Search results

Your Search

Sort Options

(1 - 9 of 9)

Goedmakers, C.M.W. 2023

Outcome after anterior cervical discectomy: from inferential statistics to Machine Learning

Doctoral Thesis

some documents under embargo until 2025-09-21

After standard surgery for neck hernias, about 25% of patients report low satisfaction. This thesis applied inferential statistics to clinical data and Machine Learning to medical imaging, with the... Show moreAfter standard surgery for neck hernias, about 25% of patients report low satisfaction. This thesis applied inferential statistics to clinical data and Machine Learning to medical imaging, with the goal of finding out where differences in functional outcomes after surgery come from and how artificial intelligence can improve the diagnostic and prognostic process. The initial idea that differences in functional recovery were due to surgical technique was refuted by an RCT from this dissertation. The differences in functional recovery between three different surgical groups (removal of the intervertebral disc without artificial material, placement of intervertebral disc prosthesis, and fusion of vertebrae with a cage) were found to be minimal. It was striking that not surgical technique, but patients' mental health and preoperative, radiological imaging were found to be predictive of clinical recovery after surgery. Although the intervertebral disc prosthesis did not deliver on the promise of preserving mobility and thus could not prevent degeneration at adjacent levels, using Deep Learning based solely on the preoperative MRI of the neck, researchers were able to predict, among other things, which patients would require reoperation after surgery for that adjacent degeneration. The Deep Learning model did that significantly better than an experienced neuroradiologist and neurosurgeon. Such Deep Learning models eliminate the need for time-consuming questionnaires and are thus more cost-effective and less stressful for the patient, while they can be used to identify radiological features important for predicting the postoperative course. After validation with larger radiological datasets, these models can support clinical decision-making and help physicians develop personalized treatment strategies. Challenges within image analysis research for the spine lies in integrating different models into one automated process, preferably built into the electronic health record. Show less

Kurchaba, S.; Vliet, J. van; Verbeek, F.J.; Veenman, C.J. 2023

Anomalous NO2 emitting ship detection with TROPOMI satellite data and machine learning

Article / Letter to editor

open access

Starting from 2021, more demanding NOx emission restrictions were introduced for ships operating in the North and Baltic Sea waters. Since all methods currently used for ship compliance monitoring are financially and time demanding, it is important to prioritize the inspection of ships that have high chances of being non-compliant. The current state-of-the-art approach for a large-scale ship NO2 estimation is a supervised machine learning-based segmentation of ship plumes on TROPOMI/S5P images. However, challenging data annotation and insufficiently complex ship emission proxy used for the validation limit the applicability of the model for ship compliance monitoring. In this study, we present a methodology towards the automated and scalable selection of potentially non-compliant ships using a combination of machine learning models on TROPOMI satellite data. It is based on a proposed regression model predicting the amount of NO2 that is expected to be produced by a ship with certain properties operating in the given atmospheric conditions. The model does not require manual labeling and is validated with TROPOMI data directly. The differences between the predicted and actual amount of produced NO2 are integrated over observations of the ship in time and are used as a measure of the inspection worthiness of a ship. To add further evidence, we compare the obtained results with the results of the previously developed segmentation-based method. Ships that are also highly deviating in accordance with the segmentation method require further attention. If no other explanations can be found by checking the TROPOMI data, the respective ships are advised to be the candidates for inspection.

Show less

Moussa, C. 2023

Algorithm selection and configuration for Noisy Intermediate Scale Quantum methods for industrial applications

Doctoral Thesis

open access

Quantum hardware comes with a different computing paradigm and new ways to tackle applications. Much effort has to be put into understanding how to leverage this technology to give real-world... Show moreQuantum hardware comes with a different computing paradigm and new ways to tackle applications. Much effort has to be put into understanding how to leverage this technology to give real-world advantages in areas of interest for industries such as combinatorial optimization or machine learning. Variational quantum algorithms (VQAs) have been introduced as a way to work within the scope of reach of the current imperfect and unstable hardware. A VQA boils down to a parameterized quantum circuit, which is a quantum circuit with adjustable real-valued parameters. These parameters are generally tweaked by a classical optimization algorithm to optimize a quantity of interest. As VQAs are most often used as heuristics, it is not clear whether they genuinely outperform current classical state-of-the-art algorithms in relevant domains of application. Plus, a VQA can come with many components (which can also be calledhyperparameters) making it a (growing) complex system to analyze performances on many considered tasks. Consequently, we will face the issues of algorithm selection and configuration, which we tackle through this thesis on many examples relevant to industrial applications. In this thesis, VQAs for combinatorial optimization, chemistry/material science, and machine learning problems were considered. Show less

Ullah, S. 2023

Model-assisted robust optimization for continuous black-box problems

Doctoral Thesis

open access

Uncertainty and noise are frequently-encountered obstacles in real-world applications of numerical optimization. The practice of optimization that deals with uncertainties and noise is commonly... Show moreUncertainty and noise are frequently-encountered obstacles in real-world applications of numerical optimization. The practice of optimization that deals with uncertainties and noise is commonly referred to as robust optimization. This thesis concentrates on robust optimization w.r.t the parametric uncertaintiesin the search variables. These parametric uncertainties are assumed to be structurally symmetric, additive in nature, and can be modeled in a deterministic or aprobabilistic fashion. This dissertation empirically studies the models, algorithms, and techniques utilized for surrogate-assisted robust optimization in this context. Based on the studies performed in the dissertation, we conclude that Kriging, SVM, and Polynomial Regression are useful modeling techniques to solve robust optimization problems. We also validate the applicability of Autoencoders and PCA for addressing high-dimensional problems. Lastly, we find that mini-max robustness is the most efficient robustness formulation technique in practical scenarios. Show less

Sbrollini, A.; Barocci, M.; Mancinelli, M.; Paris, M.; Raffaelli, S.; Marcantoni, I.; ... ; Burattini, L. 2023

Automatic diagnosis of newly emerged heart failure from serial electrocardiography by repeated structuring & learning procedure

Article / Letter to editor

open access

Heart failure (HF) diagnosis, typically visually performed by serial electrocardiography, may be supported by machine-learning approaches. Repeated structuring & learning procedure (RS & LP... Show moreHeart failure (HF) diagnosis, typically visually performed by serial electrocardiography, may be supported by machine-learning approaches. Repeated structuring & learning procedure (RS & LP) is a constructive algorithm able to automatically create artificial neural networks (ANN); it relies on three parameters, namely maximal number of hidden layers (MNL), initializations (MNI) and confirmations (MNC), arbitrarily set by the user. The aim of this study is to evaluate RS & LP robustness to varying values of parameters and to identify an optimized combination of parameter values for HF diagnosis. To this aim, the Leiden University Medical Center HF data-base was used. The database is constituted by 129 serial ECG pairs acquired in patients who experienced myocardial infarction; 48 patients developed HF at follow-up (cases), while 81 remained clinically stable (controls). Overall, 15 ANNs were created by considering 13 serial ECG features as inputs (extracted from each serial ECG pair), 2 classes as outputs (cases/controls), and varying values of MNL (1, 2, 3, 4 and 10), MNI (50, 250, 500, 1000 and 1500) and MNC (2, 5, 10, 20 and 50). The area under the curve (AUC) of the receiver operating characteristic did not significantly vary with varying parameter values (P >= 0.09). The optimized combination of parameter values, identified as the one showing the highest AUC, was obtained for MNL = 3, MNI = 500 and MNC = 50 (AUC = 86 %; ANN structure: 3 hidden layers of 14, 14 and 13 neurons, respectively). Thus, RS & LP is robust, and the optimized ANN represents a potentially useful clinical tool for a reliable auto-matic HF diagnosis. Show less

Pratiwi Bunga, C.; Dusseldorp, E.; Karch, J.D.; de Rooij, M. 2023

Predictive performance of psychological tests: is it better to use items than subscales?

Article / Letter to editor

open access

Brandsen, A. 2022

Digging in documents: using text mining to access the hidden knowledge in Dutch archaeological excavation reports

Doctoral Thesis

open access

The archaeology domain produces large amounts of texts, too much to effectively read or manually search through for research. To alleviate this problem, we created a search system (called AGNES),... Show moreThe archaeology domain produces large amounts of texts, too much to effectively read or manually search through for research. To alleviate this problem, we created a search system (called AGNES), which combines full text search with entity and geographical search. We first created a manually labelled data set to train a Named Entity Recognition model, which is used to extract entities from text. We also did a user requirement study, and usability evaluation on the system, to make sure it is suitable for archaeological research. In a case study on Early Medieval cremations, we show that using AGNES leads to a knowledge increase when compared to the knowledge of experts, gathered using previously available search engines. This shows that this kind of intelligent search system can help with literature research, find more relevant data, and lead to a better understanding of the past. Show less

Wardenaar, K.J.; Riese, H.; Giltay, E.J.; Eikelenboom, M.; Hemert, A.J. van; Beekman, A.F.; ... ; Schoevers, R.A. 2021

Common and specific determinants of 9-year depression and anxiety course-trajectories: a machine-learning investigation in the Netherlands Study of Depression and Anxiety (NESDA)

Article / Letter to editor

open access

Background: Given the strong relationship between depression and anxiety, there is an urge to investigate their shared and specific long-term course determinants. The current study aimed to... Show moreBackground: Given the strong relationship between depression and anxiety, there is an urge to investigate their shared and specific long-term course determinants. The current study aimed to identify and compare the main determinants of the 9-year trajectories of combined and pure depression and anxiety symptom severity. Methods: Respondents with a 6-month depression and/or anxiety diagnosis (n=1,701) provided baseline data on 152 sociodemographic, clinical and biological variables. Depression and anxiety symptom severity assessed at baseline, 2-, 4-, 6- and 9-year follow-up, were used to identify data-driven course-trajectory subgroups for general psychological distress, pure depression, and pure anxiety severity scores. For each outcome (classprobability), a Superlearner (SL) algorithm identified an optimally weighted (minimum mean squared error) combination of machine-learning prediction algorithms. For each outcome, the top determinants in the SL were identified by determining variable-importance and correlations between each SL-predicted and observed outcome (rho pred) were calculated. Results: Low to high prediction correlations (rho pred: 0.41-0.91, median=0.73) were found. In the SL, important determinants of psychological distress were age, young age of onset, respiratory rate, participation disability, somatic disease, low income, minor depressive disorder and mastery score. For course of pure depression and anxiety symptom severity, similar determinants were found. Specific determinants of pure depression included several types of healthcare-use, and of pure-anxiety course included somatic arousal and psychological distress. Limitations: Limited sample size for machine learning. Conclusions: The determinants of depression- and anxiety-severity course are mostly shared. Domain-specific exceptions are healthcare use for depression and somatic arousal and distress for anxiety-severity course. Show less

Sears, A.M. 2020

Algorithmic speech and freedom of expression

Article / Letter to editor

open access

Algorithms have become increasingly common, and with this development, so have algorithms that approximate human speech. This has introduced new issues with which courts and legislators will have... Show moreAlgorithms have become increasingly common, and with this development, so have algorithms that approximate human speech. This has introduced new issues with which courts and legislators will have to grapple. Courts in the United States have found that search engine results are a form of speech that is protected by the Constitution, and cases in Europe concerning liability for autocomplete suggestions have led to varied results. Beyond these instances, insight into how courts handle algorithmic speech are few and far between.By focusing on three categories of algorithmic speech, defined as curated production, interactive/responsive production, and semiautonomous production, this Article analyzes these various forms of algorithmic speech within the international framework for freedom of expression. After a brief introduction of that framework and a look towards approaches to algorithmic speech in the United States, the Article then examines whether the creators or controllers of different forms of algorithms should be considered content providers or mere intermediaries, the determination of which ultimately has implications for liability, which is also explored. The Article then looks at possible interferences with algorithmic speech, and how such interferences may be examined under the three-part test—particular attention is paid to the balancing of rights and interests at play—in order to answer the question of the extent to which algorithmic speech is worthy of protection under international standards of freedom of expression. Finally, other relevant issues surrounding algorithmic speech are discussed that will have an impact going forward, many of which involve questions of policy and societal values that accompany granting algorithmic speech protection. Show less

Leiden University Scholarly Publications

Your Search

Enabled Filters

Sort Options

Refine Results

Resource Type

Availability

Creation Date

Faculty

Collection

Topic

Language

Search results