ABAslıhan Baran

Aslıhan Baran

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Aslıhan Baran has a total of 37 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Fluid-attenuated inversion recovery magnetic resonance imaging-derived artificial intelligence dementia probability: A workflow-integrated decision support model for outpatient triage

    by Şeref Barbaros Arik, Murat Şimşek, Aslıhan Baran, Gökhan Şahin

    Objectives: This study aimed to evaluate the diagnostic performance of an artificial intelligence (AI)-based decision support model that estimates the probability of dementia using only routine fluid-attenuated inversion recovery (FLAIR) magnetic resonance imaging (MRI) sequences and to assess its potential role as a triage tool in outpatient clinical settings. Patients and methods: This retrospective single-center study included 96 patients who underwent brain MRI and had established clinical and neuropsychological diagnoses between January 2021 and December 2024. A previously published convolutional neural network model trained on 6,400 open-access MRI scans was applied to our institutional dataset to evaluate its diagnostic performance in a real-world clinical setting. For clinical interpretability, a predefined threshold of 50% was used to classify cases, and receiver operating characteristic analysis was performed to assess discriminative performance. Results: The dementia group (n = 47) had a mean age of 71.76 ± 8.32 years (range, 55 to 90 years) and included 25 females (53.2%) and 22 males (46.8%). The control (nondementia) group (n = 49) had mean age of 75.18 ± 7.48 years (range, 55 to 89 years) and included 25 females (51.0%) and 24 males (49.0%). The AI model achieved an accuracy of 89.6%, sensitivity of 78.7%, specificity of 100%, and an AUC of 0.937. The dementia probability (%) strongly correlated with clinical diagnoses (r = 0.762, p < 0.001). Notably, no false-positive cases were observed in this cohort, indicating high reliability of positive classifications. McNemar and Binomial tests confirmed that the classification performance was significantly better than chance ( p < 0.001). Conclusion: Artificial intelligence-derived dementia probability from routine FLAIR MRI provides a rapid and standardized output that may support clinical decision-making at the initial point of care. The absence of false-positive cases is consistent with the potential utility of the model as a rule-in decision-support tool, supporting prioritization of patients for further diagnostic evaluation. These findings highlight the potential of a simple, single-sequence AI approach to enhance workflow efficiency in neuroradiology practice without replacing clinical judgment.

  • Evaluation of the association between multiple sclerosis and trauma according to graded trauma levels

    by Aslıhan Baran, Bülent Müngen

    Objective: The relationship between trauma and multiple sclerosis (MS) remains unclear, partly due to differences in how trauma is defined and studied. This study examined the association between physical trauma and MS, with a focus on trauma severity.Method: Sixty-five patients with MS and 55 age- and sex-matched healthy controls were included. Trauma exposure was assessed during the one-month period preceding each relapse in the MS group and during the one-month period before each clinical evaluation in controls. Group differences were initially analyzed using the chi-square or Fisher’s exact test. Generalized estimating equations (GEE) were additionally used to account for repeated observations within participants.Results: A total of 226 relapse episodes and 110 control evaluation periods were analyzed. Trauma exposure was observed in 4.4% of pre-relapse periods and 19.1% of control periods. After accounting for repeated observations within participants using generalized estimating equations, trauma exposure was lower during relapse periods (OR = 0.103, 95% CI: 0.048–0.219; p < 0.001). Minor trauma was less frequent during the pre-relapse period (3.1% vs 14.5%; p < 0.001). Surgical procedures were less frequent during the pre-relapse period (0.9% vs 4.5%; p = 0.040).Conclusion: Trauma exposure was not associated with an increased risk of MS relapse in the acute-subacute period. Stratifying trauma by severity may provide a more meaningful understanding of the trauma–MS relationship.

  • Diagnostic Utility of Medial Dorsal Cutaneous Sensory Response and the Medial Dorsal Cutaneous-To-Radial Amplitude Ratio (MDRAR) in Diabetic Polyneuropathy

    by Aslıhan Baran, Onur Serdar Gençler, Serhat Akın

    Purpose: This study aimed to assess the diagnostic utility of the medial dorsal cutaneous (MDC) nerve and the medial dorsal cutaneous-to-radial amplitude ratio (MDRAR) in diabetic polyneuropathy (DP). Methods: Seventy-four patients clinically diagnosed with DP and 40 healthy controls underwent nerve conduction studies (NCS), including sural, radial, medial plantar (MP), and MDC sensory recordings. Most patients had recent-onset, mild-to-moderate DP. Sural-to-radial amplitude ratio (SRAR), medial plantar-to-radial amplitude ratio (MPRAR), and MDRAR were calculated. Minimal tibial F-wave latencies were height-corrected, and sural amplitudes were age-corrected. Diagnostic cut-off values were established by ROC analysis. Values below the cut-off, as well as absent responses, were classified as abnormal, and sensitivity and specificity were calculated. Results: A sural SNAP <6 µV demonstrated 42% sensitivity and 100% specificity. A minimal tibial F-wave latency ≥50 ms had 61% sensitivity and 100% specificity. For SRAR, a cut-off ≤0.40 yielded 49% sensitivity and 97% specificity; the 0.34 cut-off produced 38% sensitivity and 100% specificity, while the 0.21 cut-off yielded 19% sensitivity and 100% specificity. MPRAR and MDRAR demonstrated higher sensitivities (61 and 68%) but lower specificities (82 and 75%). Sural responses were obtainable in 82% of patients, whereas MP and MDC responses were recorded in 50 and 39%, respectively. Conclusions: MDRAR did not provide additional diagnostic value as a stand-alone electrophysiological parameter; however, bilateral absence of MDC responses emerged as a valuable marker of early distal involvement in DP. Further studies in selected patient groups are warranted to clarify the diagnostic contribution of MDRAR, particularly in early-stage and predominantly axonal forms of DP.

  • Open Access

    Effects of cervical stabilization training in patients with headache: A single‐blinded randomized controlled trial

    by H. Altmis Kacar, C. Ozkul, A. Baran, A. Guclu‐Gunduz

    Background: This study aimed to investigate the effects of Cervical Stabilization Training (CST) on the headache, neck pain and cervical musculoskeletal system in patients with headache compared to the control group.Methods: A total of 90 female patients with migraine, tension‐type headache and cervicogenic headache (CGH) participated in this study. The patients were divided into the cervical stabilization training group (CSTG) and the control group (CG). The CSTG performed the CST three times a week for 8 weeks while the CG continued their ongoing medical treatment. The pain intensity was assessed by Visual Analogue Scale, forward head posture by craniovertebral angle measurement, the endurance of deep cervical flexor muscles by craniocervical flexion test and the endurance of cervical muscles by flexor and extensor endurance tests before and after 8 weeks. In addition, disability levels, health‐related quality of life, sleep quality and mood were assessed by the Migraine Disability Assessment questionnaire, Neck Disability Index (NDI), Short Form 36 Quality of Life Scale, the Pittsburgh Sleep Quality Index and Beck Depression Scale, respectively.Results: Headache frequency, duration and intensity, neck pain intensity and forward head posture reduced while activation and performance of deep cervical flexor muscles, the endurance of cervical flexor and extensor muscles increased in the CSTG (p < 0.05). Furthermore, the disability levels, quality of life, sleep quality and mood also improved in the CSTG (p < 0.05).Conclusions: This study suggests that CST reduces headaches and neck pain by improving the cervical musculoskeletal system in patients with headache.Significance: The CST improved the headache frequency, duration and intensity, neck pain intensity, cervical posture, activation of deep cervical flexor muscles and endurance of cervical muscles in patients with headache. In addition, improvements in the cervical musculoskeletal system contributed to a reduction in the intensity of headaches and neck pain. Therefore, CST may be preferred in the treatment of headaches, especially with coexisting neck pain.


  • Paraneoplastik Otoantikorlar

    by Aslıhan Baran, Ferit Aslan

    Paraneoplastik sendromlar, kanserin doğrudan invazyonu veya metastazı dışında, malign ve normal dokular arasındaki immün çapraz reaksiyonlar veya humoral faktörler nedeniyle uzaktan ortaya çıkan sistemik bozukluklardır. En sık nörolojik sistemleri etkileyen bu sendromlar (PNS), vakaların %80'inde kanser tanısı konmadan önce saptanmaktadır. Bu durum, gizli tümörlerin erken evrede teşhis edilmesine olanak tanır. 2021 yılında PNS-Care paneli, PNS bağlamında antikorları kanser birlikteliği sıklığına göre üç gruba ayırmıştır: Kanser ilişkisi %70'ten fazla olan "Yüksek Riskli Antikorlar" (Hu, Yo, Ri, CV2/CRMP5, SOX1, PCA2, Amfifizin, Ma2/Ma, Tr, KLHL11); hücre içi antijenleri hedefler ve sitotoksik T hücre aracılı patogeneze sahiptir. Kanser ilişkisi %30-70 arasında olan "Orta Riskli Antikorlar" (AMPAR, GABABR, mGluR5, NMDAR, CASPR2, P/Q VGCC) ise hücre yüzeyi veya sinaptik proteinleri hedefleyerek doğrudan antikor aracılı mekanizmalarla çalışır. Üçüncü grup ise %30'dan az kanser ilişkisi gösteren düşük riskli gruptur. Tanı aşamasında serum ve BOS testlerinin birlikte yapılması önerilir. Pozitif yüksek riskli antikor saptandığında, ilk tarama negatif olsa bile tümör taramalarının 2 yıl boyunca 4-6 ayda bir tekrarlanması kritik önem taşır. Paraneoplastic syndromes are systemic disorders caused by humoral factors or immune cross-reactivity between malignant and normal tissues, occurring remote from the primary tumor or metastasis. Most frequently inducing neurological manifestations, paraneoplastic neurological syndromes (PNS) are detected before a cancer diagnosis in 80% of cases, enabling the early identification of occult malignancies. In 2021, the PNS-Care panel updated the diagnostic criteria and classified onconeuronal antibodies into three risk categories based on their cancer association frequency. "High-Risk Antibodies" (>70% cancer-associated), such as Hu, Yo, Ri, and CV2/CRMP5, typically target intracellular antigens and are mediated by cytotoxic T-cell mechanisms. Conversely, "Intermediate-Risk Antibodies" (30%-70% cancer-associated), including NMDAR, AMPAR, GABABR, and P/Q VGCC, target cell surface or synaptic proteins, driving directly pathogenic antibody-mediated responses. "Low-Risk Antibodies" exhibit less than a 30% correlation with underlying malignancies. For robust diagnosis, concurrent testing of both serum and cerebrospinal fluid (CSF) is highly recommended. Clinically, identifying high-risk antibodies necessitates rigorous tumor screening every 4 to 6 months for a duration of 2 years, even if initial oncological screenings yield negative results.

  • Open Access

    Paraneoplastik Sendromlar

    by Mehmet Uzun, İrEm Uğurlu, Aslıhan Baran, Ferit Aslan, Melike Özçelik, Pervin Can Şancı, Serkan Enki, İrEm Bilgetekin, Osman Cüre, Eyyüp Ayas, et al.