A Case of Type 2 Diastematomyelia With Spina Bifida in a Pediatric Female Patient.

This case report presents the clinical and radiological findings of a seven-year-old female with type 2 diastematomyelia and spina bifida, emphasizing the complexity of congenital spinal anomalies in pediatric patients. The patient presented with a two-month history of lower back pain, prompting diagnostic investigations. Radiographic examination revealed spina bifida at the L3-L5 levels, subsequently confirmed by magnetic resonance imaging (MRI), which disclosed bifid spinous processes, an absent posterior arch, and a split spinal cord terminating at the L3-L4 disc levels. The Vancouver classification system facilitated a standardized characterization of congenital spinal anomalies. The multidisciplinary approach involving orthopedic and neurosurgical specialists led to a conclusive diagnosis of type 2 diastematomyelia with simple spinal dysraphism. Surgical intervention, encompassing laminectomy and correction of the split spinal cord, was successfully performed, resulting in the stabilization of the patient. This case underscores the importance of early diagnosis, advanced imaging modalities, and collaborative management in addressing rare congenital spinal anomalies. The discussion delves into the clinical implications, diagnostic challenges, and the pivotal role of surgical intervention. Insights from this case contribute to the existing literature, guiding healthcare professionals in understanding and managing similar cases with potential implications for future research and treatment strategies.

Primary Negative Prognostic Factors in Pediatric and Adult Patients Undergoing Trigger Finger Surgery.

Objectives This study aims to investigate the negative prognostic indicators of pediatric and adult trigger finger surgery patients concerning complications, recurrence, and satisfaction. Methods A retrospective study was conducted on 61 patients with a total of 91 trigger fingers, including 31 in children and 30 in adult patients, all of whom were treated using a standardized surgical technique. The study considered several demographic and clinical factors, including age, gender, dominant hand, body mass index, occupation, history of trauma, single or multiple finger involvement, staging according to Green classification, diabetes mellitus, comorbidities, recurrence, revision surgery, utilization of non-surgical treatment methods, need for rehabilitation after surgery, time to return to work, the time interval from clinic initiation to the surgery, satisfaction and the duration of the follow-up period. In addition, the quick version of the disabilities of the arm, shoulder, and hand (QDASH); and the visual analog scale (VAS) were used to assess patients' data. Results In adult patients, a statistically significant relationship was observed between the increasing grade of the Green stage and complication rate (p<0.001), recurrence (p<0.001), and lower satisfaction (p<0.001). No statistically significant relationship was identified between Green's classification and complications (p=0.129), recurrence (p=0.854), or satisfaction (p=0.143) in pediatric patients. While a statistically significant relationship existed between the time interval from clinic initiation to surgery and complications (p=0.033) in adult patients, no significant relationships were observed for recurrence or satisfaction. Conversely, there was no statistically significant relationship between the time interval from clinic initiation to surgery and complications, recurrence, or satisfaction in pediatric patients. Conclusion This study demonstrates that increasing the grade of the Green stage and duration of symptoms before surgery were the substantial factors contributing to prognosis in adult patients but not in pediatric patients. These findings can assist physicians during patients' treatment management. We suggest that physicians consider these factors for patients' satisfaction.

The International Classification of Functioning Disability and Health Framework (ICF): a new approach to enhance sport and physical activity participation among people with disabilities in Scotland.

This research provides a pilot study of the International Classification of Functioning Disability and Health Framework (ICF) involving persons with disabilities (PWD) with and without lived experience of sport participation in Scotland. National surveys in Scotland provide limited information on the nature of individual disability restricting the understanding of the relationship between disability and sport and physical activity participation. The ICF is a framework that aims to describe and classify functioning and thus can be used as a tool to provide a more detailed description of impairment for PWDs beyond their clinical condition. This knowledge has the potential to enhance the development of policies to increase the participation levels in this group. The ICF has also been used to inform the current IPC classification system at a competitive and elite level. As part of a larger study, 450 participants aged between 12 and 70 years completed an online questionnaire examining attitudes to, and participation in, sport and physical activity as well as completing the structural and functional components of the ICF. Subsequently, 18 people participated in focus groups aged between 13 and 61 years. The focus groups examined four meta-theme areas: physical, social, psychological, and sport-specific factors. The results confirm that the ICF provided a more detailed indicator of the key impairments that could have an impact on sport and physical activity participation. There was a clear lack of awareness of the links between the ICF and the classification system for competitive parasport. We concluded that a modified ICF-based assessment tool, incorporating social and environmental factors, has the potential to predict the likelihood of participation and offers a more comprehensive picture of both individual and national disability characteristics. This allows for the development of targeted policies and strategies to assist those with a disability to participate in sport. The overall framework presents a shift in thinking, in policy terms, for those in public health and in sport governance and delivery. The significance of this work is especially concerned with public health and wellbeing and sport development policy as pathways from recreational sport user to elite athlete parasport classification and performance.

Assessment of the severity of diabetic polyneuropathy aids in predicting the risk of developing diabetic complications in patients with untreated diabetes.

This study aimed to determine the efficacy of assessing the severity of diabetic polyneuropathy (DPN) in patients with untreated diabetes. Seventy-two patients with untreated type 2 diabetes who were hospitalized for glycemic control were enrolled and divided into the following two groups: patients who had no prior diagnosis and patients who were unattended or had discontinued treatment. Electrophysiological criteria consistent with Baba's classification were used to diagnose and assess the severity of DPN. The patients were divided into three subgroups: no DPN (stage 0), mild DPN (stage 1), and moderate or more-severe DPN (stages 2-4). Intergroup comparisons were performed for the clinical characteristics and the results of the nerve conduction studies. Twenty-two (30%), 25 (35%), and 25 (35%) patients were categorized into the no DPN, mild DPN, and moderate or more-severe DPN subgroups, respectively. The number of patients who were unattended or had discontinued treatment in the moderate or more-severe DPN subgroup was significantly higher than that in the no DPN subgroup. The patients in the moderate or more-severe DPN subgroup had an increased risk of developing diabetic retinopathy and nephropathy, with odds ratios of 19.5 and 11.0 for advanced stages of retinopathy and nephropathy, respectively. Thus, the assessment of the severity of DPN could aid in the prediction of the risk of developing diabetic complications in patients with untreated diabetes.

Improved empirical mode decomposition bagging RCSP combined with Fisher discriminant method for EEG feature extraction and classification.

Background: Traditional Common Spatial Pattern (CSP) algorithms for Electroencephalogram (EEG) signal classification are sensitive to noise and can produce low accuracy in small sample datasets. New method: To solve the problem, an improved Empirical Mode Decomposition (EMD) Bagging Regularized CSP (RCSP) algorithm is proposed. It filters EEG signals through improved EMD, inhibits high-frequency noise, retains effective information in the characteristic frequency band, and uses Bagging algorithm for data reconstruction. Feature extraction is performed with regularization of spatial patterns and Fisher linear discriminant analysis for feature classification. T-test is used for classification. Results: The improved EMD Bagging RCSP algorithm has improved accuracy and robustness compared to CSP and its derivatives. The average classification rate is increased by about 6%, demonstrating the effectiveness and correctness of the proposed algorithm.Comparison with existing methods: The proposed algorithm outperforms CSP and its derivatives by retaining effective information and inhibiting high-frequency noise in small sample EEG datasets. Conclusions: The proposed EMD Bagging RCSP algorithm provides a reliable and effective method for EEG signal classification and can be used in various applications, including brain-computer interfaces and clinical EEG diagnosis.

Benchmarking feature selection and feature extraction methods to improve the performances of machine-learning algorithms for patient classification using metabolomics biomedical data.

Objective: Classification tasks are an open challenge in the field of biomedicine. While several machine-learning techniques exist to accomplish this objective, several peculiarities associated with biomedical data, especially when it comes to omics measurements, prevent their use or good performance achievements. Omics approaches aim to understand a complex biological system through systematic analysis of its content at the molecular level. On the other hand, omics data are heterogeneous, sparse and affected by the classical "curse of dimensionality" problem, i.e. having much fewer observation, samples (n) than omics features (p). Furthermore, a major problem with multi-omics data is the imbalance either at the class or feature level. The objective of this work is to study whether feature extraction and/or feature selection techniques can improve the performances of classification machine-learning algorithms on omics measurements. Methods: Among all omics, metabolomics has emerged as a powerful tool in cancer research, facilitating a deeper understanding of the complex metabolic landscape associated with tumorigenesis and tumor progression. Thus, we selected three publicly available metabolomics datasets, and we applied several feature extraction techniques both linear and non-linear, coupled or not with feature selection methods, and evaluated the performances regarding patient classification in the different configurations for the three datasets. Results: We provide general workflow and guidelines on when to use those techniques depending on the characteristics of the data available. To further test the extension of our approach to other omics data, we have included a transcriptomics and a proteomics data. Overall, for all datasets, we showed that applying supervised feature selection improves the performances of feature extraction methods for classification purposes. Scripts used to perform all analyses are available at: https://github.com/Plant-Net/Metabolomic_project/.

Causes and Management of Cutaneous Adverse Drug Reactions: A Comprehensive Review.

Cutaneous adverse drug reactions (CADRs) are one of the most broadly studied and rigorously researched conditions in recent dermatological advancements. Also termed as "toxidermia," they are heavily involved and are of utmost importance to be understood and studied in the modern healthcare industry. In simple terms, they are dermatological manifestations which result from systemic drug administration to patients. Since allopathy is influenced by the medicines and drugs provided to the patients, cutaneous skin eruptions are a common occurrence in recent times. It is a need of the hour to understand the causative factors for such skin eruptions and the correct management and handling of such disorders to provide better healthcare to patients. The withdrawal of the causative drug which induces the reaction plays a key role in treatment. The risk factors are to be thoroughly studied, and dosages must be in accordance with the patient's situation. They are some of the common public health problems. The age group which is affected is highly variable as people from all age groups can be affected. Those who are affected comprise approximately 10% of all hospitalized patients, and it is also observed in about 1-4% of people who are on multiple medications.

A comprehensive review on efficient artificial intelligence models for classification of abnormal cardiac rhythms using electrocardiograms.

Deep learning has made many advances in data classification using electrocardiogram (ECG) waveforms. Over the past decade, data science research has focused on developing artificial intelligence (AI) based models that can analyze ECG waveforms to identify and classify abnormal cardiac rhythms accurately. However, the primary drawback of the current AI models is that most of these models are heavy, computationally intensive, and inefficient in terms of cost for real-time implementation. In this review, we first discuss the current state-of-the-art AI models utilized for ECG-based cardiac rhythm classification. Next, we present some of the upcoming modeling methodologies which have the potential to perform real-time implementation of AI-based heart rhythm diagnosis. These models hold significant promise in being lightweight and computationally efficient without compromising the accuracy. Contemporary models predominantly utilize 12-lead ECG for cardiac rhythm classification and cardiovascular status prediction, increasing the computational burden and making real-time implementation challenging. We also summarize research studies evaluating the potential of efficient data setups to reduce the number of ECG leads without affecting classification accuracy. Lastly, we present future perspectives on AI's utility in precision medicine by providing opportunities for accurate prediction and diagnostics of cardiovascular status in patients.

Intertrochanteric (Reverse Oblique) Fracture Subclassifications AO/OTA 31-A3 Have No Effect on Outcomes or Postoperative Complications.

Background: Reverse oblique intertrochanteric fractures (ROFs) are unstable extracapsular hip fractures that present a mechanical challenge. These fractures are classified as AO/Orthopaedic Trauma Association (OTA) 31-A3 according to the Trauma Association classification system and can further be subclassified into 3 subtypes based on their specific characteristics. The study aimed to evaluate and compare the radiographic and clinical outcomes of the 3 subtypes of ROFs. Methods: A retrospective study was conducted at a single high-volume, tertiary center, where data were collected from electronic medical records of consecutive patients who underwent surgical fixation of AO/OTA 31-A3 fractures. Patients with less than 1-year follow-up, pathological fractures, and revision surgery were excluded. The subtypes of fractures were classified as 31-A3.1 (simple oblique), 31-A3.2 (simple transverse), and 31-A3.3 (wedge or multi-fragmentary). The operation was done using 4 different fixation methods, and radiological evaluation was performed at routine intervals. Results: The final population consisted of 265 patients (60.8% women) with a mean age of 77.4 years (range, 50-100 years) and the mean follow-up time was 35 months (range, 12-116 months). The incidence of medical complications was similar across the groups. However, there was a trend toward a higher incidence of orthopedic complications and revision rates in the 31-A3.2 group, although this was not statistically significant (p = 0.21 and p = 0.14, respectively). Conclusions: Based on the findings of this study, no significant differences were observed between the groups, indicating that the subclassifications of AO/OTA 31-A3 fractures do not have a significant impact on surgical outcomes or the occurrence of postoperative complications.

Cluster analysis defines four groups of Japanese patients with adult-onset Still's disease.

OBJECTIVES: To define groups and characterize differences in the prognosis of patients with adult-onset Still's disease (AOSD). METHODS: We performed a retrospective cohort study. Patients with AOSD were grouped using hierarchical unsupervised cluster analysis according to age, sex, clinical features, and laboratory data. The primary endpoints were overall survival and drug-free remission rate. RESULTS: A total of 153 patients with AOSD were placed into four clusters. Those in Cluster 1 had a young onset, tended to be female, and had fewer complications and moderate ferritin concentrations. Those in Cluster 2 had a young onset and had more complications and higher ferritin concentrations. Those in Cluster 3 had a young onset, tended to be male, and had no lymphadenopathy and fewer complications. Those in Cluster 4 had an older onset, tended to be female, and had more complications and higher ferritin concentrations. Overall survival tended to be lower (P = .0539) in Cluster 4, and drug-free remission was higher in Clusters 1, 2, and 3 [hazard ratios (HRs) 2.19, 3.37, and 3.62 vs. Cluster 4, respectively]. CONCLUSIONS: Four groups of AOSD that have distinct clinical manifestations, ferritin concentrations, severity, and drug-free remission rate were identified, which were lowest in Cluster 4. Graphical Abstract.

Avoidant Restrictive Food Intake Disorder (ARFID)-Looking beyond the eating disorder lens?

Avoidant Restrictive Food Intake Disorder (ARFID) was first included as a diagnostic category in 2013, and over the past 10 years has been adopted by the international eating disorder community. While greater awareness of these difficulties has increased identification, demand and enabled advocacy for clinical services, the heterogeneous nature of ARFID poses unique challenges for eating disorder clinicians and researchers. This commentary aims to reflect on some of these challenges, focussing specifically on the risk of viewing ARFID through an eating disorder lens. This includes potential biases in the literature as most recent research has been conducted in specialist child and adolescent eating disorder clinic settings, bringing in to question the generalisability of findings to the broad spectrum of individuals affected by ARFID. We also consider whether viewing ARFID predominantly through an eating disorder lens risks us as a field being blinkered to the range of effective skills our multi-disciplinary feeding colleagues may bring. There are opportunities that may come with the eating disorder field navigating treatment pathways for ARFID, including more joined up working with multi-disciplinary colleagues, the ability to transfer skills used in ARFID treatment to individuals with eating disorder presentations, and most notably an opportunity to provide more effective treatment and service pathways for individuals with ARFID and their families. However, these opportunities will only be realised if eating disorder clinicians and researchers step out of their current silos.

Prioritize Variant Reclassification in Pediatric Long QT Syndrome-Time to Revisit.

Congenital long QT syndrome (LQTS) is an inherited arrhythmia syndrome associated with sudden cardiac death. Accurate interpretation and classification of genetic variants in LQTS patients are crucial for effective management. All patients with LQTS with a positive genetic test over the past 18 years (2002-2020) in our single tertiary pediatric cardiac center were identified. Reevaluation of the reported variants in LQTS genes was conducted using the American College of Genetics and Genomics (ACMG) guideline after refinement by the US ClinGen SVI working group and guideline by Walsh et al. on genetic variant reclassification, under multidisciplinary input. Among the 59 variants identified. 18 variants (30.5%) were reclassified. A significant larger portion of variants of unknown significance (VUS) were reclassified compared to likely pathogenic (LP)/pathogenic (P) variants (57.7% vs 9.1%, p < 0.001). The rate of reclassification was significantly higher in the limited/disputed evidence group compared to the definite/moderate evidence group (p = 0.0006). All LP/P variants were downgraded in the limited/disputed evidence group (p = 0.0057). VUS upgrades are associated with VUS located in genes within the definite/moderate evidence group (p = 0.0403) and with VUS present in patients exhibiting higher corrected QT intervals (QTc) (p = 0.0445). A significant number of pediatric LQTS variants were reclassified, particularly for VUS. The strength of the gene-disease association of the genes influences the reclassification performance. The study provides important insights and guidance for pediatricians to seek for reclassification of "outdated variants" in order to facilitate contemporary precision medicine.

Towards a taxonomy for assessing and classifying the needs of curly hair: A mixed method, ethnographic and quantitative data study.

Hair defined as curly has an elliptical cross sectional area and unique 3D form. While the chemical, morphological and mechanical characteristics of such hair are being explored using a range of analytical techniques, hair assembly (head of hair) characteristics and individual behaviour are difficult to determine via tress-based instrumental and sensory testing. Since the demand for more efficacious and personalized products is expected to gain pace, this project sets the groundwork for developing a taxonomy for exploring and classifying curly hair needs from an individual's perspective. A mixed-method exploratory sequential design was used to gather information from people with curly hair starting with a novel in the field of cosmetics qualitative research method, Subjective Evidence-Based Ethnography (SEBE) (n = 14) and followed by an online survey (n = 212). The SEBE data analysis identified four common hair goals (aesthetic, haptic, practical and emotive) and a group of perceptions related to hair management routines. The survey explored the relationship of these hair goals with hair perceptions, hair esteem, hair characteristics and demographic variables. The findings suggest that hair goals and perceptions are stronger predictors of hair esteem than other characteristics such as hair length or curl type. Hence, a taxonomy for classifying curly hair should facilitate the development of more appropriate products, and product testing methods should incorporate such personal information in addition to objective fibre and hair assembly data. The focus of this study is on curly hair due to the lack of established methods for its objective evaluation and the personal challenges faced by people with curly and textured hair; however, the approach could be adopted to include straighter hair types.

Les cheveux décrits comme bouclés ont une surface transversale elliptique et une forme tridimensionnelle unique. Si les caractéristiques chimiques, morphologiques et mécaniques de ces cheveux sont étudiées à l'aide de diverses techniques d'analyse, il reste difficile de déterminer les caractéristiques de l'assemblage capillaire (tête du cheveu) et le comportement individuel d'une chevelure via des analyses instrumentales de la tresse et des tests sensoriels. La demande de produits plus efficaces et personnalisés allant sans doute augmenter à l'avenir, ce projet pose les bases d'une taxonomie visant à étudier et à classer les besoins liés aux cheveux bouclés du point de vue de la personne qui les porte. Une approche séquentielle à méthodes mixtes a été utilisée pour recueillir des informations qualitatives auprès de personnes ayant des cheveux bouclés à l'aide d'une ethnographie factuelle subjective (Subjective Evidence­Based Ethnography, SEBE) (n = 14), suivie d'une enquête en ligne (n = 228). L'analyse des données SEBE a permis d'identifier quatre objectifs capillaires fréquents et un ensemble de perceptions liées aux routines de gestion des cheveux. L'enquête a étudié la relation entre ces objectifs capillaires et la perception des cheveux, l'estime de soi liée aux cheveux, les caractéristiques des cheveux et les variables démographiques. Les résultats suggèrent que les objectifs et les perceptions des cheveux constituent des facteurs prédictifs plus puissants de l'estime de soi liée aux cheveux que d'autres caractéristiques comme la longueur des cheveux ou le type de boucle. Par conséquent, une taxonomie pour classer les cheveux bouclés doit faciliter le développement de produits plus appropriés, et les méthodes de test des produits devraient incorporer ces informations personnelles en plus des données objectives sur les fibres et les assemblages capillaires. Cette étude se concentre sur les cheveux bouclés en raison du manque de méthodes établies pour évaluer objectivement ce type de cheveux et des défis personnels auxquels les personnes ayant des cheveux bouclés et à texture sont confrontées. Toutefois, l'approche adoptée ici pourrait aussi permettre d'étudier les cheveux plus raides.

Designing a deep hybridized residual and SE model for MRI image-based brain tumor prediction.

Deep learning techniques have become crucial in the detection of brain tumors but classifying numerous images is time-consuming and error-prone, impacting timely diagnosis. This can hinder the effectiveness of these techniques in detecting brain tumors in a timely manner. To address this limitation, this study introduces a novel brain tumor detection system. The main objective is to overcome the challenges associated with acquiring a large and well-classified dataset. The proposed approach involves generating synthetic Magnetic Resonance Imaging (MRI) images that mimic the patterns commonly found in brain MRI images. The system utilizes a dataset consisting of small images that are unbalanced in terms of class distribution. To enhance the accuracy of tumor detection, two deep learning models are employed. Using a hybrid ResNet+SE model, we capture feature distributions within unbalanced classes, creating a more balanced dataset. The second model, a tailored classifier identifies brain tumors in MRI images. The proposed method has shown promising results, achieving a high detection accuracy of 98.79%. This highlights the potential of the model as an efficient and cost-effective system for brain tumor detection.

The morphological variability of the piriformis muscle.

BACKGROUND: The aim of the study is to create several classifications of the piriformis muscle (PM): proximal and distal attachments, potential fusions, and the relationship with the sciatic nerve. It is the first comprehensive anatomical examination of this subject. MATERIALS AND METHODS: One hundred and twenty-four lower limbs from 62 cadavers, fixed in 10% formalin, were examined. RESULTS: The piriformis muscle was present in 120 limbs (96.8% of cases). Four types of proximal attachment were described (I-IV). The most common type was Type I, in which the proximal attachment was at the anterior surface of the sacrum, between S2 and S4 (52 lower limbs; 43.3%). The rarest type was Type IV, in which the proximal attachment was at the gluteal surface of the ilium near the margin of the greater sciatic notch and from the gluteus medius (12 cases; 10%). Three types of distal attachment were distinguished. The most common was Type 1, a single tendon. This type comprised two subtypes: A and B (105 lower limbs; 87.5%). The other two types accounted for 12.5% of the total. Fusions were noted between the piriformis muscle and adjacent muscles in 31.7%. Four patterns were observed in which the sciatic nerve ran against the piriformis muscle. The most common variation in the relationship was the common fibular nerve exiting superior to the piriformis muscle and the tibial nerve passing inferior to it (10 cases; 8.3%). CONCLUSIONS: The piriformis muscle is highly morphologically variable in both its proximal and distal attachments and its relationship with the sciatic nerve. There are four types of proximal attachment and three types of distal attachment. The piriformis muscle shows numerous fusions with its adjacent muscles: gluteus medius or minimus or superior gemellus. A new (fourth) type of relationship was demonstrated between the piriformis muscle and sciatic nerve. The piriformis muscle was absent in four cases.

Japanese Classification of Esophageal Cancer, 12th Edition: Part I.

This is the first half of English edition of Japanese Classification of Esophageal Cancer, 12th Edition that was published by the Japan Esophageal Society in 2022.

Traumatic thoracic spine fracture: can we predict when MRI would modify the fracture classification or decision-making compared to CT alone?

PURPOSE: To determine the impact of magnetic resonance imaging (MRI) on fracture classification for thoracic spine fractures (TSFs) compared to computed tomography (CT) alone. METHODS: This study was a retrospective review of 63 consecutive patients with TSFs who underwent CT and MRI within ten days of injury. Three reviewers classified all fractures according to the AOSpine Classification and the Thoracolumbar AOSpine Injury severity score (TLAOSIS). Posterior ligamentous complex (PLC) injury on MRI was defined by "black stripe discontinuity" and on CT by the presence of vertebral body translation, facet joint malalignment, horizontal laminar or spinous process fracture, and interspinous widening. The proportion of patients with AO type A/B/C and with TLAOSIS ≤ 5 and ≥ 6 was compared between CT and MRI. Classification and regression trees were used to create a series of predictive models for the probability of PLC injury in AO type A fractures. RESULTS: AO classification using CT was as follows: type A in 35 patients (55%), type B in 18 patients (29%), and type C in 10 patients (16%). Thirty-three patients (52%) had a TLAOSIS ≤5, while the remaining 30 (48%) had TLAOSI ≥6. The addition of MRI after CT upgraded type A to type B fractures in 10 patients (16%) and changed TL AOSIS from ≤5 to ≥6 in 8 cases (12.8%). Type A fractures with load sharing score (LSC) ≥6 had a 60% chance of upgrading to type B, while LSC <6 had a 12.5% chance of upgrading to type B. CONCLUSIONS: CT yielded (89%) accuracy in diagnosing PLC injury in TSFs. The addition of MRI after CT substantially changed the AO classification or TLAOISS, compared to CT alone, thus suggesting an added value of MRI for PLC assessment for TSFs classification.

Patients with antiphospholipid syndrome and a first venous or arterial thrombotic event: clinical characteristics, antibody profiles and estimate of the risk of recurrence.

OBJECTIVES: Thrombosis in antiphospholipid syndrome (APS) involves in most cases the venous circulation. Why in some patients thrombotic APS affects the arterial circulation and in particular cerebral circulation is unknown. In previous studies, both patient characteristics and antiphospholipid antibody types and titers have been associated with arterial thrombosis. Aim of this study was to compare the clinical characteristics and laboratory findings of venous and arterial thrombotic APS from a large series of patients. METHODS: Data were retrieved from the Start 2 antiphospholipid, a multicenter prospective register of long-term collected data from Thrombosis Centers in Italy. RESULTS: Of 167 patients with thrombotic APS, 114 (68 %) had a venous and 53 (32 %) had an arterial event as first clinical manifestation. Several clinical characteristics and risk factors were different among groups in univariate analysis. Using logistic regression analysis, reduced creatinine clearance and hyperlipidemia were independent variable for the occurrence of arterial APS. Notably, no difference in antiphospholipid antibody profiles and aß2-Glycoprotein I levels were found between groups. A higher adjusted global antiphospholipid syndrome score (aGAPSS) was found in arterial group indicating a possible high recurrence rate in arterial APS. CONCLUSIONS: These data have pathophysiological and clinical implication since associated conditions might predispose patients to arterial rather than venous events and call to a close monitoring and treatment of arterial APS due to their increased tendency to recurrence.

Identifying gray matter alterations in Cushing's disease using machine learning: An interpretable approach.

BACKGROUND: Cushing's Disease (CD) is a rare clinical syndrome characterized by excessive secretion of adrenocorticotrophic hormone, leading to significant functional and structural brain alterations as observed in Magnetic Resonance Imaging (MRI). While traditional statistical analysis has been widely employed to investigate these MRI changes in CD, it has lacked the ability to predict individual-level outcomes. PURPOSE: To address this problem, this paper has proposed an interpretable machine learning (ML) framework, including model-level assessment, feature-level assessment, and biology-level assessment to ensure a comprehensive analysis based on structural MRI of CD. METHODS: The ML framework has effectively identified the changes in brain regions in the stage of model-level assessment, verified the effectiveness of these altered brain regions to predict CD from normal controls in the stage of feature-level assessment, and carried out a correlation analysis between altered brain regions and clinical symptoms in the stage of biology-level assessment. RESULTS: The experimental results of this study have demonstrated that the Insula, Fusiform gyrus, Superior frontal gyrus, Precuneus, and the opercular portion of the Inferior frontal gyrus of CD showed significant alterations in brain regions. Furthermore, our study has revealed significant correlations between clinical symptoms and the frontotemporal lobes, insulin, and olfactory cortex, which also have been confirmed by previous studies. CONCLUSIONS: The ML framework proposed in this study exhibits exceptional potential in uncovering the intricate pathophysiological mechanisms underlying CD, with potential applicability in diagnosing other diseases.

Comprehensive data analysis of white blood cells with classification and segmentation by using deep learning approaches.

Deep learning approaches have frequently been used in the classification and segmentation of human peripheral blood cells. The common feature of previous studies was that they used more than one dataset, but used them separately. No study has been found that combines more than two datasets to use together. In classification, five types of white blood cells were identified by using a mixture of four different datasets. In segmentation, four types of white blood cells were determined, and three different neural networks, including CNN (Convolutional Neural Network), UNet and SegNet, were applied. The classification results of the presented study were compared with those of related studies. The balanced accuracy was 98.03%, and the test accuracy of the train-independent dataset was determined to be 97.27%. For segmentation, accuracy rates of 98.9% for train-dependent dataset and 92.82% for train-independent dataset for the proposed CNN were obtained in both nucleus and cytoplasm detection. In the presented study, the proposed method showed that it could detect white blood cells from a train-independent dataset with high accuracy. Additionally, it is promising as a diagnostic tool that can be used in the clinical field, with successful results in classification and segmentation.