Background: Recent advances in data-driven computational approaches have been helpful in devising tools to objectively diagnose psychiatric disorders. However, current machine learning studies... Show moreBackground: Recent advances in data-driven computational approaches have been helpful in devising tools to objectively diagnose psychiatric disorders. However, current machine learning studies limited to small homogeneous samples, different methodologies, and different imaging collection protocols, limit the ability to directly compare and generalize their results. Here we aimed to classify individuals with PTSD versus controls and assess the generalizability using a large heterogeneous brain datasets from the ENIGMA-PGC PTSD Working group. Methods: We analyzed brain MRI data from 3,477 structural-MRI; 2,495 resting state-fMRI; and 1,952 diffusion-MRI. First, we identified the brain features that best distinguish individuals with PTSD from controls using traditional machine learning methods. Second, we assessed the utility of the denoising variational autoencoder (DVAE) and evaluated its classification performance. Third, we assessed the generalizability and reproducibility of both models using leave-one-site-out cross-validation procedure for each modality. Results: We found lower performance in classifying PTSD vs. controls with data from over 20 sites (60 % test AUC for s-MRI, 59 % for rs-fMRI and 56 % for D-MRI), as compared to other studies run on single-site data. The performance increased when classifying PTSD from HC without trauma history in each modality (75 % AUC). The classification performance remained intact when applying the DVAE framework, which reduced the number of features. Finally, we found that the DVAE framework achieved better generalization to unseen datasets compared with the traditional machine learning frameworks, albeit performance was slightly above chance. Conclusion: These results have the potential to provide a baseline classification performance for PTSD when using large scale neuroimaging datasets. Our findings show that the control group used can heavily affect classification performance. The DVAE framework provided better generalizability for the multi-site data. This may be more significant in clinical practice since the neuroimaging-based diagnostic DVAE classification models are much less site-specific, rendering them more generalizable. Show less
Transport inspectorates are looking for novel methods to identify dangerous behavior, ultimately to reduce risks associated to the movements of people and goods. We explore a data-driven approach... Show moreTransport inspectorates are looking for novel methods to identify dangerous behavior, ultimately to reduce risks associated to the movements of people and goods. We explore a data-driven approach to arrive at smart inspections of vehicles. Inspections are smart when they are performed (1) accurate, (2) automated, (3) fair, and (4) in an interpretable manner. We leverage tools from the network science and machine learning domain to encode the behavioral aspect of vehicle’s behavior. Tools used in this thesis include community detection, link prediction, and assortativity. We explore their applicability and provide technical methods. In the final chapter, we also discuss the matter of fairness in machine learning. Show less
The focus of this thesis is on the technical methods which help promote the movement towards Trustworthy AI, specifically within the Inspectorate of the Netherlands.The goal is develop and assess... Show moreThe focus of this thesis is on the technical methods which help promote the movement towards Trustworthy AI, specifically within the Inspectorate of the Netherlands.The goal is develop and assess the technical methods which are required to shift the actions of the Inspectorate to a data-driven paradigm, concretely under a supervised classification framework of machine learning.The aspect of reliability is addressed as a data quality concern, viz. missingness and noise.The aspect of fairness is addressed as a counter to bias in the selection process of inspections.The conclusion is that, whilst no complete solution has yet been suggested, it is possible to address the concerns related to data quality and data bias, culminating in well-performing classification models which are reliable and fair. Show less
Rutgers, J.J.; Banki, T.; Kamp, A. van der; Waterlander, T.J.; Scheijde-Vermeulen, M.A.; Heuvel-Eibrink, M.M. van den; ... ; Krijger, R.R. de 2021
Background Histopathological classification of Wilms tumors determines treatment regimen. Machine learning has been shown to contribute to histopathological classification in various malignancies... Show moreBackground Histopathological classification of Wilms tumors determines treatment regimen. Machine learning has been shown to contribute to histopathological classification in various malignancies but requires large numbers of manually annotated images and thus specific pathological knowledge. This study aimed to assess whether trained, inexperienced observers could contribute to reliable annotation of Wilms tumor components for classification performed by machine learning. Methods Four inexperienced observers (medical students) were trained in histopathology of normal kidneys and Wilms tumors by an experienced observer (pediatric pathologist). Twenty randomly selected scanned Wilms tumor-slides (from n = 1472 slides) were annotated, and annotations were independently classified by both the inexperienced observers and two experienced pediatric pathologists. Agreement between the six observers and for each tissue element was measured using kappa statistics (kappa). Results Pairwise interobserver agreement between all inexperienced and experienced observers was high (range: 0.845-0.950). The interobserver variability for the different histological elements, including all vital tumor components and therapy-related effects, showed high values for all kappa-coefficients (> 0.827). Conclusions Inexperienced observers can be trained to recognize specific histopathological tumor and tissue elements with high interobserver agreement with experienced observers. Nevertheless, supervision by experienced pathologists remains necessary. Results of this study can be used to facilitate more rapid progress for supervised machine learning-based algorithm development in pediatric pathology and beyond. Show less