Repeated epidural delivery of Shinbaro2: effects on neural recovery, inflammation, and pain modulation in a rat model of lumbar spinal stenosis.

The choice of treatment for lumbar spinal stenosis (LSS) depends on symptom severity. When severe motor issues with urinary dysfunction are not present, conservative treatment is often considered to be the priority. One such conservative treatment is epidural injection, which is effective in alleviating inflammation and the pain caused by LSS-affected nerves. In this study, Shinbaro2 (Sh2), pharmacopuncture using natural herbal medicines for patients with disc diseases, is introduced as an epidural to treat LSS in a rat model. The treatment of primary sensory neurons from the rats' dorsal root ganglion (DRG) neurons with Sh2 at various concentrations (0.5, 1, and 2 mg/mL) was found to be safe and non-toxic. Furthermore, it remarkably stimulated axonal outgrowth even under H2O2-treated conditions, indicating its potential for stimulating nerve regeneration. When LSS rats received epidural injections of two different concentrations of Sh2 (1 and 2 mg/kg) once daily for 4 weeks, a significant reduction was seen in ED1+ macrophages surrounding the silicone block used for LSS induction. Moreover, epidural injection of Sh2 in the DRG led to a significant suppression of pain-related factors. Notably, Sh2 treatment resulted in improved locomotor recovery, as evaluated by the Basso, Beattie, and Bresnahan scale and the horizontal ladder test. Additionally, hind paw hypersensitivity, assessed using the Von Frey test, was reduced, and normal gait was restored. Our findings demonstrate that epidural Sh2 injection not only reduced inflammation but also improved locomotor function and pain in LSS model rats. Thus, Sh2 delivery via epidural injection has potential as an effective treatment option for LSS.

Association between cerebral artery stenosis and depressive symptoms in elderly patients.

OBJECTIVE: To examine the association between cerebral artery stenosis and depressive symptoms in elderly patients. METHODS: The study participants were 365 patients aged ≥65 years who visited the psychiatric outpatient clinic, Samsung Medical Center between January 1, 2000, and December 31, 2019, and were diagnosed with depressive disorder. They had brain imaging tests including magnetic resonance angiography (MRA), psychological evaluations including the 15-item Geriatric Depression Scale (GDS-15), and lab tests. Individuals' cerebral artery stenosis was identified and the association with significant depressive symptoms was examined. RESULTS: Of the 365 subjects, 108 had at least one location of cerebral artery stenosis (29.6 %). The mean score of GDS-15 in the stenosis group was 8.1 (SD, 3.8), higher than the mean GDS-15 score of 6.5 (SD, 4.0) for the group without stenosis (p < 0.001). Compared to no middle cerebral artery (MCA) stenosis, having MCA stenosis was associated with significant depressive symptoms (p = 0.005). Compared to no posterior cerebral artery (PCA) stenosis, having left PCA stenosis was associated with significant depressive symptoms (p = 0.022). In the multivariable linear regression analysis, only bilateral MCA stenosis had a positive association with the score of GDS-15 (p = 0.013). CONCLUSION: Bilateral MCA stenosis and left PCA stenosis are associated with significant depressive symptoms among elderly patients, with bilateral MCA stenosis positively associated with the severity of depression.

Psychiatric adverse events following COVID-19 vaccination: a population-based cohort study in Seoul, South Korea.

Evidence has suggested an increased risk of psychiatric manifestations following viral infections including coronavirus disease-2019 (COVID-19). However, psychiatric adverse events (AEs) after COVID-19 vaccination, which were documented in case reports and case series, remain unclear. This study is aimed to investigate the psychiatric AEs after COVID-19 vaccination from a large population-based cohort in Seoul, South Korea. We recruited 50% of the Seoul-resident population randomly selected from the Korean National Health Insurance Service (KNHIS) claims database on 1, January, 2021. The included participants (n = 2,027,353) from the Korean National Health Insurance Service claims database were divided into two groups according to COVID-19 vaccination. The cumulative incidences per 10,000 of psychiatric AEs were assessed on one week, two weeks, one month, and three months after COVID-19 vaccination. Hazard ratios (HRs) and 95% Confidence interval (CIs) of psychiatric AEs were measured for the vaccinated population. The cumulative incidence of depression, anxiety, dissociative, stress-related, and somatoform disorders, sleep disorders, and sexual disorders at three months following COVID-19 vaccination were higher in the vaccination group than no vaccination group. However, schizophrenia and bipolar disorders showed lower cumulative incidence in the vaccination group than in the non-vaccinated group. Depression (HR [95% CI] = 1.683 [1.520-1.863]), anxiety, dissociative, stress-related, and somatoform disorders (HR [95% CI] = 1.439 [1.322-1.568]), and sleep disorders (HR [95% CI] = 1.934 [1.738-2.152]) showed increased risks after COVID-19 vaccination, whereas the risks of schizophrenia (HR [95% CI] = 0.231 [0.164-0.326]) and bipolar disorder (HR [95% CI] = 0.672 [0.470-0.962]). COVID-19 vaccination increased the risks of depression, anxiety, dissociative, stress-related, and somatoform disorders, and sleep disorders while reducing the risk of schizophrenia and bipolar disorder. Therefore, special cautions are necessary for administering additional COVID-19 vaccinations to populations vulnerable to psychiatric AEs.

Autism spectrum disorders detection based on multi-task transformer neural network.

Autism Spectrum Disorders (ASD) are neurodevelopmental disorders that cause people difficulties in social interaction and communication. Identifying ASD patients based on resting-state functional magnetic resonance imaging (rs-fMRI) data is a promising diagnostic tool, but challenging due to the complex and unclear etiology of autism. And it is difficult to effectively identify ASD patients with a single data source (single task). Therefore, to address this challenge, we propose a novel multi-task learning framework for ASD identification based on rs-fMRI data, which can leverage useful information from multiple related tasks to improve the generalization performance of the model. Meanwhile, we adopt an attention mechanism to extract ASD-related features from each rs-fMRI dataset, which can enhance the feature representation and interpretability of the model. The results show that our method outperforms state-of-the-art methods in terms of accuracy, sensitivity and specificity. This work provides a new perspective and solution for ASD identification based on rs-fMRI data using multi-task learning. It also demonstrates the potential and value of machine learning for advancing neuroscience research and clinical practice.

Determination of permissive and restraining cancer-associated fibroblast (DeCAF) subtypes.

Cancer-associated fibroblast (CAF) subpopulations in pancreatic ductal adenocarcinoma (PDAC) have been identified using single-cell RNA sequencing (scRNAseq) with divergent characteristics, but their clinical relevance remains unclear. We translate scRNAseq-derived CAF cell-subpopulation-specific marker genes to bulk RNAseq data, and develop a single- sample classifier, DeCAF, for the classification of clinically rest raining and perm issive CAF subtypes. We validate DeCAF in 19 independent bulk transcriptomic datasets across four tumor types (PDAC, mesothelioma, bladder and renal cell carcinoma). DeCAF subtypes have distinct histology features, immune landscapes, and are prognostic and predict response to therapy across cancer types. We demonstrate that DeCAF is clinically replicable and robust for the classification of CAF subtypes in patients for multiple tumor types, providing a better framework for the future development and translation of therapies against permissive CAF subtypes and preservation of restraining CAF subtypes. Significance: We introduce a replicable and robust classifier, DeCAF, that delineates the significance of the role of permissive and restraining CAF subtypes in cancer patients. DeCAF is clinically tractable, prognostic and predictive of treatment response in multiple cancer types and lays the translational groundwork for the preclinical and clinical development of CAF subtype specific therapies.

Inhibition of Amyloid-ß (Aß)-Induced Cognitive Impairment and Neuroinflammation in CHI3L1 Knockout Mice through Downregulation of ERK-PTX3 Pathway.

Several clinical studies reported that the elevated expression of Chitinase-3-like 1 (CHI3L1) was observed in patients suffering from a wide range of diseases: cancer, metabolic, and neurological diseases. However, the role of CHI3L1 in AD is still unclear. Our previous study demonstrated that 2-({3-[2-(1-Cyclohexen-1-yl)ethyl]-6,7-dimethoxy-4-oxo-3,4-dihydro-2-quinazolinyl}culfanyl)-N-(4-ethylphenyl)butanamide, a CHI3L1 inhibiting compound, alleviates memory and cognitive impairment and inhibits neuroinflammation in AD mouse models. In this study, we studied the detailed correlation of CHI3L1 and AD using serum from AD patients and using CHI3L1 knockout (KO) mice with Aß infusion (300 pmol/day, 14 days). Serum levels of CHI3L1 were significantly elevated in patients with AD compared to normal subjects, and receiver operating characteristic (ROC) analysis data based on serum analysis suggested that CHI3L1 could be a significant diagnostic reference for AD. To reveal the role of CHI3L1 in AD, we investigated the CHI3L1 deficiency effect on memory impairment in Aß-infused mice and microglial BV-2 cells. In CHI3L1 KO mice, Aß infusion resulted in lower levels of memory dysfunction and neuroinflammation compared to that of WT mice. CHI3L1 deficiency selectively inhibited phosphorylation of ERK and IκB as well as inhibition of neuroinflammation-related factors in vivo and in vitro. On the other hand, treatment with recombinant CHI3L1 increased neuroinflammation-related factors and promoted phosphorylation of IκB except for ERK in vitro. Web-based gene network analysis and our results showed that CHI3L1 is closely correlated with PTX3. Moreover, in AD patients, we found that serum levels of PTX3 were correlated with serum levels of CHI3L1 by Spearman correlation analysis. These results suggest that CHI3L1 deficiency could inhibit AD development by blocking the ERK-dependent PTX3 pathway.

U-shaped convolutional transformer GAN with multi-resolution consistency loss for restoring brain functional time-series and dementia diagnosis.

Introduction: The blood oxygen level-dependent (BOLD) signal derived from functional neuroimaging is commonly used in brain network analysis and dementia diagnosis. Missing the BOLD signal may lead to bad performance and misinterpretation of findings when analyzing neurological disease. Few studies have focused on the restoration of brain functional time-series data. Methods: In this paper, a novel U-shaped convolutional transformer GAN (UCT-GAN) model is proposed to restore the missing brain functional time-series data. The proposed model leverages the power of generative adversarial networks (GANs) while incorporating a U-shaped architecture to effectively capture hierarchical features in the restoration process. Besides, the multi-level temporal-correlated attention and the convolutional sampling in the transformer-based generator are devised to capture the global and local temporal features for the missing time series and associate their long-range relationship with the other brain regions. Furthermore, by introducing multi-resolution consistency loss, the proposed model can promote the learning of diverse temporal patterns and maintain consistency across different temporal resolutions, thus effectively restoring complex brain functional dynamics. Results: We theoretically tested our model on the public Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, and our experiments demonstrate that the proposed model outperforms existing methods in terms of both quantitative metrics and qualitative assessments. The model's ability to preserve the underlying topological structure of the brain functional networks during restoration is a particularly notable achievement. Conclusion: Overall, the proposed model offers a promising solution for restoring brain functional time-series and contributes to the advancement of neuroscience research by providing enhanced tools for disease analysis and interpretation.

Anti-chitinase-3-like 1 antibody attenuated atopic dermatitis-like skin inflammation through inhibition of STAT3-dependent CXCL8 expression.

BACKGROUND AND PURPOSE: Chitinase-3-like 1 (CHI3L1) causes skin inflammation in the progression of atopic dermatitis. We investigated if anti-CHI3L1 antibody could prevent the development of atopic dermatitis and its mechanisms of action. EXPERIMENTAL APPROACH: The effect of CHI3L1 antibody on phthalic anhydride-induced atopic dermatitis animal model and in vitro reconstructed human skin (RHS) model were investigated. Expression and release of atopic dermatitis-related cytokines were determined using an enzyme-linked immunosorbent assay, and RT-qPCR, STAT3 and CXCL8 signalling were measured by western blotting. KEY RESULTS: Anti-CHI3L1 antibody suppressed phthalic anhydride-induced epidermal thickening, clinical score, IgE level and infiltration of inflammatory cells, and reduced phthalic anhydride-induced inflammatory cytokines concentration. In addition, CHI3L1 antibody treatment inhibited the expression of STAT3 activity in phthalic anhydride-treated skin. It was also confirmed that CHI3L1 antibody treatment alleviated atopic dermatitis-related inflammation in the RHS model. The inhibitory effects of CHI3L1 antibody was similar or more effective compared with that of the IL-4 antibody. We further found that CHI3L1 is associated with CXCL8 by protein-association network analysis. siRNA of CHI3L1 blocked the mRNA levels of CHI3L1, IL-1ß, IL-4, CXCL8, TSLP, and the expression of CHI3L1 and p-STAT, and the level of CXCL8, whereas recombinant level of CXCL8 was elevated. Moreover, siRNA of STAT3 reduced the mRNA level of these cytokines. CHI3L1 and p-STAT3 expression correlated with the reduced CXCL8 level in the RHS in vitro model. CONCLUSION AND IMPLICATIONS: Our data demonstrated that CHI3L1 antibody could be a promising effective therapeutic drug for atopic dermatitis.

The efficacy of anterior vertebral body tethering in lenke type 6 curves for adolescent idiopathic scoliosis.

PURPOSE: Spinal fusion is the standard treatment for severe forms of adolescent idiopathic scoliosis (AIS). However, with the lowest instrumented vertebra that is usually located at L3 or L4, patients are prone to develop adjacent segment degeneration in the long term. Vertebral body tethering (VBT) as motion preserving technique has become an alternative for select patients with AIS. Several studies have presented the outcome after thoracic VBT but no study has analyzed the outcome after VBT for Lenke type 6 curves. METHODS: This is a retrospective single center data analysis of patients who have had bilateral VBT for Lenke type 6 curves and a minimum follow up of 24 months. Radiographic analysis was performed on several time points. Suspected tether breakages were additionally analyzed with respect to location and time at occurrence. RESULTS: 25 patients were included. Immediate thoracic curve correction was 55.4% and 71.7% for TL/L curves. Loss of correction was higher for TL/L curves and resulted in a correction rate of 48.3% for thoracic curves and 48.9% for TL/L curves at 24 months post-operatively. 22 patients were suspected to have at least one segment with a tether breakage. Three patients required a re-VBT but no patient received posterior spinal fusion. CONCLUSION: Bilateral VBT for Lenke type 6 curves is feasible and shows a significant curve correction for thoracic and TL/L curves at a minimum of 24 months post-operatively. Tether breakage rate and loss of correction remain an unfavorable observation that needs to be improved in the future.

Comparative Analysis of Monoaxial and Polyaxial Pedicle Screws in the Surgical Correction of Adolescent Idiopathic Scoliosis.

Background: Although several biomechanical studies have been reported, few clinical studies have compared the efficacy of monoaxial and polyaxial pedicle screws in the surgical treatment of adolescent idiopathic scoliosis (AIS). This study aims to compare the radiological and clinical outcomes of mono- and polyaxial pedicle screws in the surgical treatment of AIS. Methods: A total of 46 AIS patients who underwent surgery to treat scoliosis using pedicle screw instrumentation (PSI) and rod derotation (RD) were divided into two groups according to the use of pedicle screws: the monoaxial group (n = 23) and polyaxial group (n = 23). Results: The correction rate of the main Cobb's angle was higher in the monoaxial group (70.2%) than in the polyaxial group (65.3%) (p = 0.040). No differences in the rotational correction of the apical vertebra were evident between the two groups. SRS-22 scores showed no significant differences according to the type of pedicle screws used. Conclusions: The use of polyaxial pedicle screws resulted in coronal, sagittal, and rotational correction outcomes comparable to those associated with the use of monoaxial pedicle screws for surgical treatment using PSI and RD to treat moderate cases of AIS.

In Situ Changes in Mechanical Properties Based on Gas Saturation Inside Pressure Vessels.

In previous studies, difficulties were encountered in measuring changes within high-pressure vessels owing to limitations such as sensor connectors and sensor failures under high-pressure conditions. In addition, polymer-gas mixtures experience instantaneous gas desorption upon exiting high-pressure vessels owing to pressure differentials, leading to measurement errors. In this study, a device using magnetic sensors was developed to measure the real-time changes in gas-saturated polymers inside pressure vessels. Experiments on polymethyl methacrylate gas adsorption were conducted with parameters including pressure at 5 MPa and temperatures ranging from -20 to 40 °C for 60 and 180 min. It was observed that at -20 °C, the maximum magnetic field force density and deflection were 391.53 µT and 5.83 mm, respectively, whereas at 40 °C, deflection did not occur, with a value of 321.79 µT. Based on gas saturation experiments, a new model for deflection in high-pressure atmospheres is proposed. Additionally, an ANSYS analysis was conducted to predict the changes in Young's modulus based on gas saturation. In previous studies, mechanical properties were measured outside the pressure vessel, resulting in an error due to a pressure difference, while the proposed method is characterized by the ability to directly measure polymer behavior according to gas saturation in high-pressure vessels using a magnetic sensor in real time. Therefore, it is possible to predict polymer behavior, making it easy to control variables in high-pressure polymer processes.

Extracellular Vesicles from Ecklonia cava and Phlorotannin Promote Rejuvenation in Aged Skin.

Plant-derived extracellular vesicles (EVs) elicit diverse biological effects, including promoting skin health. EVs isolated from Ecklonia cava (EV-EC) carry heat shock protein 70 (HSP70), which inhibits key regulators such as TNF-α, MAPKs, and NF-κB, consequently downregulating matrix metalloproteinases (MMPs). Aging exacerbates oxidative stress, upregulating MAPK and NF-κB signaling and worsening extracellular matrix degradation in the skin. E. cava-derived phlorotannin (PT) mitigates MAPK and NF-κB signaling. We evaluated the impact of EV-EC and PT on skin rejuvenation using an in vitro keratinocyte senescence model and an in vivo aged-mouse model. Western blotting confirmed the presence of HSP70 in EV-EC. Treatment with EV-EC and PT in senescent keratinocytes increased HSP70 expression and decreased the expression of TNF-α, MAPK, NF-κB, activator protein-1 (AP-1), and MMPs. Oxidative stress was also reduced. Sequential treatment with PT and EV-EC (PT/EV-EC) yielded more significant results compared to individual treatments. The administration of PT/EV-EC to the back skin of aged mice mirrored the in vitro findings, resulting in increased collagen fiber accumulation and improved elasticity in the aged skin. Therefore, PT/EV-EC holds promise in promoting skin rejuvenation by increasing HSP70 expression, decreasing the expression of MMPs, and reducing oxidative stress in aged skin.

Evaluating the validity and reliability of the Korean version of Scales for Outcomes in Parkinson's Disease-Cognition.

Objective: The Scales for Outcomes in Parkinson's Disease-Cognition (SCOPA-Cog) was developed to screen for cognition in PD. In this study, we aimed to evaluate the validity and reliability of the Korean version of the SCOPA-cog. Methods: We recruited 129 PD patients from 31 clinics with movement disorders in South Korea. The original version of the SCOPA-cognition was translated into Korean using the translation-retranslation method. The test-rest method with an intraclass correlation coefficient (ICC) and Cronbach's alpha coefficient were used to assess reliability. The Spearman's Rank correlation analysis with Montreal Cognitive Assessment-Korean version (MOCA-K) and Korean Mini-Mental State Examination (K-MMSE) were used to assess concurrent validity. Results: The Cronbach's alpha coefficient was 0.797, and the ICC was 0.887. Spearman's rank correlation analysis showed a significant correlation with the K-MMSE and MOCA-K scores (r = 0.546 and r = 0.683, respectively). Conclusions: Our results demonstrate that K-SCOPA-Cog exhibits good reliability and validity.

Early-term outcome of apical fusion with vertebral body tethering for thoracolumbar curves in adolescent idiopathic scoliosis: a preliminary study.

INTRODUCTION: Vertebral body tethering (VBT) has become an alternative option for select patients with idiopathic scoliosis. However, studies have shown a high number of tether breakages, specifically after thoracolumbar (TL) VBT, that can have a negative impact on the outcome, when the breakage occurs within the first year after surgery. In order to overcome this problem, we have started to apply an apical fusion (AF) in combination with TL VBT for select patients. This study aims to analyze the outcome after AF plus VBT. METHODS: This is a retrospective single surgeon's data analysis. All patients were included who have had TL VBT after January 2022 and a follow-up of 12 months. Patients were grouped based on whether they only had VBT or VBT + AF. RESULTS: Twenty-five patients were analyzed (15 VBT, 10 VBT + AF). Both groups showed a significant curve correction for thoracic and TL curves. Minor loss of correction was observed in both groups. A significant difference was seen regarding early tether breakages, which were found in 60% of VBT patients and 10% of VBT + AF patients. CONCLUSION: The preliminary data shows a significant reduction of early tether breakages when TL VBT is applied in combination with AF.

Hidden Blood Loss and Its Risk Factors for Oblique Lumbar Interbody Fusion.

(1) Background: The amount of blood loss during oblique lumber interbody fusion (OLIF) surgery is often underestimated and may contribute to adverse postoperative outcomes. This study aims to evaluate hidden blood loss (HBL) in patients who underwent OLIF for degenerative lumbar spine disease and to analyze its risk factors. (2) Methods: The medical records of 179 patients who underwent OLIF surgery from 2015 to 2022 were reviewed. The HBL and total blood loss (TBL) were estimated using the Gross formula. Pearson correlation, Spearman correlation, and multivariate linear regression analyses were used to investigate risk factors for HBL. (3) Results: The mean HBL was 675.2 mL, and the mean hemoglobin loss was 1.7 g/dL during OLIF surgery. In the multivariate linear regression analysis, TBL (p < 0.001), estimated blood loss (p < 0.001), and pedicle screw fixation type (p = 0.039) were identified as independent risk factors of HBL. (4) Conclusions: The OLIF is associated with substantial perioperative HBL, for which we identified risk factors of TBL, EBL, and pedicle screw fixation type. Notably, OLIF with percutaneous pedicle screw fixation resulted in greater HBL than stand-alone OLIF or OLIF with open pedicle screw fixation.

Revision Extension of Fusion Surgery in Thoracolumbar Spine Using a Newly Designed Revision Rod - Comparative Matched Cohort Study Versus Implant-Replacement Surgery.

STUDY DESIGN: Retrospective cohort study. OBJECTIVE: To compare the results of revision extension of fusion surgery using the newly designed revision rod and implant-replacement surgery in thoracolumbar spine. METHODS: Thirty-one patients who underwent extension of fusion surgery using the revision rod for adjacent segment disease were included in this study. Thirty-one patients who underwent implant-replacement revision surgery were selected as a control group by matching age, sex, preoperative diagnosis, and number of revision segments. RESULTS: The mean age was 70.7 ± 8.0 years in the revision rod (RR) group and 69.0 ± 8.4 years in the control group. Preoperative diagnoses, underlying diseases, and mean number of revision segments (2.2 ± 1.1) were similar in both groups. The change of hemoglobin (1.0 ± 1.9 vs 2.5 ± 1.5 g/dl; P < .01), hematocrit (4.1 ± 4.9 vs 7.2 ± 4.4 % P < .01) and albumin (.8 ± .9 vs 1.3 ± .4 g/dl; P < .01) levels before and after surgery showed significant differences between the two groups. Hemovac drainage was significantly less in the RR group (P = .01). The mean operative time was shorter in the RR group (203.5 ± 9.5 min vs 233.5 ± 8.7 min; P = .12) with no statistical difference. Radiological results showed that the average lumbar lordosis 2 years after surgery was lower in the RR group compared to the control group (25.1 ± 9.9° vs 32.9 ± 9.8°; P = .02). Union rates and clinical outcomes were not different between the two groups. CONCLUSIONS: Revision extension of fusion surgery using a newly designed revision rod had less hemovac drainage and superior laboratory findings compared to implant-replacement revision surgery.

Effects of vitamin family members on insulin resistance and diabetes complications.

The following letter to the editor highlights the article "Effects of vitamin D supplementation on glucose and lipid metabolism in patients with type 2 diabetes mellitus and risk factors for insulin resistance" in World J Diabetes 2023 Oct 15; 14 (10): 1514-1523. It is necessary to explore the role of vitamin family members in insulin resistance and diabetes complications.

Artificial Intelligence-Based Diagnostic Support System for Patent Ductus Arteriosus in Premature Infants.

Background: Patent ductus arteriosus (PDA) is a prevalent congenital heart defect in premature infants, associated with significant morbidity and mortality. Accurate and timely diagnosis of PDA is crucial, given the vulnerability of this population. Methods: We introduce an artificial intelligence (AI)-based PDA diagnostic support system designed to assist medical professionals in diagnosing PDA in premature infants. This study utilized electronic health record (EHR) data from 409 premature infants spanning a decade at Severance Children's Hospital. Our system integrates a data viewer, data analyzer, and AI-based diagnosis supporter, facilitating comprehensive data presentation, analysis, and early symptom detection. Results: The system's performance was evaluated through diagnostic tests involving medical professionals. This early detection model achieved an accuracy rate of up to 84%, enabling detection up to 3.3 days in advance. In diagnostic tests, medical professionals using the system with the AI-based diagnosis supporter outperformed those using the system without the supporter. Conclusions: Our AI-based PDA diagnostic support system offers a comprehensive solution for medical professionals to accurately diagnose PDA in a timely manner in premature infants. The collaborative integration of medical expertise and technological innovation demonstrated in this study underscores the potential of AI-driven tools in advancing neonatal diagnosis and care.