RESUMEN
Background: Next-generation sequencing liquid biopsy (NGS-LB) for colorectal cancer (CRC) detection and surveillance remains an expensive technology as economies of scale have not yet been realized. Nevertheless, the cost of sequencing has decreased while sensitivity has increased, raising the question of whether cost-effectiveness (CE) has already been achieved from the perspective of European healthcare systems. Objectives: This health economic (HE) modeling study explores the CE of NGS-LB for CRC based on direct treatment costs compared to standard care without liquid biopsy in Spain, France, and Germany. Methods: A structured literature search was used to collect evidence from 2009 to 2020 on the stage-dependent quality of life (quality-adjusted life-years, QALY), efficacy, and total direct treatment costs (TDC) of NGS-LB. A decision-analytic Markov model was developed. Over the remaining lifetime, cumulative life expectancy (LE), TDC, and QALYs were calculated for 60-year-old men and women in CRC stage III with different assumed effects of NGS-LB of 1% or 3% on improved survival and reduced stage progression, respectively. Results: The use of NGS-LB increases LE by 0.19 years in Spanish men (France: 0.19 years, Germany: 0.13 years) and by 0.21 years in Spanish women (France: 0.21 years, Germany: 0.14 years), respectively. The 3% discounted cost per QALY gained was 35,571.95 for Spanish men (France: 31,705.15 , Germany: 37,537.68 ) and 35,435.71 for Spanish women (France: 31,295.57 , Germany: 38,137.08 ) in the scenario with 3% improved survival and reduced disease progression. Compared to the other two countries, Germany has by far the highest TDC, which can amount to >80k euros in the last treatment year. Conclusion: In this explorative HE modeling study, NGS-LB achieves generally accepted CE levels in CRC treatment from the health system perspective in three major European economies under assumptions of small improvements in cancer recurrence and survival. Confirmation of these findings through clinical trials is encouraged.
Is it worthwhile to use next generation liquid biopsy for cancer recurrence detection on patients with colorectal cancer? Colon cancer is common. Worldwide, almost one million people die from it every year. Next Generation Sequencing Liquid Biopsy is a very sensitive technology for detecting cancer cells and their genetic information in the blood. Therefore, it is a good way to detect cancer and to detect early recurrence of a previously treated tumor. This test procedure is not yet used very often. Therefore, it is still expensive. Furthermore, there are still no studies that have demonstrated that and how liquid biopsy can aid doctors and patients after initial treatment. The research team of this study has developed an analytical model to investigate what performance liquid biopsy should have to demonstrate an affordable patient benefit in terms of quality of life, survival and cost per additional quality-adjusted life year gained. To do this, they studied the existing medical literature and many cost studies on colorectal cancer for the countries of Spain, France and Germany to feed their model. Then, they made different assumptions about the performance of liquid biopsy and did calculations. In the process, they also particularly examined the significance of specific influencing factors such as costs or disease progression in so-called sensitivity analyses. As a result, the authors found that there are large differences in treatment costs for colorectal cancer between the three countries Spain, France and Germany. Furthermore, even small improvements in the progression of cancer and the survival of cancer patients lead to the economic efficiency of liquid biopsy for the health care system. However, these are still thought experiments, so the research team of this study says that there should be further clinical trials to assess the impact of liquid biopsy on cancer progression and patient survival by using this technology. By this, one could confirm or contradict the authors' educated assumptions and possibly pave a new way towards medical progress for people with colorectal cancer.
RESUMEN
Introduction: Major depressive disorder (MDD) is the most common mental disorder worldwide, leading to impairment in quality and independence of life. Electroencephalography (EEG) biomarkers processed with machine learning (ML) algorithms have been explored for objective diagnoses with promising results. However, the generalizability of those models, a prerequisite for clinical application, is restricted by small datasets. One approach to train ML models with good generalizability is complementing the original with synthetic data produced by generative algorithms. Another advantage of synthetic data is the possibility of publishing the data for other researchers without risking patient data privacy. Synthetic EEG time-series have not yet been generated for two clinical populations like MDD patients and healthy controls. Methods: We first reviewed 27 studies presenting EEG data augmentation with generative algorithms for classification tasks, like diagnosis, for the possibilities and shortcomings of recent methods. The subsequent empirical study generated EEG time-series based on two public datasets with 30/28 and 24/29 subjects (MDD/controls). To obtain baseline diagnostic accuracies, convolutional neural networks (CNN) were trained with time-series from each dataset. The data were synthesized with generative adversarial networks (GAN) consisting of CNNs. We evaluated the synthetic data qualitatively and quantitatively and finally used it for re-training the diagnostic model. Results: The reviewed studies improved their classification accuracies by between 1 and 40% with the synthetic data. Our own diagnostic accuracy improved up to 10% for one dataset but not significantly for the other. We found a rich repertoire of generative models in the reviewed literature, solving various technical issues. A major shortcoming in the field is the lack of meaningful evaluation metrics for synthetic data. The few studies analyzing the data in the frequency domain, including our own, show that only some features can be produced truthfully. Discussion: The systematic review combined with our own investigation provides an overview of the available methods for generating EEG data for a classification task, their possibilities, and shortcomings. The approach is promising and the technical basis is set. For a broad application of these techniques in neuroscience research or clinical application, the methods need fine-tuning facilitated by domain expertise in (clinical) EEG research.
RESUMEN
BACKGROUND: Alzheimer's disease (AD) is a neurodegenerative disorder with homogenous disease patterns. Neuropathological changes precede symptoms by up to two decades making neuroimaging biomarkers a prime candidate for early diagnosis, prognosis, and patient stratification. OBJECTIVE: The goal of the study was to discern intermediate AD stages and their precursors based on neuroanatomical features for stratifying patients on their progression through different stages. METHODS: Data include grey matter features from 14 brain regions extracted from longitudinal structural MRI and cognitive data obtained from 1,017 healthy controls and AD patients of ADNI. AD progression was modeled with a Hidden Markov Model, whose hidden states signify disease stages derived from the neuroanatomical data. To tie the progression in brain atrophy to a behavioral marker, we analyzed the ADAS-cog sub-scores in the stages. RESULTS: The optimal model consists of eight states with differentiable neuroanatomical features, forming two routes crossing once at a very early point and merging at the final state. The cortical route is characterized by early and sustained atrophy in cortical regions. The limbic route is characterized by early decrease in limbic regions. Cognitive differences between the two routes are most noticeable in the memory domain with subjects from the limbic route experiencing stronger memory impairments. CONCLUSION: Our findings corroborate that more than one pattern of grey matter deterioration with several discernable stages can be identified in the progression of AD. These neuroanatomical subtypes are behaviorally meaningful and provide a door into early diagnosis of AD and prognosis of the disease's progression.