A multi-modal hybrid phenotype-aware graph framework for neuropsychiatric disorder diagnosis

Validation of a Portuguese version of a generic health quality-of-life questionnaire for children with neurological and neuropsychiatric disorders, including epilepsy

Surgical treatment for primary hyperparathyroidism (PHPT) has traditionally prioritized “bones and stones” over “moans and groans”. As widespread routine biochemical testing and screening for osteoporosis becomes commonplace, more patients with “asymptomatic” or “minimally symptomatic” disease are being diagnosed. Strong indications for surgery remain confined to young patients and those with established osteoporosis or renal calculi.1 There remains some reluctance to refer patients for surgery where disease is “asymptomatic” particularly in those aged >50 years.2 Current guidelines focus on biochemical cure and longer-term improvements in bone mineral density and reduction in renal calculi as measures of success following surgery.1 From the patient perspective, the most concerning symptoms are often the “nonspecific symptoms” of PHPT. These include anxiety, depression, fatigue, cognitive decline, aches, and pains. Improvements in these “nonspecific symptoms” are well-documented following surgery and can be measured by both validated disease-specific patient-reported outcome measures (PROMs) and correlated with global health-related quality of life scores.3 As clinicians, it is difficult to predict the degree to which any individual patient will benefit from surgery particularly regarding neurocognitive symptoms. Why one patient bounds back into the clinic after surgery and another is disappointed at the lack of improvement in symptoms is not fully understood. Longer-term data on neurocognitive symptom change and the development of neuropsychiatric diagnoses after parathyroidectomy is lacking. In this manuscript, Song and colleagues investigate the effect of parathyroidectomy on the subsequent diagnosis of neuropsychiatric disorders.4 The study population is a large retrospective cohort of 3728 patients from their institutional database, encompassing health data from a population of over one million individuals. Notably, individuals with both “classical PHPT” (with elevation of both serum calcium and PTH) and “normohormonal PHPT” (elevation of serum calcium with normal PTH) are included. Normocalcemic patients and those with secondary causes of hyperparathyroidism are excluded. Just under half of the patients received surgery. Baseline differences in age, race, marital status, and PTH levels between the nonoperative and operative groups suggest some bias in surgical selection. Propensity score matching has been used to adjust for these potential confounders. At a median of 4.2 years follow-up, there was a significantly lower rate of new diagnoses of cognitive impairment, somnolence, and schizophrenia in the operative group. Diagnoses of anxiety, depression, and suicidal ideation were not influenced by operative management. In addition, a decreased likelihood of needing future hospitalization for neuropsychiatric disorders was found in those who underwent parathyroidectomy. The authors are to be congratulated on putting together such a large dataset investigating this important question. Steps have been taken to ensure the completeness of the data; reporting only a 3.4% loss to follow-up. The authors have been open about the limitations of their research and measured in their conclusions. Unlike prior studies on this topic that have utilized PROMs, the outcome measure in this study involves a neuropsychiatric diagnosis. No threshold for “diagnosis” is given, but it is probable that only those who sought health care for neuropsychiatric symptoms severe enough to warrant a “diagnosis” are included in this study. Thus, although the subtleties of the patient experience (including less prominent anxiety and depressive symptoms) are unlikely to be captured, this study brings us data about healthcare utilization for neuropsychiatric symptoms including hospitalization. The suggestion that parathyroidectomy might prevent or delay future neuropsychiatric disorders is persuasive. Further prospective data are required to confirm this association, establish causation, and identify those subsets of patients who are most likely to benefit. Nevertheless, this study brings to the evidence base tantalizing data indicating a possible role in neuropsychiatric health prevention (or preservation) with parathyroidectomy. This is likely to be an attractive proposition to many patients and their physicians and suggests that the indications for parathyroidectomy in “asymptomatic PHPT” be expanded. This is consistent with evolving modern surgical practice, including the recent Australian and New Zealand guidelines advocating for surgery in any patient with PHPT and an expected life expectancy of >10 years.5 For many years, endocrine surgeons have argued that “asymptomatic PHPT” is not truly asymptomatic and that surgery should be considered in all patients fit for anesthesia. This manuscript suggests that we move a little further beyond this notion, and turn our focus to the role of parathyroidectomy in preventing future health morbidity (physical and psychological), to the longer term benefit of both our patients and the health system. Open access publishing facilitated by The University of Newcastle, as part of the Wiley - The University of Newcastle agreement via the Council of Australian University Librarians. Christine J. O'Neill: Conceptualization; writing—original draft; writing—review & editing.

Reverse triiodothyronine (rT3) is traditionally regarded as a biologically inactive isomer of triiodothyronine (T3), produced primarily via peripheral deiodination of thyroxine (T4). Although T3 binds to nuclear thyroid hormone receptors and regulates transcription of genes essential to neuronal development, synaptic plasticity, and myelination, rT3 lacks such agonist activity. Recent studies suggest rT3 may competitively inhibit T3 at receptor sites and influence thyroid hormone bioavailability by modulating deiodinase enzyme activity. These effects position rT3 as a potentially significant contributor to the pathophysiology of various neuropsychiatric conditions. A comprehensive literature review was conducted through 2024 using biomedical databases including PubMed, Scopus, and Google Scholar. Inclusion criteria targeted peer-reviewed studies investigating rT3 regulation, deiodinase enzyme function (particularly type 3 deiodinase, D3), and clinical correlations between altered thyroid hormone profiles and psychiatric illnesses. Key terms included "reverse T3," "thyroid metabolism," "deiodinase activity," "functional hypothyroidism," and various neuropsychiatric diagnoses. Articles emphasizing both molecular mechanisms and clinical outcomes were prioritized. Increased D3 activity during physiological stress, trauma, chronic inflammation, or psychiatric illness shifts T4 metabolism away from active T3 and toward inactive rT3. This leads to a biochemical state described as "functional hypothyroidism," where serum T4 and thyroid-stimulating hormone (TSH) levels may appear normal, yet intracellular T3 action is diminished. Elevated rT3 and reduced T3/rT3 ratios have been identified in patients with depression, bipolar disorder, generalized anxiety, cognitive impairment, and schizophrenia. These alterations correlate with symptom severity and treatment resistance in some individuals. Additionally, rT3 has shown promise as a biomarker for disrupted thyroid signaling in neuropsychiatric contexts, potentially guiding more personalized treatment approaches. Reverse T3, long viewed as a passive by-product, may play an active regulatory role in neuropsychiatric disorders by interfering with T3 signaling at the cellular level. Functional hypothyroidism driven by excess rT3 represents a distinct biochemical phenotype contributing to mood, cognition, and behavioral dysfunction. Recognition of this mechanism underscores the need for expanded thyroid assessment beyond standard TSH and T4 testing in psychiatric populations. Future research should focus on the therapeutic implications of correcting rT3 dominance and restoring optimal intracellular thyroid hormone activity.

In this paper, a novel framework for global diagnosis of autism spectrum disorder (ASD) using task-based functional MRI data is presented. A speech fMRI experiment is held to obtain local features related to the functional activity of the brain. This study proposes both global diagnosis and local diagnosis by analyzing brain brainnetome atlas (BNT) which will lead to the first step of providing personalized medicine. The diagnosis pipeline consists of four steps on functional MRI volumes. The experimental results show that the global classification accuracy of our framework is about 75.8% and is much higher than other alternatives. Finally, comprehensive brain maps are provided for different individuals to indicate the degree of susceptibility of each brain area for autism, moving towards the idea of personalized medicine.

The neuroepithelium has been used as an experimental model to find biological markers for neuropsychiatric disease diagnosis. Patent information permits understanding of the state of the art of neuroepithelium in neuropsychiatric disease diagnosis, as well as the identification of trends in research and development on this theme. In this article, we discuss diverse methods for obtaining primary cultures of olfactory neurons obtained by animal dissection or by postmortem biopsy of human cadavers. The principal owners of patents related to olfactory neuroepithelia are universities such as John Hopkins and Bristol-Myers Squibb. The USA has the most research lines and approved patents in the world, while Rutgers, the State University of New Jersey, provides composition and methods related to the diagnoses and treatment of neuropsychiatric disorders.

The evaluation of suspected neuropsychiatric disorder in a series of 17 patients is described. The heuristic value of DSM-III's multiaxial approach is noted. The use of routine and neuropsychological tests, EEGs, CAT scans, T-3 and T-4 tests, and lumbar puncture, in conjunction with prolonged behavioral observation in a stable, therapeutic milieu, provided the means for clarification of neuropsychiatric illness in this series of complex cases. The value of CAT scans, neuropsychological tests and of prolonged behavioral observation in selected cases is discussed.

Obsessive Compulsive Disorder (OCD) is a neuropsychiatric brain disorder disease and diagnosis, treatment process of the disease is used EEG analysis. Recent studies suggested that the OCD is caused by dysfunction in brain's frontal lobe. The GFS that was developed as a novel synchronization criteria, computes phase difference between neural oscillations in the brain. Studies were published that indicates fall of GFS values. In this study, it was investigated how OCD effect phase difference between neuronal oscillations. For this purpose, results of the GFS method was applied to 19 channels EEG, indicates OCD decrease of neural synchronization in brain's frontal lobe at Delta and Beta 3 frequency bands..

Introduction: Autism spectrum disorder (ASD) is a neuropsychiatric disorder characterized by impaired social skills and limited or repetitive behaviors. In this study, we investigated the role of the ABCA13 gene in the etiopathogenesis of ASD. Methods: Single-nucleotide variants were evaluated in 79 ASD patients (59 males +20 females) with no established genetic etiology associated with ASD using whole-exome sequencing/clinical exome sequencing method. Family segregation analysis was performed using Sanger sequencing. We presented the clinical and genetic findings of these cases and their parents in detail. Results: We presented 10 different ABCA13 gene variants in cases with ASD and 10 parents carrying the same ABCA13 gene variant. There of these variants were likely pathogenic and seven variants were classified as variant of uncertain significance. Our cases had a comorbidity rate for attention deficit hyperactivity disorder (ADHD) as 70%. Various types of neuropsychiatric symptoms and diagnoses were detected including ADHD, anxiety disorder, intellectual disability, delay in speech, and febrile convulsion among the parents. Conclusion: To date, very few variants have been reported in the ABCA13 gene. Our findings enrich the role of ABCA13 gene may play a common role in the landscape of neuropsychiatric disorders.

The explorations of brain functional connectivity (FC) network using resting-state functional magnetic resonance imaging (rs-fMRI) can provide crucial insights into discriminative analysis of neuropsychiatric disorders such as schizophrenia (SZ). Graph attention network (GAT), which could capture the local stationary on the network topology and aggregate the features of neighboring nodes, has advantages in learning the feature representation of brain regions. However, GAT only can obtain the node-level features that reflect local information, ignoring the spatial information within the connectivity-based features that proved to be important for SZ diagnosis. In addition, existing graph learning techniques usually rely on a single graph topology to represent neighborhood information, and only consider a single correlation measure for connectivity features. Comprehensive analysis of multiple graph topologies and multiple measures of FC can leverage their complementary information that may contribute to identifying patients. In this paper, we propose a multi-graph attention network (MGAT) with bilinear convolution (BC) neural network framework for SZ diagnosis and functional connectivity analysis. Besides multiple correlation measures to construct connectivity networks from different perspectives, we further propose two different graph construction methods to capture both the low- and high-level graph topologies, respectively. Especially, the MGAT module is developed to learn multiple node interaction features on each graph topology, and the BC module is utilized to learn the spatial connectivity features of the brain network for disease prediction. Importantly, the rationality and advantages of our proposed method can be validated by the experiments on SZ identification. Therefore, we speculate that this framework may also be potentially used as a diagnostic tool for other neuropsychiatric disorders.

Monogenetic diseases associated with chromosome 15 pose diagnostic challenges due to their intricate inheritance patterns. A novel framework is needed to address the complex challenges. Hence, two novel deep learning approaches have been proposed for the diagnosis with the aim of improving accuracy: an alignment-free method using mean shift clustering, one-hot encoding, and a Convolutional Neural Network (CNN) – Bidirectional Long-Short term Memory (BiLSTM) architecture optimized by Elephant Herd Optimization (EHO), and an alignment-based method employing the Needleman-Wunsch algorithm, CNN-BiLSTM, and Horse Herd Optimization (HHO). The nature-inspired genetic optimization techniques, EHO and HHO optimizes model performance by effectively exploring the search space.

Introduction The diagnosis of specific learning disorders (SLDs) in adults has increased substantially over the past two decades, particularly within selective postsecondary and professional training settings. Part II of this paper examines why adult SLD diagnosis is especially vulnerable to error and bias, despite diagnostic criteria requiring substantial, developmentally grounded academic impairment. Methods We synthesize empirical research from neuropsychology, education, and psychometrics to identify systematic sources of diagnostic distortion in adult SLD assessment. Particular emphasis is placed on statistical artifacts (e.g. restriction of range), base-rate neglect, contextual performance effects, performance validity, reliance on self-report, and the misapplication of sociostructural frameworks to clinical decision-making. Results To combat overdiagnosis and ground diagnosis in empirically-supported practices, we propose a four-step diagnostic framework for first time diagnosis of SLD in adults: 1) Documented academic achievement below at least the 16th percentile relative to the general population norms; 2) Clear evidence of onset in early school years, including impairment when scaffolding and supports are removed; 3) Evidence that academic difficulties persisted despite adequate educational opportunity and, when available, targeted intervention; and 4) Exclusion of contextual, motivational, neurological/medical, language, or instructional explanations. Conclusions Accurate diagnosis of SLD in adulthood requires population-referenced criteria, corroborated evidence of childhood onset, objective demonstration of current academic impairment, systematic exclusion of alternative explanations, and assessment of performance credibility. Adoption of a structured, evidence-based diagnostic framework is essential to preserving the scientific validity, ethical application, and equitable use of SLD diagnoses in adult educational and professional settings.

Framework for Deep Learning Diagnosis of Plant Disorders in Horticultural Crops: From Data Collection Tools to User-Friendly Web and Mobile Apps

The early and precise identification of neuro-cardiac conditions is one of the greatest clinical problems as the interactions between cardiovascular and the nervous systems are intricate. The paper introduces an AI-Enhanced Multimodal Framework, which combines electrocardiogram (ECG), electroencephalogram (EEG), and clinical textual information, to help to diagnose neuro-cardiac abnormalities in the early stages. The suggested system uses deep multimodal learning to derive discriminative representation of heterogeneous biomedical signals and textual metadata and then a fusion mechanism is used to infer inter-modal correlation with disease progression. High-level preprocessing and signal improvement algorithms are used to process noise and variability of bio signals, and contextual embeddings are generated based on clinical narratives by transformer-based language models. The experimental findings on benchmark data sets indicate that multimodal fusion model performs significantly better as compared to unimodal baselines in accuracy and sensitivity in identifying comorbid neuro-cardiac conditions. The framework offers the basis to smart, data-driven health care systems, which can produce diagnostic information in real time and in interpretable forms, which will potentially result in better patient outcomes because of proactive clinical decision support.

PAC-KENReg: An interpretable hypergraph framework capturing nonlinear and dynamic functional connectivity for neuropsychiatric disease diagnosis.

A consistency-driven pseudo-labeling framework for robust functional connectivity modeling in neuropsychiatric disorder diagnosis