EAElahe Akbarian

Elahe Akbarian

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Elahe Akbarian has a total of 35 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Top Cited Papers
    Open Access

    Artificial intelligence in ADHD diagnosis: a comprehensive review of machine learning applications, clinical validation challenges, and implementation barriers in precision medicine

    byĀ Bita Fallahpour, Ghasem Dastjerdi, Elahe Akbarian, Alireza Emarati, Zahra Sadr, Seyed Alireza Dastgheib, Amirhossein Shahbazi, Reza Bahrami, Mohammad Golshan-Tafti, Amirmasoud Shiri, et al.

    Background: Attention Deficit Hyperactivity Disorder (ADHD) affects approximately 7.2% of the global population, representing one of the most prevalent neurodevelopmental disorders. While current clinical diagnostic approaches, including validated instruments such as the SNAP-IV, Conners-4, and ADHD-RS, enable trained clinicians to reach reliable diagnoses in most cases, certain clinical scenarios remain challenging, including borderline presentations, complex comorbidity patterns, and settings with limited access to specialist clinicians. The absence of objective biomarkers meeting established clinical criteria has motivated exploration of computational approaches as potential augmentative diagnostic tools. Methods: This comprehensive narrative review analyzes machine learning (ML) and deep learning (DL) applications across the ADHD clinical pathway, encompassing objective diagnosis, subtype differentiation, prediction of treatment response, digital therapeutic interventions, and long-term outcome prognostication. PubMed/MEDLINE, Scopus, Web of Science, IEEE Xplore, and Google Scholar were searched from inception through September 2025 across multiple modalities including electroencephalography (EEG), neuroimaging, wearable technology, virtual reality, eye-tracking, genomics, digital therapeutics, and multimodal integration approaches. Diagnostic performance, clinical validation, model interpretability, class imbalance considerations, and translational potential were evaluated while identifying critical gaps requiring additional research. Results: EEG-based classification demonstrates the most consistent high performance, with recent studies achieving accuracies exceeding 99% using advanced CNN and transformer architectures; however, these results are typically obtained from small, single-site datasets and should be interpreted with caution. Wearable technology shows significant promise with 89% accuracy in large-scale validation ( n = 450; AUC = 0.95), while virtual reality assessments achieve clinically relevant performance (AUC = 0.893). Eye-tracking technology achieves exceptional diagnostic performance (AUC = 0.965, accuracy = 90.8%), and genomic approaches utilizing advanced polygenic risk scores achieve meaningful performance (AUC = 0.72). Multimodal integration approaches demonstrate superior diagnostic accuracy compared to single-modality assessments. Importantly, well-validated studies employing rigorous multi-site validation typically report realistic performance in the range of 70–85%, and metrics such as ROC-AUC, sensitivity, specificity, and positive predictive value (PPV) provide more clinically meaningful evaluations than overall accuracy alone, particularly given the class imbalance inherent in ADHD prevalence (5–10%). Conclusions: While ML/DL technologies show considerable promise for augmenting objective ADHD assessment, including diagnosis, treatment response prediction, and long-term outcome prognostication, realistic clinical performance typically ranges from 70 to 85% for well-validated studies. The field requires addressing critical challenges including methodological rigor, clinical validation standards, appropriate handling of class imbalance, gold-standard diagnostic validation, algorithmic interpretability, privacy-preserving techniques, and regulatory frameworks to achieve successful clinical translation. Clinical trial number: Not applicable


  • Open Access

    Unveiling developmental delays in early childhood: insights from a comparative study of the Bayley Scales (BSID-III) and the ASQ-3 in Iran

    byĀ Mehran Karimi, Alireza Emarati, Zahra Nafei, Farimah Shamsi, Niloofar Gashty Mazar, Elahe Akbarian

    Developmental delay in early childhood is a significant concern with multifaceted causes and implications. The Bayley Scales of Infant and Toddler Development (BSID-III) is widely used for developmental assessment, but its use in Iranian children has been understudied. This study aimed to evaluate the developmental delays of Iranian children aged 1 to 42 months, investigate the association between parental education and these developmental outcomes, and compare developmental outcomes between the BSID-III and the Ages and Stages Questionnaire, Third Edition (ASQ-3). These findings contribute to informing clinical practices, policy makers, and early intervention programs aimed at promoting optimal development for all children. In this cross-sectional study, 707 Iranian children from Yazd, Iran, with suspected developmental delays were recruited from two health centers. Trained examiners administered the Persian-adapted and validated version of the BSID-III following standardized procedures. We hypothesized differences in BSID-III scores compared to normative samples, considering age, gender, and parental education. Additionally, comparisons between BSID-III scores and the validated Iranian version of ASQ-3 outcomes were explored to gain further insights. The study sample exhibited varying rates of developmental delays across Cognitive (15.8%), Receptive Communication (20.1%), Expressive Communication (18.4%), Fine Motor (13.6%) and Gross Motor (15.7%) domains. Additionally, Age-related differences were observed, particularly in Receptive and Expressive Communication, where older children showed higher rates of delays. Gender differences were also significant in the Language Scale, with females showing slightly higher rates of normal development. Moreover, parental education emerged as a significant factor, with higher levels associated with a reduced occurrence of developmental delays. Furthermore, comparisons between BSID-III results and ASQ-3 outcomes highlighted discrepancies, suggesting an imperfect alignment between measures. The analysis demonstrated fair agreement for Cognitive-Problem Solving and Gross Motor development, but poor agreement for Fine Motor development, highlighting the complexity of developmental assessment and the need for cautious interpretation of test results. This study enhances our understanding of developmental assessment in Iranian children with suspected delays by emphasizing culturally sensitive adaptations for assessment tools alongside recognizing how parental education influences developmental trajectories. Future research with diverse, longitudinal samples is warranted to gain a more comprehensive picture.


  • Open Access

    Assessing Developmental Delays in Early Childhood: Insights from Iranian Children Using the Bayley Scales of Infant and Toddler Development (BSID-III)

    byĀ Mehran Karimi, Alireza Emarati, Zahra Nafei, Farimah Shamsi, Niloofar Gashty Mazar, Elahe Akbarian

    Background Developmental delay in early childhood is a significant concern with multifaceted causes and implications. The Bayley Scales of Infant and Toddler Development (BSID-III) is widely used for developmental assessment but remains understudied in Iranian children. Methods This cross-sectional study assessed 707 Iranian children aged 1 to 42 months in Yazd, Iran, using the BSID-III. We hypothesized differences in BSID-III scores compared to normative samples, considering age, gender, and parental education. Data were collected from two health centers in Yazd, with trained examiners following standardized procedures. Parental education was analyzed for its impact on developmental outcomes. Comparisons between BSID-III scores and Ages and Stages Questionnaire (ASQ) outcomes provided additional insights. Results Iranian children exhibited varying rates of developmental disorders across cognitive, language, and motor domains, influenced by parental education (higher parental education correlated with a reduced occurrence of developmental disorders). For instance, in the cognitive domain, 15.8% of children demonstrated developmental disorders. The language scale exhibited varying rates: 20.1% for perceptual communication and 18.4% for expressive communication. Furthermore, the BSID-III and ASQ results demonstrated discordances, highlighting the complexities of assessment. Conclusions This study contributes to the knowledge of developmental assessment in Iranian early childhood. It emphasizes the importance of culturally sensitive adaptations of assessment tools and the role of parental education in shaping developmental outcomes. Future research should incorporate diverse, longitudinal samples for enhanced understanding. Ultimately, this study aims to inform clinical practices, policy development, and early intervention programs, committed to fostering optimal development for all children, irrespective of their backgrounds.

  • Open Access

    Diabetic Ketoacidosis in Children Before and During COVID-19 Pandemic: A Cross-sectional Study

    byĀ Mahtab Ordooei, Mehran Karimi, Elahe Akbarian, Zahra Rasoulizadeh

    Background: Coronavirus disease 2019 (COVID-19) has spread quickly. Comorbidities, such as diabetes, have been determined as critical risk factors for COVID-19. Objectives: This study aimed to determine the frequency and severity of diabetic ketoacidosis (DKA) in children before and during the COVID-19 pandemic. Methods: This retrospective study examined children aged less than 18 years diagnosed with DKA hospitalized in Yazd Shahid Sadoughi Hospital from February 20, 2020, to November 21, 2021. The collected information was compared to those obtained during the same period in 2019 (pre-pandemic). According to the inclusion criteria, only children with suspected symptoms of COVID-19 or an infected family member underwent PCR. Results: The study included 70 children with confirmed DKA during the COVID-19 pandemic and 33 children hospitalized during the pre-pandemic period. The findings showed that the rate of DKA was higher during the pandemic than in the pre-pandemic period. In the DKA subgroups (during the COVID-19 pandemic vs. pre-pandemic), 35.7% vs. 21.2% were severe, 37.1% vs. 36.4% were moderate, and 27.1% vs. 42.4% were mild. Of 70 children, 30 underwent PCR tests for COVID-19, showing six positive cases. Among positive cases, five had mild symptoms, while one was hospitalized with signs of respiratory distress, polyuria, and polydipsia. All physical examinations of this patient were normal, except for the chest exam. Conclusions: A remarkable increase was observed in the frequency and severity of DKA in children during the pandemic.


  • Open Access

    Which Groups of Children Are at More Risk of Fatality during COVID‐19 Pandemic? A Case‐Control Study in Yazd, Iran

    byĀ Behnam Shafaei, Zahra Nafei, Mehran Karimi, Nasrin Behniafard, Farimah Shamsi, Masoud Faisal, Amir Pasha Amel Shahbaz, Elahe Akbarian

    Introduction. The study aims to investigate the characteristics, comorbidities, laboratory findings, and clinical manifestations of under 18‐year‐old patients who died with the diagnosis of COVID‐19 and determination of the most prevalent risk factors. Method. This case‐control study was performed at a referral hospital in Yazd from March 2020 to August 2021. All patients under 18 years who were diagnosed through real‐time RT‐PCR, chest computed tomography, and the World Health Organization definition were divided into deceased and survived groups. The characteristics (age and sex), disease severity, comorbidities, laboratory findings, and clinical manifestations of the two groups were compared and analyzed using SPSS, version 18 (SPSS Inc., Chicago, III., USA). Results. A total of 24 patients in the deceased group and 167 patients in the survived group were compared. The highest mortality rate was observed in the age group of 1 month to 5 years, although no statistically significant relationship was found between age groups and the risk of mortality. Disease severity, dyspnea, low oxygen saturation on admission, length of hospital stays, and hospitalization history before the last admission were significantly correlated with mortality (P < 0.05). Lymphopenia increased the probability of mortality by more than two times (OR: 2.568; 95% CI (0.962–6.852)), but this was not the case for D‐dimer and C‐reactive protein. Furthermore, 27.5% of survived patients had normal chest CT scans, which was a statistically significant difference compared to the deceased patients (P: 0.031). Conclusion. Based on the findings of this study, dyspnea, low oxygen saturation, and lymphopenia are critical indicators for identifying high‐risk children with COVID‐19 and triaging them for better care and treatment.


  • Open Access

    Survival and Mortality in Hospitalized Children with COVID‐19: A Referral Center Experience in Yazd, Iran

    byĀ Farimah Shamsi, Mehran Karimi, Zahra Nafei, Elahe Akbarian

    Introduction. COVID‐19 prognostic risk factors, therapeutic protocols, and clinical outcomes in pediatric cases are still under investigation. Materials and Methods. This historical cohort study evaluated the survival time of hospitalized children (1 month–18 years old) with COVID‐19 admitted from March 2020 to August 2021 to an educational hospital in Yazd, Iran. The follow‐up of patients was performed at least one month after discharge. Results. From 183 hospitalized cases, 24 children were deceased. The median age of patients was 5.41, and 54.2% were male. The survival rate after one‐month follow‐up was 0.88, and the most significant predictors associated with survival time were the male sex, positive history of hospitalization, lymphopenia, hypoxia, and length of stay more than two weeks using Bayesian Cox regression analysis. Conclusion. Accurate estimation of the impact of predictors on poor outcomes may help healthcare providers use therapeutic protocols based on risk factors and healthcare requirements of each patient to improve their survival.


  • Association of IRF6 rs2235371 Polymorphism with Non-Syndromic Cleft Lip/Palate: A Meta-analysis

    byĀ Hossein Neamatzadeh, Masoud Zare-Shehneh, Mahta Mazaheri, Karim Daliri, Elahe Akbarian, Elnaz Sheikhpour

    Background: The previous published data on the association between interferon regulatory factor 6 (IRF6) polymorphisms and non-syndromic Cleft Lip/Palate (NSCL ± P) risk remained inconclusive. The aim of this study was to conduct a meta-analysis to further assess the associations. Methods: A comprehensive search in PubMed, EMBASE, Web of Science, and CNKI for all eligible studies up July 2021. Results: A total of 23 studies with 6,161 cases and 8,919 controls were selected for this meta-analysis. Overall pooled analysis suggest a significant association between IRF6 rs2235371 polymorphism and CL±P risk under all the five genetic models, i.e., allele (A vs. G: OR=0.754, 95% CI 0.628-0.905, P=0.002), homozygote (AA vs. GG: OR=0.621 95% 0.405-0.953, P=0.029), heterozygote (AC vs. GG: OR=0.619, 95% CI 0.485-0.791, P≤0.001), dominant (AA+AG vs. GG: OR=0.550, 95% CI 0.381-0.794, P=0.001) and recessive model (AA vs. AG+GG: OR=0.583, 95% CI 0.423-0.804, P=0.001). Subgroup analysis by ethnicity showed that rs2235371 was associated with NSCL±P risk in Asians. Conclusion: This meta-analysis provides strong evidences that IRF6 rs2235371 might be associated with risk of NSCL ± P.


  • New onset of diabetes in a child infected with COVID-19: a case report

    byĀ Mahtab Ordooei, Nasrin Behniafard, Fahimeh Soheilipour, Elahe Akbarian

    Background Diabetic ketoacidosis (DKA) is a serious complication of type 1 diabetes. A few studies have reported that COVID-19 is associated with the development of new-onset diabetes. Here, we present an infected child with new onset diabetes leading to DKA. Case presentation A 10-year-old patient with respiratory distress admitted to the Emergency Department of our center. The patient’s COVID-19 Polymerase Chain Reaction (PCR) test was positive and also biochemical analyses confirmed that he had DKA. Despite standard initial treatments, ketoacidosis remained resistant; hence we prescribed oral bicarbonate (40 cc every 8 h) to treat the patient's refractory acidosis. Due to the patient’s improvement, he was discharged after 10 days (7 days in the PICU), receiving outpatient enoxaparin (for a week) and ongoing subcutaneous insulin. Conclusion We report an interesting case of a child with COVID-19 infection precipitating presentation with new onset diabetes. Due to refractory acidosis, starting oral bicarbonate treatment after 2 days improved acidosis and tachypnea in the patient. The patient’s medical team suggest close biochemical monitoring, prescribing enoxaparin for high level of D-dimer, and ordering oral bicarbonate acidosis persists.