Classic Syndrome Research Articles

DSMN-ESS: Dual-Stream Multitask Network for Epilepsy Syndrome Classification and Seizure Detection

DSMN-ESS: Dual-Stream Multitask Network for Epilepsy Syndrome Classification and Seizure Detection

Two-Stream Attention 3-D Deep Network-Based Childhood Epilepsy Syndrome Classification

Epilepsy syndromes are typical childhood nervous system diseases, usually containing several different seizure types commonly seen. There exist around 20 known childhood epilepsy syndromes and accurate classifying these epilepsy syndromes plays a vital guidance to diagnosis and treatment. Current research mainly focused on seizure detection, while few have been presented on epilepsy syndrome classification. In this article, a novel two-stream 3-D attention module-based deep network (TSA3-D) is developed to exploit multichannel time-frequency and frequency-space features of interictal EEGs for epilepsy syndrome classification. Two multichannel montage transforms are applied for EEG feature optimization to reduce artifact affection. In TSA3-D, both the channelwise attention (CA) and dual spatial attention (DSA)-based 3-D attention modules are developed to enhance the EEG feature learning capability. The study is conducted on the long-term interictal EEGs of 115 subjects from the Children’s Hospital, Zhejiang University School of Medicine (CHZU). These data belong to seven typical childhood epilepsy syndromes and one normal control group. Experimental results show that TSA3-D can achieve an overall accuracy of 99.52%, the highest among when compared with the state-of-the-art (SOTA) methods.

Development of a Metabolic Syndrome Classification and Prediction Model for Koreans Using Deep Learning Technology: The Korea National Health and Nutrition Examination Survey (KNHANES) (2013-2018).

The prevalence of metabolic syndrome (MetS) and its cost are increasing due to lifestyle changes and aging. This study aimed to develop a deep neural network model for prediction and classification of MetS according to nutrient intake and other MetS-related factors. This study included 17,848 individuals aged 40-69 years from the Korea National Health and Nutrition Examination Survey (2013-2018). We set MetS (3-5 risk factors present) as the dependent variable and 52 MetS-related factors and nutrient intake variables as independent variables in a regression analysis. The analysis compared and analyzed model accuracy, precision and recall by conventional logistic regression, machine learning-based logistic regression and deep learning. The accuracy of train data was 81.2089, and the accuracy of test data was 81.1485 in a MetS classification and prediction model developed in this study. These accuracies were higher than those obtained by conventional logistic regression or machine learning-based logistic regression. Precision, recall, and F1-score also showed the high accuracy in the deep learning model. Blood alanine aminotransferase (β = 12.2035) level showed the highest regression coefficient followed by blood aspartate aminotransferase (β = 11.771) level, waist circumference (β = 10.8555), body mass index (β = 10.3842), and blood glycated hemoglobin (β = 10.1802) level. Fats (cholesterol [β = -2.0545] and saturated fatty acid [β = -2.0483]) showed high regression coefficients among nutrient intakes. The deep learning model for classification and prediction on MetS showed a higher accuracy than conventional logistic regression or machine learning-based logistic regression.

Spontaneous intracranial hypotension: a case series and literature review.

Spontaneous intracranial hypotension (SIH) is a condition of negative intracranial pressure resulting from cerebrospinal fluid (CSF) leakage from the dural sac and is a well-known cause of orthostatic headache. Diagnosis and management can be difficult, often requiring coordination between multiple disciplines. Low CSF pressure and diffuse meningeal enhancement on brain MRI are the major instrumental features of the classic syndrome. Neuroimaging plays a key role in diagnosing SIH, particularly in atypical clinical presentations, by recognizing the specific findings of brain sagging on MRI and detecting the level of CSF leak on spinal imaging, thus guiding therapy accordingly. Since SIH could present with such a heterogeneous clinical picture, careful history taking and increased awareness of atypical presentations are of utmost importance. We review the existing SIH literature, illustrate management, clinical and neuroimaging findings of four consecutive patients with atypical SIH, who were recently referred to our hospital for evaluation to simplify and streamline the management of SIH.

Letter: Cerebrospinal Fluid Shunting for Idiopathic Intracranial Hypertension: A Systematic Review, Meta-Analysis, and Implications for a Modern Management Protocol.

Letter: Cerebrospinal Fluid Shunting for Idiopathic Intracranial Hypertension: A Systematic Review, Meta-Analysis, and Implications for a Modern Management Protocol.

Impact of the International Consensus Classification of myelodysplastic syndromes.

The impact of the 2022 International Consensus Classification (ICC) of myelodysplastic syndromes (MDS) needs study. We analysed data from 989 MDS subjects classified using the 2016 World Health Organization (WHO) criteria to determine the impact of the new proposal. Our analyses suggested the ICC criteria of MDS-SF3B1 identifies a more homogenous disease entity than the WHO 2016 criteria of myelodysplastic syndromes with ring sideroblasts (MDS-RS). MDS, not otherwise specified with single lineage dysplasia (MDS, NOS-SLD) patients had a better prognosis than MDS, NOS with multilineage dysplasia (MDS, NOS-MLD) patients. MDS with mutated TP53 and MDS/acute myeloid leukaemia with mutated TP53 patients had the briefest survivals. These data support the ICC of MDS, which allows more accurate diagnoses and risk stratification.

Lacunary stroke. Clinical cases

Introduction. Cerebral microangiopathy is the leading cause of vascular cognitive disorders accompined by dementia in the final stages of the disease. Purpose – to study the spectrum of lacunar syndromes in patients with acute cerebrovascular accidents based on our own observations and provide a description of rare clinical variants of the didorders. Materials and methods. We examined 18 patients (10 men and 8 women) aged 33 to 66 years (mean age 52.33 years) in the acute period of lacunar strokes (LS). We studied the neurological status, the data of laboratory-instrumental, speech therapy and neuropsychological testing. The diagnosis of LS was verified using magnetic resonance imaging. Results. Lacunar strokes were more common in patients of mature age (72.22 %) suffering from arterial hypertension (88.89 %) in combination with obesity (44.44 %); patients with atherosclerosis of the coronary and cerebral arteries (27.78 %), type 2 diabetes mellitus (22.22 %) found to have lacunar stroke less often. The sensorimotor hemisyndrome was found to be prevailed (44.44 %). Other classical lacunar syndromes were detected less frequently: with the same frequency (16.67 %) – isolated hemihypesthesia and «hemiballism / hemichorea», as well as «dysarthria – clumsy hand» (11.11 %). The predominant localization of the lesion is the right hemisphere (88.89 %), the internal capsule (66.67 %), rarely the thalamus (27.78 %). Multiple LS were registered in 27.78 % of cases, including the patients with tandem atherostenosis of the cerebral arteries. Descriptions of two clinical cases of LS are presented. Conclusion. Sensorimotor hemisyndrome dominated in clinical scenario. We also observed more rare disorders – bulbar syndrome with anarthria with bilateral damage to the knee of the internal capsule and hyperkinetic syndrome with myoclonus of the respiratory, vocal and articular apparatus. The right-hemispheric lesion predominated with the localization of foci in the internal capsule, the thalamus suffered rarely. Multiple LS were registered in 27.78 % of cases. LSs have unfavorable prognosis for patients with uncontrolled arterial hypertension combined with tandem stenoses of extra- and intracerebral arteries with cognitive disorders that made it difficult to manage patients. The relevance of LS neuroimaging in overweight patients was noted.

Crouzon syndrome with acanthosis nigricans: a case report and literature review.

Crouzon syndrome with acanthosis nigricans is an autosomal dominant disease, with typical features of classic Crouzon craniosynostosis, verrucous hyperplasia, and hyperpigmentation of the skin. While several mutations in FGFR2 cause classic Crouzon syndrome, Crouzon syndrome with acanthosis nigricans results from a point mutation in the fibroblast growth factor receptor 3 gene (FGFR3). We report the case of an 8-year-old Vietnamese girl diagnosed with Crouzon syndrome with acanthosis nigricans, showing typical clinical features, including a crouzonoid face and dark plaques on the skin. Genetic testing showed a missense variation in FGFR3, associated with Crouzon syndrome with acanthosis nigricans. Following diagnosis, we treated acanthosis nigricans with 10% urea cream. This case study and literature review discuss the cutaneous manifestations and dermatological treatments while demonstrating the importance of clinical examination and evaluation of the patient's medical history during diagnosis. Our findings contribute to the global pool of data, providing practical insights into the manifestations of Crouzon syndrome.

Do labels matter? Analysis of teachers' self‐efficacy towards the autism spectrum disorder depending on the diagnostic label used (ASD or Asperger's)

Changes in the classification of autism and Asperger's syndrome led to changes in social perception of ASD. Since last criteria, studies indicate higher levels of stigma towards ASD than towards Asperger's. These prejudices are barriers to inclusive education. Thus, it is relevant (1) to evaluate pre‐service teachers' self‐efficacy towards the label of ASD; (2) to evaluate pre‐service teachers' self‐efficacy towards the label of Asperger's and (3) to compare those results to analyse whether the use of different diagnostic labels brings about different levels of self‐efficacy. One hundred and eighty‐six primary education pre‐service teachers participated in the current study. Two adaptations of the Autism Self‐Efficacy Scale for Teachers (ASSET) were used: a version with the label of ‘ASD’ (n = 96) and another for ‘Asperger's’ (n = 90). The scores obtained by the group asked about ASD were high according to the ASSET score range, while the scores obtained by the group asked about Asperger's were medium. After comparing the results, participants asked about the label ASD showed higher levels of self‐efficacy than participants asked about Asperger's. These results could be a consequence of the consolidation of the ASD diagnosis among society and the higher presence of children with ASD in schools and cultural products, among other factors.

Effect of prone positioning on end-expiratory lung volume, strain and oxygenation change over time in COVID-19 acute respiratory distress syndrome: A prospective physiological study.

Prone position (PP) is a recommended intervention in severe classical acute respiratory distress syndrome (ARDS). Changes in lung resting volume, respiratory mechanics and gas exchange during a 16-h cycle of PP in COVID-19 ARDS has not been yet elucidated. Patients with severe COVID-19 ARDS were enrolled between May and September 2021 in a prospective cohort study in a University Teaching Hospital. Lung resting volume was quantitatively assessed by multiple breath nitrogen wash-in/wash-out technique to measure the end-expiratory lung volume (EELV). Timepoints included the following: Baseline, Supine Position (S1); start of PP (P0), and every 4-h (P4; P8; P12) until the end of PP (P16); and Supine Position (S2). Respiratory mechanics and gas exchange were assessed at each timepoint. 40 mechanically ventilated patients were included. EELV/predicted body weight (PBW) increased significantly over time. The highest increase was observed at P4. The highest absolute EELV/PBW values were observed at the end of the PP (P16 vs S1; median 33.5 ml/kg [InterQuartileRange, 28.2-38.7] vs 23.4 ml/kg [18.5-26.4], p < 0.001). Strain decreased immediately after PP and remained stable between P4 and P16. PaO2/FiO2 increased during PP reaching the highest level at P12 (P12 vs S1; 163 [138-217] vs 81 [65-97], p < 0.001). EELV/PBW, strain and PaO2/FiO2 decreased at S2 although EELV/PBW and PaO2/FiO2 were still significantly higher as compared to S1. Both absolute values over time and changes of strain and PaO2/FiO2 at P16 and S2 versus S1 were strongly associated with EELV/PBW levels. In severe COVID-19 ARDS, EELV steadily increased over a 16-h cycle of PP peaking at P16. Strain gradually decreased, and oxygenation improved over time. Changes in strain and oxygenation at the end of PP and back to SP were strongly associated with changes in EELV/PBW. Whether the change in EELV and oxygenation during PP may play a role on outcomes in COVID-ARDS deserves further investigation. [www.ClinicalTrials.gov], identifier [NCT04818164].

Research Progress on Phenotypic Classification of Acute Respiratory Distress Syndrome: A Narrative Review.

Acute respiratory distress syndrome (ARDS) is a clinical syndrome that is characterized by an acute onset and refractory hypoxemia. It remains an important contributor to high mortality in critically ill patients, and the majority of clinical randomized controlled trials on ARDS provide underwhelming findings, which is attributed in large part to its pathophysiological and clinical heterogeneity, among other aspects. It is now widely accepted that ARDS is highly heterogeneous, growing evidences support this. ARDS phenotypic and subphenotypic studies aim to further differentiate and identify ARDS heterogeneity in the hope that clinicians can benefit from it, then can diagnose ARDS faster and more accurately and provide targeted treatments. This review collates and evaluates the major phenotype-related research advances of recent years, with a specific focus on ARDS biomarkers and clinical factors.

Retrospective analysis of the sex chromosomal copy number variations in 186 fetuses using single nucleotide polymorphism arrays.

Sex chromosomal abnormalities are associated with multiple defects. However, the types of sex chromosomal abnormalities during pregnancy in Fujian Province, China, are not recorded. In this retrospective analysis, we showed the sex chromosomal abnormalities of 186 fetuses, including 162 cases of X chromosomal abnormalities and 22 cases of Y chromosomal abnormalities in Fujian Province. We detected 73 cases of Turner syndrome, 24 cases of triple X syndrome, 37 cases of Klinefelter syndrome, and 14 cases of XYY syndrome. It was observed that 67.3% fetuses with classic Turner syndrome had their growth arrested. Moreover, we found 21 cases of mosaic Turner syndrome, 3 cases of mosaic Triple X syndrome, 2 cases of mosaic Klinefelter syndrome, and 1 case of mosaic XYY syndrome. Furthermore, 37 cases of large scales of sex chromosomal deletions/duplications were detected, including 30 cases of X chromosomal deletions/duplications and 7 cases of Y chromosomal deletions/duplications. Parent-of-origins of five cases of sex chromosomal deletions/duplications were determined. One case was with de novo X chromosomal variations, while the sex chromosomal deletions/duplications in other four cases were inherited from their parents. Overall, our results presented a detailed manifestation of sex chromosomal abnormalities of 186 fetuses in Fujian Province and suggested the important roles of single nucleotide polymorphism (SNP) array analysis in the prenatal diagnosis of sex chromosomal abnormalities. Also, determining the parent-of-origins of the deletions/duplications was critical for the prenatal diagnosis of sex chromosomal abnormalities.

The International Consensus Classification (ICC) of hematologic neoplasms with germline predisposition, pediatric myelodysplastic syndrome, and juvenile myelomonocytic leukemia.

Updating the classification of hematologic neoplasia with germline predisposition, pediatric myelodysplastic syndrome (MDS), and juvenile myelomonocytic leukemia (JMML) is critical for diagnosis, therapy, research, and clinical trials. Advances in next-generation sequencing technology have led to the identification of an expanding group of genes that predispose to the development of hematolymphoid neoplasia when mutated in germline configuration and inherited. This review encompasses recent advances in the classification of myeloid and lymphoblastic neoplasia with germline predisposition summarizing important genetic and phenotypic information, relevant laboratory testing, and pathologic bone marrow features. Genes are organized into three major categories including (1) those that are not associated with constitutional disorder and include CEBPA, DDX41, and TP53; (2) those associated with thrombocytopenia or platelet dysfunction including RUNX1, ANKRD26, and ETV6; and (3) those associated with constitutional disorders affecting multiple organ systems including GATA2, SAMD9, and SAMD9L, inherited genetic mutations associated with classic bone marrow failure syndromes and JMML, and Down syndrome. A provisional category of germline predisposition genes is created to recognize genes with growing evidence that may be formally included in future revised classifications as substantial supporting data emerges. We also detail advances in the classification of pediatric myelodysplastic syndrome (MDS), expanding the definition of refractory cytopenia of childhood (RCC) to include early manifestation of MDS in patients with germline predisposition. Finally, updates in the classification of juvenile myelomonocytic leukemia are presented which genetically define JMML as a myeloproliferative/myelodysplastic disease harboring canonical RAS pathway mutations. Diseases with features overlapping with JMML that do not carry RAS pathway mutations are classified as JMML-like. The review is based on the International Consensus Classification (ICC) of Myeloid and Lymphoid Neoplasms as reported by Arber et al. (Blood 140(11):1200-1228, 2022).

Lynch syndrome, molecular mechanisms and variant classification.

Patients with the heritable cancer disease, Lynch syndrome, carry germline variants in the MLH1, MSH2, MSH6 and PMS2 genes, encoding the central components of the DNA mismatch repair system. Loss-of-function variants disrupt the DNA mismatch repair system and give rise to a detrimental increase in the cellular mutational burden and cancer development. The treatment prospects for Lynch syndrome rely heavily on early diagnosis; however, accurate diagnosis is inextricably linked to correct clinical interpretation of individual variants. Protein variant classification traditionally relies on cumulative information from occurrence in patients, as well as experimental testing of the individual variants. The complexity of variant classification is due to (1) that variants of unknown significance are rare in the population and phenotypic information on the specific variants is missing, and (2) that individual variant testing is challenging, costly and slow. Here, we summarise recent developments in high-throughput technologies and computational prediction tools for the assessment of variants of unknown significance in Lynch syndrome. These approaches may vastly increase the number of interpretable variants and could also provide important mechanistic insights into the disease. These insights may in turn pave the road towards developing personalised treatment approaches for Lynch syndrome.

A Reflection of Metabolic Syndrome through the Window of COVID-19

COVID-19 and metabolic syndrome, though seemingly different disorders, appear to share certain common pathogenic components, especially in the development of COVID-19-associated diabetes mellitus. The similarities include impairment in immunoendothelial, gastrointestinal, pancreatic, adipose and mitochondrial functions, with several critical micronutrients undergirding the intricate interactions among these dysfunctions. This discussion aims to highlight the parallels between COVID-19 and metabolic syndrome and to propose the possibility of SARS-CoV-2 being a prototype of an acquired etiological agent which can eventually lead to the development of classical metabolic syndrome. Based on the proposed model, the discussion will include the implication for early management of COVID-19 and metabolic syndrome.

Balloon-Assisted Corpus Callosotomy. Reducing the Impact of Transcallosal Approaches.

The interhemispheric transcallosal approach is widely used to remove intraventricular lesions. Corpus callosotomy gives immediate access to the ventricular chambers but is invasive in nature. Loss of callosal fibers, although normally tolerate, may cause disturbances ranging from a classical disconnection syndrome up to minor neuropsychological changes. To open an operative window in the corpus callosum through separation rather than disconnection of the white matter fibers. In 7 patients undergoing the interhemispheric transcallosal approach for intraventricular lesions, lying around or below the foramen of Monro, a stoma was created within the corpus callosum by using a 4F Fogarty catheter. The series included 3 colloid of the third ventricle, 2 thalamic cavernomas, 1 subependymoma, and 1 ependymoma of the foramen of Monro. We illustrate the technique and the clinico-radiological outcome, focusing on the size of callosotomy as seen on postoperative MRI. The balloon-assisted corpus callosotomy provided a circular, smooth-walled access to the ventricular chambers, which allowed uncomplicated removal of the lesions. On postoperative MRI, the size of the callosotomy shrinked compared with surgery (2.8-6.4 mm at follow-up vs 6-9 mm as measured intraoperatively). No signs of disconnection syndrome or new permanent deficits were observed in this series. The balloon-assisted technique produces a small callosotomy, without clinical consequences, showing a self-closing trend on postoperative MRI. This technique is a rewarding tool to reduce the impact of callosotomy while keeping the advantages of microsurgical interhemispheric approaches.

The Role of Adult Cancer Predisposition Genes in Hematological Malignancies of Childhood

Background: Increasing evidence suggests that adult cancer genes (ACGs) contribute substantially to the development of several malignancies in childhood, although with reduced penetrance. The association of BRCA1 and BRCA2 with breast and ovarian cancer is sufficiently described, as well as the presence of heterozygous mutations in one of the mismatch repair genes (MSH2, MSH6, MLH1, PMS2) in hereditary colon carcinoma. Moreover, there is a plethora of genes, mainly regulating DNA repair mechanisms and cell cycle arrest as BRIP1, CHEK2, ATM, PALB2, HOXB13, RAD51C, RAD51D, which predispose to a variety of adult type cancers. The recurrent presence of pathogenic variants in one of the ACGs is observed in several pediatric cancer cohorts and gaining recognition in the field of pediatric cancer susceptibility. However, the incidence and impact of ACGs in childhood cancer and especially in pediatric hematological malignancies is not fully explored yet. Aims: Our aim is to understand the frequency and the impact of germline variants in adult cancer predisposition genes in the etiology of hematological malignancies in children. Methods: We analyzed parent-child whole exome sequencing (WES) data of 162 children (<18yrs) with hematological malignancies (N=117 leukemia, N=43 lymphoma, N=2 myelodysplastic syndrome) for the presence of pathogenic variants in adult onset cancer predisposition genes. For part of the detected variants, we performed further functional analysis to investigate the effect of the alteration on protein function. Results: We diagnosed a classical cancer predisposition syndrome associated with the respective hematological malignancy in 5/162 patients (3%): Li-Fraumeni (N=1), Constitutional mismatch repair deficiency (CMMRD) (N=1), Nijmegen-Breakage syndrome (NBS) (N=1) and Noonan syndrome (N=2). Additionally we identified in 19/162 patients a pathogenic / likely pathogenic variant (P/LP) in one of the ACGs, including BRIP1, CHEK2, HOXB13, BRCA1, MSH2 and STK11. Strikingly, we observed a high frequency of CHEK2 germline variants in our cohort (15/162) (Figure 1A). The majority of those patients had a leukemia (N=11 BCP-ALL, N=1 T-ALL, N=1 CML) and two patients were diagnosed with a Hodgkin lymphoma. Interestingly, eight different CHEK2 variants including three truncating variants were detected in our cohort. Three variants were recurrent (p.Ile157Thr N=5, p.Ile160Met N=3, p.Thr367Metfs*15 N=2). According to the classification of the American College of Medical Genetics and Genomics 7/8 variants identified in 14 patients were predicted to be pathogenic or likely pathogenic. For two of these variants an impaired function had been already described in the literature. To test the functional consequences of the five remaining variants, we overexpressed these, in comparison to two control CHEK2 variants, in U2OS cells. Four out of seven variants (N=1 truncating, N=1 in-frame deletion, N=2 missense) led to loss of protein expression (Figure 1B) and loss of CHEK2-Thr68 phosphorylation upon irradiation induced DNA damage. Hence, according to the functional analysis, five out of fifteen patients carried a CHEK2 variant impairing its function. Interestingly, 4/5 patients with a pathogenic variant had a BCP-ALL and 1/5 had a BCR-ABL CML that rapidly progressed to lymphoid blast crisis while under imatinib therapy (400 mg/m2). Conclusion/Summary: We identified heterozygous pathogenic variants in ACGs in the germline of 11.7% of children with hematological malignancies by WES-based screening of 162 cases. Strikingly 14/162 patients (8,6%) harbored a P/LP variant in the CHEK2 gene. Functional studies revealed that five patients carried a germline variant leading to loss of CHEK2 expression and/or loss of Thr68 phosphorylation upon irradiation. We conclude that impaired CHEK2 function may be an important germline-encoded host factor predisposing to the development of hematological malignancies in children. Figure 1 (A): Schematic representation of the CHEK2 protein indicating the localization of the identified variants. The length of the bars correlates to the number of patients with the respective CHEK2 variant and the color of the bars to the variant type (green: missense, red: frameshift indels, orange: splicing). (B): Western blot analysis of HA-tagged CHEK2 protein variants ectopically expressed in U2OS cells. GAPDH was used as a loading control. Figure 1View largeDownload PPTFigure 1View largeDownload PPT Close modal

3D figure of epilepsy syndromes.

We propose an instructive figure that summarized the classification of epilepsy syndromes according to the 2022 report of the ILAE Task Force on Nosology and Definitions. Our aim is to present on the same figure different concepts such as the names of epilepsy syndromes, their extreme and classical ages of onset, their epilepsy types (generalized, focal, or generalized and focal) but also their membership in groups of epilepsy syndromes as for self-limited or developmental and epileptic encephalopathies. With this figure, we provide an interactive tool, as supplementary data, helping to present this classification and link it to electro-clinical mandatory, alerts, and exclusionary criteria of each syndrome, in accordance with the ILAE position papers on syndromes classification and nosology. This report may be used as an illustrative tool for teaching epilepsy syndromes and as a practical and comprehensive aid for the classification of epilepsy individuals' syndromes.

Abstract 15435: Evaluating Sex-Disparities in Machine Learning Decision Support Tools for Acute Coronary Syndrome Classification in the Emergency Department

Introduction: Women are less likely than men to be promptly diagnosed with acute coronary syndrome (ACS) and have worse post-ACS outcomes. These diagnostic failures are partially due to ACS findings on surface ECG manifesting differently in women, which may result in unnecessary delays in treatment. To narrow health disparities, we aim to investigate the sex-specific signatures of ACS as they appear on ECGs. Methods: This was a prospective observational cohort study of chest-pain patients evaluated for suspected ACS at 3 UPMC-affiliated tertiary care hospitals. After featurization, all ECG data were separately fed into 7 machine learning classifiers to predict ACS. We examined the results by sex. We also investigated two other methods: (1) building two independent models based respectively on the female and male subgroups and (2) building a model based on the initial total sample supplemented by the patients’ sex. We used Shapley values to explain the decision-making criteria of the models. We report the results for random forest, the best performing classifier. Results: Our sample consisted of 4132 patients (Age 59 ± 16; 47% female; 15% ACS). Machine learning models continue to disproportionately underperform in females across all classifiers evaluated. The sensitivity, specificity and false negative rate in the global model blinded to sex were 82.89%, 76.22% and 17.11% for men, and 67.39%, 74.16% and 32.61% for women (p&lt;0.0001). This statistically significant gap could not be alleviated by building sex-specific models or feeding sex to the input of the model. Indeed, the rate of false negatives in sex-specific models and global models with sex as input were 14.67% and 18.42% for men, and 34.04% and 32.61% for women (p&lt;0.0001). The explainability analysis of the sex-specific models revealed that STT configuration in lateral leads is most informative in women, whereas STT configuration in all leads and particularly in anterolateral leads most informative in men. Conclusions: Machine learning models display crucial sex differences in the ACS signatures on the ECG that consistently put women in a detrimental situation. The alternative methods investigated here are not adequate solutions for this disparity. Thus, further investigations should be conducted.

Variant connective tissue (joint hypermobility) and its relevance to depression and anxiety in adolescents: a cohort-based case–control study

ObjectiveTo test whether variant connective tissue structure, as indicated by the presence of joint hypermobility, poses a developmental risk for mood disorders in adolescence.DesignCohort-based case–control study.SettingData from the Avon Longitudinal...