Efficient Diagnosis Research Articles

Clinical Characteristics and Whole Exome Sequencing Analysis in Serbian Cases of Clubfoot Deformity-Single Center Study.

Recognized as one of the most serious musculoskeletal deformities, occurring in 1-2 per 1000 newborns, 80% of clubfeet are idiopathic while 20% present with associated malformations. The etiopathogenesis of clubfoot is described as multifactorial, including both genetic and environmental risk factors. The aim of this study was to analyze possible genetic causes of isolated and syndromic clubfoot in Serbian children, as well as to correlate clinical and genetic characteristics that would provide insight into clubfoot etiopathogenesis and possibly contribute to global knowledge about clinical features of different genetically defined disorders. We evaluated 50 randomly selected, eligible children with clubfoot aged 3 to 16 years that were initially hospitalized and treated at University Children's Hospital between November 2006 and November 2022. The tested parameters were gender, age, dominant foot, affected foot, degree of deformity, treatment, neuromuscular disorders, positive family history, and maternal smoking. According to the presence of defined genetic mutation/s by whole exome sequencing (WES), patients were separated into two groups: positive (with genetic mutation/s) and negative (without genetic mutation/s). Seven patients were found to be positive, i.e., with genetic mutation/s. A statistically significant difference between categorical variables was found for families with a history of clubfoot, where more than half (57.14%) of patients with confirmed genetic mutation/s also had a family history of genetic mutation/s (p = 0.023). The results from this study further expand the genetic epidemiology of clubfoot. This study contributes to the establishment of genetic diagnostic strategies in pediatric patients with this condition, which can lead to more efficient genetic diagnosis.

Biological window excited up-conversion persistent luminescence nanoparticles for bioimaging and photodynamic therapy

Near-infrared (NIR) persistent luminescence nanoparticles (PLNPs) have inherent advantages for high-sensitivity bioimaging due to the separation of excitation and emission light. However, the single-wavelength emission of NIR PLNPs for bioimaging limits their use in photodynamic therapy (PDT). Herein, a biological window excited up-conversion (UC) PLNPs, Zn3Ga2SnO8:Cr3+,Yb3+,Ho3+ (ZGS), was reported for bioimaging and PDT. ZGS exhibits NIR persistent luminescence (PersL) after red LED excitation and visible UCL under 980 nm excitation. The NIR PersL is designed for in vivo bioimaging; the visible UCL is used to activate photosensitizer (PS) to generate reactive oxygen species (ROS) for PDT. The dual-functional ZGS with UCL and PersL provides an effective method for bioimaging and PDT, which is expected to further promote the application of PLNPs in the integration of efficient diagnosis and treatment.

Processing of clinical notes for efficient diagnosis with feedback attention-based BiLSTM.

Predicting a patient's future health state through the analysis of their clinical records is an emerging area in the field of intelligent medicine. It has the potential to assist healthcare professionals in prescribing treatments safely, making more accurate diagnoses, and improving patient care. However, clinical notes have been underutilized due to their complexity, high dimensionality, and sparsity. Nevertheless, these clinical records hold significant promise for enhancing clinical decision. To tackle these problems, a novel feedback attention-based bidirectional long short-term memory (FABiLSTM) model has been proposed for more effective diagnosis using clinical records. This model incorporates PubMedBERT for filtering irrelevant information, enhances global vector word embeddings for numerical representations and K-means clustering, and performs to explore term frequency and inverse document frequency intricacies. The proposed approach excels in capturing information, aiding accurate disease prediction. The predictive capability is further enhanced with the help of a billiards-inspired optimization algorithm. The effectiveness of the FABiLSTM method has been assessed with the MIMIC-III dataset, yielding impressive results in accuracy, precision, F1 score, and recall score of 98.52%, 98%, 98.2%, and 98.2% individually. These results reveal ways in which the proposed technique excels in comparison with current practices.

#996 Validation of peritoneal NGAL as a biomarker for peritonitis: a comparison between laboratory-base method and rapid stick test

Abstract Background and Aims Neutrophil gelatinase-associated lipocalin (NGAL) is a protein involved in iron homeostasis, inflammation, and fibrosis. Initially discovered in human granulocytes, NGAL is found in various tissues. In renal contexts, NGAL's small size (23-25 kDa) and positive charge aid glomerular filtration and absorption in the proximal tubule. Notably, elevated NGAL levels were identified in peritoneal fluids during peritonitis in 2009, establishing it as a biomarker for early Peritoneal Dialysis (PD)-associated peritonitis diagnosis for values more than 100 μg/L. While our medical centre currently relies on the lab-based NGAL assay (NGALlab), advancements introduce the NGAL dipstick test (NGALds), offering a rapid and semi-quantitative colorimetric assessment. This study compares NGALds with NGALlab in clinical practice, assessing NGALds's potential for early peritonitis detection in PD patients' peritoneal fluid. Method This study involves a validation of diagnostic accuracy conducted through a retrospective analysis of parallel samples obtained from peritoneal effluents. Samples were collected from both healthy patients during routine analysis and from cases with suspected or confirmed peritonitis. Both NGALlab and NGALds analyses were conducted on each sample. The analysis aimed to evaluate the performance of the new NGALds by comparing it with the established NGALlab. Peritoneal NGALlab quantification employed the standard BioPorto test (BioPorto Diagnostics, Hellerup, Denmark), utilizing a particle-enhanced turbidimetric immunoassay. The novel NGALds is a rapid semi-quantitative assay that measures NGAL levels in biological fluids through colourimetric test strips, utilizing an antibody sandwich lateral flow dipstick test. NGAL values were categorized into colour-coded levels: 25 μg/L, 50 μg/L, 100 μg/L, 150 μg/L, 300 μg/L, and 600 μg/L. Statistical analyses were performed using SPSS Statistics 26.0 software. Spearman rank correlation coefficients (Rs) assessed categorical groups of NGAL values for peritoneal NGALds and NGALlab tests. A graphic comparison of these two tests was presented through a Bland-Altman plot Results Out of 301 peritoneal effluent samples, 156 were diagnosed with suspected peritonitis by ISPD Criteria. As Table 1 showed, NGALds showed a strong correlation with NGALlab categories (Rs = 0.876, P = 10−96), successfully diagnosing 96% (150 out of 156) peritonitis cases. Discrepancies between NGALlab and NGALds, visualized in the Bland-Altman plot (Fig. 1), were most notable when NGAL values exceeded the 600 μg/L threshold. However, this difference doesn't impact clinical significance, as high NGAL values remain diagnostically for peritonitis with both methods. Conclusion In conclusion, our study underscores a significant correlation between NGAL values measured by the laboratory method (NGALlab) and the NGAL dipstick test (NGALds). Importantly, NGALds exhibited a strong capability, correctly identifying 96% of peritonitis cases determined by NGALlab. Beyond statistical correlation, the NGAL dipstick emerges as a valid alternative for swift evaluation in patients presenting symptoms suggestive of peritonitis. Its ease of use, rapidity, and semi-quantitative colorimetric assessment make NGALds a patient-friendly tool. This user-friendly characteristic holds immense potential for streamlined clinical workflows, allowing for prompt and efficient peritonitis diagnosis.

#758 NGAL dipstick for peritonitis: bridging the gap between rapid assessment and clinical efficiency in peritoneal dialysis

Abstract Background and Aims Neutrophil gelatinase-associated lipocalin (NGAL) is a versatile protein known for its multifunctional roles, extending beyond its conventional use as a biomarker. It actively participates in crucial biological processes such as inflammation, proliferation, and migration. This study seeks to evaluate NGALds, a recently developed dipstick test, in comparison to the established laboratory method (NGALlab) for the early detection of peritonitis related to peritoneal dialysis (PD). The focus of the investigation lies in analyzing peritoneal fluid to develop a rapid and effective diagnostic tool, aiming to enhance the management of peritonitis. Method A retrospective analysis was undertaken to validate diagnostic accuracy, utilizing parallel samples obtained from peritoneal effluents. Samples were obtained from both PD stable patients undergoing routine analysis and from PD patients with suspected or confirmed peritonitis. The assessment of NGALds involved a direct comparison with the established NGALlab. Peritoneal NGALlab quantification was conducted using the BioPorto test, employing a particle-enhanced turbidimetric immunoassay. The NGALds, a rapid semi-quantitative assay, utilized colorimetric test strips and an antibody sandwich lateral flow dipstick test. The greatest value of NGAL detected by dipstick is 600 μg/L. Statistical analyses, including Spearman rank correlation coefficients (Rs), were performed with SPSS Statistics 26.0 software. Additionally, ROC analysis was carried out using white cell count and percentage of Neutrophils in peritoneal fluids as the gold standard. Results Among the 301 peritoneal effluent samples analyzed, 156 were diagnosed with suspected peritonitis using NGALlab and ISPD criteria. Each sample underwent analyses with both NGALlab and NGALds. As depicted in Fig. 1, NGALds exhibited a robust correlation with NGALlab categories (Rs = 0.876, P < 0.001), accurately identifying 96% (150 out of 156) of peritonitis cases. Discrepancies between NGALlab and NGALds were most evident when NGAL values exceeded the 600 μg/L threshold. Nevertheless, these variations did not impact clinical significance, as both methods consistently diagnosed elevated NGAL values indicative of peritonitis. After ROC analysis, which yielded an AUC of 0.82 (p < 0.001) (Fig. 2), the Youden Index was employed to identify a threshold value of 100 μg/L for the diagnosis of suspected peritonitis. Importantly, the application of this threshold to NGALds demonstrated a positive predictive value of 0.64 and a negative predictive value of 0.87. Conclusion In conclusion, our study reinforces the significant correlation between NGAL values obtained through the laboratory standard (NGALlab) and the novel NGAL dipstick test (NGALds). Notably, NGALds exhibited high efficacy, accurately identifying 96% of peritonitis cases diagnosed by NGALlab. This robust performance positions the NGAL dipstick as a valuable and accessible alternative for rapid assessment in patients exhibiting symptoms indicative of peritonitis. The user-friendly attributes of NGALds not only make it a practical diagnostic tool but also a patient-centric one. Furthermore, the high negative predictive value provides confidence in considering NGALds as a frontline diagnostic tool for suspected peritonitis. The ease of use and prompt results open a promising avenue for improving clinical workflows, offering an opportunity for expedited and efficient peritonitis diagnosis. For instance, NGALds could find utility in centres where NGAL is unavailable in the laboratory or at the patient's home.

5G-enabled smart hospitals: Innovations in patient care and facility management.

Smart hospitals represent the pinnacle of healthcare innovation, leveraging cutting-edge technologies to transform patient care and facility management. This article addresses the pressing need for effective implementation of 5G technology in smart hospitals, aiming to enhance connectivity, improve patient outcomes, and drive operational efficiency. The methodology employed involves a comprehensive review of existing literature, case studies, and expert insights to analyze the impact of 5G on various aspects of smart hospital operations. The article highlights the significance of 5G technology in enabling real-time data analytics, remote monitoring, and telemedicine, thus revolutionizing healthcare delivery. By providing high-speed, low-latency connectivity, 5G facilitates seamless communication and collaboration among healthcare providers, leading to more efficient diagnosis, treatment, and patient care. Additionally, the adoption of 5G enables smart hospitals to leverage artificial intelligence (AI)-based solutions for predictive analytics, personalized medicine and enhanced patient engagement. Furthermore, the article explores the potential of 5G-enabled smart hospitals in enhancing disaster preparedness and emergency response efforts. Case studies and examples demonstrate how 5G technology can improve situational awareness, coordinate resources, and deliver timely care during natural disasters and pandemics. Overall, this article underscores the transformative impact of 5G technology on smart hospitals and emphasizes the importance of embracing innovation to meet the evolving needs of patients and communities. By adopting 5G technology, smart hospitals can usher in a new era of healthcare delivery characterized by enhanced connectivity, improved patient outcomes, and unparalleled efficiency.

The Superiority of Fine-tuning over Full-training for the Efficient Diagnosis of COPD from CXR Images

This research investigates the use of deep learning for diagnosing lung diseases like Chronic Obstructive Pulmonary Disease (COPD) using Chest X-rays (CXR). The study compares the impact of deep learning on improving these diagnoses by comparing the performance of models trained from the scratch with those enhanced through fine-tuning established architectures like InceptionV3, ResNet50, and VGG-19. The study revealed that fine-tuning pre-trained models offers significant benefits: faster convergence, improved stability, and increased accuracy. Data augmentation techniques were found to be particularly useful when dealing with limited or unbalanced datasets. A custom CNN model, Iyke-Net, showed promising results when fine-tuned. Interestingly, it was observed that models using grayscale images outperformed those using colour images in disease classification, suggesting that colour information might be less critical than previously thought for certain diagnostic procedures. The study emphasizes the importance of balancing model complexity with computational efficiency and diagnostic accuracy. It advocates for refining existing deep learning models for COPD diagnosis from CXR images, paving the way for further innovations in AI-enhanced medical diagnostics.

Development of a Simple Method to Detect the Carbapenemase-Producing Genes blaNDM, blaOXA-48-like, blaIMP, blaKPC, and blaVIM Using a LAMP Method with Lateral Flow DNA Chromatography.

Infections by carbapenemase-producing Enterobacterales constitute a global public health threat. The rapid and efficient diagnosis of Enterobacterales infection is critical for prompt treatment and infection control, especially in hospital settings. We developed a novel loop-mediated isothermal amplification (LAMP) method combined with DNA chromatography to identify five major groups of carbapenemase-producing genes (blaNDM, blaOXA-48-like, blaIMP, blaKPC, and blaVIM). This method uses DNA-DNA hybridization-based detection in which LAMP products can be easily visualized as colored lines. No specific technical expertise, expensive equipment, or special facilities are required for this method, allowing its broad application. Here, 73 bacteria collections including strains with carbapenemase-producing genes were tested. Compared to sequencing results, LAMP DNA chromatography for five carbapenemase-producing genes had a sensitivity and specificity of 100% and >97%, respectively. This newly developed method can be a valuable rapid diagnostic test to guide appropriate treatments and infection control measures, especially in resource-limited settings.

Analysis of hot spots and trends in rolling bearing fault diagnosis research based on scientific knowledge mapping

As a key component of mechanical equipment, real-time monitoring and diagnosis of rolling bearings play a critical role in ensuring the stable operation of equipment and the safety of operators. In order to present the current status and trends of fault diagnosis research on rolling bearings more intuitively, the scientific knowledge mapping was used to visualize and analyze the relevant literature in the article. The results show that the number of publications in this area of research has grown significantly in recent years, with China, India, the United States, and England having contributed significantly. The journals such as MECHANICAL SYSTEMS AND SIGNAL PROCESSING, MEASUREMENT, and JOURNAL OF SOUND AND VIBRATION have played an important role in disseminating cutting-edge technologies in this field. In addition, the exploration of modern methods based on data-driven and artificial intelligence, as well as their application to real-world problems, are gradually becoming the focus of research. Through summarising and analysing, the application of modern data processing techniques, the development of more efficient and practical intelligent fault diagnosis techniques, and the close integration of laboratory research and practical applications will become future research trends.

A Mobile-Based System for Detecting Plant Leaf Diseases Using Deep Convolutional Neural Network

Plant diseases pose a significant challenge to agriculture in India, causing substantial losses in crop production each year. Limited-resource farmers often struggle with diagnosing these diseases accurately, especially when relying on visual observation of leaf symptoms. Hence, there is an urgent need to enhance the detection, monitoring, and prediction of crop diseases to mitigate agricultural losses effectively. To address this challenge, we propose a mobile-based system empowered by Machine Learning (ML) and computer vision tailored for the Indian context. Our system utilizes Convolutional Neural Networks (CNNs) as the core deep learning engine to classify 37 disease categories commonly found in Indian crops. We have curated a comprehensive dataset comprising 96,206 images of plant leaves, encompassing both healthy and infected, for training, validation, and testing purposes. The user interface of our system is designed as an Android mobile application, enabling farmers to capture images of diseased plant leaves effortlessly. Upon image capture, the system swiftly identifies the disease category and presents it to the user along with a confidence percentage. This functionality empowers farmers to take timely action to protect their crops, thereby reducing reliance on incorrect fertilizers that may exacerbate plant stress. Furthermore, we evaluated the performance of our system using various metrics, including classification accuracy and processing time. Our results indicate an impressive overall classification accuracy of 94% across the 37 disease classes prevalent in 14 different crop species commonly cultivated in India. In essence, our ML-powered mobile-based solution offers Indian farmers a robust tool for efficient crop disease diagnosis and management, ultimately contributing to the enhancement of agricultural productivity and sustainability in the country.

Analysis of the Effects of Population Structure and Environmental Factors on Rice Nitrogen Nutrition Index and Yield Based on Machine Learning

With the development of rice varieties and mechanized planting technology, reliable and efficient nitrogen and planting density status diagnosis and recommendation methods have become critical to the success of precise nitrogen and planting density management in crops. In this study, we combined population structure, plant shape characteristics, environmental weather conditions, and management information data using a machine learning model to simulate the responses of the yield and nitrogen nutrition index and developed an ensemble learning model-based nitrogen and planting density recommendation strategy for different varieties of rice types. In the third stage, the NNI and yield prediction effect of the ensemble learning model was more significantly improved than that of the other two stages. The scenario analysis results show that the optimal yields and nitrogen nutrition indices were obtained with a density and nitrogen amount of 100.1 × 104 plant/ha and 161.05 kg·ha−1 for the large-spike type variety of rice, 75.08 × 104 plant/ha and 159.52 kg·ha−1 for the intermediate type variety of rice, and 75.08 × 104 plant/ha and 133.47 kg·ha−1 for the panicle number type variety of rice, respectively. These results provide a scientific basis for the nitrogen application and planting density for a high yield and nitrogen nutrition index of rice in northeast China.

Machine Learning Approaches for ADHD Detection

This report explores the application of deep learning convolutional neural networks (CNNs) for analyzing brain MRI scans to assist in the diagnosis of Attention Deficit Hyperactivity Disorder (ADHD) syndrome. ADHD is a neuro developmental disorder that affects millions of individuals worldwide, characterized by difficulties in attention, hyperactivity, and impulsivity. Traditional methods of diagnosis rely on subjective assessments and behavioral observations, leading to inaccuracies and delays in treatment. Leveraging the power of deep learning CNNs for MRI analysis offers the potential for more objective and efficient diagnosis, facilitating timely intervention and personalized treatment strategies

Detecting Diabetic Foot Ulcer with CNN and CapsNet: A Comparative Investigation of Model Performance

Diabetic foot ulcer (DFU) poses a substantial health risk to patients and healthcare resources, necessitating accurate and efficient diagnosis. This study harnesses the power of convolutional neural networks (CNNs) and capsule networks (CapsNets) to redefine DFU classification, aiming for enhanced accuracy and efficiency. By integrating state-of-the-art deep learning architectures, we address the limitations of existing diagnostic methodologies. Through comprehensive data pre-processing, feature extraction, and classification, our system seeks to improve diagnostic precision and contribute to better patient outcomes. A comparative analysis between CNNs and CapsNets evaluates key performance metrics, guiding future advancements in medical image diagnosis. Furthermore, computational timing assessments ensure practicality in medical settings. This research underscores the potential of deep learning in revolutionizing medical image diagnosis and emphasizes the critical role of accurate DFU detection in diabetic care.

Deep learning-based efficient diagnosis of periapical diseases with dental X-rays

Diagnosis of periapical diseases usually requires a lot of time and effort from the dentist to perform a series of examinations and evaluations, although X-rays have been available to assist in visualizing the condition of the apical region of the tooth. To achieve efficient automated detection and diagnosis of periapical diseases (periapical granuloma, periapical abscess, periapical cysts, and condensing osteitis) by dental X-rays, a deep learning-based approach is proposed, which includes an improved Mask R-CNN-based lesion area segmentation network and a neural network classifier based on six texture features extracted from the segmented lesion regions. The results demonstrate that the average pixel accuracy of lesion area segmentation is over 0.97, while the average Dice Similarity Coefficient for segmentation is over 0.95. The accuracy, precision, recall, and F1 score of this method for the diagnosis of periapical diseases are all above 0.99. Precise segmentation and accurate classification of four distinct types of periapical diseases are achieved using this method, making it possible to create automated systems that can assist in the clinical diagnosis of periapical diseases, potentially streamlining the diagnostic process, reducing the workload of dentists, and improving overall patient care.

QCML: Qualified Contrastive Machine Learning methodology for infectious disease diagnosis in CT images

The COVID-19 pandemic has had a terrible effect on human health, and computer-aided diagnostic (CAD) systems for chest computed tomography have emerged as a potential alternative for COVID-19 diagnosis. Yet, since the cost of data annotation may be excessively costly in the medical area, there is a shortage of data that has been annotated. A considerable quantity of labelled data is required in order to train a CAD system to a high level of accuracy. The study aims to describe an automatic and precise COVID-19 diagnostic method that utilizes a restricted amount of labelled CT images to solve this problem. The framework of the system is known as Qualified Contrastive Machine Learning (QCML), and the improvements that we have made may be summed up as follows: 1) In order to make use of all of the image's characteristics, we combine features with a two-dimensional discrete wavelet transform. 2) We employ the COVID-Net encoder with a redesign that focuses on the efficiency of learning and the task specificity of the data. 3) In order to strengthen our capacity to generalize, we have implemented a novel pertaining technique that is based on Qualified Contrastive Machine Learning. 4) In order to get better categorization results, we have included an extra auxiliary work. The application of Qualified Contrastive Machine Learning methodology for infectious disease diagnosis in CT images offers an accuracy of 93.55%, a recall of 91.59%, a precision of 96.92%, and an F1-score of 94.18%, demonstrating the potential for accurate and efficient COVID-19 diagnosis with limited labelled data.

Near-infrared Light-Triggered Size-Shrinkable theranostic nanomicelles for effective tumor targeting and regression

Most nanomedicines with suitable sizes (normally 100–200 nm) exhibit favorable accumulation in the periphery of tumors but hardly penetrate into deep tumors. Effective penetration of nanomedicines requires smaller sizes (less than 30 nm) to overcome the elevated tumor interstitial fluid pressure. Moreover, integrating an efficient diagnostic agent in the nanomedicines is in high demand for precision theranostics of tumors. To this end, a near-infrared light (NIR) −triggered size-shrinkable micelle system (Fe3O4@AuNFs/DOX-M) coloaded antitumor drug doxorubicin (DOX) and biomodal imaging agent magnetic gold nanoflower (Fe3O4@AuNFs) was developed to achieve efficient theranostic of tumors. Upon the accumulation of Fe3O4@AuNFs/DOX-M in the tumor periphery, a NIR laser was irradiated near the tumor sites, and the loaded Fe3O4@Au NFs could convert the light energy to heat, which triggered the cleavage of DOX-M to the ultra-small micelles (∼5 nm), thus realizing the deep penetration of micelles and on-demand drug release. Moreover, Fe3O4@AuNFs in the micelles could also be used as CT/MRI dual-modal contrast agent to “visualize” the tumor. Up to 92.6 % of tumor inhibition was achieved for the developed Fe3O4@AuNFs/DOX-M under NIR irradiation. This versatile micelle system provided a promising drug carrier platform realizing efficient tumor dual-modal diagnosis and photothermal-chemotherapy integration.

Machine and deep learning methods in identifying malaria through microscopic blood smear: A systematic review

Despite the persistency of World Health Organization to eliminate malaria since 1987, malaria disease continues to pose a significant threat to global health. As the severity of malaria persists over the years, there is a critical need for an automated diagnosis system for more efficient diagnosis and effective treatment administration. To mitigate the increase in mosquito-borne diseases, there has been a heightened interest in the application of Artificial intelligence (AI), specifically deep learning. With the assistance of the Preferred Reporting Items for Systematic Review and Meta-Analyses (PRISMA) framework, an extensive review of current state of automated malaria diagnosis systems utilizing machine learning and deep learning approaches was performed across eight scientific databases, with 50 articles shortlisted from the years 2015–2023. Besides, identifying the research gaps, we synthesise the existing literature, analyse the outcomes, and explore the critical parameters that influence model performance. From the review, the prevailing models primarily focus on binary classification while disregarding cross-dataset validations and multi-stage classification. This gap challenges the delivering effective treatments, especially considering potential drug resistance. Established protocols and classification models are needed to anticipate the specific malaria species. The keywords in automated malaria diagnosis that we identified include machine learning, deep learning, transfer learning, and convolutional neural networks. Through examinations of the constraints in current methodologies, we provide valuable suggestions that could propel the field of automated malaria diagnosis. This systematic review provides a comprehensive overview, critical insights, and a roadmap for future research endeavours in this vital domain of healthcare.

Sistem Pakar Diagnosa Paget's Disease dengan Menerapkan Algoritma Teorema Bayes

Paget's Disease, also known as Paget's Disease of the bone, is a bone disorder that typically arises in the elderly, particularly after the age of 40. The risk of this disease increases with advancing age. Aging and genetic factors are believed to play a role in the development of this condition. Symptoms include bone pain, bone fragility, abnormal bone growth, changes in bone shape, decreased hearing, as well as symptoms such as headaches, dizziness, and joint complaints. Expert systems or artificial intelligence draw inspiration from the knowledge of experts to analyze situations. With algorithms like the Bayes theorem, this system provides solutions to emerging issues. In this context, expert systems aid doctors in identifying diseases without face-to-face consultations. The Bayes theorem serves as the foundation for this mechanism, emulating expert abilities. This research applies the Bayes theorem for an efficient and objective diagnosis of Paget's Disease. The results indicate a strong likelihood of patients having Paget's Disease at 73.87%. Consequently, the use of expert systems has the potential to enhance efficiency and objectivity in handling cases, assisting doctors in formulating diagnoses based on presenting symptoms.

COMPARATIVE ANALYSIS OF FAULT DIAGNOSIS IN POWER SYSTEM USING EVOLUTIONARY COMPUTATION AND MACHINE LEARNING

This paper provides a comparative analysis of fault diagnosis in power systems using evolutionary computation and machine learning techniques. Power system faults, including line-to-ground, line-to-line, and three-phase faults, pose significant challenges to the stability and reliability of electrical grids. Efficient and accurate fault diagnosis is crucial for minimizing downtime and maintaining optimal power delivery. This research evaluates the performance of various evolutionary computation algorithms such as genetic algorithms, particle swarm optimization and differential evolution alongside machine learning methods including decision trees, support vector machines, and k-nearest neighbor, in diagnosing power system faults. The study compares the accuracy, speed, and reliability of these methods in detecting and classifying faults under different system conditions. The findings highlight the strengths and limitations of EC and ML-based fault diagnosis techniques in power systems, providing valuable insights for researchers and practitioners in the field. Key Words: Fault diagnosis, Power system, Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Differential Evolution(DE) , Support Vector Machine (SVM) , Decision Tree (DT), K-Nearest Neighbors (KNN).

A novel battery abnormality diagnosis method using multi-scale normalized coefficient of variation in real-world vehicles

Accurate and efficient diagnosis of battery voltage abnormality is crucial for the safe operation of electric vehicles. This paper proposes an innovative battery voltage abnormality diagnosis method based on a normalized coefficient of variation in real-world electric vehicles. Vehicle and laboratory data are collected and analyzed, with joint preprocessing to improve data quality, and battery voltages are log-transformed to improve the contribution of anomalous voltage fluctuations. The normalized coefficient of variation is proposed to detect the fluctuation inconsistency of cell voltage, and the risk coefficient rule is formulated by Z-score and normalization. Furthermore, the validity and robustness are verified by laboratory and real-world battery faults. The results demonstrate that the optimal slide step and calculation window for real-world under-voltage fault are 10 and 40, and those for laboratory lithium plating and real-world thermal runaway are both 10 and 50, respectively. More importantly, this study introduces a battery abnormality diagnosis strategy based on the vehicle T-box, anticipated to be widely implemented to ensure the safety of real-vehicle operations. This method not only enhances the accuracy and efficiency of detecting electric vehicle battery abnormalities, but also offers a practical solution to prevent battery related faults.