Refine
Document Type
- Article (20)
- Working Paper (4)
- Bachelor Thesis (1)
- Conference Proceeding (1)
- Master's Thesis (1)
- Preprint (1)
- Report (1)
Has Fulltext
- yes (29) (remove)
Is part of the Bibliography
- no (29) (remove)
Keywords
- machine learning (29) (remove)
Institute
- Medizin (9)
- Wirtschaftswissenschaften (7)
- Center for Financial Studies (CFS) (4)
- Biochemie, Chemie und Pharmazie (3)
- Buchmann Institut für Molekulare Lebenswissenschaften (BMLS) (2)
- Frankfurt Institute for Advanced Studies (FIAS) (2)
- House of Finance (HoF) (2)
- Psychologie (2)
- Biochemie und Chemie (1)
- Biodiversität und Klima Forschungszentrum (BiK-F) (1)
- Biowissenschaften (1)
- Exzellenzcluster Die Herausbildung normativer Ordnungen (1)
- Gesellschaftswissenschaften (1)
- Informatik (1)
- Informatik und Mathematik (1)
- Institute for Monetary and Financial Stability (IMFS) (1)
- MPI für empirische Ästhetik (1)
- Physik (1)
- Senckenbergische Naturforschende Gesellschaft (1)
- Sustainable Architecture for Finance in Europe (SAFE) (1)
Scores to identify patients at high risk of progression of coronavirus disease (COVID-19), caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), may become instrumental for clinical decision-making and patient management. We used patient data from the multicentre Lean European Open Survey on SARS-CoV-2-Infected Patients (LEOSS) and applied variable selection to develop a simplified scoring system to identify patients at increased risk of critical illness or death. A total of 1946 patients who tested positive for SARS-CoV-2 were included in the initial analysis and assigned to derivation and validation cohorts (n = 1297 and n = 649, respectively). Stability selection from over 100 baseline predictors for the combined endpoint of progression to the critical phase or COVID-19-related death enabled the development of a simplified score consisting of five predictors: C-reactive protein (CRP), age, clinical disease phase (uncomplicated vs. complicated), serum urea, and D-dimer (abbreviated as CAPS-D score). This score yielded an area under the curve (AUC) of 0.81 (95% confidence interval [CI]: 0.77–0.85) in the validation cohort for predicting the combined endpoint within 7 days of diagnosis and 0.81 (95% CI: 0.77–0.85) during full follow-up. We used an additional prospective cohort of 682 patients, diagnosed largely after the “first wave” of the pandemic to validate the predictive accuracy of the score and observed similar results (AUC for the event within 7 days: 0.83 [95% CI: 0.78–0.87]; for full follow-up: 0.82 [95% CI: 0.78–0.86]). An easily applicable score to calculate the risk of COVID-19 progression to critical illness or death was thus established and validated.
With the ongoing loss of global biodiversity, long-term recordings of species distribution patterns are increasingly becoming important to investigate the causes and consequences for their change. Therefore, the digitization of scientific literature, both modern and historical, has been attracting growing attention in recent years. To meet this growing demand the Specialised Information Service for Biodiversity Research (BIOfid) was launched in 2017 with the aim of increasing the availability and accessibility of biodiversity information. Closely tied to the research community the interdisciplinary BIOfid team is digitizing data sources of biodiversity related research and provides a modern and professional infrastructure for hosting and sharing them. As a pilot project, German publications on the distribution and ecology of vascular plants, birds, moths and butterflies covering the past 250 years are prioritized. Large parts of the text corpus defined in accordance with the needs of the relevant German research community have already been transferred to a machine-readable format and will be publicly accessible soon. Software tools for text mining, semantic annotation and analysis with respect to the current trends in machine learning are developed to maximize bioscientific data output through user-specific queries that can be created via the BIOfid web portal (https://www.biofid.de/). To boost knowledge discovery, specific ontologies focusing on morphological traits and taxonomy are being prepared and will continuously be extended to keep up with an ever-expanding volume of literature sources.
Human functional brain connectivity can be temporally decomposed into states of high and low cofluctuation, defined as coactivation of brain regions over time. Rare states of particularly high cofluctuation have been shown to reflect fundamentals of intrinsic functional network architecture and to be highly subject-specific. However, it is unclear whether such network-defining states also contribute to individual variations in cognitive abilities – which strongly rely on the interactions among distributed brain regions. By introducing CMEP, a new eigenvector-based prediction framework, we show that as few as 16 temporally separated time frames (< 1.5% of 10min resting-state fMRI) can significantly predict individual differences in intelligence (N = 263, p < .001). Against previous expectations, individual’s network-defining time frames of particularly high cofluctuation do not predict intelligence. Multiple functional brain networks contribute to the prediction, and all results replicate in an independent sample (N = 831). Our results suggest that although fundamentals of person-specific functional connectomes can be derived from few time frames of highest connectivity, temporally distributed information is necessary to extract information about cognitive abilities. This information is not restricted to specific connectivity states, like network-defining high-cofluctuation states, but rather reflected across the entire length of the brain connectivity time series.
Analysis of machine learning prediction quality for automated subgroups within the MIMIC III dataset
(2023)
The motivation for this master’s thesis is to explore the potential of predictive data analytics in the field of medicine. For this, the MIMIC-III dataset offers an extensive foundation for the construction of prediction models, including Random Forest, XGBOOST, and deep learning networks. These models were implemented to forecast the mortality of 2,655 stroke patients.
The first part of the thesis involved conducting a comprehensive data analysis of the filtered MIMIC-III dataset.
Subsequently, the effectiveness and fairness of the predictive models were evaluated. Although the performance levels of the developed models did not match those reported in related research, their potential became evident. The results obtained demonstrated promising capabilities and highlighted the effectiveness of the applied methodologies. Moreover, the feature relevance within the XGBOOST model was examined to increase model explainability.
Finally, relevant subgroups were identified to perform a comparative analysis of the prediction performance across these subgroups. While this approach can be regarded as a valuable methodology, it was not possible to investigate underlying reasons for potential unfairness across clusters. Inside the test data, not enough instances remained per subgroup for further fairness or feature relevance analysis.
In conclusion, the implementation of an alternative use case with a higher patient count is recommended.
The code for this analysis is made available via a GitHub repository and includes a frontend to visualize the results.
Bayesian inference is ubiquitous in science and widely used in biomedical research such as cell sorting or “omics” approaches, as well as in machine learning (ML), artificial neural networks, and “big data” applications. However, the calculation is not robust in regions of low evidence. In cases where one group has a lower mean but a higher variance than another group, new cases with larger values are implausibly assigned to the group with typically smaller values. An approach for a robust extension of Bayesian inference is proposed that proceeds in two main steps starting from the Bayesian posterior probabilities. First, cases with low evidence are labeled as “uncertain” class membership. The boundary for low probabilities of class assignment (threshold 𝜀
) is calculated using a computed ABC analysis as a data-based technique for item categorization. This leaves a number of cases with uncertain classification (p < 𝜀
). Second, cases with uncertain class membership are relabeled based on the distance to neighboring classified cases based on Voronoi cells. The approach is demonstrated on biomedical data typically analyzed with Bayesian statistics, such as flow cytometric data sets or biomarkers used in medical diagnostics, where it increased the class assignment accuracy by 1–10% depending on the data set. The proposed extension of the Bayesian inference of class membership can be used to obtain robust and plausible class assignments even for data at the extremes of the distribution and/or for which evidence is weak.
Phenotypical screening is a widely used approach in drug discovery for the identification of small molecules with cellular activities. However, functional annotation of identified hits often poses a challenge. The development of small molecules with narrow or exclusive target selectivity such as chemical probes and chemogenomic (CG) libraries, greatly diminishes this challenge, but non-specific effects caused by compound toxicity or interference with basic cellular functions still pose a problem to associate phenotypic readouts with molecular targets. Hence, each compound should ideally be comprehensively characterized regarding its effects on general cell functions. Here, we report an optimized live-cell multiplexed assay that classifies cells based on nuclear morphology, presenting an excellent indicator for cellular responses such as early apoptosis and necrosis. This basic readout in combination with the detection of other general cell damaging activities of small molecules such as changes in cytoskeletal morphology, cell cycle and mitochondrial health provides a comprehensive time-dependent characterization of the effect of small molecules on cellular health in a single experiment. The developed high-content assay offers multi-dimensional comprehensive characterization that can be used to delineate generic effects regarding cell functions and cell viability, allowing an assessment of compound suitability for subsequent detailed phenotypic and mechanistic studies.
When we browse via WiFi on our laptop or mobile phone, we receive data over a noisy channel. The received message may differ from the one that was sent originally. Luckily it is often possible to reconstruct the original message but it may take a lot of time. That’s because decoding the received message is a complex problem, NP-hard to be exact. As we continue browsing, new information is sent to us in a high frequency. So if lags are to be avoided and as memory is finite, there is not much time left for decoding. Coding theory tackles this problem by creating models of the channels we use to communicate and tailor codes based on the channel properties. A well known family of codes are Low-Density Parity-Check codes (LDPC codes), they are widely used in standards like WiFi and DVB-T2. In practical settings the complexity of decoding a received message can be heavily reduced by using LDPC codes and approximative decoding algorithms. This thesis lays out the basic construction of LDPC codes and a proper decoding using the sum-product algorithm. On this basis a neural network to improve decoding is introduced. Therefore the sum-product algorithm is transformed into a neural network decoder. This approach was first presented by Nachmani et al. and treated in detail by Navneet Agrawal in 2017. To find out how machine learning can improve the codes, the bit error rates of the trained neural network decoder are compared with the bit error rates of the classic sum-product algorithm approach. Experiments with static and dynamic training datasets of diverse sizes, various signal-to-noise ratios, a feed forward as well as a recurrent architecture show how to tune the neural network decoder even further. Results of the experiments are used to verify statements made in Agrawal’s work. In addition, corrections and improvements in the area of metrics are presented. An implementation of the neural network to facilitate access for others will be made available to the public.
The state-of-the-art pattern recognition method in machine learning (deep convolution neural network) is used to identify the equation of state (EoS) employed in the relativistic hydrodynamic simulations of heavy ion collisions. High-level correlations of particle spectra in transverse momentum and azimuthal angle learned by the network act as an effective EoS-meter in deciphering the nature of the phase transition in QCD. The EoS-meter is model independent and insensitive to other simulation inputs including the initial conditions and shear viscosity for hydrodynamic simulations. Through this study we demonstrate that there is a traceable encoder of the dynamical information from the phase structure that survives the evolution and exists in the final snapshot of heavy ion collisions and one can exclusively and effectively decode these information from the highly complex final output with machine learning when traditional methods fail. Besides the deep neural network, the performance of traditional machine learning classifiers are also provided.
The discussion about the interplay between digital technologies and the process of globalization is often focused around the following question: who has access to global information networks and who benefits from digital communication technologies? These are essential questions and it can hardly be denied that they confront us with a series of political and ethical questions. However, we also need to recognize the ongoing digitalization of the globe, a process where more and more people are put on various kinds of maps...
Advanced machine learning has achieved extraordinary success in recent years. “Active” operational risk beyond ex post analysis of measured-data machine learning could provide help beyond the regime of traditional statistical analysis when it comes to the “known unknown” or even the “unknown unknown.” While machine learning has been tested successfully in the regime of the “known,” heuristics typically provide better results for an active operational risk management (in the sense of forecasting). However, precursors in existing data can open a chance for machine learning to provide early warnings even for the regime of the “unknown unknown.”