1,720,976 research outputs found
Challenges in biomedical data science: data-driven solutions to clinical questions
No full textData are influencing every aspect of our lives, from our work activities, to our spare time and even to our health. In this regard, medical diagnosis and treatments are often supported by quantitative measures and observations, such as laboratory tests, medical imaging or genetic analysis. In medicine, as well as in several other scientific domains, the amount of data involved in each decision-making process
has become overwhelming. The complexity of the phenomena under investigation and the scale of modern data collections has long superseded human analysis and insights potential
Paths of graduates from the University of Genoa (1990-2016) = Percorsi dei laureati dell’Università di Genova (1990-2016)
No full textIl contributo descrive in forma di data visualization i percorsi, le scelte formative e gli esiti lavorativi di diverse migliaia di studenti dell'Università di Genova nell'arco temporale che va dal 1990 al 2016.
Si fonda sull'interconnessione e l'analisi di amplissime raccolte di dati (UniGe, AlmaLaurea, ISTAT) e costituisce uno strumento di sintesi a supporto delle attività di orientamento degli studenti e di programmazione dell'offerta formativa da parte delle università.
Il contributo esprime in forma sintetica la ricerca interdisciplinare design - data science, che mediante complexity design, data analysis e data visualization, ha promosso l'utilizzo dei dati a supporto delle attività decisionali individuali e collettive legate all'ambito accademico.
Costituisce quindi un esempio primo di strumento proprio della data driven society, a servizio del redesign di processi tradizionali su base oggettiva. I risultati dell'intera ricerca impattano profondamente sulla società, agendo su due fronti complementari. Da un lato, supportano i singoli attori/studenti nel loro processo di autodefinizione, cuore dell'idea stessa di Accademia. Dall'altro, forniscono ai decisori dell'accademia - per la prima volta in forma intellegibile - gli strumenti necessari ad anticipare, comprendere e verificare l'esito finale delle scelte di costruzione dei percorsi formativi.
Il contributo è uno dei prodotti di una ricerca finanziata dall'Università di Genova - Importo finanziamento: 150.000 euro
PALLADIO: A Parallel Framework for Robust Variable Selection in High-Dimensional Data
No full textThe main goal of supervised data analytics is to model a target phenomenon given a limited amount of samples, each represented by an arbitrarily large number of variables. Especially when the number of variables is much larger than the number of available samples, variable selection is a key step as it allows to identify a possibly reduced subset of relevant variables describing the observed phenomenon. Obtaining interpretable and reliable results, in this highly indeterminate scenario, is often a non-trivial task. In this work we present PALLADIO, a framework designed for HPC cluster architectures, that is able to provide robust variable selection in high-dimensional problems. PALLADIO is developed in Python and it integrates CUDA kernels to decrease the computational time needed for several independent element-wise operations. The scalability of the proposed framework is assessed on synthetic data of different sizes, which represent realistic scenarios
Improving disease course detection in multiple sclerosis: an alternative patient-reported outcomes-based strategy
No full textPredicting multiple sclerosis disease course with patient centred outcomes (PCOs): a machine learning approach
No full textBackground: Achieving an accurate clinical course description in Multiple Sclerosis (MS) is a very hard task even for clinical experts, but it is crucial for communication, prognosis, treatment decision-making, design and recruitment of clinical trials. In this context, meaningful data being “hidden” into Patient Centered Outcomes (PCOs), could provide, through Advanced Machine learning (ML) approaches, a new perspective in predicting MS disease course.
Aims: This work aims at using PRO, CS and anthropometric measures to build a statistical model for the detection of MS courses by means of machine learning techniques. The analysis has been conducted on the dataset of the ongoing Italian MS Foundation (FISM) initiative “A New Functional Profile to Monitor the Progression Of Disability In Multiple Sclerosis - PROMOPRO-MS”.
Methods: The dataset is composed of 778 patients with MS, that were enrolled in the study without any inclusion/exclusion criteria unless MS diagnosis. The variables identified in the study were based on functions sufficient to encompass the patient"s disability and to represent whole-person behaviours. The set of PCOs selected were related mainly to mobility, fatigue, cognitive performances, emotional status, bladder continence, quality of life. Both unsupervised and supervised machine learning methods were taken into account. The first goal was to assess whether the collected features could discriminate any of the different disease courses by using unsupervised learning techniques looking for a meaningful data structure, then to apply a supervised approach, inferred in the previous step, in order to learn a classifier based only on a subset of the available features.
Results: The applied machine learning techniques showed that patients with MS (PwMS) diagnosed as relapsing-remitting (RR) could be isolated from other clinical courses (ALL). In particular, nine “top” questions were selected by the "Features Selection" supervised (FS) algorithm: three questions from Life Satisfaction Index, three items from Functional Independence Measure; two from Modified Fatigue Impact Scale and one from Hospital Anxiety and Depression Scale.
Conclusions: To the very best of our knowledge this is the first study which predicted MS course taking only into account a small subset of anthropometric and questionnaires variables, which could be proposed as a novel questionnaire, tailored for RR detection
Adenine: A HPC-oriented tool for biological data exploration
No full textadenine is a machine learning framework designed for biological data exploration and visualization. Its goal is to help bioinformaticians achieving a first and quick overview of the main structures underlying their data. This software tool encompasses state-of-the-art techniques for missing values imputing, data preprocessing, dimensionality reduction and clustering. adenine has a scalable architecture which seamlessly work on single workstations as well as on high-performance computing facilities. adenine is capable of generating publication-ready plots along with quantitative descriptions of the results. In this paper we provide an example of exploratory analysis on a publicly available gene expression data set of colorectal cancer samples. The software and its documentation are available at https://github.com/slipguru/adenine under FreeBSD license
Predicting diabetes second-line therapy initiation in the Australian population via time span-guided neural attention network
Full text linkIntroduction The first line of treatment for people with Diabetes mellitus is metformin. However, over the course of the disease metformin may fail to achieve appropriate glycemic control, and a second-line therapy may become necessary. In this paper we introduce Tangle, a time span-guided neural attention model that can accurately and timely predict the upcoming need for a second-line diabetes therapy from administrative data in the Australian adult population. The method is suitable for designing automatic therapy review recommendations for patients and their providers without the need to collect clinical measures. Data We analyzed seven years of de-identified records (2008-2014) of the 10% publicly available linked sample of Medicare Benefits Schedule (MBS) and Pharmaceutical Benefits Scheme (PBS) electronic databases of Australia. Methods By design, Tangle inherits the representational power of pre-trained word embedding, such as GloVe, to encode sequences of claims with the related MBS codes. Moreover, the proposed attention mechanism natively exploits the information hidden in the time span between two successive claims (measured in number of days). We compared the proposed method against state-of-the-art sequence classification methods. Results Tangle outperforms state-of-the-art recurrent neural networks, including attention-based models. In particular, when the proposed time span-guided attention strategy is coupled with pre-trained embedding methods, the model performance reaches an Area Under the ROC Curve of 90%, an improvement of almost 10 percentage points over an attentionless recurrent architecture
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
- …
