Despite the excellent prognosis post thyroidectomy and radioiodine therapy, papillary thyroid cancer (PTC) patients still undergo dismal outcomes, especially when tumors undergo de-differentiation and thus progress to radioiodine refractory status. Our knowledge on the pathogenesis mechanisms of PTC and NIS protein (responsible for iodine uptake) activity is still behind satisfaction. To increase our knowledge on these issues, we conducted this study.

We analyzed microarray data to identify the genes differentially expressed between normal and tumor thyroid tissues. Next, pathway enrichment analysis was conducted to derive candidate genes and pathways involved in PTC oncogenesis and NIS activity. The expression of candidate genes was confirmed by an independent TCGA dataset. Then, we used siRNA to knockdown the MDM2 gene to examine the potential pathogenesis mechanisms of MDM2 and MDM2-P53-NIS axis in cells. Also, we examined whether oncogenic activities, including cell proliferation, colony formation, cell migration and cell invasion, were altered with MDM2 knockdown. Moreover, NIS protein intensity in cell membrane was also investigated.

Through analyzing microarray data, pathway enrichment and correlation analyses, we focused on MDM2 since it could be involved in the MDM2-P53-NIS axis. Knockdown of MDM2 significantly reduced the mRNA levels and protein abundance of MDM2. In addition, P53 protein was also elevated with MDM2 knockdown. With MDM2 knockdown, cell proliferation and colony formation were repressed. And, both cell migration and invasion abilities were interfered. Moreover, MDM2 knockdown also enhanced the intensity of membrane NIS protein.

MDM2 knockdown not only reduced the oncogenic activities of thyroid cancer but also enhanced the intensity of NIS protein responsible for iodine intake in thyroid gland. Therefore, MDM2 could serve as a prognosis indicator in thyroid cancer.

Attention Deficit Hyperactivity Disorder (ADHD) is a prevalent neurodevelopmental disorder that significantly impacts learning, daily functioning, and personal development. Astaxanthin (ASTA), a naturally occurring antioxidant, has garnered interest as a potential therapeutic agent for various diseases, particularly in mitigating oxidative stress. This study explores a novel application of ASTA in the context of ADHD, aiming to investigate its therapeutic effects and underlying mechanisms. Spontaneously hypertensive rats (SHRs), widely used ADHD model animals, were treated with ASTA (50/100 mg/kg/day) for three weeks, 5 mg/kg/day atomoxetine (ATO) as the positive, and Wistar Kyoto (WKY) rats as control. Behavioral improvements were assessed using the open field test (OFT) and the Morris water maze (MWM). Biochemical analyses were conducted to evaluate changes in the levels of various neurotrophic factors, while histological examinations were performed to assess neuroprotective effects. Additionally, the role of ASTA in the brain-gut axis was investigated. The behavioral symptoms of hyperactivity, anxiety, and impaired spatial memory in ADHD animals were mitigated by ASTA. This improvement is primarily attributed to the restoration of neurotransmitter levels, particularly dopamine (DA), achieved through the modulation of several critical components within the dopamine system, including dopamine receptor 1 (DR1), dopamine transporter (DAT), tyrosine hydroxylase (TH), and synaptic-associated protein 25 (SNAP-25). Additionally, regulating the serotonin transporter (SERT) and glial cell-derived neurotrophic factor (GDNF) supports the recovery of serotonin levels and facilitates optimal brain development. Furthermore, cerebellar cells were protected, and the structure of the intestinal microbiota was regulated. ASTA can mitigate ADHD symptoms in SHR through the modulation of the dopaminergic system, multiple neurotransmitters, neurotrophic factors, and the neuro-intestinal environment, which establishes ASTA as a promising nutraceutical candidate for adjunctive therapy in pediatric ADHD.

Attention-deficit/hyperactivity disorder (ADHD) is a common psychiatric condition among children and adolescents, often associated with a high risk of psychiatric comorbidities. Currently, ADHD diagnosis relies exclusively on clinical presentation and patient history, underscoring the need for clinically relevant, reliable, and objective biomarkers. Such biomarkers may enable earlier diagnosis and lead to improved treatment outcomes. Our research team has focused on identifying potential biomarkers for ADHD by investigating its possible pathomechanisms, with consideration of the aforementioned criteria. Given the significant sex-related differences in ADHD prevalence (male predominance) and the age-related variability in its symptomatology, we explored the role of neuroendocrine systems in ADHD. Specifically, we examined the epigenetic regulation mechanism involved in ADHD pathogenesis and developed a diagnostic model based on peripheral microRNA. Additionally, we investigated the role of microbiota dysbiosis in the pathophysiology of ADHD and provided novel insights into its management. This paper presents a summary of our findings on potential biomarkers for ADHD. By analyzing blood, salivary, and fecal samples, we identified several promising biomarkers that may serve as objective parameters for improving the diagnostic accuracy for ADHD. Further research involving larger cohort studies is required to confirm the reliability of these biomarkers.

MicroRNA-126 (miR-126) has emerged as one of the most extensively studied microRNAs in the context of human diseases, particularly in vascular disorders and cancer. Its high degree of conservation across vertebrates underscores its evolutionary significance and essential functional roles. Extensive research has been devoted to elucidating the molecular mechanisms through which miR-126 modulates key physiological and pathological processes, including angiogenesis, immune response, inflammation, tumor growth, and metastasis. Furthermore, miR-126 plays a causal role in the pathogenesis of various diseases, serving as potential biomarkers for disease prediction, diagnosis, prognosis and drug response, as well as a promising therapeutic target. In this review, we synthesize findings from 283 articles, focusing on the roles of miR-126 in critical biological processes such as cell development, survival, cycle regulation, proliferation, migration, invasion, communication, and metabolism. Additionally, miR-126 represents a promising candidate for miRNA-based therapeutic strategies. A comprehensive understanding and evaluation of miR-126 are crucial for advancing its clinical applications and therapeutic potential.

The overall prevalence of placenta accreta spectrum (PAS) is approximately 0.17 %, but it accounts for 7 % of maternal mortality and is associated with intraoperative and postoperative morbidity. The pathogenesis mechanisms of PAS include an imbalance between decidualization and trophoblast invasion. The aim of this study is to identify the pathogenesis roles of miR-34a in PAS.

For this purpose, we collected 15 placenta tissues from pregnant subjects with PAS complications and another 15 placenta tissues from normal pregnancy (NP) cases. Then, we conducted in situ hybridization assay to compare miR-34a expression level, followed by in vitro simulations of NP and PAS with miR-34a and scrambled control (SC) mimic transfection in cells, respectively. Next, we conducted in vitro cellular assays to investigate the pathogenesis mechanisms of miR-34a in PAS.

We first confirmed significantly lower level of miR-34a in the trophoblast villous (TV) from PAS patients. By in vitro assays, lower miR-34a led to significantly higher cell proliferation and enhanced cell migration in TV epithelial cells. In addition, lower miR-34a resulted in elevated angiogenesis ability in vascular endothelial cells. Finally, to identify the pathway involved by miR-34a in PAS, we used microarray (raw data available via NCBI GEO database with accession number GSE279257) and flow cytometry to confirm that lower miR-34a significantly repressed the apoptosis activity in TV epithelial cells.

In this study, we not only confirmed miR-34a as a biomarker of PAS but also clarified the in vitro pathogenesis mechanism of miR-34a in PAS.

Attention deficit hyperactivity disorder (ADHD) is a prevalent neurodevelopmental disorder in childhood. There is growing evidence that both preterm birth and maternal education levels substantially affect the likelihood of ADHD in children. However, there are limited systematic reviews and meta-analyses examining these associations.

To systematically review and conduct a meta-analysis on the association of preterm birth and maternal education level on the risk of ADHD in children.

We conducted a comprehensive literature search across MEDLINE (PubMed), Web of Science, Embase, and the Cochrane Library, including studies published up to June 17, 2024. Data synthesis was performed using random-effect models, and the quality of studies was assessed using the Newcastle-Ottawa Scale.

This study included twelve studies, which revealed a significant association between premature delivery and an increased risk of ADHD in children [odds ratio (OR) = 2.76, 95% confidence interval (CI): 2.52-3.04, P < 0.001, I² = 1.9%). Conversely, higher maternal education levels were significantly associated with a reduced risk of ADHD in children (OR = 0.59, 95%CI: 0.48-0.73, P < 0.001, I² = 47.1%). Subgroup analysis further indicated that maternal education levels significantly influenced ADHD risk, particularly in studies conducted in China (OR = 0.59, 95%CI: 0.46-0.75, P < 0.001, I² = 81.2%), while no significant association was observed in studies from other regions (OR = 1.25, 95%CI: 0.66-2.40, P = 0.495, I² = 92.3%). The sensitivity analysis confirmed the robustness of our findings, showing no significant publication bias.

This study found that preterm birth significantly increases the risk of ADHD in children, while a higher maternal education level serves as a protective factor against ADHD. To reduce the incidence of ADHD in children, public health policies should focus on early intervention for preterm infants and improving maternal education levels.

There have been increasing efforts to develop prediction models supporting personalised detection, prediction, or treatment of ADHD. We overviewed the current status of prediction science in ADHD by: (1) systematically reviewing and appraising available prediction models; (2) quantitatively assessing factors impacting the performance of published models. We did a PRISMA/CHARMS/TRIPOD-compliant systematic review (PROSPERO: CRD42023387502), searching, until 20/12/2023, studies reporting internally and/or externally validated diagnostic/prognostic/treatment-response prediction models in ADHD. Using meta-regressions, we explored the impact of factors affecting the area under the curve (AUC) of the models. We assessed the study risk of bias with the Prediction Model Risk of Bias Assessment Tool (PROBAST). From 7764 identified records, 100 prediction models were included (88% diagnostic, 5% prognostic, and 7% treatment-response). Of these, 96% and 7% were internally and externally validated, respectively. None was implemented in clinical practice. Only 8% of the models were deemed at low risk of bias; 67% were considered at high risk of bias. Clinical, neuroimaging, and cognitive predictors were used in 35%, 31%, and 27% of the studies, respectively. The performance of ADHD prediction models was increased in those models including, compared to those models not including, clinical predictors (β = 6.54, p = 0.007). Type of validation, age range, type of model, number of predictors, study quality, and other type of predictors did not alter the AUC. Several prediction models have been developed to support the diagnosis of ADHD. However, efforts to predict outcomes or treatment response have been limited, and none of the available models is ready for implementation into clinical practice. The use of clinical predictors, which may be combined with other type of predictors, seems to improve the performance of the models. A new generation of research should address these gaps by conducting high quality, replicable, and externally validated models, followed by implementation research.

MicroRNAs (miRNAs) are emerging as crucial elements in the regulation of gene expression, playing a significant role in the underlying neurobiology of a wide range of neuropsychiatric disorders. This review examines the intricate involvement of miRNAs in neuropsychiatric disorders, such as Alzheimer's disease (AD), Parkinson's disease (PD), Huntington's disease (HD), Fragile X syndrome (FXS), autism spectrum disorder (ASD), attention-deficit hyperactivity disorder (ADHD), Tourette syndrome (TS), schizophrenia (SCZ), and mood disorders. This review highlights how miRNA dysregulation can illuminate the molecular pathways of these diseases and potentially serve as biomarkers for early diagnosis and prognosis. Specifically, miRNAs' ability to target genes critical to the pathology of neurodegenerative diseases, their role in the development of trinucleotide repeat and neurodevelopmental disorders, and their distinctive patterns in SCZ and mood disorders are discussed. The review also stresses the value of miRNAs in precision neuropsychiatry, where they could predict treatment outcomes and aid in disease management. Furthermore, the study of conserved miRNAs in model organisms like Drosophila underscores their broad utility and provides deeper mechanistic insights into their biological functions. This comprehensive examination of miRNAs across various conditions advocates for their integration into clinical practice, promising advancements in personalized healthcare for neurological and psychiatric conditions.

Exploring the epigenetic regulations, such as microRNA, in newborns holds significant promise for enhancing our ability to address and potentially prevent early-life developmental delays.

Hence, this research seeks to investigate if the expression of miRNA in the umbilical cord blood of infants can forecast their developmental outcomes as they grow older.

We enrolled 143 full-term newborns, delivered either via cesarean section (CS) or through natural spontaneous delivery (NSD). We then analyzed the profiles of specific miRNAs (miR-486-5p, miR-126-5p, miR-140-3p, miR-151a-3p, miR-142-5p, and miR-30e-5p) in the umbilical cord blood of these infants. Subsequently, we performed follow-up assessments using Bayley-III scores when the cohort reached 1 year of age. Furthermore, we conducted pathway-enrichment analyses on the target genes associated with these examined miRNAs.

When comparing newborns delivered via cesarean section (CS) to those born via natural spontaneous delivery (NSD), we observed notable differences. Specifically, newborns through NSD displayed significantly higher ΔCt values for miR-486-5p, alongside lower ΔCt values for miR-126-5p and miR-151a-3p in their cord blood. At 1 year of age, cognitive development was significantly linked to the ΔCt values of miR-140-3p and miR-142-5p, while language development showed a significant association with the ΔCt values of miR-140-3p. Moreover, our pathway enrichment analyses revealed that the target genes of these miRNAs were consistently involved in the pathways related to neurons, such as axon guidance and the neurotrophin signaling pathway.

In summary, this study represents a pioneering effort in elucidating the potential connections between miRNA levels in cord blood and the health indicators and neurodevelopment of newborns at 1 year of age. Our findings underscore the significance of miRNA levels at birth in influencing mechanisms related to neurodevelopment.

ADHD has huge knowledge gaps concerning its etiology. MicroRNAs (miRNAs) provide promising diagnostic biomarkers of human pathophysiology and may be a novel therapeutic option. The aim was to investigate the levels of miR-34c-3p, miR-155, miR-138-1, miR-296-5p, and plasma brain-derived neurotrophic factor (BDNF) in a group of children with ADHD compared to neurotypicals and to explore correlations between these measures and some clinical data. The participants were children with ADHD in Group I (N = 41; age: 8.2 ± 2) and neurotypical ones in Group II (N = 40; age: 8.6 ± 2.5). Group I was subjected to clinical examination, the Stanford Binet intelligence scale-5, the preschool language scale, and Conner's parent rating scale-R. Measuring the expression levels of the miRNAs was performed by qRT-PCR for all participants. The BDNF level was measured by ELISA. The lowest scores on the IQ subtest were knowledge and working memory. No discrepancies were noticed between the receptive and expressive language ages. The highest scores on the Conner's scale were those for cognitive problems. Participants with ADHD exhibited higher plasma BDNF levels compared to controls (p = 0.0003). Expression patterns of only miR-34c-3p and miR-138-1 were downregulated with significant statistical differences (p˂0.01). However, expression levels of miR-296-5p showed negative correlation with the total scores of IQ (p = 0.03). MiR-34c-3p, miR-138-1, while BDNF showed good diagnostic potential. The downregulated levels of miR-34c-3p and miR-138-1, together with high BDNF levels, are suggested to be involved in the etiology of ADHD in Egyptian children. Gender differences influenced the expression patterns of miRNAs only in children with ADHD.

Inappropriate levels of hyperactivity, impulsivity, and inattention characterize attention deficit hyperactivity disorder, a common childhood-onset neuropsychiatric disorder. The cognitive function and learning ability of children with attention deficit hyperactivity disorder are affected, and these symptoms may persist to adulthood if they are not treated. The diagnosis of attention deficit hyperactivity disorder is only based on symptoms and objective tests for attention deficit hyperactivity disorder are missing. Treatments for attention deficit hyperactivity disorder in children include medications, behavior therapy, counseling, and education services which can relieve many of the symptoms of attention deficit hyperactivity disorder but cannot cure it. There is a need for a molecular biomarker to distinguish attention deficit hyperactivity disorder from healthy subjects and other neurological conditions, which would allow for an earlier and more accurate diagnosis and appropriate treatment to be initiated. Abnormal expression of microRNAs is connected to brain development and disease and could provide novel biomarkers for the diagnosis and prognosis of attention deficit hyperactivity disorder. The recent studies reviewed had performed microRNA profiling in whole blood, white blood cells, blood plasma, and blood serum of children with attention deficit hyperactivity disorder. A large number of microRNAs were dysregulated when compared to healthy controls and with some overlap between individual studies. From the studies that had included a validation set of patients and controls, potential candidate biomarkers for attention deficit hyperactivity disorder in children could be miR-140-3p, let-7g-5p, -30e-5p, -223-3p, -142-5p, -486-5p, -151a-3p, -151a-5p, and -126-5p in total white blood cells, and miR-4516, -6090, -4763-3p, -4281, -4466, -101-3p, -130a-3p, -138-5p, -195-5p, and -106b-5p in blood serum. Further studies are warranted with children and adults with attention deficit hyperactivity disorder, and consideration should be given to utilizing rat models of attention deficit hyperactivity disorder. Animal studies could be used to confirm microRNA findings in human patients and to test the effects of targeting specific microRNAs on disease progression and behavior.

Attention-deficit/hyperactivity disorder (ADHD) is a prevalent neurodevelopmental disorder in children with unknown etiology. Impaired learning ability was commonly reported in ADHD patients and has been associated with dopamine uptake in the striatum of an animal model. Another evidence also indicated that micro-RNA (miR)-200b-3p is associated with learning ability in various animal models. However, the association between miR-200b-3p and ADHD-related symptoms remains unclear. Therefore, the current study investigated the role of miR-200b-3p in ADHD-related symptoms such as inattention and striatal inflammatory cytokines. To verify the influence of miR-200b-3p in ADHD-related symptoms, striatal stereotaxic injection of miR-200b-3p antagomir (AT) was performed on spontaneously hypertensive rats (SHR). The antioxidant activity and expressions of miR-200b-3p, slit guidance ligand 2 (Slit2), and inflammatory cytokines in the striatum of SHR were measured using quantitative real-time polymerase chain reaction (RT-qPCR), immunohistochemistry (IHC), immunoblotting, and enzyme-linked immunosorbent assay (ELISA). The spontaneous alternation of SHR was tested using a three-arm Y-shaped maze. The administration of miR-200b-3p AT or taurine significantly decreased striatal tumor necrosis factor (TNF)-α, interleukin (IL)-1β, and IL-6 in SHR, along with increased super-oxide dismutase (SOD) and glutathione peroxidase (GSH-Px) activities and significantly higher spontaneous alternation. In this paper, we show that miR-200b-3p AT and taurine alleviates ADHD-related symptoms in SHR. These findings provide insights into ADHD's molecular basis and suggest miR-200b-3p as a potential therapeutic target. Concurrently, this study also suggests broad implications for treating neurodevelopmental disorders affecting learning activity such as ADHD.

Langerhans cell histiocytosis (LCH) is an inflammatory myeloid neoplasm characterized by the accumulation of clonal mononuclear phagocyte system cells expressing CD1a and CD207. In the past decade, molecular profiling of LCH as well as other histiocytic neoplasms demonstrated that these diseases are driven by MAPK activating alterations, with somatic BRAFV600E mutations in >50% of patients with LCH, and clinical inhibition of MAPK signaling has demonstrated remarkable clinical efficacy. At the same time, activating alterations in kinase-encoding genes, such as PIK3CA, ALK, RET, and CSF1R, which can activate mitogenic pathways independent from the MAPK pathway, have been reported in a subset of histiocytic neoplasms with anecdotal evidence of successful targeted treatment of histiocytoses harboring driver alterations in RET, ALK, and CSF1R. However, evidence supporting the biological consequences of expression of PIK3CA mutations in hematopoietic cells has been lacking, and whether targeted inhibition of PI3K is clinically efficacious in histiocytic neoplasms is unknown. Here, we provide evidence that activating mutations in PIK3CA can drive histiocytic neoplasms in vivo using a conditional knockin mouse expressing mutant PIK3CAH1047R in monocyte/dendritic cell progenitors. In parallel, we demonstrate successful treatment of PIK3CA-mutated, multisystemic LCH using alpelisib, an inhibitor of the alpha catalytic subunit of PI3K. Alpelisib demonstrated a tolerable safety profile at a dose of 750 mg per week and clinical and metabolic complete remission in a patient with PIK3CA-mutated LCH. These data demonstrate PIK3CA as a targetable noncanonical driver of LCH and underscore the importance of mutational analysis-based personalized treatment in histiocytic neoplasms.

Attention-deficit/hyperactivity disorder (ADHD) is a prevalent and highly heritable neurodevelopmental disorder of major societal concern. Diagnosis can be challenging and there are large knowledge gaps regarding its etiology, though studies suggest an interplay of genetic and environmental factors involving epigenetic mechanisms. MicroRNAs (miRNAs) show promise as biomarkers of human pathology and novel therapies, and here we aimed to identify blood miRNAs associated with traits of ADHD as possible biomarker candidates and further explore their biological relevance.

Our study population consisted of 1126 children (aged 5-12 years, 46% female) from the Human Early Life Exposome study, a study spanning six ongoing population-based European birth cohorts. Expression profiles of miRNAs in whole blood samples were quantified by microarray and tested for association with ADHD-related measures of behavior and neuropsychological functions from questionnaires (Conner's Rating Scale and Child Behavior Checklist) and computer-based tests (the N-back task and Attention Network Test).

We identified 29 miRNAs significantly associated (false discovery rate < .05) with the Conner's questionnaire-rated trait hyperactivity, 15 of which have been linked to ADHD in previous studies. Investigation into their biological relevance revealed involvement in several pathways related to neurodevelopment and function, as well as being linked with other neurodevelopmental or psychiatric disorders known to overlap with ADHD both in symptomology, genetic risk, and co-occurrence, such as autism spectrum disorder or schizophrenia. An additional three miRNAs were significantly associated with Conner's-rated inattention. No associations were found with questionnaire-rated total ADHD index or with computer-based tests.

The large overlap of our hyperactivity-associated miRNAs with previous studies on ADHD is intriguing and warrant further investigation. Though this study should be considered explorative and preliminary, these findings contribute towards identifying a set of miRNAs for use as blood-based biomarkers to aid in earlier and easier ADHD diagnosis.

Attention-deficit/hyperactivity disorder (ADHD) is a highly prevalent and heterogeneous neurodevelopmental disorder in children and has a high chance of persisting in adulthood. The development of individualized, efficient, and reliable treatment strategies is limited by the lack of understanding of the underlying neural mechanisms. Diverging and inconsistent findings from existing studies suggest that ADHD may be simultaneously associated with multivariate factors across cognitive, genetic, and biological domains. Machine learning algorithms are more capable of detecting complex interactions between multiple variables than conventional statistical methods. Here we present a narrative review of the existing machine learning studies that have contributed to understanding mechanisms underlying ADHD with a focus on behavioral and neurocognitive problems, neurobiological measures including genetic data, structural magnetic resonance imaging (MRI), task-based and resting-state functional MRI (fMRI), electroencephalogram, and functional near-infrared spectroscopy, and prevention and treatment strategies. Implications of machine learning models in ADHD research are discussed. Although increasing evidence suggests that machine learning has potential in studying ADHD, extra precautions are still required when designing machine learning strategies considering the limitations of interpretability and generalization.

Changes in protein glycosylation are associated with most biological processes, and the importance of glycomic analysis in the research of disorders is constantly increasing, including in the neurodevelopmental field. We glycoprofiled sera in 10 children with attention-deficit hyperactivity disorder (ADHD) and 10 matching healthy controls for 3 types of samples: whole serum, sera after depletion of abundant proteins (albumin and IgG), and isolated IgG. The analytical methods used were a lectin-based glycoprotein microarray enabling high-throughput glycan analysis and matrix-assisted laser desorption/ionization time-of-flight (MALDI-TOF) mass spectrometry (MS) as a standard method for the identification of glycan structures. For microarray analysis, the samples printed on microarray slides were incubated with biotinylated lectins and detected using the fluorescent conjugate of streptavidin by a microarray scanner. In the ADHD patient samples, we found increased antennary fucosylation, decreased di-/triantennary N-glycans with bisecting N-acetylglucosamine (GlcNAc), and decreased α2-3 sialylation. The results obtained by both independent methods were consistent. The study's sample size and design do not allow far-reaching conclusions to be drawn. In any case, there is a strong demand for a better and more comprehensive diagnosis of ADHD, and the obtained results emphasize that the presented approach brings new horizons to studying functional associations of glycan alterations in ADHD.

Psychiatric disorders affect millions of individuals and their families worldwide, and the costs to society are substantial and are expected to rise due to a lack of effective treatments. Personalized medicine-customized treatment tailored to the individual-offers a solution. Although most mental diseases are influenced by genetic and environmental factors, finding genetic biomarkers that predict treatment efficacy has been challenging. This review highlights the potential of epigenetics as a tool for predicting treatment efficacy and personalizing medicine for psychiatric disorders. We examine previous studies that have attempted to predict treatment efficacy through epigenetics, provide an experimental model, and note the potential challenges at each stage. While the field is still in its infancy, epigenetics holds promise as a predictive tool by examining individual patients' epigenetic profiles in conjunction with other indicators. However, further research is needed, including additional studies, replication, validation, and application beyond clinical settings.

Attention-deficit/hyperactivity disorder (ADHD) is a heterogeneous disorder with a high degree of psychiatric and physical comorbidity, which complicates its diagnosis in childhood and adolescence. We analyzed registry data from 238,696 persons born and living in Sweden between 1995 and 1999. Several machine learning techniques were used to assess the ability of registry data to inform the diagnosis of ADHD in childhood and adolescence: logistic regression, random Forest, gradient boosting, XGBoost, penalized logistic regression, deep neural network (DNN), and ensemble models. The best fitting model was the DNN, achieving an area under the receiver operating characteristic curve of 0.75, 95% CI (0.74-0.76) and balanced accuracy of 0.69. At the 0.45 probability threshold, sensitivity was 71.66% and specificity was 65.0%. There was an overall agreement in the feature importance among all models (τ > .5). The top 5 features contributing to classification were having a parent with criminal convictions, male sex, having a relative with ADHD, number of academic subjects failed, and speech/learning disabilities. A DNN model predicting childhood and adolescent ADHD trained exclusively on Swedish register data achieved good discrimination. If replicated and validated in an external sample, and proven to be cost-effective, this model could be used to alert clinicians to individuals who ought to be screened for ADHD and to aid clinicians' decision-making with the goal of decreasing misdiagnoses. Further research is needed to validate results in different populations and to incorporate new predictors.