Refine
Year of publication
Document Type
- Article (21)
- Working Paper (3)
Language
- English (24)
Has Fulltext
- yes (24)
Is part of the Bibliography
- no (24)
Keywords
- Machine learning (24) (remove)
Institute
- Medizin (12)
- Wirtschaftswissenschaften (7)
- Center for Financial Studies (CFS) (3)
- House of Finance (HoF) (3)
- Informatik und Mathematik (3)
- Psychologie (3)
- Sustainable Architecture for Finance in Europe (SAFE) (3)
- Frankfurt Institute for Advanced Studies (FIAS) (1)
- Informatik (1)
- MPI für Hirnforschung (1)
Artificial Intelligence (AI) and Machine Learning (ML) are currently hot topics in industry and business practice, while management-oriented research disciplines seem reluctant to adopt these sophisticated data analytics methods as research instruments. Even the Information Systems (IS) discipline with its close connections to Computer Science seems to be conservative when conducting empirical research endeavors. To assess the magnitude of the problem and to understand its causes, we conducted a bibliographic review on publications in high-level IS journals. We reviewed 1,838 articles that matched corresponding keyword-queries in journals from the AIS senior scholar basket, Electronic Markets and Decision Support Systems (Ranked B). In addition, we conducted a survey among IS researchers (N = 110). Based on the findings from our sample we evaluate different potential causes that could explain why ML methods are rather underrepresented in top-tier journals and discuss how the IS discipline could successfully incorporate ML methods in research undertakings.
This article discusses the counterpart of interactive machine learning, i.e., human learning while being in the loop in a human-machine collaboration. For such cases we propose the use of a Contradiction Matrix to assess the overlap and the contradictions of human and machine predictions. We show in a small-scaled user study with experts in the area of pneumology (1) that machine-learning based systems can classify X-rays with respect to diseases with a meaningful accuracy, (2) humans partly use contradictions to reconsider their initial diagnosis, and (3) that this leads to a higher overlap between human and machine diagnoses at the end of the collaboration situation. We argue that disclosure of information on diagnosis uncertainty can be beneficial to make the human expert reconsider her or his initial assessment which may ultimately result in a deliberate agreement. In the light of the observations from our project, it becomes apparent that collaborative learning in such a human-in-the-loop scenario could lead to mutual benefits for both human learning and interactive machine learning. Bearing the differences in reasoning and learning processes of humans and intelligent systems in mind, we argue that interdisciplinary research teams have the best chances at tackling this undertaking and generating valuable insights.
We focus on the role of social media as a high-frequency, unfiltered mass information transmission channel and how its use for government communication affects the aggregate stock markets. To measure this effect, we concentrate on one of the most prominent Twitter users, the 45th President of the United States, Donald J. Trump. We analyze around 1,400 of his tweets related to the US economy and classify them by topic and textual sentiment using machine learning algorithms. We investigate whether the tweets contain relevant information for financial markets, i.e. whether they affect market returns, volatility, and trading volumes. Using high-frequency data, we find that Trump’s tweets are most often a reaction to pre-existing market trends and therefore do not provide material new information that would influence prices or trading. We show that past market information can help predict Trump’s decision to tweet about the economy.
The Gleason grading system remains the most powerful prognostic predictor for patients with prostate cancer since the 1960s. Its application requires highly-trained pathologists, is tedious and yet suffers from limited inter-pathologist reproducibility, especially for the intermediate Gleason score 7. Automated annotation procedures constitute a viable solution to remedy these limitations. In this study, we present a deep learning approach for automated Gleason grading of prostate cancer tissue microarrays with Hematoxylin and Eosin (H&E) staining. Our system was trained using detailed Gleason annotations on a discovery cohort of 641 patients and was then evaluated on an independent test cohort of 245 patients annotated by two pathologists. On the test cohort, the inter-annotator agreements between the model and each pathologist, quantified via Cohen’s quadratic kappa statistic, were 0.75 and 0.71 respectively, comparable with the inter-pathologist agreement (kappa = 0.71). Furthermore, the model’s Gleason score assignments achieved pathology expert-level stratification of patients into prognostically distinct groups, on the basis of disease-specific survival data available for the test cohort. Overall, our study shows promising results regarding the applicability of deep learning-based solutions towards more objective and reproducible prostate cancer grading, especially for cases with heterogeneous Gleason patterns.
Objectives: To analyze the performance of radiological assessment categories and quantitative computational analysis of apparent diffusion coefficient (ADC) maps using variant machine learning algorithms to differentiate clinically significant versus insignificant prostate cancer (PCa). Methods: Retrospectively, 73 patients were included in the study. The patients (mean age, 66.3 ± 7.6 years) were examined with multiparametric MRI (mpMRI) prior to radical prostatectomy (n = 33) or targeted biopsy (n = 40). The index lesion was annotated in MRI ADC and the equivalent histologic slides according to the highest Gleason Grade Group (GrG). Volumes of interest (VOIs) were determined for each lesion and normal-appearing peripheral zone. VOIs were processed by radiomic analysis. For the classification of lesions according to their clinical significance (GrG ≥ 3), principal component (PC) analysis, univariate analysis (UA) with consecutive support vector machines, neural networks, and random forest analysis were performed. Results: PC analysis discriminated between benign and malignant prostate tissue. PC evaluation yielded no stratification of PCa lesions according to their clinical significance, but UA revealed differences in clinical assessment categories and radiomic features. We trained three classification models with fifteen feature subsets. We identified a subset of shape features which improved the diagnostic accuracy of the clinical assessment categories (maximum increase in diagnostic accuracy ΔAUC = + 0.05, p < 0.001) while also identifying combinations of features and models which reduced overall accuracy. Conclusions: The impact of radiomic features to differentiate PCa lesions according to their clinical significance remains controversial. It depends on feature selection and the employed machine learning algorithms. It can result in improvement or reduction of diagnostic performance.
Measuring and reducing energy consumption constitutes a crucial concern in public policies aimed at mitigating global warming. The real estate sector faces the challenge of enhancing building efficiency, where insights from experts play a pivotal role in the evaluation process. This research employs a machine learning approach to analyze expert opinions, seeking to extract the key determinants influencing potential residential building efficiency and establishing an efficient prediction framework. The study leverages open Energy Performance Certificate databases from two countries with distinct latitudes, namely the UK and Italy, to investigate whether enhancing energy efficiency necessitates different intervention approaches. The findings reveal the existence of non-linear relationships between efficiency and building characteristics, which cannot be captured by conventional linear modeling frameworks. By offering insights into the determinants of residential building efficiency, this study provides guidance to policymakers and stakeholders in formulating effective and sustainable strategies for energy efficiency improvement.
Background: The ability to approximate intra-operative hemoglobin loss with reasonable precision and linearity is prerequisite for determination of a relevant surgical outcome parameter: This information enables comparison of surgical procedures between different techniques, surgeons or hospitals, and supports anticipation of transfusion needs. Different formulas have been proposed, but none of them were validated for accuracy, precision and linearity against a cohort with precisely measured hemoglobin loss and, possibly for that reason, neither has established itself as gold standard. We sought to identify the minimal dataset needed to generate reasonably precise and accurate hemoglobin loss prediction tools and to derive and validate an estimation formula.
Methods: Routinely available clinical and laboratory data from a cohort of 401 healthy individuals with controlled hemoglobin loss between 29 and 233 g were extracted from medical charts. Supervised learning algorithms were applied to identify a minimal data set and to generate and validate a formula for calculation of hemoglobin loss.
Results: Of the classical supervised learning algorithms applied, the linear and Ridge regression models performed at least as well as the more complex models. Most straightforward to analyze and check for robustness, we proceeded with linear regression. Weight, height, sex and hemoglobin concentration before and on the morning after the intervention were sufficient to generate a formula for estimation of hemoglobin loss. The resulting model yields an outstanding R2 of 53.2% with similar precision throughout the entire range of volumes or donor sizes, thereby meaningfully outperforming previously proposed medical models.
Conclusions: The resulting formula will allow objective benchmarking of surgical blood loss, enabling informed decision making as to the need for pre-operative type-and-cross only vs. reservation of packed red cell units, depending on a patient’s anemia tolerance, and thus contributing to resource management.
CRFVoter : gene and protein related object recognition using a conglomerate of CRF-based tools
(2019)
Background: Gene and protein related objects are an important class of entities in biomedical research, whose identification and extraction from scientific articles is attracting increasing interest. In this work, we describe an approach to the BioCreative V.5 challenge regarding the recognition and classification of gene and protein related objects. For this purpose, we transform the task as posed by BioCreative V.5 into a sequence labeling problem. We present a series of sequence labeling systems that we used and adapted in our experiments for solving this task. Our experiments show how to optimize the hyperparameters of the classifiers involved. To this end, we utilize various algorithms for hyperparameter optimization. Finally, we present CRFVoter, a two-stage application of Conditional Random Field (CRF) that integrates the optimized sequence labelers from our study into one ensemble classifier.
Results: We analyze the impact of hyperparameter optimization regarding named entity recognition in biomedical research and show that this optimization results in a performance increase of up to 60%. In our evaluation, our ensemble classifier based on multiple sequence labelers, called CRFVoter, outperforms each individual extractor’s performance. For the blinded test set provided by the BioCreative organizers, CRFVoter achieves an F-score of 75%, a recall of 71% and a precision of 80%. For the GPRO type 1 evaluation, CRFVoter achieves an F-Score of 73%, a recall of 70% and achieved the best precision (77%) among all task participants.
Conclusion: CRFVoter is effective when multiple sequence labeling systems are to be used and performs better then the individual systems collected by it.
A positive association between brain size and intelligence is firmly established, but whether region-specific anatomical differences contribute to general intelligence remains an open question. Results from voxel-based morphometry (VBM) - one of the most widely used morphometric methods - have remained inconclusive so far. Here, we applied cross-validated machine learning-based predictive modeling to test whether out-of-sample prediction of individual intelligence scores is possible on the basis of voxel-wise gray matter volume. Features were derived from structural magnetic resonance imaging data (N = 308) using (a) a purely data-driven method (principal component analysis) and (b) a domain knowledge-based approach (atlas parcellation). When using relative gray matter (corrected for total brain size), only the atlas-based approach provided significant prediction, while absolute gray matter (uncorrected) allowed for above-chance prediction with both approaches. Importantly, in all significant predictions, the absolute error was relatively high, i.e., greater than ten IQ points, and in the atlas-based models, the predicted IQ scores varied closely around the sample mean. This renders the practical value even of statistically significant prediction results questionable. Analyses based on the gray matter of functional brain networks yielded significant predictions for the fronto-parietal network and the cerebellum. However, the mean absolute errors were not reduced in contrast to the global models, suggesting that general intelligence may be related more to global than region-specific differences in gray matter volume. More generally, our study highlights the importance of predictive statistical analysis approaches for clarifying the neurobiological bases of intelligence and provides important suggestions for future research using predictive modeling.
Purpose: While more advanced COVID-19 necessitates medical interventions and hospitalization, patients with mild COVID-19 do not require this. Identifying patients at risk of progressing to advanced COVID-19 might guide treatment decisions, particularly for better prioritizing patients in need for hospitalization.
Methods: We developed a machine learning-based predictor for deriving a clinical score identifying patients with asymptomatic/mild COVID-19 at risk of progressing to advanced COVID-19. Clinical data from SARS-CoV-2 positive patients from the multicenter Lean European Open Survey on SARS-CoV-2 Infected Patients (LEOSS) were used for discovery (2020-03-16 to 2020-07-14) and validation (data from 2020-07-15 to 2021-02-16).
Results: The LEOSS dataset contains 473 baseline patient parameters measured at the first patient contact. After training the predictor model on a training dataset comprising 1233 patients, 20 of the 473 parameters were selected for the predictor model. From the predictor model, we delineated a composite predictive score (SACOV-19, Score for the prediction of an Advanced stage of COVID-19) with eleven variables. In the validation cohort (n = 2264 patients), we observed good prediction performance with an area under the curve (AUC) of 0.73 ± 0.01. Besides temperature, age, body mass index and smoking habit, variables indicating pulmonary involvement (respiration rate, oxygen saturation, dyspnea), inflammation (CRP, LDH, lymphocyte counts), and acute kidney injury at diagnosis were identified. For better interpretability, the predictor was translated into a web interface.
Conclusion: We present a machine learning-based predictor model and a clinical score for identifying patients at risk of developing advanced COVID-19.