Abnormal Cases Research Articles

Sewage water management and healthcare monitoring in IoT using Optimized deep residual network

ABSTRACT The Internet of Things (IoT) is termed as the interconnection of different smart objects with respect to devices. In this research, two different application scenarios are considered to show the efficiency of the Deep Residual Network (DRN) through multicast routing. The entities involved in the process are IoT nodes, IoT heads, and base stations (BS). The nodes are allowed to capture the information, and the collected data are routed to BS through the head node. The process of routing is made using the CrowWhale optimisation algorithm that enables to transfer the data packets from IoT nodes to BS. In the sewage water management system, entering sewage water into fresh water is detected by DRN which is trained using an optimisation algorithm. In the healthcare system, heart disease prediction is done using DRN to detect normal and abnormal cases more effectively. The adopted CrowWhale-ETR+DRN offered energy, accuracy and sensitivity as 82.54, 0.967, and 0.978 with 100 nodes for the environmental protection dataset. The energy, accuracy, and sensitivity obtained by the proposed model are 83.232, 0.964, and 0.974 using 100 nodes for the heart disease dataset, respectively.

Plasma acylcarnitines and amino acids in dyslipidemia: An integrated metabolomics and machine learning approach.

The Discovery of underlying intermediates associated with the development of dyslipidemia results in a better understanding of pathophysiology of dyslipidemia and their modification will be a promising preventive and therapeutic strategy for the management of dyslipidemia. The entire dataset was selected from the Surveillance of Risk Factors of Noncommunicable Diseases (NCDs) in 30 provinces of Iran (STEPs 2016 Country report in Iran) that included 1200 subjects and was stratified into four binary classes with normal and abnormal cases based on their levels of triglyceride (TG), total cholesterol (TC), high-density lipoprotein cholesterol (HDL-C), and non-HDL-C.Plasma concentrations of 20 amino acids and 30 acylcarnitines in each class of dyslipidemia were evaluated using Tandem mass spectrometry. Then, these attributes, along with baseline characteristics data, were used to check whether machine learning (ML) algorithms could classify cases and controls. Our ML framework accurately predicts TG binary classes. Among the models tested, the SVM model stood out, performing slightly better with an AUC of 0.81 and a standard deviation of test accuracy at 0.04. Consequently, it was chosen as the optimal model for TG classification. Moreover, the findings showed that alanine, phenylalanine, methionine, C3, C14:2, and C16 had great power in differentiating patients with high TG from normal TG controls. Conclusions: The comprehensive output of this work, along with sex-specific attributes, will improve our understanding of the underlying intermediates involved in dyslipidemia. The online version contains supplementary material available at 10.1007/s40200-024-01384-9.

Deep learning algorithm applied to plain CT images to identify superior mesenteric artery abnormalities

ObjectivesAtypical presentations, lack of biomarkers, and low sensitivity of plain CT can delay the diagnosis of superior mesenteric artery (SMA) abnormalities, resulting in poor clinical outcomes. Our study aims to develop a deep learning (DL) model for detecting SMA abnormalities in plain CT and evaluate its performance in comparison with a clinical model and radiologist assessment. Materials and MethodsA total of 1048 patients comprised the internal (474 patients with SMA abnormalities, 474 controls) and external testing (50 patients with SMA abnormalities, 50 controls) cohorts. The internal cohort was divided into the training cohort (n = 776), validation cohort (n = 86), and internal testing cohort (n = 86). A total of 5 You Only Look Once version 8 (YOLOv8)–based DL submodels were developed, and the performance of the optimal submodel was compared with that of a clinical model and of experienced radiologists. ResultsOf the submodels, YOLOv8x had the best performance. The area under the curve (AUC) of the YOLOv8x submodel was higher than that of the clinical model (internal test set: 0.990 vs 0.878, P =.002; external test set: 0.967 vs 0.912, P =.140) and that of all radiologists (P <.001). The YOLOv8x submodel, when compared with radiologist assessment, demonstrated higher sensitivity (internal test set: 100.0 % vs 70.7 %, P =.002; external test set: 96.0 % vs 68.8 %, P <.001) and specificity (internal test set: 90.7 % vs 66.0 %, P =.025; external test set: = 88.0 % vs 66.0 %, P <.001). ConclusionUsing plain CT images, YOLOv8x was able to efficiently identify cases of SMA abnormalities. This could potentially improve early diagnosis accuracy and thus improve clinical outcomes.

Few-Shot Metering Anomaly Diagnosis with Variable Relation Mining

Metering anomalies not only mean huge economic losses but also indicate the faults of equipment and power lines, especially within the substation. As a result, metering anomaly diagnosis is becoming one of the most important missions in smart grids. However, due to the insufficient and imbalanced anomaly cases, identifying the anomalies in smart meter data accurately and efficiently remains challenging. Existing methods usually employ few-shot learning models in computer vision directly, which requires the rich experience of human experts and sufficient abnormal cases for training. It blocks model generalizing to various application scenarios. To address these shortcomings, we propose a novel framework for metering anomaly diagnosis based on few-shot learning, named FSMAD. Firstly, we design a fault data injection model to emulate anomalies, so that no abnormal samples are required in the training phase. Secondly, we provide a learnable variable transformation to reveal inherent relationships among various smart meter data and help FSMAD extract more efficient features. Finally, the deeper metric network is equipped to support FSMAD in obtaining powerful comparison capability. Extensive experiments on a real-world dataset demonstrate the advantages of our FSMAD over state-of-the-art methods.

Cytogenetic profiling unveils Jacobs syndrome (47, XYY) - A unique chromosomal abnormality case from Nepal

Jacobs syndrome (47, XYY) is a rare genetic condition observed in males due to incorrect segregation of chromosomes during the first or second meiotic cell division. A 38-year-old male with infertility issues, tall stature, and neurodevelopmental

INTERNATIONAL CRITERIA EKG COMPARISON STUDY

https://youtu.be/4jm0uzAQNm8 BACKGROUND There has been an evolution of athlete specific Electrocardiogram (EKG) criteria over the years, resulting in improved specificity and lower false positive rates, starting with the European Society of Cardiology 2005 guidelines and most recently with the current 2017 International Recommendations. The consistency of EKG interpretation with the 2017 International Criteria have been compared between various groups, including local and specialized center physicians. Whether novice EKG interpreters (undergraduate/graduate students) can be taught to accurately interpret athletes’ EKGs with the 2017 International Criteria has not been extensively studied. This study seeks to assess the accuracy and variability of novice EKG interpreters, compared to cardiologist interpretations and expert readers. METHODS Three novice EKG interpreters (undergraduate exercise science students) were trained in interpreting EKGs of athletes with the 2017 International Criteria during one semester under the instruction of an expert reader. During an annual high school, sports screening day 1350 EKGs were collected and assigned a corresponding number. The on-site cardiologists evaluated the EKGs in real-time and classified as “normal” or “abnormal” according to the International Criteria. Following the sports physical day, three novice EKG interpreters (students), a cardiologist and a Clinical Exercise Physiology Professor (expert reader) were asked separately to classify the same EKGs as “normal or “abnormal” according to the International Criteria. All readers were blinded to the initial classifications made by the cardiologist during the sports physical event. Information regarding the athlete's age, gender, race/ethnicity, and sport was provided on the EKGs. We assessed the agreement between the cardiologist, expert reader and students in interpreting EKGs using Fleiss' kappa analysis. RESULTS 1350 athlete EKGs (males = 879; females = 471, age (mean + SD) 15.09 + 1.3y) including 37 (2.7%) abnormal cases were reviewed. The inter-rater agreement between novice readers, expert reader, and physicians in classifying an EKG as abnormal was good (k = 0.7, p &amp;lt; .001). CONCLUSION This study demonstrated that novice EKG readers could correctly classify EKGs based on the International Criteria as “normal and abnormal” to identify athletes at high risk of acute cardiovascular events

Diagnosing oral and maxillofacial diseases using deep learning

The classification and localization of odontogenic lesions from panoramic radiographs is a challenging task due to the positional biases and class imbalances of the lesions. To address these challenges, a novel neural network, DOLNet, is proposed that uses mutually influencing hierarchical attention across different image scales to jointly learn the global representation of the entire jaw and the local discrepancy between normal tissue and lesions. The proposed approach uses local attention to learn representations within a patch. From the patch-level representations, we generate inter-patch, i.e., global, attention maps to represent the positional prior of lesions in the whole image. Global attention enables the reciprocal calibration of path-level representations by considering non-local information from other patches, thereby improving the generation of whole-image-level representation. To address class imbalances, we propose an effective data augmentation technique that involves merging lesion crops with normal images, thereby synthesizing new abnormal cases for effective model training. Our approach outperforms recent studies, enhancing the classification performance by up to 42.4% and 44.2% in recall and F1 scores, respectively, and ensuring robust lesion localization with respect to lesion size variations and positional biases. Our approach further outperforms human expert clinicians in classification by 10.7 % and 10.8 % in recall and F1 score, respectively.

Parameatal Urethral Cyst in a 20-Year-Old Male Patient: A Case Report

The parameatal urethral cyst is a rare anomaly and appears as a small blister in proximity to the urethral meatus. These cysts may result from occlusion of paraurethral ducts or, in other cases, from faulty preputial separation from the glans along the coronal sulcus. A 20-year-old male patient came to our outpatient clinic at dr. M. Soewandhie General Hospital Surabaya with a cystic lesion on the right side of the external urethral meatus. The patient only found out about his situation one year ago, and he did not experience any complaints except a branched urination. On physical examination, an 8 mm cystic lesion was found on the right side of the external urethral meatus. The patient consented to complete surgical excision of the cyst. The procedure was performed under regional anesthesia. The cyst was completely resected from the surrounding tissues. One month after surgery, there is no post-operative pain and good urine flow, and the patient is also satisfied with the post-operative condition. Histologic examination shows pieces of tissue in the form of polypoid lined with squamous epithelium underneath, stroma of fibrous tissue with proliferation of blood vessels and some inflammatory cells of lymphocytes in between. There are no signs of malignancy. Parameatal urethral cyst is an abnormal and rare case, usually asymptomatic. However, sometimes dysuria, urinary retention, branching urine, and cosmetic problems are the reasons that cause patients to seek a doctor's help. It can be diagnosed just on physical examination and can be cured by complete excision.

Influence of corneal diameter on the accuracy of corneal tomography in patients with forme fruste keratoconus or thin corneas

ABSTRACT Clinical relevance The detection of subclinical ectasia is important in preoperative screening for laser-refractive surgery. Previous studies have confirmed the impact of corneal diameter on the diagnostic accuracy of several ectasia indices in tomographically normal eyes. Background This study aimed to investigate the influence of corneal diameter on the diagnostic accuracy of Pentacam tomographic indices in eyes with forme fruste keratoconus (FFKC) and thin corneas. Methods One hundred and one eyes of 101 patients with FFKC (FFKC group), 104 eyes of 104 patients with a corneal thickness <490 μm (thin cornea group), and 200 eyes of 200 normal subjects (normal group) were analysed in the study. Pentacam ectasia indices were compared between the groups. Results The results of multiple linear regression analysis showed that the standardised coefficients for corneal diameter and overall deviation of normality (BAD-D) were −0.386, −0.552, and −0.552 for the FFKC, thin cornea, and normal groups, respectively (p < 0.001). Comparing for the classifications (normal versus abnormal) of the individual indices demonstrated that for corneal diameters ≤11.9 mm, the rates of abnormal cases were significantly higher in the FFKC group than in the normal group for seven indices and in the thin cornea group than normal group for nine indices. For corneal diameters >11.9 mm, the rates of abnormal cases were higher in the FFKC than normal group for three indices and higher in the thin cornea group than normal group for seven indices. Conclusion Belin/Ambrosio Enhanced Ectasia display indices may underestimate the risk of ectasia in patients with large corneas, especially those with FFKC.

Temporal involvement of phosphatidylinositol 4-phosphate 5-kinase γ in differentiation of Z-bands and myofilament bundles as well as intercalated discs in mouse heart at mid-gestation.

Considering the occurrence of serious heart failure in a gene knockout mouse of PIP5Kγ and in congenital abnormal cases in humans in which the gene was defective as reported by others, the present study attempted to localize PIP5Kγ in the heart during prenatal stages. It was done on the basis of the supposition that phenotypes caused by gene mutation of a given molecule are owed to the functional deterioration of selective cellular sites normally expressing it at significantly higher levels in wild mice. PIP5Kγ-immunoreactivity was the highest in the heart at E10 in contrast to almost non-significant levels of the immunoreactivity in surrounding organs and tissues such as liver. The immunoreactivity gradually weakened in the heart with the prenatal age, and it was at non-significant levels at newborn and postnatal stages. Six patterns in localization of distinct immunoreactivity for PIP5Kγ were recognized in cardiomyocytes: (1) its localization on the plasma membranes and subjacent cytoplasm without association with short myofibrils and (2) its localization on them as well as short myofibrils in association with them in cardiomyocytes of early differentiation at E10; (3) its spot-like localization along long myofibrils in cardiomyocytes of advanced differentiation at E10; (4) rare occurrences of such spot-like localization along long myofibrils in cardiomyocytes of advanced differentiation at E14; (5) its localization at Z-bands of long myofibrils; and (6) its localization at intercellular junctions including the intercalated discs in cardiomyocytes of advanced differentiation at E10 and E14, especially dominant at the latter stage. No distinct localization of PIP5Kγ-immunoreactivity of any patterns was seen in the heart at E18 and P1D. The present finding suggests that sites of PIP5Kγ-appearance and probably of its high activity in cardiomyocytes are shifted from the plasma membranes through short myofibrils subjacent to the plasma membranes and long myofibrils, to Z-bands as well as to the intercalated discs during the mid-term gestation. It is further suggested that PIP5Kγ is involved in the differentiation of myofibrils as well as intercellular junctions including the intercalated discs at later stages of the mid-term gestation. Failures in its involvement in the differentiation of these structural components are thus likely to cause the mid-term gestation lethality of the mutant mice for PIP5Kγ.

The results of total repair for tetralogy of fallot with an abnormal coronary artery

The objective of this study evaluated the results of total repair for tetralogy of Fallot with an abnormal coronary artery.&#x0D; Methods: This was a review of seri Tetralogy of Fallot with an abnormal coronary artery cases who underwent total repair from 1/2018 to 6/2023.&#x0D; Results: There were 10 patients who underwent complete surgical repair, include 6 males and 4 females. The mean age was 6,8 months (range 4 months to 17 months)and the mean weight was 7,2 kilograms. 6 patients had Left Anterior Descending (LAD) artery originating from Right Coronary Artery (RCA), 3 patients with RCA originating from LAD and 1 patient with one major banche of RCA crossing the infundibulum. There were 7 patients with Pulmonary Valve Preserve (PVP) and 3 patients with Conduit Using (CU). The time of cardiopulmonary bypass, aortic clamping and ventilator were: 90 mins; 63 mins and 16 hours. There was not intrahospital mortality. Echocardiography post -operation: in PVP group all patient had a competence pulmonary valve and mean gradient was 12,5 mmHg; in CU group, there were not pulmonary valve regurgitation and mean gradient was 9 mmHg. During follow-up time 30 months after surgery, there was no late death; 2 patient in PVP group who had moderate pulmonary valve regurgitation and mean gradient was 22 mmHg; in CU group, there was a competence pulmonary valve with mean gradient 26 mmHg.&#x0D; Conclusion: There was a good result of total repair for tetralogy of Fallot with an abnormal coronary artery.

Enhancing lung abnormalities diagnosis using hybrid DCNN-ViT-GRU model with explainable AI: A deep learning approach

In this study, we propose a novel approach called DCNN-ViT-GRU, which combines deep Convolutional Neural Networks (CNNs) with Gated Recurrent Units (GRUs) and the Vision Transformer (ViT) model for the accurate detection and classification of lung abnormalities. By leveraging the strengths of both CNNs and the ViT model, our architecture automatically extracts meaningful features from lung images, leading to improved diagnostic capabilities. The DCNN-ViT-GRU model utilizes a combination of deep CNN and GRU layers, allowing it to effectively capture local and global patterns. This comprehensive feature representation enhances the model's ability to identify various abnormalities in lung images, including lung cancer, COVID-19, and pneumonia. To further enhance the interpretability and transparency of our model, we integrate Explainable Artificial Intelligence (XAI) techniques, including LIME and SHAP. This integration provides valuable insights into the decision-making process of the DCNN-ViT-GRU model, enabling clinicians to understand and validate the predictions made by the model. We evaluated the performance of our proposed approach on diverse datasets containing cases of lung abnormalities. Through cross-validation, our DCNN-ViT-GRU model achieved impressive weighted mean accuracy of 99% and 99.86% for two distinct datasets, demonstrating its superior performance. Furthermore, in hold-out validation on separate datasets, the model achieved accuracies of 99.09% and 99.87%, respectively. Integrating the XAI techniques enhances the interpretability of the DCNN-ViT-GRU model and provides clinicians with valuable insights regarding the factors contributing to the diagnosis of lung abnormalities. This approach presents a promising solution for accurate and interpretable lung abnormalities detection and classification, with potential implications for improved patient care and treatment planning.

Endoscopic treatment of patients with idiopathic hydrocephalus with extraventricular cisternal obstruction of the cerebrospinal tract

The possibility of developing extraventricular CSF pathways obstruction was demonstrated in the mid-20th century. The development of neuroimaging (mainly MRI) and endoscopic techniques made it possible to plan and perform minimally invasive surgeries in a narrow anatomical corridor and achieve the regression of neurological symptoms. Purpose of the study: to determine the effectiveness of endoscopic surgery for hydrocephalus due to idiopathic extraventricular CSF pathways obstruction. Materials and methods. Sixty-five patients with signs of extraventricular obstruction underwent examination and surgical treatment at the Center of Neurosurgery from 2007 to 2020. The preoperative Kiefer Scale score was 6.8±3.3 (0-15) points, and the Rankin Scale score — 2.2±1 (0-5) points. Endoscopic third ventriculocisternostomy was performed as the first operation in 42 (64.6 %) patients. Ventriculoperitoneal shunting was performed in 17 (26.1 %) patients. Six (9.2 %) patients were not operated on. Results. After endoscopic surgery, the condition of the patients significantly improved (p &lt; 0.001) after 2 and 12 months. Complete or partial regression of symptoms was noted in 85 % of the patients 1 year after surgery. After shunt surgery, the trend was comparable. The only radiological parameter that changes and correlates with the patients’ condition is the position of the premammillary membrane and the flow void. The remaining indicators of the CSF system of the brain did not actually change. In all cases of the endoscopic surgery, an additional membrane conglomerate that corresponded to preoperative tomograms was found under the premammillary membrane. Conclusion. The high efficiency of endoscopic third ventriculocisternostomy allows recommending this technique as the primary one in patients with extraventricular CSF pathways obstruction, with the exception of cases of anatomy abnormalities of the third ventricular fundus area (short premammillary membrane in combination with a high-lying basilar bifurcation) and cisterns of the posterior cranial fossa base (narrow cisterns, whose dimensions do not allow inserting an endoscope under the premamillary membrane).

Relationship Between Obesity and Global Longitudinal Strain in the Pediatric Single Ventricle Fontan Population Across Ventricular Morphologies.

Obesity is associated with diminished myocardial function as measured by strain echocardiography in children and young adults with normal cardiac anatomy. Data are lacking about the effect of obesity on myocardial strain in patients with a single ventricle. In this study, the relationship between body mass index (BMI) and single ventricle myocardial strain in the Fontan population was assessed. Thirty-eight abnormal BMI Fontan cases (21 overweight and 17 obese) and 30 normal BMI Fontan controls matched based on single ventricular morphology, age, and sex were included in the study. Ventricular morphology was categorized as single right ventricle, single left ventricle, or biventricular. Single ventricle global longitudinal peak systolic strain (GLS) and other echocardiographic measurements were performed and compared between groups, with a P≤0.05 defined as significant. The abnormal BMI group demonstrated diminished GLS (-15.7±3.6% versus -17.2±3.2%, [P=0.03]) and elevated systolic blood pressure (P=0.04) compared with the normal BMI group. On subgroup analysis of those with single right ventricle morphology, the abnormal BMI group demonstrated diminished GLS compared with controls. There was no significant difference in GLS between the abnormal BMI and control groups in the single left ventricle and biventricular subgroups. Analyzed by ventricular morphology, no other variables were statistically different in the abnormal BMI group including systolic blood pressure. Inter-reader reproducibility for GLS and strain rate were excellent for both measures. Obesity has an adverse relationship with myocardial strain in the young Fontan population, with the most maladaptive response seen in the single right ventricle.

Abnormal uterine bleeding diagnoses and care following COVID-19 vaccination

BackgroundThere is evidence suggesting that COVID-19 vaccination may be associated with small, transitory effects on uterine bleeding, possibly including menstrual timing, flow, and duration, in some individuals. However, changes in health care seeking, diagnosis, and workup for abnormal uterine bleeding in the COVID-19 vaccine era are less clear. ObjectivesTo assess the impact of COVID-19 vaccination on incident abnormal uterine bleeding diagnosis and diagnostic evaluation in a large integrated health system. Study DesignUsing segmented regression, we assessed whether the availability of COVID-19 vaccines was associated with changes in monthly, population-based rates of incident abnormal uterine bleeding diagnoses compared to the pre-pandemic period in health system members ages 16-44 years who were not menopausal. We also compared clinical and demographic characteristics of patients diagnosed with incident abnormal uterine bleeding between December 2020 through October 13, 2021 by vaccination status (never vaccinated, vaccinated in the 60 days prior to diagnosis, vaccinated more than 60 days prior to diagnosis) and conducted detailed chart review of patients diagnosed with abnormal uterine bleeding within 1-60 days of COVID-19 vaccination in the same time period. ResultsIn monthly populations ranging from 79,000 to 85,000 female health system members, incidence of abnormal uterine bleeding diagnosis per 100,000 person-days ranged from 8.97 to 19.19. There was no significant change in the level or trend in the incidence of abnormal uterine bleeding diagnoses between the pre-pandemic (January 2019-January 2020) and post-COVID-19 vaccine (December 2020-December 2021) periods. A comparison of clinical characteristics of 2,717 abnormal uterine bleeding cases by vaccination status suggested that abnormal bleeding among recently vaccinated patients was similar or less severe than abnormal bleeding among patients who had never been vaccinated patients or those vaccinated more than 60 days prior. There were also significant differences in age and race of patients with incident abnormal uterine bleeding diagnoses by vaccination status: never vaccinated patients were the youngest and those vaccinated more than 60 days prior were the oldest; the proportion of patients who were Black/African American was highest among never vaccinated patients, and the proportion of Asian patients was higher among vaccinated patients. Chart review of 114 confirmed post-vaccination abnormal uterine bleeding cases diagnosed from December 2020 through October 13, 2021 found that the most common symptoms reported were changes in timing, duration, and volume of bleeding. Approximately one-third of cases received no diagnostic workup; 57% had no etiology for the bleeding documented in the electronic health record. In 12% of cases, the patient mentioned or asked about a possible link between their bleeding and their recent COVID-19 vaccine. ConclusionsThe availability of COVID-19 vaccination was not associated with a change in incidence of medically attended abnormal uterine bleeding in our population of over 79,000 female patients of reproductive age. Additionally, among 2,717 patients with abnormal uterine bleeding diagnoses in the period following COVID-19 vaccine availability, receipt of the vaccine was not associated with greater bleeding severity.

P-51 Association of Bardet-Biedl syndrome with differences of sex development and pituitary hypoplasia

Abstract Introduction Bardet-Biedl syndrome (BBS) is a rare autosomal recessive genetic disorder involving hypogonadism manifested by cryptorchidism, micropenis and/or delayed puberty Clinical Case We report the case of a 13-year-old child, who was consulted for obesity and whose physical examination showed major signs of SBB: global obesity, polydactyly, learning difficulties and visual disorders. Genital examination revealed a 1 cm genital tubercle with a single orifice and two genital swelling without palpable gonads. Biological investigations revealed hypogonadotropic hypogonadism, corticotropic insufficiency, low AMH with a non- stimulable HCG test and a 46XY male karyotype. Pelvic MRI did not show any gonads or internal genitalia but noted ectopy and malrotation of the right kidney. The diagnosis of a testicular regression syndrome is very likely in this case. At the fundus photography: presence of bilateral retinal dystrophy with high myopia. At the hypothalamohypophyseal level: a strong pituitary hypoplasia was objectified. Conclusion BBS is a rare autosomal recessive multisystem ciliopathy. The incidence of BBS is 1 in 150,000–160,000 in Europe and North America. BBS is caused by a dysfunction of the gene coding for proteins that are implicated in the function of the primary cilia and in important signaling pathways. The core features of the syndrome include retinal degeneration, obesity, polydactyly, cognitive impairment, renal anomalies and urogenital malformations. To date, pathogenic variants in 26 genes have been shown to be involved in the molecular basis of this rare ciliopathy. To our knowledge, only one study conducted on 11 children with BBS found among them 7 cases of pituitary abnormalities, 4 of which showed hypoplasia. While no association with a testicular regression syndrome has been described. This makes our patient the first described association of these 3 pathologies.

Individual age determination based on computed tomography knee analysis using artificial neural networks and computer vision: Preliminary results

BACKGROUND: Currently, studies have focused on the modernization of existing methods of forensic age assessment (bone and skeletal) through the active use of modern methods of medical imaging (e.g., computed tomography) and artificial intelligence for their analysis. This approach enables the creation of new methods for assessing biological age, which is characterized by increased accuracy and reproducibility.&#x0D; AIM: To develop and test an algorithm for predicting the biological age of an individual based on computed tomography analysis of the knee joint using artificial neural networks and computer vision.&#x0D; MATERIALS AND METHODS: This observational retrospective transverse (one time) study analyzed computed tomography scans (334) of the knee joint performed in the Departments of Radiation Diagnostics of the Priorov Central Institute for Trauma and Orthopedics, Vreden National Medical Center for Traumatology and Orthopedics, between 2018 and 2021. The study enrolled persons of both sexes aged 13–45 years. Cases of developmental abnormalities, knee injuries, signs of general connective tissue pathology were excluded. Research methods include the use of intelligent information technologies (a formalized set of mathematical and software solutions).&#x0D; RESULTS: Based on the experiments conducted, an algorithm for assessing age according to the computed tomography scans of the knee joint has been developed. The main components of the developed system are as follows: a preprocessing module, an intelligent computing core, a data analysis module, a three-dimensional reconstruction module, a property extraction module, and a final age assessment module. The essence of the proposed method is the simultaneous use of artificial neural networks and clearly formalized mathematical procedures for calculating the properties of the epiphyseal line. To obtain the results and conduct primary experimental studies that confirmed the feasibility, correctness, and operability of the method, software using the YOLOv5 neural network was developed. The result of the error matrix analysis after training shows a probability of correct recognition of the order of 80%. Verification of experimental studies was performed on 46 cases. At present, the age estimation error is approximately 1 year for children and adolescents.&#x0D; CONCLUSIONS: The experimental results have confirmed the adequacy of the age estimates obtained to the actual age of the individual and, consequently, the applicability of the proposed method in forensic medical institutions. The proposed method is currently implemented as a set of software components with subsequent manual integration of automatically calculated data. The plan was to supplement the database of computed tomography images to increase the training sample and the accuracy of age prediction.

Deep-learning model for prenatal congenital heart disease screening generalizes to community setting and outperforms clinical detection.

Despite nearly universal prenatal ultrasound screening programs, congenital heart defects (CHD) are still missed, which may result in severe morbidity or even death. Deep machine learning (DL) can automate image recognition from ultrasound. The main aim of this study was to assess the performance of a previously developed DL model, trained on images from a tertiary center, using fetal ultrasound images obtained during the second-trimester standard anomaly scan in a low-risk population. A secondary aim was to compare initial screening diagnosis, which made use of live imaging at the point-of-care, with diagnosis by clinicians evaluating only stored images. All pregnancies with isolated severe CHD in the Northwestern region of The Netherlands between 2015 and 2016 with available stored images were evaluated, as well as a sample of normal fetuses' examinations from the same region and time period. We compared the accuracy of the initial clinical diagnosis (made in real time with access to live imaging) with that of the model (which had only stored imaging available) and with the performance of three blinded human experts who had access only to the stored images (like the model). We analyzed performance according to ultrasound study characteristics, such as duration and quality (scored independently by investigators), number of stored images and availability of screening views. A total of 42 normal fetuses and 66 cases of isolated CHD at birth were analyzed. Of the abnormal cases, 31 were missed and 35 were detected at the time of the clinical anatomy scan (sensitivity, 53%). Model sensitivity and specificity were 91% and 78%, respectively. Blinded human experts (n = 3) achieved mean ± SD sensitivity and specificity of 55 ± 10% (range, 47-67%) and 71 ± 13% (range, 57-83%), respectively. There was a statistically significant difference in model correctness according to expert-graded image quality (P = 0.03). The abnormal cases included 19 lesions that the model had not encountered during its training; the model's performance in these cases (16/19 correct) was not statistically significantly different from that for previously encountered lesions (P = 0.41). A previously trained DL algorithm had higher sensitivity than initial clinical assessment in detecting CHD in a cohort in which over 50% of CHD cases were initially missed clinically. Notably, the DL algorithm performed well on community-acquired images in a low-risk population, including lesions to which it had not been exposed previously. Furthermore, when both the model and blinded human experts had access to only stored images and not the full range of images available to a clinician during a live scan, the model outperformed the human experts. Together, these findings support the proposition that use of DL models can improve prenatal detection of CHD. © 2023 International Society of Ultrasound in Obstetrics and Gynecology.

MAGNETIC RESONANCE IMAGING FINDINGS IN SEIZURE PATIENTS WITH NORMAL NEUROLOGICAL EXAMINATION

Background: Imaging plays a critical role in the treatment and diagnosis of individuals experiencing seizures, particularly those whose seizures cannot be explained. In various circumstances, CT scans and MRIs (Magnetic Resonance Imaging) are utilized in tandem. Objective: The purpose of this research was to evaluate the MRI findings of patients referred to Alavi Hospital with seizures and a normal neurological examination. Methods: This case-series study examined one hundred patients with epilepsy who underwent normal neurological examinations. All patients' imaging reports were meticulously examined, and any changes were documented in pre-established checklists that comprised of the following: age, gender, family history, EEG (electroencephalogram) results, neurological assessments (including motor, plantar, and tendon reflexes), and MRI findings derived from the patients' files and clinical histories. Result: In the range of 11 to 58 years, the mean age of patients was 7.46 + 32.62 years. Males comprised forty-six (46%) of the patients. In45% of the cases, a familial history of seizures was documented (n=45). Normal EEG results were obtained in 62 cases (62%). Twenty cases (20%) of abnormalities were detected on MRI, seven of which were tumor lesions, as reported by the radiologist. The imaging of the patient's brain revealed no significant correlation between the pathological findings and variables such as age, gender, or family history. No significant correlation was observed between electroencephalogram results and pathological findings on brain imaging in patients with epilepsy. Conclusion: brain imaging partially compensates for the false negatives that occur during electroencephalograms, and concurrently employing both modalities enhances the ability to diagnose underlying issues in patients experiencing seizures.

Investigating the Impact of Pregnancy-Induced Hypertension on Fetal Outcomes: A Comprehensive Study in Maternity Hospitals

Background: Hypertension in pregnancy is a major obstetric complication that poses a significant risk to maternal and fetal health, leading to increased morbidity and mortality. According to the World Health Organization, hypertensive disorders of pregnancy (HDP) claim the life of at least one woman every seven minutes. HDPs are associated with an increased risk of adverse fetal and neonatal outcomes, including preterm birth, intrauterine growth restriction (IUGR), perinatal mortality, and maternal morbidity and mortality. Prompt recognition and management of PIH are essential to mitigate these complications and ensure optimal maternal and fetal outcomes. Hence the study was undertaken to assess the impact of Pregnancy Induced Hypertension on fetal outcome among Antenatal mother with PIH at maternity hospital of Anand and Kheda district. Objectives: To assess the clinical presentation among mother with PIH at maternity hospital; To assess the impact of Pregnancy Induced Hypertension on fetal outcome. Methodology: A Prospective study was conducted at Dr. N. D. Desai hospital, Nadiad. Sample size was 30. Sample was selected by Consecutive Sampling Technique. The data regarding Demographic variable, Obstetric History, Classification of PIH, Blood pressure, Drug Received &amp; Fetal outcomes was collected using Structured Interview Scheduled. The result is computed by using descriptive and frequency and percentage using tables, graph etc. Data were analysed according to objectives of the study. Results: In present study, the incidence of gestational hypertension, pre-eclampsia, and eclampsia was 10%, 86.66%, and 3.33%, respectively. These conditions were more common in primipara. The symptoms of pregnancy-induced hypertension (PIH) included pedal edema (60%), vomiting (43.33%), blurry vision (6.66%), convulsions (3.33%), and dizziness (6.66%), as well as epigastric pain (16.66%) and lower abdominal pain (36.66%). Most mothers (83.33%) received antihypertensive medication. The study also found that fetal complications included preterm births (66.66%) and low birth weight (56.66%). Additionally, 63.33% of babies required NICU admission, and there were cases of post-term birth (3.33%), congenital abnormalities (3.33%), birth asphyxia (3.33%), and neonatal deaths (10%). Conclusion: Pregnancy-induced hypertension is a common and serious condition that can have devastating effects on both mothers and babies. To combat this, we need to raise awareness and take action at both community and hospital levels to reduce the risks and improve outcomes.