Search Results (1,050)

Background: Coronavirus disease 2019 (COVID-19) has led to the expansion of the spectrum of invasive fungal infections beyond traditional immunocompromised populations. Although COVID-19-associated pulmonary aspergillosis is increasingly being recognised, COVID-19-associated mucormycosis remains rare, particularly in non-endemic regions. Concurrent COVID-19-associated invasive tracheobronchial aspergillosis and pulmonary mucormycosis with histopathological confirmation is exceedingly uncommon and poses significant diagnostic and therapeutic challenges. Case presentation: We report the case of a 57-year-old female with myelodysplastic syndrome who underwent haploidentical allogeneic haematopoietic stem cell transplantation. During post-transplant recovery, she developed COVID-19 pneumonia, complicated by respiratory deterioration and radiological findings, including a reverse halo sign. Bronchoscopy revealed multiple whitish plaques in the right main bronchus. Despite negative serum and bronchoalveolar lavage fluid galactomannan assay results, cytopathological examination revealed septate hyphae and Aspergillus fumigatus was subsequently identified. Given the patient’s risk factors and clinical features, liposomal amphotericin B therapy was initiated. Subsequent surgical resection and histopathological analysis confirmed the presence of Rhizopus microsporus. Following antifungal therapy and surgical intervention, the patient recovered and was discharged in stable condition. Conclusions: This case highlights the critical need for heightened clinical suspicion of combined invasive fungal infections in severely immunocompromised patients with COVID-19, even in non-endemic regions for mucormycosis. Early tissue-based diagnostic interventions and prompt initiation of optimal antifungal therapy are essential for obtaining ideal outcomes when co-infection is suspected. Full article

Tuberculosis (TB) is an ancient and re-emerging granulomatous infectious disease that continues to challenge public health. Early diagnosis and prompt effective treatment are crucial for preventing disease progression and reducing both morbidity and mortality. These steps play a vital role in infection control and in lowering death rates at both individual and population levels. Although diagnostic methods have improved sufficiently in recent decades, TB can still present with ambiguous laboratory and imaging features. This ambiguity can lead to diagnostic pitfalls and potentially disastrous outcomes due to delayed diagnosis. In this article, we present a case of TB that was difficult to diagnose. The disease had invaded the mediastinum, right atrium, right coronary artery, and inferior vena cava (IVC), resulting in Budd–Chiari syndrome. This rare presentation created clinical, laboratory, and radiological confusion, resulting in a diagnostic dilemma that ultimately led to open cardiac surgery. The patient initially presented with progressive shortness of breath on exertion and fatigue, which suggested possible heart disease. This suspicion was reinforced by computed tomography (CT) imaging, which showed infiltrative mass lesions predominantly in the right side of the heart, invading the right coronary artery and IVC, with imaging features mimicking angiosarcoma. Although laboratory findings revealed an exudative effusion with lymphocyte predominance and elevated adenosine deaminase (ADA), the Gram stain was negative for bacteria, and an acid-fast bacilli (AFB) smear was also negative. These findings contributed to diagnostic uncertainty and delayed the confirmation of TB. Open surgery with excisional biopsy and histopathological analysis ultimately confirmed TB. We conclude that TB should not be ruled out solely based on negative Mycobacterium bacteria in pericardial effusion or AFB smear. TB can mimic aggressive tumors such as angiosarcoma or lymphoma with invasion of the surrounding tissues and blood vessels. Awareness of the clinical presentation, imaging findings, and potential diagnostic pitfalls of TB is essential, especially in endemic regions. Full article

Background/Objectives: Accurate diagnosis of brain tumors is one of the most important challenges in neuro-oncology since tumor classification and volumetric segmentation inform treatment planning. Two-dimensional classification and three-dimensional segmentation deep learning models can augment radiological workflows, particularly if paired with explainable AI techniques to improve model interpretability. The objective of this research was to develop a web-based brain tumor segmentation and classification diagnosis platform. Methods: A diagnosis system was developed combining 2D tumor classification and 3D volumetric segmentation. Classification employed a fine-tuned MobileNetV2 model trained on a glioma, meningioma, pituitary tumor, and normal control dataset. Segmentation employed a SegResNet model trained on BraTS multi-channel MRI with synthetic no-tumor data. A meta-classifier MLP was used for binary tumor detection from volumetric features. Explainability was offered using XRAI maps for 2D predictions and Gaussian overlays for 3D visualizations. The platform was incorporated into a web interface for clinical use. Results: MobileNetV2 2D model recorded 98.09% classification accuracy for tumor classification. 3D SegResNet obtained Dice coefficients around 68–70% for tumor segmentations. The MLP-based tumor detection module recorded 100% detection accuracy. Explainability modules could identify the area of the tumor, and saliency and overlay maps were consistent with real pathological features in both 2D and 3D. Conclusions: Deep learning diagnosis system possesses improved brain tumor classification and segmentation with interpretable outcomes by utilizing XAI techniques. Deployment as a web tool and a user-friendly interface made it suitable for clinical usage in radiology workflows. Full article

Background/Objectives: Pituitary tumors account for over 90% of all sellar region masses. However, a spectrum of rare neoplastic, inflammatory, infectious, and vascular lesions—benign and malignant—can arise in the intra- and parasellar compartments and clinically and radiologically mimic PitNETs. We report a cohort of 47 such rare and cystic midline intracranial lesions, emphasizing their distinctive morphological, clinical, and imaging features and the personalized treatment strategies applied. Methods: In this retrospective single-center study, we reviewed all patients treated for suspected PitNETs via transsphenoidal approach between 2015 and 2024. Of 529 surgical cases, we excluded confirmed PitNETs, meningiomas, and classical intradural craniopharyngiomas. Collected data encompassed patient demographics, tumor characteristics, presenting symptoms, extent of resection or medical therapy, endocrine outcomes, and follow-up information. Results: Among all 529 patients who underwent surgical treatment for sellar lesions from 2015 to 2024, 47 cases (8.9%) were identified as rare or cystic masses. Forty-six underwent transsphenoidal resection; one patient with hypophysitis received corticosteroid therapy alone. Presenting symptoms included headache (n = 16), dizziness (n = 5), oculomotor disturbances (n = 2), and visual impairment (n = 17). Endocrine dysfunction was found in 30 patients, 27 of whom required hydrocortisone replacement. Histopathological diagnoses were led by colloid cysts (n = 14) and Rathke’s cleft cysts (n = 11). The remaining 22 cases comprised plasmacytoma, germinoma, lymphoma, pituicytoma, inverted papilloma, metastatic carcinoma, chordoma, nasopharyngeal carcinoma, chloroma, and other rare entities. Preoperative imaging diagnosis proved incorrect in 38% (18/47) of cases, with several lesions initially misidentified as PitNETs. Conclusions: Nearly 9% of presumed PitNETs were rare, often benign or inflammatory lesions requiring distinct management. Most could be safely resected and demonstrated excellent long-term outcomes. Yet, despite advanced imaging techniques, accurate preoperative differentiation remains challenging, with over one-third misdiagnosed. Clinical red flags—such as early hormone deficits, rapid progression or atypical imaging findings—should prompt early interdisciplinary evaluation and, when indicated, image-guided biopsy to avoid unnecessary surgery and ensure tailored therapy. Full article

Background: Multisegmental lumbar degenerative disease (ms-LDD) is a common condition in older adults, often requiring surgical intervention. While rigid stabilization remains the gold standard, it is associated with complications such as adjacent segment disease (ASD), higher blood loss, and longer recovery times. The Dynesys dynamic stabilization system offers an alternative by preserving motion while stabilizing the spine. However, data comparing Dynesys with fusion in multisegmental cases are limited. Objective: This study evaluates the clinical and radiographic outcomes of Dynesys dynamic stabilization versus rigid stabilization in the treatment of ms-LDD. Methods: A retrospective analysis was conducted on 53 patients (mean age: 62.25 ± 15.37 years) who underwent either Dynesys dynamic stabilization (n = 27) or PLIF (n = 26) for ms-LDD involving at least seven motion segments. Clinical outcomes were assessed using the Visual Analog Scale (VAS) and Oswestry Disability Index (ODI), while radiological parameters such as lumbar lordosis (LL), sagittal vertical axis (SVA), and spinopelvic parameters (pelvic incidence, pelvic tilt and, sacral slope) were analyzed. A two-stage surgical approach was employed in the Dynesys group to enhance osseointegration, particularly in elderly osteoporotic patients. Results: Both groups showed significant improvements in VAS and ODI scores postoperatively (p < 0.001), with no significant differences between them. However, the Dynesys group demonstrated superior sagittal alignment correction, with a significant increase in LL (p < 0.002) and a significant decrease in SVA (p < 0.0015), whereas changes in the rigid stabilization group were not statistically significant. Additionally, the Dynesys group had fewer complications, including a lower incidence of ASD (0 vs. 6 cases). The two-stage technique facilitated improved screw osseointegration and reduced surgical risks in osteoporotic patients. Conclusions: Dynesys dynamic stabilization is an effective alternative to rigid stabilization in ms-LDD, offering comparable pain relief and functional improvement while preserving motion and reducing ASD risk. The two-stage approach enhances long-term stability, making it particularly suitable for elderly or osteoporotic patients. Further long-term studies are needed to confirm these findings. Full article

Background: Epidermal growth factor receptor (EGFR) mutations are presented in approximately 50% of East Asian populations with advanced non-small cell lung cancer (NSCLC). While EGFR-tyrosine kinase inhibitors (TKIs) are the standard treatment, patient outcomes are also influenced by host-related factors. This study aimed to investigate clinical and radiological factors associated with early mortality and develop a prognostic prediction model in advanced EGFR-mutated NSCLC. Methods: A retrospective cohort was conducted in patients with EGFR-mutated NSCLC treated with first line EGFR-TKIs from January 2012 to October 2022 at Chiang Mai University Hospital. Clinical data and radiologic findings at the initiation of treatment were analyzed. A multivariable flexible parametric survival model was used to determine the predictors of death at 18 months. The predicted survival probabilities at 6, 12, and 18 months were estimated, and the model performance was evaluated. Results: Among 189 patients, 84 (44.4%) died within 18 months. Significant predictors of mortality included body mass index <18.5 or ≥23, bone metastasis, neutrophil-to-lymphocyte ratio ≥ 5, albumin-to-globulin ratio < 1, and mean pulmonary artery diameter ≥ 29 mm. The model demonstrated good performance (Harrell’s C-statistic = 0.72; 95% CI: 0.66–0.78). Based on bootstrap internal validation, the optimism-corrected Harrell’s C-statistic was 0.71 (95% CI: 0.71–0.71), derived from an apparent C-statistic of 0.75 (95% CI: 0.74–0.75) and an estimated optimism of 0.04 (95% CI: 0.03–0.04). Estimated 18-month survival ranged from 87.1% in those without risk factors to 2.1% in those with all predictors. A web-based tool was developed for clinical use. Conclusions: The prognostic model developed from fundamental clinical and radiologic parameters demonstrated promising utility in predicting 18-month mortality in patients with advanced EGFR-mutated NSCLC receiving first-line EGFR-TKI therapy. Full article

Background and Objectives: Multiple sclerosis (MS) is a chronic immune-mediated neurological disorder that primarily affects young adults and is frequently accompanied by psychiatric comorbidities such as depression and anxiety, both of which significantly diminish patients’ quality of life (QoL). This study investigated the effect of two oral disease-modifying therapies (DMTs), fingolimod and cladribine, on mental health and QoL in patients with relapsing-remitting MS (RRMS). The aim of the study was to compare levels of depression, anxiety, and health-related quality of life (HRQoL) in RRMS patients treated with fingolimod or cladribine, and to evaluate their associations with clinical and radiological parameters. Materials and Methods: Eighty RRMS patients aged 18 to 50 years with Expanded Disability Status Scale (EDSS) scores of 3.0 or less, no recent disease relapse, and no history of antidepressant use were enrolled. Forty patients were treated with fingolimod and forty with cladribine. Depression and anxiety were assessed using the Hamilton Depression Rating Scale (HDRS) and the Hamilton Anxiety Rating Scale (HARS). QoL was evaluated using the Multiple Sclerosis QoL-54 (MSQOL-54) instrument. Additional clinical data, including MRI-based lesion burden, EDSS scores, age, disease duration, and occupational status, were collected. Results: No statistically significant differences were observed between the two groups regarding HDRS and HARS scores (p > 0.05). However, patients treated with fingolimod had significantly higher scores in the Energy/Fatigue subdomain (7.55 ± 2.02 vs. 6.56 ± 2.57, p = 0.046) and Composite Mental Health (CMH) score (64.73 ± 15.01 vs. 56.00 ± 18.93, p = 0.029) compared to those treated with cladribine. No significant differences were found in the independent items of the MSQOL-54. A negative correlation was identified between total lesion load and QoL scores. Conclusions: Although fingolimod and cladribine exert comparable effects on depression and anxiety levels, fingolimod may be associated with better mental health outcomes and reduced fatigue in RRMS patients. Furthermore, lesion burden and clinical parameters such as age and EDSS score may independently influence QoL, regardless of the DMT used. Full article

Background: Pancreatic cystic lesions (PCLs), including intraductal papillary mucinous neoplasms (IPMNs) and mucinous cystic neoplasms (MCNs), pose a diagnostic challenge due to their variable malignant potential. Current guidelines, such as Fukuoka and American Gastroenterological Association (AGA), have moderate predictive accuracy and may lead to overtreatment or missed malignancies. Artificial intelligence (AI), incorporating machine learning (ML) and deep learning (DL), offers the potential to improve risk stratification, diagnosis, and management of PCLs by integrating clinical, radiological, and molecular data. This is the first systematic review to evaluate the application, performance, and clinical utility of AI models in the diagnosis, classification, prognosis, and management of pancreatic cysts. Methods: A systematic review was conducted in accordance with PRISMA guidelines and registered on PROSPERO (CRD420251008593). Databases searched included PubMed, EMBASE, Scopus, and Cochrane Library up to March 2025. The inclusion criteria encompassed original studies employing AI, ML, or DL in human subjects with pancreatic cysts, evaluating diagnostic, classification, or prognostic outcomes. Data were extracted on the study design, imaging modality, model type, sample size, performance metrics (accuracy, sensitivity, specificity, and area under the curve (AUC)), and validation methods. Study quality and bias were assessed using the PROBAST and adherence to TRIPOD reporting guidelines. Results: From 847 records, 31 studies met the inclusion criteria. Most were retrospective observational (n = 27, 87%) and focused on preoperative diagnostic applications (n = 30, 97%), with only one addressing prognosis. Imaging modalities included Computed Tomography (CT) (48%), endoscopic ultrasound (EUS) (26%), and Magnetic Resonance Imaging (MRI) (9.7%). Neural networks, particularly convolutional neural networks (CNNs), were the most common AI models (n = 16), followed by logistic regression (n = 4) and support vector machines (n = 3). The median reported AUC across studies was 0.912, with 55% of models achieving AUC ≥ 0.80. The models outperformed clinicians or existing guidelines in 11 studies. IPMN stratification and subtype classification were common focuses, with CNN-based EUS models achieving accuracies of up to 99.6%. Only 10 studies (32%) performed external validation. The risk of bias was high in 93.5% of studies, and TRIPOD adherence averaged 48%. Conclusions: AI demonstrates strong potential in improving the diagnosis and risk stratification of pancreatic cysts, with several models outperforming current clinical guidelines and human readers. However, widespread clinical adoption is hindered by high risk of bias, lack of external validation, and limited interpretability of complex models. Future work should prioritise multicentre prospective studies, standardised model reporting, and development of interpretable, externally validated tools to support clinical integration. Full article

Background: Transforaminal lumbar interbody fusion (TLIF) with static cages is a frequently performed procedure. Larger series focusing on the use of expandable TLIF spacers are less common. Methods: This retrospective, single-center observational cohort study reviewed consecutive patients treated by TLIF using expandable titanium interbody implants (ALTERA™, Globus Medical Inc., Audubon, PA, USA) for degenerative pathologies from L2-S1 between 11/2018 and 09/2023. Surgical parameters, adverse events, radiological outcomes (fusion rate, segmental lordosis, spinopelvic parameters), and clinical outcomes were analyzed through a mean postoperative follow-up of 12 months. Results: This study identified 270 patients (mean age 65 years, 50.4% female) who underwent TLIF with expandable interbody spacers at 324 levels. Clinical outcomes were good or excellent in 74.1% of patients at 3 months and 71.8% at 12 months. Radiographic fusion was achieved in 73.1% of assessable segments at 12 months. Segmental lordosis increased significantly from 17.8° preoperatively to 20.0° at 12 months (p < 0.001). Adverse event (AE) rates were acceptable across all timepoints, with no device failures or device-associated complications observed. Conclusions: This study demonstrates that TLIF with expandable titanium interbody implants was safe, associated with high fusion rates, and enabled significant restoration of segmental lordosis that was maintained during follow-up. Full article

The development of severe SARS-CoV-2 pneumonia is characterized by extensive lung inflammation, which, in turn, leads to respiratory distress and a decline in blood oxygen levels. Hospital admission, along with intensive care or ventilator usage, becomes necessary because this condition leads to serious respiratory problems. This review aims to provide a comprehensive overview of the pathophysiological mechanisms, diagnostic methods, and current therapeutic options for pneumonia caused by the SARS-CoV-2 virus. The pathophysiological process of severe pneumonia due to SARS-CoV-2 infection is characterized by direct lung damage from viral replication, an excessive immune system response, inflammation, impaired gas exchange, and multi-organ failure. The coexistence of various medical conditions leads to substantial lung impairment, resulting in hypoxia and respiratory failure, which can ultimately lead to fatal outcomes. The diagnosis of severe SARS-CoV-2 pneumonia is made through a combination of clinical, radiologic, and laboratory findings. A multifaceted approach integrating antiviral therapy, corticosteroids, oxygen supplementation, ventilatory management, and immunomodulation is imperative to control inflammation and enhance clinical outcomes. Early intervention, meticulous monitoring, and personalized care are paramount for enhancing survival and mitigating complications in critically ill patients with COVID-19 pneumonia. Full article

Background: Anti-synthetase Syndrome (ASyS) is an idiopathic inflammatory myopathy characterized by muscle weakness and inflammatory infiltrates in muscles. Sjogren’s disease (SD) is an autoimmune condition primarily affecting exocrine glands. Both these conditions may present lung involvement. We describe a female patient with anti-synthetase/SD overlap syndrome and review the literature to identify published cases describing this overlap, aiming to better define its clinical, radiological, and serological features. Methods: The case description was based on a retrospective collection of clinical, laboratory, and imaging data related to the patient’s diagnostic process and clinical course. Data were anonymized and handled in accordance with the competent territorial Ethics Committee. A literature review was performed using the MEDLINE and Scopus databases by combining the keywords “Anti-Synthetase syndrome”, “Sjögren disease”, “Sjögren syndrome”, “Myositis”, and “Interstitial lung disease” (ILD). Published cases were selected if they met the 2016 EULAR/ACR criteria for SD and at least one of the currently proposed classification criteria for ASyS. Results: The described case concerns a 68-year-old woman with rapidly progressive ILD. The diagnosis of anti-synthetase/SD overlap syndrome was based on clinical, serological (anti-Ro52 and anti-PL7 antibodies), histological, and radiological findings. Despite immunosuppressive and antifibrotic treatment, the clinical course worsened, leading to a poor outcome. In addition, six relevant cases were identified in the literature. Clinical presentations, autoantibody profiles, radiological findings, and outcomes were highly heterogeneous. Among the reported cases, no standardized treatment protocols were adopted, reflecting the lack of consensus in managing this rare condition. Conclusions: In anti-synthetase/SD overlap syndrome, ILD may follow a rapidly progressive course. Early recognition can be challenging, especially in the absence of muscular involvement. This case-based review highlights the need for more standardized approaches to the diagnosis and management of this rare and complex overlap syndrome. Full article

Background/Objectives: Rotator cuff calcific tendinopathy (RCCT) is one of the most common causes of non-traumatic shoulder pain. To date, there is still no consensus regarding the most effective method for its treatment. Ultrasound-guided percutaneous aspiration is suggested during the reabsorption phase of calcific metaplasia. We aimed to evaluate the effectiveness of ultrasound-guided lavage for RCCT from a clinical and radiological perspective. Methods: We involved patients affected by RCCT of the supraspinatus tendon. The approach used for the calcification lavage was the one-needle technique, consisting in inserting a 16–18 G needle on a 20 mL syringe with 0.9% saline solution, in the calcific metaplasia, under ultrasound guidance, using an in-plane approach; the repetitive action of pressing and releasing the plunger was repeated until the contents of the syringe became milky, at which point the syringe was replaced with a new one, always containing saline solution. The physiotherapy treatment began 7 days after the procedure. We assessed the Numeric Rating Scale, the Gartner classification, the Disability of the Arm, Shoulder and Hand scale, the Constant–Murley shoulder score, and the passive range of motion of flexion and abduction. Results: We included 23 subjects. The analysis of the data at baseline and t1 showed a statistically significant improvement in all the functional variables (p < 0.05). This result was mainly evident for pain, with a p-value of 0.001. Conclusions: The findings of the present prospective case series study showed an improvement in the clinical and radiological outcomes after ultrasound-guided percutaneous aspiration for rotator cuff calcific tendinopathy. Full article

Objective: This study aimed to compare the clinical and radiological outcomes of dynamic rod stabilization with and without transforaminal lumbar interbody fusion (TLIF) in patients undergoing surgery for degenerative lumbar instability. Specifically, we evaluated the prognostic value of hybrid systems in reducing adjacent segment disease (ASD), enhancing fusion rates, and improving functional outcomes. Methods: A retrospective analysis was conducted on 62 patients treated between 2019 and 2022. Group 1 (n = 34) underwent dynamic rod stabilization alone, while Group 2 (n = 28) received dynamic stabilization combined with TLIF. Radiological assessments included disk height index (DHI) and fusion rates. Clinical outcomes were measured using the Visual Analog Scale (VAS) for back and leg pain at baseline, 12, and 24 months. Statistical analysis was performed using Jamovi^® software (version 2.4.1). Results: The hybrid group (dynamic + TLIF) demonstrated significantly higher anterior fusion rates (p < 0.001) and greater improvement in VAS scores for back (p = 0.005) and leg pain (p < 0.001) at 12 months. Although operative time was longer (p = 0.002), there was no significant difference in hospital stay (p = 0.635). No significant differences were observed in ASD development (p = 0.11) or pseudoarthrosis (p = 0.396). The hybrid group maintained better lumbar lordosis and higher adjacent segment DHI. Conclusions: Hybrid dynamic stabilization combined with TLIF provides superior clinical outcomes and fusion rates compared to dynamic stabilization alone, without significantly increasing the risk of ASD. These findings support the use of hybrid constructs as a balanced strategy for treating degenerative lumbar instability. Full article

Background and Objectives: General-purpose multimodal large language models (LLMs) are increasingly used for medical image interpretation despite lacking clinical validation. This study evaluates the diagnostic reliability of ChatGPT-4o and Claude 2 in photographic assessment of adolescent idiopathic scoliosis (AIS) against radiological standards. This study examines two critical questions: whether families can derive reliable preliminary assessments from LLMs through analysis of clinical photographs and whether LLMs exhibit cognitive fidelity in their visuospatial reasoning capabilities for AIS assessment. Materials and Methods: A prospective diagnostic accuracy study (STARD-compliant) analyzed 97 adolescents (74 with AIS and 23 with postural asymmetry). Standardized clinical photographs (nine views/patient) were assessed by two LLMs and two orthopedic residents against reference radiological measurements. Primary outcomes included diagnostic accuracy (sensitivity/specificity), Cobb angle concordance (Lin’s CCC), inter-rater reliability (Cohen’s κ), and measurement agreement (Bland–Altman LoA). Results: The LLMs exhibited hazardous diagnostic inaccuracy: ChatGPT misclassified all non-AIS cases (specificity 0% [95% CI: 0.0–14.8]), while Claude 2 generated 78.3% false positives. Systematic measurement errors exceeded clinical tolerance: ChatGPT overestimated thoracic curves by +10.74° (LoA: −21.45° to +42.92°), exceeding tolerance by >800%. Both LLMs showed inverse biomechanical concordance in thoracolumbar curves (CCC ≤ −0.106). Inter-rater reliability fell below random chance (ChatGPT κ = −0.039). Universal proportional bias (slopes ≈ −1.0) caused severe curve underestimation (e.g., 10–15° error for 50° deformities). Human evaluators demonstrated superior bias control (0.3–2.8° vs. 2.6–10.7°) but suboptimal specificity (21.7–26.1%) and hazardous lumbar concordance (CCC: −0.123). Conclusions: General-purpose LLMs demonstrate clinically unacceptable inaccuracy in photographic AIS assessment, contraindicating clinical deployment. Catastrophic false positives, systematic measurement errors exceeding tolerance by 480–1074%, and inverse diagnostic concordance necessitate urgent regulatory safeguards under frameworks like the EU AI Act. Neither LLMs nor photographic human assessment achieve reliability thresholds for standalone screening, mandating domain-specific algorithm development and integration of 3D modalities. Full article

Background/Objectives: Pediatric acquired demyelinating syndromes (ADSs) encompass a heterogeneous group of disorders, including multiple sclerosis (MS), MOG antibody-associated disease (MOGAD), and neuromyelitis optica spectrum disorder (NMOSD), with distinct clinical trajectories and prognoses. While analyzed collectively at baseline to reflect real-world diagnostic uncertainty, outcome predictors were also examined according to final diagnosis. Identifying early predictors is crucial for optimizing long-term outcomes. Methods: We retrospectively analyzed 30 pediatric patients (mean onset age: 11.3 years) with ADSs. Clinical, radiological, CSF, antibody, and neurophysiological data were collected and analyzed alongside treatment strategies. Outcomes—EDSS scores, neuroradiological changes, and clinical status—were evaluated over a 3-year period. Results: Final diagnoses included MOGAD (36.6%), MS (33.3%), NMOSD (6.6%), ADEM (10%), and other ADSs (13.3%). At onset, ≥3 brain lesions were present in 76.7% of patients. Disease-modifying therapies (DMTs) were used in 37% and acute immunotherapy in 90%. EDSS progression was significantly associated with DMT use at multiple timepoints, with additional predictors including MRI lesion type, CSF findings, antibody status, and evoked potentials. At 3 years, neurocognitive function predicted clinical outcome. Conclusions: Early immunotherapy and baseline instrumental findings are key predictors of outcome in pediatric ADSs. MOGAD showed a more favorable course, while MS and NMOSD were associated with greater long-term disability. A comprehensive, early diagnostic approach is essential for improving prognosis. Full article