Citations

Clear

4093 citation(s) found for "Yu, Jonathan".

Alzheimer’s disease biomarkers of amyloid and tau influence white matter neurite alterations in dementia with Lewy bodies: a NODDI study
Przybelski, Scott A. , Lesnick, Timothy G. , Raghavan, Sheelakumari , Jain, Manoj , Miyagawa, Toji , Forsberg, Leah K. , Fields, Julie A. , Savica, Rodolfo , Graff‐Radford, Jonathan, Graff‐Radford, Neill R., Petersen, Ronald C. , Lowe, Val J. , Mak, Elijah , Reid, Robert I. , Schwarz, Christopher G. , Senjem, Matthew L. , Vemuri, Prashanthi , Jack, Clifford R. , Min, Hoon-Ki Paul , Graff‐Radford, Jonathan , Jones, David T. , Botha, Hugo , Louis, Erik K. St. , Knopman, David S. , Ramanan, Vijay K. , Graff‐Radford, Neill R. , Ferman, Tanis J. , Boeve, Bradley F. , O'Brien, John Tiernan , Kantarci, Kejal

Mayo Clinic

Alzheimer's & Dementia | December 25, 2023 | Volume: 19 | Issue: S10 | Pages: No page available

10.1002/alz.081739 Get It

AbstractBackgroundCo‐morbid Alzheimer’s disease (AD) pathology in the form of amyloid‐ß plaques and tau neurofibrillary tangles are frequently observed in people with probable dementia with Lewy bodies (DLB). Neurite Orientation Dispersion and Density Imaging (NODDI) is an emerging technique to characterize white matter (WM) tissue microstructure, although NODDI alterations and associations with AD biomarkers remain undefined in DLB. The objectives of this study are to compare NODDI and DTI parameters between DLB and controls and (ii) evaluate the pattern of DTI and NODDI changes associated with amyloid and tau deposition.MethodConsecutive patients within the DLB spectrum (n = 45), including probable DLB (n = 32) and probable Mild Cognitive Impairment with Lewy bodies (MCI‐LB) (n = 13) from the Mayo Clinic ADRC underwent multi‐shell diffusion MRI, [18F]‐Flortaucipir and [11C]‐PiB PET. A comparison group of 45 age‐ and gender‐matched clinically unimpaired controls (CU) was included. Voxelwise non‐parametric permutation models were used to determine pair‐wise group differences and assess the associations of AD biomarkers with fractional anisotropy (FA), mean diffusivity (MD), tissue‐weighted neurite density index (tNDI; NDI x (1 – Free water fraction)) and orientation dispersion index (ODI), controlling for age. Complementary analyses were performed using regions‐of‐interest (ROI) obtained from the JHU atlas.ResultCompared to CU, the DLB spectrum group exhibited widespread decreases in FA and tNDI and increases in MD and ODI, with the most pronounced effects in the cingulum bundles, uncinate, inferior and superior longitudinal fasciculi (Fig. 1). Greater [18F]‐Flortaucipir uptake was also associated with lower FA and tNDI, and higher MD and ODI in the DLB spectrum compared to CU, independently of age and [11C]‐PiB uptake (Fig. 2). In contrast, no associations were found between [11C]‐PiB uptake and any of the DTI or NODDI parameters. Complementary ROI analyses corroborated these findings.ConclusionWidespread loss of WM integrity was observed on DTI and NODDI in probable DLB and prodromal DLB. These findings were associated with greater cortical tau, but not with amyloid‐ß deposition. Although alpha‐synuclein pathology underlies the loss of WM integrity in DLB, amyloid‐independent tau pathology may also be an important influence on white matter integrity within the DLB spectrum.
Comparing approaches based on the global functional organization of the brain versus local connectivity to predict tau‐PET across the Alzheimer’s disease phenotypic spectrum
Dicks, Ellen , Barnard, Leland R , Lee, Jeyeon , Sintini, Irene , Gunter, Jeffrey L. , Kamykowski, Michael G. , Graff‐Radford, Jonathan , Fields, Julie A. , Lowe, Val J. , Whitwell, Jennifer L. , Josephs, Keith A. , Petersen, Ronald C. , Corriveau‐Lecavalier, Nick , Botha, Hugo , Schumacher, Julia , Ramanan, Vijay K. , Machulda, Mary M. , Boeve, Bradley F. , Kantarci, Kejal , Knopman, David S. , Whitwell, Jennifer L. , Jack, Clifford R. , Jones, David T.

Mayo Clinic

Alzheimer's & Dementia | December 25, 2023 | Volume: 19 | Issue: S10 | Pages: No page available

10.1002/alz.081730 Get It

AbstractBackgroundPredictive models of tau‐PET accumulation have largely relied on the functional connectome to estimate its spatial patterns in Alzheimer’s disease (AD). Patterns of global functional organization represent a promising avenue as they encapsulate many biological properties relevant to neurodevelopment, cognition and degeneration. We compared approaches based on local connectivity (from task‐free fMRI) and global organization (from FDG‐PET) to predict regional tau‐PET across AD phenotypes.MethodWe included 430 cognitively unimpaired (CU) individuals (214 A+T‐, 216 A+T+) and 62 amnestic mild cognitive impairment (aMCI), 64 amnestic AD, 21 dysexecutive AD (dAD), 41 logopenic progressive aphasia (LPA) and 49 posterior cortical atrophy (PCA) patients (all A+T+) from the Alzheimer’s Disease Research Center, Mayo Clinic Study of Aging, and Neurodegenerative Research Groups (referred to as “Mayo cohort”). The connectivity approach consisted of assessing the relationship between a region’s tau level and its functional connectivity to the region of highest tau (epicenter). The global organization approach consisted of 1) performing a principal component analysis on 3000 FDG‐PET images that did not overlap with the Mayo cohort, 2) projecting FDG‐PET images of the Mayo cohort onto the low‐dimensional space generated in Step 1 and extracting corresponding weighted values across the first 100 components, 3) using these weighted values as predictors of regional tau‐PET in a linear model and determining optimal parameters based on predicted R2 values, and 4) using the parameters from the model built in Step 3 to predict tau‐PET in the ADNI cohort (n = 86) (Fig.2).ResultThe connectivity‐based approach yielded adjusted R2 values ranging from 0.19‐0.45 across diagnostic groups (Fig.1). The global organization approach yielded averaged adjusted R2 and predicted R2 values of 0.71 and 0.63, respectively, in the Mayo cohort. Out‐of‐sample median R2 in the ADNI cohort was 0.41 (range 0.10‐0.60) (Fig.3).ConclusionAn unbiased approach based on the global functional organization of the brain and using an imaging modality widely used in clinical settings outperformed a connectome‐based one to predict regional tau‐PET across the AD phenotypic spectrum. Patterns of tau accumulation may better relate to the large‐scale physiology of the brain underlying specific mental functions rather than local connectivity factors.
NODDI May Be More Sensitive to Neurodegenerative Changes Than Structural MRI
Yu, Xi , Gebre, Robel K , Przybelski, Scott A. , Raghavan, Sheelakumari , Lesnick, Timothy G. , Lowe, Val J. , Petersen, Ronald C. , Graff‐Radford, Jonathan, Reid, Robert I. , Machulda, Mary M. , Knopman, David S. , Kantarci, Kejal , Graff‐Radford, Jonathan , Jack, Clifford R. , Vemuri, Prashanthi

Mayo Clinic

Alzheimer's & Dementia | December 25, 2023 | Volume: 19 | Issue: S10 | Pages: No page available

10.1002/alz.081716 Get It

AbstractBackgroundNeurite orientation dispersion and density imaging (NODDI) measures from diffusion MRI provide information about tissue microstructure. Our goal was to compare the sensitivity of NODDI to structural MRI (sMRI) in capturing neurodegenerative changes in the gray matter due to aging and dementia.MethodWe included 815 participants [644 cognitively unimpaired (CU), 103 MCI, 68 AD] from the Mayo Clinic Study of Aging (MCSA) and Mayo ADRC with sMRI and multi‐shell diffusion MRI. We assessed gray matter volumes scaled by head size and cortical thicknesses from sMRI and neurite density index (NDI) and isotropic volume fraction (ISOVF) from NODDI. Pairwise Spearman correlations were calculated between imaging measures and Tau‐PET SUVRs in Braak I‐II, III‐IV, and V‐VI regions of interest (ROI) in participants = 60 years. Separate multivariable linear regression models were fit for the prediction of brain age using sMRI and NODDI in 515 CU participants. The predicted age gaps were calculated as chronological age minus predicted age in the remaining participants. We compared age gaps computed by sMRI and NODDI using disease surrogates (APOE4 genotype, AD pathologies via PET, WMH via FLAIR‐MRI, vascular risk, cognition via MMSE).ResultBraak ROIs, sMRI, and NODDI measures were correlated. The correlations between ISOVF and Tau‐PET SUVRs were stronger than correlations between NDI, volume, and thickness and Tau‐PET SUVR (Fig.1). MMSE was more associated with ISOVF than Tau‐PET and other imaging measures. The sMRI regression models had a higher mean absolute error (MAE) of 4.13 years than NODDI models with an MAE of 4.02 years. The NODDI model better predicted age gap separation between CU, MCI, and AD compared to the sMRI model (Fig.2). The NODDI predicted age gap showed stronger correlations with global amyloid‐PET SUVR, meta‐ROI Tau‐PET SUVR, CMC, APOE4, and MMSE (Fig. 3).ConclusionNODDI, especially ISOVF, had stronger correlations with MMSE and Tau‐PET SUVRs across all Braak ROIs. The brain age prediction model trained using NODDI was more sensitive in detecting neurodegeneration changes than sMRI based on associations with disease surrogates. Our work suggests that NODDI in gray matter may be a more sensitive surrogate of neurodegeneration compared to sMRI.
Default mode network sub‐systems connectivity in atypical Alzheimer’s disease
Sintini, Irene , Radford, Jonathan Graff, Martin, Peter R. , Gunter, Jeffrey L. , Petersen, Ronald C. , Lowe, Val J. , Josephs, Keith A. , Whitwell, Jennifer L. , Corriveau‐Lecavalier, Nick , Jones, David T. , Singh, Neha Atulkumar , Botha, Hugo , Machulda, Mary M. , Schwarz, Christopher G. , Jack, Clifford R.

Mayo Clinic

Alzheimer's & Dementia | December 25, 2023 | Volume: 19 | Issue: S10 | Pages: No page available

10.1002/alz.081617 Get It

AbstractBackgroundDisruption of default mode network (DMN) connectivity is common in Alzheimer’s disease. We investigated cross‐sectional and one‐year longitudinal changes in DMN sub‐systems in atypical clinical presentations of AD, in relation to age and tau.MethodSixty‐four amyloid‐positive atypical AD (Aty‐AD) patients diagnosed with posterior cortical atrophy (n = 35) or logopenic progressive aphasia (n = 29) were recruited by the Neurodegenerative Research Group. Patients underwent structural and resting‐state functional MRI, and [18F]flortaucipir PET at baseline and one‐year follow‐up. 140 amyloid‐negative cognitively unimpaired (CU) individuals from the Mayo Clinic Study of Aging were included as controls. Global tau SUVR was calculated in a meta‐ROI including parietal, temporal, and occipital regions. DMN connectivity was calculated in native space for posterior (pDMN), ventral (vDMN), anterior ventral (avDMN) and anterior dorsal (adDMN) DMN sub‐systems using the dual regression method. A global measure of DMN connectivity, the Network Failure Quotient (NFQ), was calculated as (vDMN_to_pDMN+ adDMN_to_pDMN)/(pDMN+vDMN). Linear mixed‐effects models were computed for each DMN connectivity measure, including diagnosis (Aty‐AD, CU), age, time and their interaction, and a per‐person random effect. SPM paired t‐tests were run to compare baseline and follow‐up images in Aty‐AD and CU separately. Linear mixed‐effect models were run in the Aty‐AD cohort only to investigate the effect of global baseline tau SUVR on each DMN connectivity measure.ResultMixed‐effects models showed evidence of lower cross‐sectional pDMN and higher adDMN connectivity in Aty‐AD relative to CU, with no significant time effects (Fig. 1). While connectivity in all DMN sub‐systems declined with age in CU, connectivity was higher in older Aty‐AD patients relative to younger, particularly in vDMN and pDMN. A similar trend was observed for NFQ, which was significantly higher in Aty‐AD, with a negative age effect (Fig. 1). In Aty‐AD, voxel‐based analyses showed moderate evidence of decline in vDMN connectivity and increase in avDMN connectivity over time (Fig. 2). Greater baseline global tau SUVR was associated with lower vDMN connectivity, cross‐sectionally and longitudinally (Fig. 3).ConclusionDMN connectivity was altered in Aty‐AD, with strongest alterations in younger patients. The vDMN declined over time, suggesting a shift in DMN connectivity with disease progression that was likely related to tau pathology.
Comparison of longitudinal rates of atrophy and tau accumulation between posterior cortical atrophy and logopenic progressive aphasia
Sintini, Irene , Radford, Jonathan Graff, Lowe, Val J. , Josephs, Keith A. , Whitwell, Jennifer L. , Machulda, Mary M. , Singh, Neha Atulkumar , Carlos, Arenn F. , Schwarz, Christopher G. , Senjem, Matthew L. , Jack, Clifford R.

Mayo Clinic

Alzheimer's & Dementia | December 25, 2023 | Volume: 19 | Issue: S10 | Pages: No page available

10.1002/alz.081612 Get It

AbstractBackgroundPosterior cortical atrophy (PCA) and logopenic progressive aphasia (LPA) are atypical variants of Alzheimer’s disease which typically show different cross‐sectional patterns of atrophy and tau deposition. Patterns of atrophy remain distinct longitudinally. A direct comparison of rates of atrophy and tau accumulation between these syndromes has not yet been reported.MethodWe evaluated 20 PCA and 20 LPA patients; all were amyloid‐positive on [11C]PiB‐PET. Structural MRI and tau‐PET were performed at baseline and one‐year follow‐up. Annualized rates of change in grey matter volume (log Jacobians from tensor‐based morphometry) and flortaucipir‐PET SUVRs were calculated at the lobar level. A global tau SUVR was calculated using parietal, temporal, and occipital regions. Lobar rates were compared between PCA and LPA with linear models, accounting for education, sex, age, baseline global tau SUVR (for tau‐PET), with significance set at p = 0.05. SPM voxel‐level comparisons were performed, with the same covariates, with significance set at p = 0.001.ResultGroups did not differ in age, Apoe status, baseline global tau SUVR or whole brain volume, or their annualized rates of change. LPA had shorter disease duration. In the lobar models, PCA had faster rates of atrophy in the occipital lobe and there were no significant differences on rates of tau accumulation, but a trend for LPA having faster rates of tau accumulation in all lobes. Baseline global tau SUVR was negatively associated with rate of tau accumulation in parietal and temporal lobes. Age was negatively associated with rates of tau accumulation in frontal, temporal and occipital lobes and with rates of atrophy in frontal and parietal lobes. Voxel‐level analysis confirmed these results, with PCA showing faster rates of occipital atrophy, and LPA showing subtle evidence for diffuse faster rates of tau accumulation (Figure 1).ConclusionLongitudinal patterns of neuroimaging abnormalities differ between PCA and LPA, although with divergent results for tau accumulation and atrophy that may reflect differences in disease stage. Rates of change are strongly influenced by age and severity of baseline tau, with faster rates of tau accumulation in patients with younger age and lower baseline tau deposition.
Behavioral and Neuropsychiatric Differences Across Two Atypical Alzheimer’s Disease Variants: Logopenic Progressive Aphasia and Posterior Cortical Atrophy
Robinson, Carling G. , Coleman, Tia, Singh, Neha Atulkumar , Pham, Nha Trang Thu, Graff‐Radford, Jonathan , Whitwell, Jennifer L. , Josephs, Keith A. , Singh, Neha Atulkumar , Buciuc, Marina , Machulda, Mary M. , Whitwell, Jennifer L.

Mayo Clinic

Journal of Alzheimer’s Disease | December 22, 2023 | Volume: 97 | Issue: 2 | Pages: 895-908

10.3233/jad-230652 | PMID 38143349 Get It

Background: Posterior cortical atrophy (PCA) and logopenic progressive aphasia (LPA) are two common atypical Alzheimer’s disease (AD) variants. Little is known about behavioral and neuropsychiatric symptoms or activities of daily living (ADLs) in PCA and LPA, and whether they differ across syndromes. Objective: To characterize the behavioral and neuropsychiatric profiles and ADLs of PCA and LPA and compare presence/absence and severity of symptoms between syndromes. Methods: Seventy-eight atypical AD patients, 46 with PCA and 32 with LPA, completed the Neuropsychiatric Inventory Questionnaire (NPI-Q) and Cambridge Behavioral Inventory-Revised (CBI-R) at baseline and longitudinally over-time. Mann-Whitney U and Fisher’s Exact Tests assessed for differences in symptoms between the two syndromes with significance set at p ≤0.01. To eliminate demographic differences as confounders the groups were matched, and differences reanalyzed. Results: PCA were younger at onset ( p = 0.006), at time of baseline assessment ( p = 0.02) and had longer disease duration ( p = 0.01). Neuropsychiatric symptoms were common in PCA and LPA, although more common and severe in PCA. At baseline, PCA had a higher NPI-Q total score ( p = 0.01) and depression subscore ( p = 0.01) than LPA. Baseline total CBI-R scores were also higher in PCA than LPA ( p = 0.001) with PCA having worse scores in all 10 CBI-R categories. Longitudinally, there was no difference between groups on the NPI-Q. However, on the CBI-R, PCA had faster rates of worsening on self-grooming ( p = 0.01) and self-dressing ( p = 0.01) compared to LPA. Conclusions: Behavioral and neuropsychiatric symptoms are common in PCA and LPA although these symptoms are more common and severe in PCA.
Identification of Clinical Drivers of Left Atrial Enlargement Through Genomics of Left Atrial Size
Agrawal, Vineet , Manouchehri, Ali , Shi, Mingjian , Bagheri, Minoo , Gupta, Deepak K. , Kullo, Iftikhar J. , Luo, Yuan , McNally, Elizabeth M. , Puckelwartz, Megan J. , Wells, Quinn S. , Shi, Mingjian , Bagheri, Minoo , Gupta, Deepak K , Kullo, Iftikhar J , Luo, Yuan , McNally, Elizabeth M , Puckelwartz, Megan J , Ferguson, Jane F , Wells, Quinn S , Mosley, Jonathan D , Vaitinadin, Nataraja Sarma , Ferguson, Jane F.

Mayo Clinic

Circulation: Heart Failure | December 21, 2023 | Volume: 17 | Issue: 1 | Pages: No page available

10.1161/circheartfailure.123.010557 | PMID 38126226 Get It

BACKGROUND: Greater left atrial size is associated with a higher incidence of cardiovascular disease and mortality, but the full spectrum of diagnoses associated with left atrial enlargement in sex-stratified clinical populations is not well known. Our study sought to identify genetic risk mechanisms affecting left atrial diameter (LAD) in a clinical cohort. METHODS: Using Vanderbilt deidentified electronic health record, we studied 6163 females and 5993 males of European ancestry who had at least 1 LAD measure and available genotyping. A sex-stratified polygenic score was constructed for LAD variation and tested for association against 1680 International Classification of Diseases code–based phenotypes. Two-sample univariable and multivariable Mendelian randomization approaches were used to assess etiologic relationships between candidate associations and LAD. RESULTS: A phenome-wide association study identified 25 International Classification of Diseases code–based diagnoses in females and 11 in males associated with a polygenic score of LAD (false discovery rate q<0.01), 5 of which were further evaluated by Mendelian randomization (waist circumference [WC], atrial fibrillation, heart failure, systolic blood pressure, and coronary artery disease). Sex-stratified differences in the genetic associations between risk factors and a polygenic score for LAD were observed (WC for females; heart failure, systolic blood pressure, atrial fibrillation, and WC for males). By multivariable Mendelian randomization, higher WC remained significantly associated with larger LAD in females, whereas coronary artery disease, WC, and atrial fibrillation remained significantly associated with larger LAD in males. CONCLUSIONS: In a clinical population, we identified, by genomic approaches, potential etiologic risk factors for larger LAD. Further studies are needed to confirm the extent to which these risk factors may be modified to prevent or reverse adverse left atrial remodeling and the extent to which sex modifies these risk factors.
Incidence of injury and illness among paediatric Team USA athletes competing in the 2020 Tokyo and 2022 Beijing Olympic and Paralympic Games
Post, Eric G. , Anderson, Travis , Shilt, Jeffrey S. , Dugan, Eric L. , Clark, Stephanie C., Larson, Emily G., Noble-Taylor, Kayle E, Donaldson, Amber , Finnoff, Jonathan T. , Donaldson, Amber T , Finnoff, Jonathan T , Adams, William M , Anderson, Travis , Noble-Taylor, Kayle E., Robinson, David M. , Adams, William M.

Mayo Clinic

BMJ Open Sport & Exercise Medicine | December 20, 2023 | Volume: 9 | Issue: 4 | Pages: e001730

10.1136/bmjsem-2023-001730 | PMID 38143720 Get It

Objective To describe the incidence of injuries and illnesses among paediatric Team USA athletes competing in the Tokyo 2020 Olympic and Paralympic Games, and the 2022 Beijing Olympic and Paralympic Games. Methods An electronic medical record system documented all injuries and illnesses that occurred while competing in the four Games periods. Incidence (IR) with 95% CI per 1000 athlete days were calculated for both injuries and illnesses. Incidence rate ratios (IRR) were calculated to compare injury and illness rates based on age (paediatric vs non-paediatric) sex, Games period and sport type. Results Two hundred paediatric athletes (age range, 15–21 years) competed across the four Games periods, representing 16.1% of all Team USA athletes. The overall injury IR (95% CI) was 13.4 (9.8 to 18.1), and the overall illness IR was 5.5 (3.3 to 8.7). There were no differences in incidence between paediatric and non-paediatric athletes for either injury (IRR (95% CI): 0.9 (0.6 to 1.2)) or illness (IRR (95% CI): 0.9 (0.5 to 1.5)). Female paediatric athletes were more likely to sustain an injury compared with male paediatric athletes (IRR (95% CI): 2.4 (1.1 to 5.3)). The most common mechanism of injury was gradual onset (IR, 4.3 (2.3 to 7.2)), and injuries most commonly occurred during practices (IR, 7.0 (4.5 to 10.5)). Conclusion Paediatric athletes account for a substantial proportion of Team USA athletes. It is essential that paediatric sports medicine experts are included in the medical team given that paediatric Team USA athletes are just as likely as their adult teammates to sustain an injury or illness.
Abstract 19083: AI-Enabled ECG Detection of Atrial and Ventricular Septal Defects in Pediatric Patients
Greason, Grace , O’Sullivan, Donnchadh , Anjewierden, Scott , Lopez‐Jimenez, Francisco, Friedman, Paul A. , Anderson, Jason, Kashou, Anthony H. , Eidem, Benjamin W., Johnson, Jonathan N. , Madhavan, Malini , Attia, Zachi I. , López-Jiménez, Francisco , Noseworthy, Peter A. , Anderson, Jason, Niaz, Talha

Mayo Clinic

Circulation | December 19, 2023 | Volume: 148 | Issue: Suppl_1 | Pages: No page available

10.1161/circ.148.suppl_1.19083 Get It

Background: Atrial septal defects (ASD) and ventricular septal defects (VSD) are among the most common forms of congenital heart disease (CHD). Early detection and intervention for these defects are crucial to prevent complications. Given advancements in AI technology, the development of AI-enabled ECG models for detecting these defects is of significant interest. Aims: This study aimed to create AI models using pediatric ECG data for the detection of ASD, VSD, and a combined model detecting either ASD or VSD. Methods: We analyzed a dataset of 7,795 pediatric patients from Mayo Clinic who had undergone echocardiography between 2002 and 2022, with corresponding 10-second, 12-lead surface ECGs taken within 14 days of echocardiography. This dataset included 259 patients with ASDs and 139 patients with VSDs (single or multiple). The control group was comprised of 7,397 patients without significant or complex CHD. For cases and controls, we included patients with all forms of electrocardiographic abnormalities and those with valvular lesions who had less than moderate stenosis or regurgitation. The dataset was divided into training, validation, and testing subsets to develop convolutional neural network (CNN) models for ASD, VSD, and either ASD or VSD detection. Results: Our ASD and VSD detection models achieved test AUCs of 0.82 (95% CI 0.76, 0.88) and 0.80 (95% CI 0.70, 0.90), respectively. Meanwhile, a combined model that detected either ASD or VSD demonstrated a test AUC of 0.81 (95% CI, 0.76, 0.86), sensitivity of 0.73, specificity of 0.76, PPV of 0.14, and NPV of 0.98 (Figure 1). Conclusions: AI-enabled ECG models demonstrate promising performance in detecting ASD and VSD in pediatric patients. A combined model that detects either ASD or VSD also shows robust results. Future research should focus on multi-center validation of these models, refining their diagnostic capacities, and investigating their potential for early intervention in CHDs.