8,941 research outputs found
Present and future of telemedicine for pediatric care: an Italian regional experience
No full textAbstract Telemedicine has been recognized as an integral part of the National Health Service in Italy. Telemedicine can be adopted in the diagnostic therapeutic assistance pathway and in individual assistance plans. In the region of Lombardy, home care models from the perspective of the project of a public virtual hospital have been introduced. A regional operational center was proposed to ensure continuing care utilising organizational and technological solutions to deliver healthcare services remotely, with high quality standards, a positive economic impact and user friendly services for both the user and the professional. In the field of pediatrics telemedicine was also introduced at the Vittore Buzzi Children’ Hospital, in Milan, the capital of the region of Lombardy. These included routine pediatric hospital activities and innovative programs, such as early discharge, telecardiology, online supervised exercise training and preventive healthcare. Telehealth represents the evolution of health care delivery systems to adapt to new technology and the needs of the pediatric population, offering a strategic system to invest in children’s health
MACHINE LEARNING APPLIED TO CLINICAL NUTRITION: CLINICAL DECISION SUPPORT AND NEW PATTERNS RECOGNITION
No full textIntroduction. The healthcare sector is failing to utilize routinely produced clinical data to refine the care experience and to augment knowledge created in clinical study. The big data culture and the closely connected field of machine learning constitute the latest and the best opportunity yet to put to good use data created as a by-product of clinical care.
Aim of this thesis was to test the capabilities of machine learning algorithms applied to real-world clinical nutritional data to assist clinicians in their decision making process. Machine learning was used in two predictive contexts: 1) prediction of routinely collected parameters for patients non-eligible for the reference method, and 2) prediction of failure to meet clinical targets set out for the patient.
Material and methods. A large nutritional dataset collected at the International Center of Nutritional Status (University of Milan, Milan, Italy) was used for the analysis. The dataset include 15780 patients and multi-domains predictors providing informations on age, sex, education, occupation, marital status, family status, menstruation, pregnancies, diet status, diet history, physical activity, smoking, pharmacological treatments, clinical signs, weight history, physical exam, blood pressure, anthropometry, bioimpedance analysis, ultrasound (abdomen fat thicknesses), indirect calorimetry, laboratory exams, anxiety, depression, binge eating, emotion regulation, eating disorders, and adherence to a Mediterranean diet.
Machine learning algorithms were applied in order to predict the following outcomes: resting energy expenditure by indirect calorimetry, total body water by bio-impedance analysis, weight loss failure, failure to improve basal glycemia, failure to improve total cholesterolemia, failure to improve triglyceridemia. To evaluate accuracy and discrimination ability of machine learning and statistical algorithms, a series of cross-validation experiments were conducted for all outcomes, and the most accurate algorithm for each outcome was selected as the best for that outcome. Accuracy was defined with the root-mean-square error for continuous outcomes and the correct classification fraction for categorical outcomes.
Results. Machine learning algorithms outperformed statistical algorithms for all outcomes. The best performing models were tree-based models, in particular bagged decision trees performed best for continuous outcomes, while random forests performed best for categorical outcomes (with the exception of the triglyceridemia outcome which saw a boosted tree algorithm as the best performer).
In the prediction of resting energy expenditure and total body water, accuracy was high and the mean errors were deemed small in the context of clinical practice [mean (95% confidence interval) root-mean-square error 27.6 (20.9, 34.3) kcal/day and 0.842 (0.768, 0.916) l respectively].
In the prediction of weight loss failure, failure to improve basal glycemia, failure to improve total cholesterolemia, and failure to improve triglyceridemia, the mean correct classification fraction ranged between .616 and .735, but even the best algorithms showed good sensitivity but poor specificity (mean area under the ROC curve ranged between .652 and .687). For categorical outcomes unbalanced toward the event, machine learning models were the only one able to improve the accuracy of a naive classifier that assumes that all patients will experience the event, although only in weight loss failure model outcome accuracy was consistently above the naive classifier.
Discussion. Our results highlight the ability of machine learning algorithms to provide a high-accuracy alternative to reference techniques for non-eligible patients. The big-data culture paired with machine learning algorithms seem able to overcome limitations imposed from using externally-developed equations, providing highly accurate predictions.
In the setting of identifying non-responders, machine learning algorithms did not provide highly discriminant predictions, but were the only ones able to provide a better prediction of random guessing or the historical rate of event. In this more ambitious task, machine learning algorithm results need to be critically interpreted by the clinician, whose reasoning is necessarily different but can incorporate the suggestions provided from these algorithms
In bilico tra terra e acqua. Visioni e rotte di collisione su un tratto di fiume Po
No full textL’area dell’ex Centrale nucleare di Caorso è un luogo emblematico dove si concentrano, estremizzandosi, una serie di condizioni tipiche del sistema del Po, per certi versi inconciliabili: da una parte la presenza di infrastrutture ingombranti e filiere di produzione altamente impattanti, dall’altra ambienti seminaturali dall’elevato valore ecosistemico.
La sua dismissione e la restituzione del sito alla comunità aprono riflessioni che travalicano la scala locale e sollecitano temi di rilievo ideologico circa il ‘risorgere della natura’ o il ripensamento del nostro modo di vivere e modificare il pianeta.
Su tale premessa, l’articolo propone alcuni ragionamenti metodologici per indagare il potenziale che questa fase di decommissioning apre, partendo dai risultati del workshop internazionale LOL2023 del Politecnico di Milano.
Tre approcci, tre concetti, tre sguardi sul futuro equilibrio del paesaggio fluviale. Tre “reazioni” ai limiti imposti dagli attuali strumenti pianificatori, deliberatamente visionarie, ma in grado di proporre risposte potenti dinanzi a una crisi profonda e incalzante.The site of the former Caorso nuclear power plant is a notable location where a range of conditions that are typical of the Po River system, and often in conflict, are concentrated to an extreme degree. On one hand, there are massive infrastructures and highly impactful production chains, and on the other hand, there are semi-natural environments with a high ecological value.
The decommissioning of a site and its return to the community triggers thoughts and concerns beyond just the local scale. It raises questions about the resurgence of nature and the need to rethink our lifestyles and how they impact the planet. Starting from the results of the international workshop LOL2023 at the Milan Polytechnic, the article proposes methodological reasoning to investigate the potential that this decommissioning phase opens up.
Three different approaches have been taken to envision the future equilibrium of the river landscape. These concepts serve as a response to the constraints imposed by current planning tools, visionary and powerful answers capable of addressing a deep and pressing crisis
Andrea Bacová
No full textAndrea Bacová focuses on research and teaching in the field of residential architecture. Her work includes systematic research on residential buildings and their urban context. She actively participates in promoting Slovak architecture and is the author of several publications and exhibitions
Viewer-, Author-, and Ownership in the Work of Andrea Zittel
No full textAndrea Zittel invites others to collapse the distinctions between artist, viewer, and collaborator by interacting with her usable works. This thesis explores the process of interacting with Zittel\u27s works, and how it affects viewer-, author- and ownership
The Lettere of Andrea Calmo: authorial artifices and historical reality
No full textopenNonostante l’edizione di Vittorio Rossi del 1888, la raccolta di "ingegnosi cheribizzi" e di "fantastiche fantasie" di Andrea Calmo è ancora avvolta da un certo mistero. L’autore, dissimulando la propria identità dietro alla “maschera” dell’umile pescatore veneziano, è stato in grado di offrire uno spaccato della cultura e della società nella Venezia cinquecentesca.
In particolare, è il quarto libro delle Lettere ad aver suscitato maggiore interesse tra gli studiosi ed i lettori: pubblicato nel 1566, a diversi anni di distanza dai primi tre, questo libro si distingue per il fatto che tutte le epistole sono indirizzate a delle donne immaginarie o realmente esistite.
In questa sede si propone, in primo luogo, uno studio della biografia del Calmo accompagnata da un’analisi del contesto storico-culturale della Venezia cinquecentesca; in secondo luogo, invece, viene proposto un commento di alcune lettere dell’ultimo libro dell’opera calmiana, che cerchi di far luce principalmente sull’aspetto linguistico e contenutistico del testo.Despite Vittorio Rossi's 1888 edition, Andrea Calmo's collection of "ingegnosi cheribizzi" and "fantastiche fantasie" is still shrouded in a certain mystery. The author, dissimulating his own identity behind the "mask" of the humble Venetian fisherman, was able to offer a cross-section of culture and society in sixteenth-century Venice.
In particular, it is the fourth book of the Letters that has aroused greater interest among scholars and readers: published in 1566, several years after the first three, this book stands out for the fact that all the epistles are addressed to women imaginary or actually existed.
Here we propose, first of all, a study of Calmo's biography accompanied by an analysis of the historical-cultural context of sixteenth-century Venice; secondly, however, a commentary on some letters from the last book of Calmo's work is proposed, which seeks to shed light mainly on the linguistic and content aspect of the text
Long-COVID symptom monitoring: Insights from a two-year telemedicine study
No full textBackground: The diverse manifestations of Long-COVID have become increasingly important due to their significant impact on patients' lives. Telemedicine has emerged as an important tool for post COVID-19 follow-up. This study is part of a large cohort study involving COVID-positive patients monitored by the COD19 telemedicine platform operations center. We recontacted patients who were initially monitored from February 2020 to May 2020 to assess the presence of Long-COVID symptoms at a 2-year follow-up. Methods: We conducted interviews to evaluate Long-COVID symptoms at the 2-year mark and investigated whether patients had contracted a second COVID-19 infection between the 1-year and 2-year follow-ups, and recorded their vaccination status. Results: Out of 165 patients, 139 (84%) reported symptoms at the 1-year follow-up, while only 101 (61%) reported symptoms at the 2-year follow-up. Among patients with Long-COVID symptoms at the 2-year follow-up, the majority (80, 49%) had experienced Long-COVID at the 1-year follow-up, received the SARS-CoV-2 vaccine, and had not experienced a second infection between the two follow-ups. Both having Long-COVID at the 1-year follow-up and contracting a second infection were significant risk factors for presenting with Long-COVID at the 2-year follow-up. Conclusions: To the best of our knowledge, this study stands out as one of the few that includes a 2-year follow-up on Long-COVID symptoms using telemedicine. Telemedicine has proven to be an effective and innovative tool for long-term patient monitoring, early diagnosis, and treatment. Telemedicine represents a significant future challenge for healthcare
Trusted Tales: Creating Authenticity in Literary Representations from Ex-Yugoslavia
No full textThis research deals with questions of authority and authenticity and how they are expressed, constructed, and appropriated within the Anglophone book market. It considers the body of literature written about ex-Yugoslavia since the 1990s Balkan conflicts by exiled writers from the region which has entered the international literary canon. Books’ routes from original publishers into English translation are discussed through practices of trust, one of the crucial social devices underpinning their exchange. Within these cross-cultural processes, the role of cultural brokers is crucial. Symbolic and cultural resources are specifically mobilised through their powerful author brands.
By exploring authenticity in the context of book publishing, I further look at how ideas and practices of community are employed and negotiated by writers and those who promote their books. My field is multi-sited and fluid, reflecting how different individual and national positions are enacted and performed through strategies ranging from unconscious dispositions to deliberate intentions. This research thus brings together ideas of the author as an authentic, representative voice together with exile as a position that grants them a new lease of relevancy in the post-socialist context.
Although ex-Yugoslav books occupy a ‘high end’ niche of the UK market, constrained by commercial as well as political, cultural, and institutional forces, in public discourse ideas of the ‘free market’ and ‘free speech’ are mobilised to produce various types of modernisation narratives. The (post)socialist production of literature is perceived as having to ‘evolve’ into a capitalist model: this would allow not only healthy competition and consumer choice but guarantee an individual writer ‘free speech’ as a basic human right. Therefore, the most general question this research raises is what kind of foreign literature gets translated into English, under what socio-cultural conditions and which politics of representation it serves within the project of world literature
Data to guide the application of the new WHO criteria for releasing COVID-19 patients from isolation
No full textMs. Courtney Chartier, RWWL AUC, August 2011
No full textThis video is a conversation with Ms. Courtney Chartier. Ms. Chartier talks about her work on the "New Georgia Encyclopedia" and "Online Voter Education Project." Andrea Jackson, AUC Woodruff Library, is the interviewer
- …
