جامعة المعرفة
المصدر المعتمد للمعلومات البحثية والمخرجات هو قاعدة بيانات سكوبس (Elsevier Scopus) مع تدقيق بيانات الباحثين من عمادة البحث العلمي.

Research outputs

المخرجات البحثية

مقالات ومراجعات وأوراق مؤتمرات وفصول كتب، مفهرسة برقم DOI ومربوطة بباحثي الجامعة.

14 مُخرَج نتائج البحث عن «Diagnostic accuracy»

مقالوصول مفتوح2026

Histopathological findings in laparoscopic sleeve gastrectomy specimens and their relation to preoperative endoscopy

Medicine · مجلد 105 (43) · e51246-e51246

Laparoscopic sleeve gastrectomy (LSG) is the most frequently performed bariatric surgery. Although it is generally considered safe, a thorough preoperative assessment is essential to minimize the risk of complications. The need for histopathological examination of resected gastric specimens in bariatric surgery remains a subject of debate, particularly regarding the role of preoperative esophagogastroduodenoscopy (EGD). This study aimed to determine the prevalence of histopathological findings in resected specimens following sleeve gastrectomy and to assess their agreement with preoperative EGD findings at a tertiary center. This retrospective cross-sectional study examined patients who underwent LSG between 2009 to 2021. The data included demographics, comorbidities, preoperative EGD findings, and routine postoperative histopathology of the resected specimens. Diagnostic accuracy of preoperative EGD was assessed against resected-specimen histopathology. Among the 954 patients who underwent LSG, 67.1% were female, and 84.7% were Saudi nationals. Abnormal histopathological findings were observed in 45.5% (434/954) of the resected specimens, with gastritis being the predominant finding, present in 98.2% (426/434) of these. Preoperative EGD was performed in a subgroup of 357 patients (37.4%); in these, gastritis was the most prevalent EGD finding (50.1%). Helicobacter pylori was identified in 9.5% of patients who underwent preoperative EGD and in 8.0% of all resected specimens. Less common histopathological findings were metaplasia (0.6%), gastrointestinal stromal tumors (0.3%), gastric polyps (0.2%) and grade 1 gastric carcinoid (0.1%). Among the 357 patients who underwent preoperative EGD, sensitivity was 99.5%, specificity 98.3%, positive predictive value 98.4%, negative predictive value 99.4% and accuracy 98.9% against resected-specimen histopathology. Gastritis is the most prevalent histopathological finding in resected specimens following sleeve gastrectomy and on preoperative EGD, although significant pathologies are infrequent. In the selected subgroup of patients who underwent preoperative EGD, a normal EGD showed high agreement with normal histopathology of the resected specimen; these findings do not support omitting histopathological examination of resected specimens, and prospective multicenter studies are needed. Helicobacter pylori was frequently identified and was strongly associated with gastritis in unadjusted analyses; premalignant findings were too few to assess.

laparoscopic sleeve gastrectomygastric histopathologygastritisHelicobacter pylori
مقالوصول مفتوح2026

Sleep-Disordered Breathing in Children with Down Syndrome in Saudi Arabia: Current Evidence and a Proposed Care Pathway

Children · مجلد 13 (11) · 1464-1464

Background/Objectives: Children with Down syndrome are at increased risk of obstructive sleep apnea (OSA), which cannot be reliably excluded by symptoms or examination. Saudi evidence remains limited. This review synthesizes international and Saudi evidence and proposes a pediatric care pathway incorporating the transition to adult services. Methods: We conducted a structured narrative review of the English-language literature identified through PubMed/MEDLINE, selected journal websites, and reference lists. The review focused on publications from January 2018 to 17 September 2026, retaining relevant earlier studies. Evidence was synthesized qualitatively without a new meta-analysis or formal risk of bias assessment. Results: Published international estimates indicate that OSA affects approximately 50–79% of children with Down syndrome. American Academy of Pediatrics guidance recommends polysomnography (PSG) at ages 3–4 years regardless of symptoms, with earlier assessment when indicated. Nonrandomized infant intervention studies suggest potential benefits but do not establish an optimal universal screening schedule. Saudi evidence includes a small earlier PSG referral cohort and more recent caregiver surveys; no nationally representative PSG-confirmed prevalence study was identified. Arabic questionnaire validation in a mixed pediatric referral cohort does not establish Down syndrome-specific diagnostic accuracy. Published treatment evidence indicates that adenotonsillectomy often improves OSA, although residual disease commonly requires objective reassessment and individualized management. Conclusions: The evidence supports age-based PSG, earlier assessment when indicated, postoperative reassessment, and individualized multidisciplinary care. Building on this evidence, we propose a Saudi pathway linking referral tracking, family-centered positive airway pressure support, and coordinated transition. Regional networks and registry development remain unevaluated implementation proposals requiring stakeholder consultation, resource assessment, and pilot testing; they do not constitute an endorsed national guideline.

Down syndromeobstructive sleep apneasleep-disordered breathingpolysomnography screening
مقالوصول مغلق2026

Diagnostic Accuracy of Artificial Intelligence versus Clinical Diagnosis in Detecting Acute Otitis Media: A Systematic Review and Meta-analysis

Saudi Journal of Otorhinolaryngology Head and Neck Surgery

Abstract Acute otitis media (AOM) represents a prevalent infection in children globally, leading to considerable morbidity and imposing a substantial burden on healthcare systems. Prompt and precise diagnosis is critical to reducing complications, such as tympanic membrane perforation, hearing impairment, and excessive antibiotic prescribing. Advances in artificial intelligence (AI), particularly deep learning, have created opportunities to enhance diagnostic accuracy and broaden access to care, especially in low-resource settings. This systematic review and meta-analysis aimed to evaluate the diagnostic performance of AI-based systems for detecting AOM compared with conventional clinical diagnosis and to analyze their accuracy relative to human clinicians across different model architectures and diagnostic methods. Following PRISMA-DTA standards and PROSPERO registration, systematic searches were conducted in PubMed, Web of Science, and IEEE Xplore up to July 30, 2025. Eligible studies included human participants with suspected AOM, employed AI-driven diagnostic approaches, and used a clinical reference standard. The Quality Assessment of Diagnostic Accuracy Studies-2 tool assessed bias, and pooled sensitivity and specificity were estimated using a bivariate random-effects model. Nine studies published between 2020 and 2025 met the inclusion criteria. The pooled sensitivity and specificity were 91% (95% confidence interval [CI]: 77%–97%) and 99% (95% CI: 94%–100%), respectively. AI models overall matched or outperformed general practitioners and pediatricians, approaching otolaryngologist-level accuracy. AI-based tools have the potential to improve AOM detection, mitigate inequalities in healthcare access, and promote more effective diagnosis, particularly in underserved regions.

acute otitis mediaartificial intelligencedeep learningdiagnostic accuracy
مقالوصول مفتوح2026

Diagnostic Accuracy of Abdominal Ultrasound in Pediatric Patients with Signs and Symptoms of Intussusception

Medical Principles and Practice · 1-1

OBJECTIVE: Aims of the study were to evaluate the diagnostic performance of abdominal ultrasonography, specifically its positive predictive value, in children younger than 36 months presenting with suspected intussusception to the emergency department of a major tertiary care center in Saudi Arabia and to describe the associated clinical and sonographic features. METHODS: This retrospective study reviewed the medical records and radiological findings of 150 pediatric patients aged less than 36 months who presented with suspected intussusception to the emergency department in a major tertiary care center in Saudi Arabia between 2005 and 2015. Ultrasound was used as the initial diagnostic modality, and findings were confirmed using contrast enema, computed tomography scan, or intraoperative findings when applicable. RESULTS: Out of 150 suspected cases, 36 patients (24.0%) were confirmed to have intussusception. All 36 ultrasound-positive cases were subsequently confirmed by contrast enema, computed tomography, or surgery, giving a positive predictive value of 100% (36/36). Because the 114 ultrasound-negative patients were classified on the basis of clinical course rather than an independent reference standard, sensitivity, specificity, and negative predictive value could not be validly estimated and are not reported. Vomiting and bloody stool were significantly associated with confirmed diagnosis; no significant association was found with gender. CONCLUSION: In this single-center retrospective cohort, a positive abdominal ultrasound reliably predicted confirmed intussusception, supporting its established role as the first-line imaging modality for suspected pediatric intussusception. Although these regional data add local confirmation but given the retrospective design and the absence of an independent reference standard for ultrasound-negative cases, they should be interpreted with caution.

intussusceptionpediatric intussusceptionabdominal ultrasounddiagnostic accuracy
مقالوصول مفتوح2026

Development and validation of a predictive AI model for differential diagnosis of endodontic and non-endodontic orofacial pain: a comparative study

Scientific Reports · مجلد 16 (1)

Differentiating between endodontic and non-endodontic sources of orofacial pain is a diagnostic challenge owing to overlapping clinical presentations. Artificial intelligence (AI) offers a potential solution to improve the diagnostic accuracy of endodontics by analysing complex clinical and radiographic data. To evaluate the performance of an artificial intelligence (AI) model in distinguishing endodontic pain from non-endodontic pain and compare its diagnostic accuracy, sensitivity, and specificity with those of an expert panel. This cross-sectional diagnostic study included 224 participants (134 with endodontic pain and 90 without endodontic pain). Clinical and radiographic data were analysed using a random forest AI model trained on features including radiographic lesions, pain characteristics, and pulp vitality tests. Model performance metrics, including accuracy, sensitivity, specificity, and the area under the receiver operating characteristic (ROC) curve (AUC-ROC), were assessed across the training, validation, and test datasets. The model’s performance was compared to that of an expert panel using statistical tests. The AI model demonstrated an overall diagnostic accuracy of 91.8% on the test set, with sensitivity and specificity of 92.1% and 91.4%, respectively. The AI model showed significantly higher sensitivity (p = 0.03) than the expert panel (accuracy: 89.2%). Feature importance analysis identified radiographic lesions (34%), pain characteristics (28%), and pulp vitality test results (25%) as the most influential predictors. The AI model exhibited superior diagnostic accuracy compared with the expert panel, indicating its potential as a reliable tool for differentiating endodontic pain from non-endodontic sources. Incorporating AI into clinical workflows can enhance diagnostic precision and improve patient outcomes in endodontics.

endodontic painorofacial paindifferential diagnosisartificial intelligence
مقالوصول مفتوح2026

Current Evidence and Clinical Controversies in the Management of Complicated Pneumonia in Children

American Journal of Pediatrics · مجلد 12 (3) · 87-102

Background: Parapneumonic effusion (PPE) and empyema remain serious complications of childhood pneumonia associated with significant morbidity despite advances in antimicrobial therapy and surgical techniques. Accurate disease staging and timely stage-directed intervention are fundamental to optimal outcomes. Objective: To provide a current, evidence-based synthesis of the definition, etiology, diagnosis, and management of complicated pneumonia in children, with particular focus on areas of ongoing clinical controversy. Methods: A narrative review incorporating randomized controlled trials, systematic reviews, meta-analyses, Cochrane reviews, and international clinical guidelines published between 2016 and 2026 was conducted. PubMed was searched through May 2026 using terms including pneumonia, complicated pneumonia, parapneumonic effusion, empyema, VATS, fibrinolysis, decortication, and pediatric. Results: Chest radiography remains the initial imaging modality for suspected complicated pneumonia, with lateral decubitus views needed to assess pleural fluid mobility. However, chest ultrasonography is the preferred imaging modality for evaluating parapneumonic effusions and empyema because of its superior diagnostic accuracy, ability to characterize pleural collections, and absence of ionizing radiation. Management is stage-dependent, combining targeted antibiotic therapy with procedural intervention when indicated. Image-guided pigtail catheter drainage with intrapleural fibrinolytic therapy is effective for most patients. VATS demonstrates particular utility during the fibrinopurulent stage. No single fibrinolytic agent has demonstrated clear superiority; however, tissue plasminogen activator is most widely employed. Open decortication remains reserved for refractory or advanced-stage disease. Conclusion: Early diagnosis, appropriate antibiotics, and prompt intervention or surgery are all important for optimal care. The optimal outcomes require a multidisciplinary, individualized, stage-directed approach. Interventional radiology is appropriate for single loculations, while early VATS is favored for thick pleural rind or multiple loculations. Further high-quality prospective research is needed to establish definitive treatment algorithms.

complicated pneumoniapediatric pneumoniaparapneumonic effusionempyema
مقالوصول مفتوح2026

Non-Invasive Multimarker Strategy Combining IL-17A, Neutrophil–Albumin Ratio, and Fecal Calprotectin for Accurate Discrimination of IBD from IBS-D

International Journal of Molecular Sciences · مجلد 27 (12) · 5450-5450

Differentiating inflammatory bowel disease (IBD) from diarrhea-predominant irritable bowel syndrome (IBS-D) remains a major clinical challenge due to overlapping symptoms and the limited specificity of single biomarkers. A reliable, non-invasive multimarker approach is needed to improve diagnostic accuracy and reduce unnecessary endoscopic procedures. To evaluate the diagnostic performance of serum interleukin-17A (IL-17A), neutrophil-to-albumin ratio (NAR), and fecal calprotectin (FCP), individually and in combination, for discriminating IBD from IBS-D and healthy controls in Egyptian patients. In this case–control study, 300 participants (100 with IBD, 100 with IBS-D, and 100 healthy controls) were enrolled. Serum IL-17A, NAR, and FCP were measured, and subgroup analysis was performed for infected and non-infected IBS-D patients. Diagnostic performance was assessed using receiver operating characteristic (ROC) curve analysis, with optimal cutoffs determined by the Youden index. A combined biomarker model was constructed using logistic regression. All biomarkers demonstrated a significant stepwise increase from healthy controls to IBS-D and IBD (p < 0.001). IL-17A, NAR, and FCP were elevated in IBS-D compared with controls, indicating low-grade inflammation, but were highest in IBD. No significant differences were observed between infected and non-infected IBS-D patients. Among individual markers, NAR showed the highest diagnostic accuracy (AUC = 0.923), followed by FCP (AUC = 0.884) and IL-17A (AUC = 0.859). The combined model significantly improved performance (AUC = 0.973), achieving 89% sensitivity and 96% specificity. IBS-D is associated with measurable systemic and intestinal inflammation independent of infection status. The combined biomarker model integrating IL-17A, neutrophil–albumin ratio, and fecal calprotectin demonstrated promising discriminatory performance for differentiating IBD from IBS-D. These findings suggest the potential applicability of combined non-invasive biomarkers in future diagnostic stratification approaches. However, the model was developed and evaluated within a single cohort, and external validation in independent populations is required before future potential clinical application. A multimarker diagnostic panel integrating IL-17A, neutrophil–albumin ratio, and fecal calprotectin demonstrated promising diagnostic performance for differentiating inflammatory bowel disease from IBS-D. The combined model may contribute to future diagnostic stratification strategies in patients with chronic diarrhea. However, these findings were derived from a single cohort and require validation in independent populations before broader clinical application.

inflammatory bowel diseasediarrhea-predominant irritable bowel syndromeIL-17Aneutrophil-to-albumin ratio
مقالوصول مفتوح20256استشهاد· Semantic Scholar

Maize leaf disease multiclass classification and recognition for sustainable agriculture using multi preceptive deep learning model

Discover Sustainability · مجلد 6 (1)

Agriculture sector is faced with perennial challenges that threaten both its productivity and sustainability. Among the greatest threats to cereal crops is disease, especially on cereal grains such as maize. Maize is an important grain that has grown globally, yet it often falls prey to maize leaf disease, a destructive and prevalent disorder. The consequences of these diseases go beyond individual farmers; reduced yields destabilize supply chains, market stability, and global efforts towards creating sustainable food systems. The prevalence of leaf diseases adversely affects crop productivity, which directly impacts the objective of sustainable agriculture. In order to address this problem, technology, more specifically artificial intelligence, has been a game-changer. Adopting cutting-edge research for maize disease detection not only raises diagnostic accuracy but also supports sustainable agricultural practices. This approach encourages effective input use, supports food security, minimizes environmental degradation, and provides farmers with accurate tools, all of which contribute to long-term agricultural resilience and sustainability. However, the incorporation of AI in farming is confronted by a number of challenges. Numerous hindrances hinder precise detection and categorization of maize leaf diseases via artificial intelligence methods. In tackling the limitations, the current study introduces an AI-based approach. It applied Multi-scaled Xception pre-trained models to extract deep features from images. The models were fine-tuned with varying weights for advancing the feature extraction so as to enhance the likelihood of correct visual classification. In addition to its strong accuracy, the research provides a formal and strict mathematical formulation, and different optimization methods further establish the effectiveness of the model. Additionally, the examination of fusion operators helps to improve the interpretability of the model. The expected model was tested with a confidence interval, showing that its performance remains within set limits.

maize leaf diseaseplant disease classificationfine-tuningfusion operators
مقالوصول مفتوح20253استشهاد· Semantic Scholar

Evaluating liver type fatty acid binding protein as a diagnostic and prognostic biomarker in metabolic dysfunction-associated steatotic liver disease in pediatric patients

PLoS ONE · مجلد 20 (9) · e0333581-e0333581

BACKGROUND: Metabolic dysfunction-associated steatotic liver disease (MASLD), is a common liver disorder, predicted to increase globally. Currently, non-invasive methods are proposed for the assessment of (MASLD). This study aimed to investigate the use of serum Liver Type Fatty Acid Binding Protein (L-FABP) concentration as a diagnostic and prognostic biomarker in pediatric MASLD patients and to evaluate its relationship with steatosis and fibrosis. METHODS: An observational, cross-sectional study on paediatric MASLD patients. Serum levels of L-FABP and hepatic biochemical markers were measured and analyzed. Statistical analyses evaluated the association between L-FABP and other markers, while logistic regression and ROC curves assessed its diagnostic accuracy. RESULTS: Serum L-FABP levels showed a significant difference between the MASLD and control groups (P < 0.0001). The results of logistic regression revealed that each one-unit elevation of L-FABP level was associated with 144.5% higher odds of being MASLD (95% CI: 129.3% - 167.8%). A receiver operating characteristics (ROC) curve was constructed to assess the diagnostic accuracy of L-FABP. The resulted area under the ROC curve (AUC) was 0.885. The cutoff value was 5.7 ng/ mL, with sensitivity of 72.73%, and a specificity of 93.62%. The results also showed that the odds ratio of progressing from stage F2 to F3 increases by 108.9% (95% CI: 87.2% - 141.4%) for each one-unit increase in serum L-FABP level. CONCLUSION: L-FABP shows promise as a non-invasive biomarker for diagnosing and monitoring MASLD in pediatric patients. Its association with disease stages suggests its utility in assessing disease progression, particularly in advanced stages.

liver fatty acid binding proteinnon-alcoholic fatty liver diseasepediatric patientsnon-invasive biomarkers
مقالمفتوح (مستودع)20252استشهاد· Semantic Scholar

The Role of Artificial Intelligence in Early Detection and Risk Stratification of Coronary Artery Disease Using ECG and Imaging Data

Journal of Pioneering Medical Science · مجلد 14 (09) · 103-107

Coronary Artery Disease (CAD) remains a leading cause of morbidity and mortality worldwide. To evaluate the diagnostic performance of AI models in the early detection and risk stratification of CAD using ECG and imaging data and to compare their accuracy with cardiologist interpretation. Methods: This cross-sectional analytical study was conducted in Saudia, included 185 patients with suspected CAD who underwent both ECG and imaging evaluation. AI-based models, including convolutional neural networks for ECG and deep learning algorithms for imaging, were applied to detect CAD and stratify patients into risk categories. Cardiologist-confirmed diagnosis served as the reference standard. Results: The AI-ECG model achieved a sensitivity of 88.5%, specificity of 82.0% and an AUC of 0.90 (95% CI: 0.86–0.94). When ECG and imaging data were combined, diagnostic accuracy improved, with sensitivity of 92.4%, specificity of 85.2% and an AUC of 0.93 (95% CI: 0.89–0.96). AI-based risk stratification categorized 54 patients (29.2%) as low risk, 78 (42.2%) as intermediate risk and 53 (28.6%) as high risk. Confirmed CAD prevalence correlated strongly with AI-predicted risk groups, with 22.2% in the low-risk group and 88.7% in the high-risk group. Conclusion: Artificial intelligence demonstrates high accuracy in the early detection and risk stratification of CAD using ECG and imaging data. AI models performed comparably to cardiologists and offered significant efficiency gains. Integration of AI into cardiovascular workflows may enable earlier intervention, optimized resource allocation and improved patient outcomes. Further validation across larger and more diverse populations is warranted.

coronary artery diseaseartificial intelligenceearly detectionrisk stratification
مقالوصول مغلق2025

HOW PRIMARY HEALTH CARE PHYSICIANS IN SAUDI ARABIA HANDLE SUDDEN SENSORINEURAL HEARING LOSS: A CROSS-SECTIONAL STUDY.

PubMed (366) · 93-100

BACKGROUND: In order to enhance patient outcomes, Sudden Sensorineural Hearing Loss (SSNHL) must be diagnosed and treated quickly. In the early detection and treatment of SSNHL, primary care physicians (PCPs) are essential. The purpose of this study was to assess Saudi Arabian primary healthcare physicians diagnostic abilities, knowledge and practices related to SSNHL. METHODS: A cross-sectional survey of 371 PCPs in Saudi Arabia was carried out. An electronic questionnaire measuring participants knowledge, diagnosis and management methods, referral practices of SSNHL was used to gather data. SPSS version 26 was used for the statistical analysis, and a p-value of <0.05 was considered significant. RESULTS: 124 (33.4%) of participants showed good knowledge, 123 (33.2%) fair knowledge, and 124 (33.4%) poor knowledge, with a mean knowledge score of 10.58±3.85. Most physicians 282 (76%) attempted to differentiate between sensorineural and conductive hearing loss, primarily using tuning fork tests 261 (70.4%) and audiological evaluations 258 (69%). While 327 (88.1%) recognized SSNHL as requiring urgent referral for audiological testing, only 184 (49.6%) could accurately define the condition within the critical 72-hour window. Corticosteroids were prescribed by 138 (37.2%) for suspected SSNHL and 185 (49.9%) for confirmed cases. Good knowledge was significantly associated with fewer years of practice, urban-based patient care, and walk-in clinic settings (p<0.05). CONCLUSION: Although the majority of Saudi Arabian PCPs agree that SSNHL is urgent, there are still gaps in their understanding and adherence to evidence-based practices. To increase diagnostic accuracy, timely referrals, and the effective management of SSNHL cases, more training and education are advised.

sudden sensorineural hearing lossprimary care physiciansphysician knowledgediagnostic accuracy
مقالوصول مفتوح20241استشهاد· Semantic Scholar

Enhancing multiclass COVID-19 prediction with ESN-MDFS: Extreme smart network using mean dropout feature selection technique

PLoS ONE · مجلد 19 (11) · e0310011-e0310011

Deep learning and artificial intelligence offer promising tools for improving the accuracy and efficiency of diagnosing various lung conditions using portable chest x-rays (CXRs). This study explores this potential by leveraging a large dataset containing over 6,000 CXR images from publicly available sources. These images encompass COVID-19 cases, normal cases, and patients with viral or bacterial pneumonia. The research proposes a novel approach called "Enhancing COVID Prediction with ESN-MDFS" that utilizes a combination of an Extreme Smart Network (ESN) and a Mean Dropout Feature Selection Technique (MDFS). This study aimed to enhance multi-class lung condition detection in portable chest X-rays by combining static texture features with dynamic deep learning features extracted from a pre-trained VGG-16 model. To optimize performance, preprocessing, data imbalance, and hyperparameter tuning were meticulously addressed. The proposed ESN-MDFS model achieved a peak accuracy of 96.18% with an AUC of 1.00 in a six-fold cross-validation. Our findings demonstrate the model's superior ability to differentiate between COVID-19, bacterial pneumonia, viral pneumonia, and normal conditions, promising significant advancements in diagnostic accuracy and efficiency.

COVID-19 detectionchest radiographypneumonia classificationfeature selection
مقالمفتوح (مستودع)2024

A Review of Imaging Modalities in Paediatric Traumatic Brain Injury: Evaluating Diagnostic Accuracy and Clinical Outcomes: Cross Sectional Study

Journal of Advanced Trends in Medical Research · مجلد 1 (3) · 784-790

Abstract Background: Traumatic brain injury (TBI) in children is still a major concern amongst healthcare worldwide as it causes raised morbidity and mortality rate. Identification of TBI cases is therefore paramount in treatment with diagnostic imaging techniques such as the computed tomography (CT) and magnetic resonance imaging (MRI) amongst others. However, deciding between the two methods has been a challenge since radiation exposure by CT and the limitation of MRI, which include longer time for scan and most importantly, need for use of sedation amongst children. This review aims at analysing and comparing accuracy of CT and MRI in diagnosing paediatric TBI; the effects of the two MRI scans on prognosis and the contribution of the two scans in management decision-making. Furthermore, the views on safety issues connected with radiation in CT as well as whether the modern MRI methods can improve the diagnostic potential without safety issues are also discussed. Methods: A literature search using the PubMed, Scopus and Google Scholar databases was done with terms such as ‘point of care’, ‘clinical decision support’, ‘decision support system’ was used with an emphasis on articles published in the past 15 years. Article titles used were ‘paediatric traumatic brain injury’, ‘CT in paediatric TBI’, ‘MRI in paediatric TBI’ and ‘diagnostic accuracy of imaging in TBI’. The review of articles involved only patients aged between 0 and 18 years diagnosed with TBI through CT or MRI that provided data on diagnostic accuracy, clinical management and safety considerations. Results: CT is used in the management of acute TBI because it is fast and widely available, especially for instance in emergency situations. MRI, however, has the advantages of producing higher sensitivity in identification of diffuse axonal injuries and less evident pathologies of the brain that may not be identified in a CT. However, MRI has limitations such as long time to perform a scan, is expensive and requires administration of sedatives to children making it less suitable for use in the acute care settings. Third, despite its effectiveness, CT exposes the patient to radiation that increases his/her chances of getting cancer especial if the patient is a child. Newer techniques in MRI have emerged which enhance the capacity of diagnosis of paediatric TBI and its further management and prognosis; these are the diffusion tensor imaging and susceptibility-weighted imaging. Conclusions: CT and MRI should both be used in the evaluation of paediatric TBI because they each provide information that the other cannot. CT scan has remained the primary imaging modality in the acute setting because of the speed in availability and to assess the critical lesions, whereas MRI offers a detailed examination of TBI important in the post-acute phase. This review is helpful in establishing possible guidelines that will help in the use of these imaging techniques in paediatric TBI that will enhance the detection of the injury without exposing the patients to additional harm. More investigation is, therefore, required to standardise the techniques and protocols that improve the efficiency of imaging procedures for therapeutic processes, while avoiding adverse effects such as radiation hazards.

pediatric traumatic brain injurycomputed tomographymagnetic resonance imagingdiagnostic accuracy
مقالمفتوح (مستودع)202222استشهاد· Semantic Scholar

Barnacles Mating Optimizer with Deep Transfer Learning Enabled Biomedical Malaria Parasite Detection and Classification

Computational Intelligence and Neuroscience · مجلد 2022 · 1-12

Biomedical engineering involves ideologies and problem-solving methods of engineering to biology and medicine. Malaria is a life-threatening illness, which has gained significant attention among researchers. Since the manual diagnosis of malaria in a clinical setting is tedious, automated tools based on computational intelligence (CI) tools have gained considerable interest. Though earlier studies were focused on the handcrafted features, the diagnostic accuracy can be boosted through deep learning (DL) methods. This study introduces a new Barnacles Mating Optimizer with Deep Transfer Learning Enabled Biomedical Malaria Parasite Detection and Classification (BMODTL-BMPC) model. The presented BMODTL-BMPC model involves the design of intelligent models for the recognition and classification of malaria parasites. Initially, the Gaussian filtering (GF) approach is employed to eradicate noise in blood smear images. Then, Graph cuts (GC) segmentation technique is applied to determine the affected regions in the blood smear images. Moreover, the barnacles mating optimizer (BMO) algorithm with the NasNetLarge model is employed for the feature extraction process. Furthermore, the extreme learning machine (ELM) classification model is employed for the identification and classification of malaria parasites. To assure the enhanced outcomes of the BMODTL-BMPC technique, a wide-ranging experimentation analysis is performed using a benchmark dataset. The experimental results show that the BMODTL-BMPC technique outperforms other recent approaches.

malaria parasite detectionmalaria parasite classificationBarnacles Mating Optimizertransfer learning