Refine
Year of publication
- 2023 (166) (remove)
Has Fulltext
- yes (166)
Is part of the Bibliography
- no (166)
Keywords
Institute
- Physik (159)
- Frankfurt Institute for Advanced Studies (FIAS) (158)
- Informatik (158)
- Medizin (5)
Background: Biological psychiatry aims to understand mental disorders in terms of altered neurobiological pathways. However, for one of the most prevalent and disabling mental disorders, Major Depressive Disorder (MDD), patients only marginally differ from healthy individuals on the group-level. Whether Precision Psychiatry can solve this discrepancy and provide specific, reliable biomarkers remains unclear as current Machine Learning (ML) studies suffer from shortcomings pertaining to methods and data, which lead to substantial over-as well as underestimation of true model accuracy.
Methods: Addressing these issues, we quantify classification accuracy on a single-subject level in N=1,801 patients with MDD and healthy controls employing an extensive multivariate approach across a comprehensive range of neuroimaging modalities in a well-curated cohort, including structural and functional Magnetic Resonance Imaging, Diffusion Tensor Imaging as well as a polygenic risk score for depression.
Findings Training and testing a total of 2.4 million ML models, we find accuracies for diagnostic classification between 48.1% and 62.0%. Multimodal data integration of all neuroimaging modalities does not improve model performance. Similarly, training ML models on individuals stratified based on age, sex, or remission status does not lead to better classification. Even under simulated conditions of perfect reliability, performance does not substantially improve. Importantly, model error analysis identifies symptom severity as one potential target for MDD subgroup identification.
Interpretation: Although multivariate neuroimaging markers increase predictive power compared to univariate analyses, single-subject classification – even under conditions of extensive, best-practice Machine Learning optimization in a large, harmonized sample of patients diagnosed using state-of-the-art clinical assessments – does not reach clinically relevant performance. Based on this evidence, we sketch a course of action for Precision Psychiatry and future MDD biomarker research.
Purpose: The purpose of the study is to retrospectively evaluate the development and technological progress in local oncological treatments of hepatocellular carcinoma (HCC) by means of ablation techniques like laser interstitial thermal therapy (LITT), microwave ablation (MWA) and transarterial chemoembolization (TACE) in a multimodal application.
Method: This retrospective single-center study uses data generated between 1993 and 2020 (1,045 patients). Therapy results are evaluated using survival rates of Kaplan-Meier estimator, Cox proportional hazard regression and log-rank test.
Results: Median survival times in group LITT (25 patients) are 1.6 years, and, 2.6 years for LITT + TACE (67 patients). For LITT only treatments 1-/3-/5-year survival rates scored 64%, 24% and 20%. Results for combined LITT + TACE treatments were 84%, 37% and 14%. Median survival time in group MWA (227 patients) is 4.5 years. Estimated median survival time for MWA + TACE (108 patients) leads to a median survival time of 2.7 years. In group MWA the 1-/3-/5-year survival rates are 85%, 54%, 45%. Group MWA + TACE shows values of 79%, 41% and 25%. A separate group of 618 patients has been analyzed with TACE as monotherapy. Median survival time of 1 year was estimated in this group. 1-/3-/5-year survival rates are 48%, 15% and 8%. - Cox regression analysis showed that the different treatment methods are statistically significant predictors for survival of patients.
Conclusions: Treatments with MWA resulted in best median survival rates, followed by MWA + TACE in combination. Survival rates of MWA only are significantly higher vs. LITT, vs. LITT + TACE and vs. TACE monotherapy.
Epigenetic neural glioblastoma enhances synaptic integration and predicts therapeutic vulnerability
(2023)
Neural-tumor interactions drive glioma growth as evidenced in preclinical models, but clinical validation is nascent. We present an epigenetically defined neural signature of glioblastoma that independently affects patients survival. We use reference signatures of neural cells to deconvolve tumor DNA and classify samples into low- or high-neural tumors. High-neural glioblastomas exhibit hypomethylated CpG sites and upregulation of genes associated with synaptic integration. Single-cell transcriptomic analysis reveals high abundance of stem cell-like malignant cells classified as oligodendrocyte precursor and neural precursor cell-like in high-neural glioblastoma. High-neural glioblastoma cells engender neuron-to-glioma synapse formation in vitro and in vivo and show an unfavorable survival after xenografting. In patients, a high-neural signature associates with decreased survival as well as increased functional connectivity and can be detected via DNA analytes and brain-derived neurotrophic factor in plasma. Our study presents an epigenetically defined malignant neural signature in high-grade gliomas that is prognostically relevant.