %) nanophosphor for improved imaging and diagnosis of cracked tooth syndrome. Herein, the double perovskite structured Ba2ZnWO6:Eu3+ (1–11 mol %), M+ (M+ = Na, K, and Li (1 wt %)) nanophosphors were synthesized via the sonochemical route. The photoluminescence emission spectra of the prepared Ba2ZnWO6:Eu3+ (1–11 mol %) nanophosphors displaying distinct peaks at 583, 595, 613, 662, and 720 nm, which ascribed to transitions from state 5D0 to 7FJ (J = 1–4) state of the Eu3+ ions, respectively. By adopting a strategic charge compensation mechanism, the enhancement in the luminescence emission intensity of about 1.5-fold was achieved after co-doping K+ (1 wt %) with Ba2ZnWO6:Eu3+ (3 mol %) nanophosphor. The photometric studies of the phosphors portray their orange-red emission with excellent quantum efficiency (82.52 %), and color purity (∼ 99 %). The emission intensity was sustained up to 73.71 % at 473 K, indicating excellent thermal stability of the phosphor. The in vitro cytotoxicity assessments of the optimized nanophosphor demonstrated its biocompatibility on normal non-malignant oral fibroblasts. The visualized microcracks in the tooth using optimized Ba2ZnWO6:Eu3+ (3 mol %), K+ (1 wt %) nanophosphor under UV excitation of UV 365 and 395 nm light revealed the orientation of microcracks, crack width, depth of the crack, and microcrack branching without any stain. The aforementioned results demonstrated that the proposed methodology paves the way for a new avenue in dental imaging technology with the potential to revolutionize and improve patient care outcomes.

Classification of Malaria Using Convolutional Neural Network Method on Microscopic Image of Blood Smear

Malaria, a critical global health issue, can lead to severe complications and mortality if not treated promptly. The conventional diagnostic method, involving a microscopic examination of blood smears, is time-consuming and requires extensive expertise. To address these challenges, computer-assisted diagnostic methods have been explored. Among these, Convolutional Neural Networks (CNN), a deep learning technique, has shown considerable promise for image classification tasks, including the analysis of microscopic blood smear images. In this study, we employ the NIH Malaria dataset, which consists of 27,558 images, to train a CNN model. The dataset is divided into parasitized (malaria-infected) and uninfected. The CNN architecture designed for this study includes three convolutional layers and two fully connected layers. We compare the performance of this model with that of a pre-trained VGG-16 model to determine the most effective approach for malaria diagnosis. The proposed CNN model demonstrates high accuracy, achieving a value of 96.81%. Furthermore, it records a recall of 0.97, a precision of 0.97, and an F1-score of 0.97. These metrics indicate a robust performance, outperforming previous studies and highlighting the model's potential for accurate malaria diagnosis. This study underscores the potential of CNN in medical image classification and supports its implementation in clinical settings to enhance diagnostic accuracy and efficiency. The findings suggest that with further refinement and validation, such models could significantly improve the speed and reliability of malaria diagnostics, ultimately aiding in better disease management and patient outcomes.

Enabling Intelligence on the Edge: Leveraging Edge Impulse to Deploy Multiple Deep Learning Models on Edge Devices for Tomato Leaf Disease Detection

Tomato diseases, including Leaf blight, Leaf curl, Septoria leaf spot, and Verticillium wilt, are responsible for up to 50% of annual yield loss, significantly impacting global tomato production, valued at approximately USD 87 billion. In Ghana, there is a yield gap of about 50% in tomato production, which requires drastic measures to increase the yield of tomatoes. Conventional diagnostic methods are labor-intensive and impractical for real-time application, highlighting the need for innovative solutions. This study addresses these issues in Ghana by utilizing Edge Impulse to deploy multiple deep-learning models on a single mobile device, facilitating the rapid and precise detection of tomato leaf diseases in the field. This work compiled and rigorously prepared a comprehensive Ghanaian dataset of tomato leaf images, applying advanced preprocessing and augmentation techniques to enhance robustness. Using TensorFlow, we designed and optimized efficient convolutional neural network (CNN) architectures, including MobileNet, Inception, ShuffleNet, Squeezenet, EfficientNet, and a custom Deep Neural Network (DNN). The models were converted to TensorFlow Lite format and quantized to int8, substantially reducing the model size and improving inference speed. Deployment files were generated, and the Edge Impulse platform was configured to enable multiple model deployments on a mobile device. Performance evaluations across edge hardware provided metrics such as inference speed, accuracy, and resource utilization, demonstrating reliable real-time detection. EfficientNet achieved a high training accuracy of 97.12% with a compact 4.60 MB model size, proving its efficacy for mobile device deployment. In contrast, the custom DNN model is optimized for microcontroller unit (MCU) deployment. This edge artificial intelligence (AI) technology integration into agricultural practices offers scalable, cost-effective, and accessible solutions for disease classification, enhancing crop management, and supporting sustainable farming practices.

A urine-based liquid biopsy for detection of upper tract urothelial carcinoma: a self-matched study

BackgroundTo establish the pathological diagnosis of UTUC before treatment is profitable. At present, the conventional pathological diagnostic methods have certain problems. Besides, the urine-based DNA methylation test have been already utilized to detect bladder cancer.ObjectiveTo evaluate the sensitivity and specificity of DNA methylation plus 17 genes mutation test and compare the combined test with cytology.Materials and methodsWe included 45 patients from April 2019 to May 2022, all of whom underwent radical nephroureterectomy (RNU), nephrectomy, diagnostic ureteroscopy or tissue biopsy. Before surgery, the urine samples were collected for DNA methylation plus 17 genes mutation test and cytology. The test performance was calculated, and comparative ROC curves were drawn.ResultsThe median age of the patients was 67 years. The Kappa value of the DNA methylation plus 17 genes mutation test and tissue pathology was 0.59 (p<0.001). The sensitivity/specificity/PPV/NPV of DNA methylation plus 17 genes mutation test was 86/80/94/62% compared with 29/100/100/29% for cytology. The AUC of DNA methylation plus 17 genes mutation test was 0.829 (p<0.001).The mutated gene proportion of UTUC patients was 51.43% for TERT and 25.71% for TP53.ConclusionThe test performance of DNA methylation plus 17 genes mutation test was satisfactory, which may replace cytology in the future. Further multicenter studies with larger samples are needed to confirm the clinical value of this promising method.Novelty & impact statementsWe evaluated the diagnostic efficacy of a urine-based liquid biopsy for the detection of UTUC and compared the combined test with cytology. We found satisfactory results and concluded that the test could partly replace cytology. Further studies are needed.

Aptamers: precision tools for diagnosing and treating infectious diseases.

Infectious diseases represent a significant global health challenge, with bacteria, fungi, viruses, and parasitic protozoa being significant causative agents. The shared symptoms among diseases and the emergence of new pathogen variations make diagnosis and treatment complex. Conventional diagnostic methods are laborious and intricate, underscoring the need for rapid, accurate techniques. Aptamer-based technologies offer a promising solution, as they are cost-effective, sensitive, specific, and convenient for molecular disease diagnosis. Aptamers, which are single-stranded RNA or DNA sequences, serve as nucleotide equivalents of monoclonal antibodies, displaying high specificity and affinity for target molecules. They are structurally robust, allowing for long-term storage without substantial activity loss. Aptamers find applications in diverse fields such as drug screening, material science, and environmental monitoring. In biomedicine, they are extensively studied for biomarker detection, diagnostics, imaging, and targeted therapy. This comprehensive review focuses on the utility of aptamers in managing infectious diseases, particularly in the realms of diagnostics and therapeutics.

Transforming respiratory tract infection diagnosis in the kingdom of saudi arabia through point-of-care testing: A white paper for policy makers

With the evident increased prevalence of respiratory tract infections (RTIs) such as Respiratory Syncytial Virus (RSV), influenza, Group A Streptococcus (GAS), and COVID-19, the conventional diagnostic methods are considered sub-optimal in providing timely management to patients in the Kingdom of Saudi Arabia (KSA). Gaps in current diagnostics are magnified by the Kingdom's unique demographic composition, comprising 11.9 million foreign workers, and the annual influx of over 10 million pilgrims. Current gaps in timely diagnosis leads to delays in treatment, misuse of antibiotics, and protracted hospital stays, subsequently compromising patient care, and escalating healthcare costs. KSA healthcare stakeholders suggest that the integration of rapid molecular Point-of-Care Testing (POCT) into the Kingdom's healthcare infrastructure is an absolute necessity. This publication serves as an urgent call for action aimed at healthcare policymakers in Saudi Arabia, to review the existing diagnostic challenges and include rapid POCTs in the Saudi healthcare strategy for respiratory infections.

Vaginal microbiota of pregnant women with Ureaplasma urealyticum and Mycoplasma hominis infections.

The association between preterm birth and Mycoplasma species such as Mycoplasma hominis and Ureaplasma urealyticum has been extensively investigated. In a clinical setting, conventional diagnostic methods for them involve culture methods for Mycoplasma spp. and Ureaplasma spp., along with PCR tests. However, the clinical utility of these tests remains controversial, highlighting the necessity for more robust and reliable methods for identifying and understanding Mycoplasma infections. This study aimed to assess the distribution of microbiota in pregnant women with Mycoplasma hominis and Ureaplasma urealyticum infection by the comparison of conventional diagnostic methods with vaginal microbial community analysis. This prospective case-control study involved 228 Korean pregnant women and utilized vaginal microbial community analysis, Ureaplasma/Mycoplasma culture, and 12-multiplex PCR for sexually transmitted diseases. Cross-correlation analysis in SPSS 27 compared the results of two conventional methods with vaginal microbial community analysis. R software generated box plots depicting the relative abundance of microorganisms. Network analysis was conducted using Cytoscape. Positive Ureaplasma urealyticum culture findings were observed in 60.2% of patients, with 76.4% positive for Ureaplasma parvum PCR and 13.2% positive for Ureaplasma urealyticum PCR. Mycoplasma hominis culture was positive only in two patients, while Mycoplasma hominis PCR was positive in eight women. Vaginal microbial community analysis identified significant differences in relative abundances of Gardnerella species type I and Fannyhessea vaginae between the Ureaplasma urealyticum PCR positive and negative groups. Mycoplasma hominis PCR positive patients exhibited significant differences in 11 bacterial species, including Gardnerella species I and Fannyhessea vaginae. This study suggests that STD-PCR may be more accurate than Ureaplasma/Mycoplasma culture for the diagnosis of Mycoplasma hominis and Ureaplasma urealyticum infection. Also, the presence of Gardnerella species I and Fannyhessea vaginae implies their potential influences on Ureaplasma urealyticum and Mycoplasma hominis infections based on results of vaginal microbial community analysis. Therefore, vaginal microbial community analysis may give the more information of their pathophysiology.

Decoding the hidden realm: Molecular pioneering unravelling osteoarticular tuberculosis diagnosis

Osteoarticular tuberculosis (TB), a form of extrapulmonary tuberculosis, refers to the involvement of Mycobacterium tuberculosis (M.tb) in the bones and joints. While pulmonary tuberculosis is the most common form, osteoarticular TB represents a relatively rare but significant manifestation, accounting for approximately 1–3% of all TB cases. Accurate and timely diagnosis plays a pivotal role in the management of osteoarticular TB. Conventional diagnostic methods for osteoarticular TB, such as acid-fast bacilli smear microscopy and culture, have limitations in terms of sensitivity, specificity, and turnaround time. The purpose of this review is to comprehensively evaluate and synthesize the existing literature on molecular pioneering in osteoarticular TB diagnosis. Molecular techniques, such as nucleic acid amplification tests and gene-based assays, have emerged as promising tools for diagnosing TB. These techniques target specific genetic sequences of M.tb, enabling rapid and sensitive detection of the pathogen. However, the diagnostic accuracy, advantages, and limitations of these molecular techniques in the context of osteoarticular TB diagnosis require further investigation and consolidation of evidence. Furthermore, this review aims to identify areas for future research and development in the field of molecular diagnostics for osteoarticular TB.

Improved diagnostic accuracy for leptomeningeal dissemination in pediatric brain tumors using contrast-enhanced FLAIR imaging

Abstract Background Central nervous system cancers are a leading cause of childhood cancer-related mortality. Accurate staging and assessment of leptomeningeal spread, particularly in aggressive neoplasms such as embryonal tumors, is crucial for treatment planning and prognosis. Conventional diagnostic methods, relying on magnetic resonance imaging (MRI) and cerebrospinal fluid (CSF) cytology, have limitations, including high false-negative rates and sensitivity issues. In this retrospective study, we aim to compare the diagnostic sensitivity of contrast-enhanced T2-weighted fluid-attenuated inversion recovery (CE-T2W-FLAIR) and 2D and 3D contrast-enhanced T1-weighted imaging (CE-T1WI) for detecting leptomeningeal disease. Methods We retrospectively reviewed 1372 MRI brain studies of 297 patients aged 1–19 years. We included only those MRI examinations adhering to our neuro-oncology protocol while excluding incomplete or suboptimal studies. A control group without leptomeningeal disease was matched for disease and age. Three groups of 2 neuroradiologists each, blinded to case status, reviewed the images using various sequences. The results were compared using the McNemar test and chi-squared test for P-values. Results The sensitivity of CE-T2W-FLAIR sequence was significantly higher compared with that of CE-T1WI (P = .025). There was no statistically significant difference between the sensitivity of 2D CE-T1WI and 3D CE-T1WI (P = .3173). The specificity of the 3D CE-T1WI was significantly lower compared with those of CE-T2W-FLAIR and 2D CE-T1WI (P = .014). The positive predictive values for CE-T2W-FLAIR, 2D CE-T1WI, and 3D CE-T1WI were 100%, 100%, and 68.4%, respectively, whereas the negative predictive values were 100%, 85.7%, and 85.71%, respectively. Conclusions The inclusion of CE-T2W-FLAIR in the MRI protocol improves sensitivity and specificity in diagnosing leptomeningeal spread in pediatric brain tumors.