Development and validation of a multimodal nomogram predicting anxiety and depression in Parkinson’s disease: integrating plasma biomarkers and clinical phenotypes
Aug 2026· Frontiers in Aging Neuroscience· Vol 18· 0 citations· 17 references
Medicine
TL;DR
Combining peripheral plasma NfL levels with standard clinical phenotypes provides an objective, quantifiable, and non-invasive tool for early risk stratification of affective disorders in PD.
Abstract
Introduction Anxiety and depression are prevalent, disabling, yet frequently underdiagnosed non-motor symptoms in Parkinson’s disease (PD). This study aimed to develop and validate a non-invasive model predicting these affective disorders by integrating peripheral blood biomarkers with standardized clinical scales to facilitate early screening. Methods We retrospectively analyzed data from 290 patients with PD, who were randomly allocated into a training cohort (n = 203) and a validation cohort (n = 87). Baseline plasma neurofilament light chain (NfL) levels and clinical phenotypes were assessed. Independent risk factors were determined via multivariate logistic regression analysis to construct the clinical prediction nomogram. Model performance was comprehensively evaluated using the area under the receiver operating characteristic curve (AUC) for discrimination, calibration curves for risk consistency, and decision curve analysis (DCA) for clinical utility. Results Multivariate logistic regression identified plasma NfL, Hoehn and Yahr stage, MMSE score, and MDS-UPDRS Part III score as independent predictors for anxiety and depression in PD patients (all p < 0.05). The established model exhibited high discriminative power, achieving an AUC of 0.94 (95% CI: 0.873–0.964) in the training cohort and 0.84 (95% CI: 0.782–0.879) in the validation cohort. Calibration curves demonstrated excellent consistency between predicted and actual probabilities, and DCA confirmed strong clinical net benefits. Discussion In conclusion, combining peripheral plasma NfL levels with standard clinical phenotypes provides an objective, quantifiable, and non-invasive tool for early risk stratification of affective disorders in PD. This multimodal nomogram effectively expands the therapeutic window for timely personalized psychiatric interventions, potentially improving long-term quality of life and clinical outcomes for PD patients.
Objectives: To develop and validate a questionnaire-based nomogram for predicting individual stroke risk, providing a practical, non-clinical tool for community-level stroke risk assessment without requiring clinical measurements. Methods: Data were derived from the 2024 Korea National Health and Nutrition Examination Survey. Of 6,998 participants, 364 (91 with stroke; 273 without) were included after excluding missing data and applying 1:3 propensity score matching. Logistic regression analyses identified independent predictors, which were incorporated into a nomogram. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and predictive values. Results: Age, poor subjective health status, physician-diagnosed hypertension, and physician-diagnosed dyslipidemia were independently associated with stroke. Stroke risk increased with age, and poor subjective health was associated with substantially higher odds compared with good health. Hypertension and dyslipidemia were also significant predictors. The nomogram demonstrated acceptable discrimination (AUC = 0.706), with a sensitivity of 73.63% and a specificity of 63.74%. Conclusions: In addition to established factors such as age, hypertension, and dyslipidemia, subjective health status may serve as a meaningful indicator of stroke risk. This questionnaire-based nomogram offers a practical, non-invasive approach for risk estimation in community settings and may support early identification and population-level prevention strategies.
Jeong-Eun Kim, Sang-Dol Kim· Journal of Mechanics in Medi...· 0 citations
Parkinson’s disease (PD) is a multisystem neurodegenerative disorder with both central and peripheral manifestations. This study aimed to comprehensively characterize structural and functional alterations in the retina and brain, as well as systemic blood biomarkers, in patients with clinically diagnosed PD compared with healthy controls, using a multimodal imaging approach. Blood-derived biomarkers and OCT data were collected from 29 PD patients and 25 healthy participants over an average interval of 2.7 years. MRI scans were performed using a Philips 1.5 Tesla scanner. Retinal and brain structural and perfusion metrics were analyzed using linear regression models adjusted for age, with statistical significance determined through false discovery rate (FDR) correction. The diagnostic performance was assessed using logistic regression, LASSO-penalized logistic regression model and ROC curve analysis. The study indicated that reduced ALT serum is the only significant hematological marker (p = 0.0253). Structural MRI revealed significant volume reductions in the left amygdala and caudate (p = 0.0241 and 0.0035 respectively); However, these findings necessitate careful interpretation due to limitations in spatial resolution. Perfusion MRI showed lower cerebral blood flow in gray matter and the whole brain (p = 0.02) in PD patients. The best imaging biomarker (PCASL total CBF) achieved an AUC of 0.79. A LASSO-penalized logistic regression model integrating left amygdala volume, left caudate volume, and SGPT achieved a significantly elevated AUC of 0.954, with 100% sensitivity and 86.7% specificity. The integration of central and peripheral biomarkers encompasses complementary aspects of Parkinson’s disease pathology, providing a more comprehensive diagnostic framework than any singular modality.
Background Undergraduate depression is prevalent, yet traditional screening is unidimensional and inefficient. We developed a biopsychosocial risk classification model for the cross-sectional identification of current depressive symptoms. Methods A cross-sectional study enrolled 898 undergraduates from a medical university in Western China (March–June 2024). The participants were randomized to training (n = 719, 80%) and test (n = 179, 20%) sets. Assessments included demographics, somatic symptoms (Somatic Symptom Scale), insomnia severity (Insomnia Severity Index, ISI), and depressive symptoms (Patient Health Questionnaire-9, PHQ-9). To avoid circularity, all PHQ-9 items were excluded from predictors; the total score defined the outcome (≥5). Independent risk factors were identified via univariate and multivariate logistic regression. Three models—random forest, XGBoost, and logistic regression—were developed. Performance was evaluated using discriminative metrics (AUC, accuracy, sensitivity, specificity, PPV, NPV, and F1 score), calibration plots, and decision curve analysis. Internal validation utilized fivefold cross-validation and bootstrap resampling (1,000 iterations). Subgroup analyses stratified the results by gender, grade, and somatic symptom severity. Results The point prevalence of depressive symptoms (PHQ-9 ≥5) was 45.21% (406/898), which was significantly higher in women (OR = 2.98). Multivariate analysis identified severe somatic symptoms (OR = 37.94), moderate somatic symptoms, and social isolation as key independent risk factors. Excluding PHQ-9 items to avoid circularity, the random forest model achieved an AUC of 0.872 (95% CI: 0.841–0.903), outperforming scale-only (ΔAUC = 0.110, p < 0.001) and linear models (ΔAUC = 0.031, p = 0.042). Feature importance consistently highlighted somatic distress, insomnia severity, and lack of close friends over emotional items. Calibration was excellent (Hosmer–Lemeshow p > 0.05), and decision curve analysis supported net clinical benefit (thresholds 0.2–0.9). Conclusion A comprehensive model combining physiological, psychological, and social factors yields excellent cross-sectional discriminative capability and stability for identifying undergraduates currently at risk for depressive symptoms. The proposed three-step clinical pathway (universal screening, targeted re-evaluation, and precision intervention) can facilitate large-scale, early identification in university settings. Due to the cross-sectional design, the term “prediction” is not used in a temporal or causal sense; rather, the model estimates the probability of concurrent depressive symptoms.
Xue Liang, Liu-Yi Lu, Qian Liao et al.· Frontiers in Psychiatry· 0 citations
BACKGROUND
In-stent Restenosis (ISR) represents a major challenge in interventional cardiology, and psychological distress is known to worsen coronary heart disease outcomes. However, the prevalence and determinants of anxiety and depression specifically in ISR patients remain largely uncharacterized. This study aimed to investigate the incidence and independent risk factors of these symptoms and to develop predictive models for their early identification.
METHODS
A single-center retrospective study involving 256 patients with confirmed ISR was conducted. Psychological status was assessed using the Self-Rating Anxiety Scale (SAS) and Self-Rating Depression Scale (SDS). Univariate and multivariate logistic regression analyses were employed to identify independent risk factors. Nomograms were constructed and validated based on these factors, with model performance evaluated by the area under the curve (AUC), calibration plots, and Decision Curve Analysis (DCA).
RESULTS
The prevalence of anxiety and depression symptoms was 37.89% and 42.58%, respectively. Multivariate analysis identified poorer sleep quality (higher Pittsburgh Sleep Quality Index (PSQI) score), lower social support (lower Social Support Rating Scale (SSRS) score), higher New York Heart Association (NYHA) classification (≥Ⅲ), multiple stents (≥2), and suburban/rural residence as independent risk factors for anxiety. For depression, older age, higher PSQI score, lower SSRS score, multiple stents, and advanced Mehran classification (III/IV) were significant predictors. The nomograms demonstrated good predictive accuracy, with AUCs of 0.79 (95% confidence interval (CI): 0.74-0.85) for anxiety and 0.82 (95% CI: 0.76-0.87) for depression, along with good calibration and clinical utility.
CONCLUSIONS
Anxiety symptoms and depressive symptoms are highly prevalent in ISR patients. The developed nomograms, incorporating clinical and psychosocial factors, provide effective tools for individualized risk stratification, facilitating early identification and targeted psychological interventions to improve patient outcomes.
Si-Hui Sun, Xiao-Xian Wu, Lichen Tang et al.· Actas espanolas de psiquiatr...· 0 citations
Abstract Non-motor symptoms, including rapid eye movement sleep behaviour disorder (RBD), depression and anxiety, are common and often co-occurring in patients with Parkinson’s disease. This study aimed to investigate their potential shared neurobiological substrates by integrating structural, functional and neurochemical imaging data. We analysed data from 638 Parkinson’s disease patients from the Parkinson’s Progression Markers Initiative (PPMI), with available 3T T1-weighted MRI scans. RBD, depression and anxiety severity were assessed using validated clinical scales (RBD Screening Questionnaire Score, Geriatric Depression Scale and State-Trait Anxiety Inventory). Voxel-based morphometry (VBM) multivariate regression analyses were performed to identify grey matter (GM) volume loss associated with each clinical symptom. All analyses were rigorously controlled for a comprehensive set of potential confounders, including age, sex, education, disease duration, motor severity and cognitive dysfunction, thereby minimizing confounding effects related to other aspects of the disease. Coordinate-based network mapping was then applied using a large normative resting-state functional connectome (N = 1000), to characterize symptom-specific functional networks based on brain areas functionally connected to the VBM-derived clusters. Finally, spatial correlations between these networks and normative neurotransmitter density maps from PET data were assessed. VBM analyses revealed distinct patterns of GM atrophy across the three symptoms (pFWE<0.05), overlapping in the left middle temporal and right middle frontal gyri. The coordinate-based functional network mapping approach demonstrated that the GM atrophy pattern associated with each symptom (pFWE < 10−6) converged onto brain networks involving several cortical regions and overlapping across symptoms, and with the greatest spatial affinity, among canonical large-scale networks, with the Dorsal and Ventral Attention networks. All three symptom-related networks showed significant alignment with the noradrenaline transporters (NAT) spatial distribution (pFDR < 0.05). Overall, this study proposes a novel conceptual and methodological framework integrating well-established and validated techniques to identify the neuroanatomical bases of specific diseases or symptoms, potentially of interest for future research. Our neuroimaging findings in the large PPMI cohort of early Parkinson’s disease patients demonstrate that the brain networks associated with RBD, depression and anxiety non-motor symptoms were largely overlapping, involved the attention networks and were spatially aligned with the noradrenergic system, suggesting that these symptoms may have shared neurobiological substrates.
Chiara Camastra, Aldo Quattrone, A. Quattrone· Brain Communications· 0 citations
Objectives This study aimed to develop and internally validate a nomogram prediction model for differentiating subacute combined degeneration of the spinal cord (SCD) from other neurological disorders, based on established clinical predictors including a symptom scale score, risk factors, and laboratory indicators. Methods We retrospectively enrolled 80 patients with SCD (SCD group) and 80 patients with other neurological disorders (non-SCD group) treated at Beijing Yanhua Hospital from March 2015 to March 2025. Demographic characteristics, SCD-related risk factors, SCD symptom scale scores, and laboratory indicators were collected. Eight risk factors for vitamin B12 deficiency were integrated into the Risk Load Score of B12 Deficiency (RLSS). The RLSS, total SCD symptom scale score, and serum homocysteine (Hcy) were included as candidate variables. LASSO regression was used for variable compression and selection. The selected variables were entered into multivariate logistic regression to construct the nomogram prediction model. We evaluated the model’s discrimination, calibration, and clinical utility, and performed internal validation using Bootstrap resampling (1,000 Bootstrap resamples). Results LASSO regression identified three non-zero coefficient predictors (total SCD symptom scale score, RLSS, and Hcy) from the seven candidate variables (RLSS, total SCD symptom scale score, Hcy, MCV, age, sex, and disease duration). Multivariate logistic regression showed that RLSS, Hcy, and total SCD symptom scale score were all independent predictors of SCD. The area under the curve (AUC) of the combined model was 0.954. The decrease in the C-index after Bootstrap correction was less than 0.05, indicating good calibration (Hosmer-Lemeshow χ2 = 2.326, p = 0.969; Brier score = 0.095). Decision curve analysis showed significant clinical net benefit across threshold probabilities of 0.1 to 0.8. Conclusion The nomogram model based on total SCD symptom scale score, RLSS, and Hcy demonstrated good discrimination and calibration in differentiating SCD from non-SCD neurological disorders, as confirmed by internal validation. With its simple operation and readily available indicators, this model provides visualized decision support for early clinical identification of SCD. However, external validation is required before it can be recommended for routine use in primary healthcare settings.
Xiao-Fan Zhang, Zhi-Qiang Li, Dan-Dan Liu et al.· Frontiers in Neurology· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
