1,720,977 research outputs found
Interpretable Artificial Intelligence to Predict Disease Progression-Related Outcomes via Electronic Healthcare Records Data
No full textConsidering the opportunities given by EHR data towards the development of AI algorithms within healthcare, and the potential impact that such approaches may have if successfully deployed to the real world after overcoming trust-related limitations, in this thesis, we propose three new specific frameworks to develop interpretable and easy-to-use AI-based tools to predict disease progression-related outcomes using data collected in EHR systems. We complete the description of each framework with a case study tied to a disease and its corresponding data flow obtained from EHR infrastructures. The first framework (Chapter 2) is designed to develop interpretable and easy-to-use risk scores. To provide an explicative case study, the proposed framework is applied to obtain a tool to predict hospitalizations caused by heart failure using the administrative claims of 176,018 patients with diabetes extracted from the EHR system of the Veneto Region, Italy. The second framework (Chapter 3), concerns the development of explainable deep learning-based natural language processing algorithms that extract relevant structured information from unstructured free-form text. The case study for this second framework concerns the development of a tool to identify a past hospitalization related to cardiovascular complications using the text of 197,411 routine visits undergone by 16,876 patients with diabetes followed at the diabetes outpatient clinic of the University Hospital of Padua. Finally, the third framework (Chapter 4) is designed as a solid methodological core to allow models to be fairly trained and evaluated while ensuring model interpretability and the possibility of deploying them to real-world clinical software. This framework is model-agnostic and can be applied without specific restrictions related to the underlying methodologic approach or domain of application. The case study for this last framework concerns the development and deployment of a tool useful to predict death due to amyotrophic lateral sclerosis using data from 2,209 patients collected during daily clinical practice by neurologists at two centers of excellence in Turin, Italy, and Lisbon, Portugal.
Ultimately, this thesis demonstrates the potential of AI algorithms built by exploiting EHR data through proper development workflows that ensure solid model development and validation as well as result interpretability
Learned Primal Dual Reconstruction for PET
Full text linkWe have adapted, implemented and trained the Learned Primal Dual algorithm suggested by Adler and Öktem and evaluated its performance in reconstructing projection data from our PET scanner. Learned Primal Dual reconstructions are compared to Maximum Likelihood Expectation Maximisation (MLEM) reconstructions. Different strategies for training are also compared. Whenever the noise level of the data to reconstruct is sufficiently represented in the training set, the Learned Primal Dual algorithm performs well on the recovery of the activity concentrations and on noise reduction as compared to MLEM. The algorithm is also shown to be robust against the appearance of artefacts, even when the images that are to be reconstructed present features were not present in the training set. Once trained, the algorithm reconstructs images in few seconds or less
Deep-learning-based natural-language-processing models to identify cardiovascular disease hospitalisations of patients with diabetes from routine visits' text
Full text link: Writing notes is the most widespread method to report clinical events. Therefore, most of the information about the disease history of a patient remains locked behind free-form text. Natural language processing (NLP) provides a solution to automatically transform free-form text into structured data. In the present work, electronic healthcare records data of patients with diabetes were used to develop deep-learning based NLP models to automatically identify, within free-form text describing routine visits, the occurrence of hospitalisations related to cardiovascular disease (CVDs), an outcome of diabetes. Four possible time windows of increasing level of expected difficulty were considered: infinite, 24 months, 12 months, and 6 months. Model performance was evaluated by means of the area under the precision recall curve, as well as precision, recall, and F1-score after thresholding. Results showed that the proposed NLP approach was successful for both the infinite and 24-month windows, while, as expected, performance deteriorated with shorter time windows. Possible clinical applications of tools based on the proposed NLP approach include the retrospective filling of medical records with respect to a patient's CVD history for epidemiological and research purposes as well as for clinical decision making
Explainable Deep-Learning Model Reveals Past Cardiovascular Disease in Patients with Diabetes Using Free-Form Visit Reports
No full textCharacterization of Chronic Kidney Disease Progression in Patients with Diabetes via Group-Based Multi-Trajectory Modeling
No full textPatients suffering from chronic kidney disease (CKD) show a reduction in kidney functionality. Uncontrolled diabetes is among the causes of CKD. As patients with diabetes attend periodic visits, relevant amounts of data end up being available within EHR systems. This information could be exploited to extract insights into disease progression and provide clinicians with tools to better understand the expected disease course. In this work, we applied multi-trajectory group-based trajectory models (GBTM) to identify and characterize groups of patients with similar progression patterns of CKD and diabetes. Specifically, we studied a population of 7,000 patients with diabetes and an initial diagnosis of CKD stage III followed at diabetes outpatient clinics spread across the Veneto Region (Italy). GBTM analysis led to the identification of 6 unique groups of patients with differing CKD and diabetes progression trajectories. Our results suggest that multi-trajectory modeling via GBTM can shed light on the progression of CKD and its interaction with glycemic control, as well as provide clinicians with tools to preemptively identify patients expected to experience significant CKD worsening
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Appropriate Similarity Measures for Author Cocitation Analysis
Full text linkWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
Dispelling the Myths Behind First-author Citation Counts
Full text linkWe conducted a full-scale evaluative citation analysis study of scholars in the XML research field to explore just how different from each other author rankings resulting from different citation counting methods actually are, and to demonstrate the capability of emerging data and tools on the Web in supporting more realistic citation counting methods. Our results contest some common arguments for the continued
use of first-author citation counts in the evaluation of scholars, such as high correlations between author rankings by first-author citation counts and other citation
counting methods, and high costs of using more realistic citation counting methods that are not well-supported by the ISI databases. It is argued that increasingly available digital full text research papers make it possible for citation analysis studies to go beyond what the ISI databases have directly supported and to employ more
sophisticated methods
- …
