1,720,983 research outputs found
Process Mining in Healthcare
No full textNel presente elaborato è stato descritto il progetto di ricerca. Il filone principale è incentrato sull’utilizzo del Process Mining (PM) nella valutazione dei processi volti alla diagnosi del disturbo neurocognitivo lieve (MCI). Il primo step è stata la collaborazione alla redazione del Consensus Conference Europeo per l’utilizzo dei biomarcatori nella diagnosi del MCI. Successivamente sono descritti tre ambiti di applicazione del PM:
1. Un progetto pilota in cui sono stati valutati i percorsi diagnostici in pazienti afferiti ad una Memory Clinic di Ginevra.
2. Il progetto Valico in cui è stata valutata l’aderenza alle raccomandazioni italiane dei percorsi compiuti dai pazienti afferenti a 3 centri italiani sia con un indice di aderenza che con il conformance checking. Successivamente sono state valutate la deviazione dei percorsi diagnostici rispetto all’atteso.
3. Eurovalico, un progetto in fase di attuazione (in attesa conferma dei comitati etici) il cui scopo è valutare in centri europei i percorsi diagnostici pre e post pubblicazioni delle raccomandazioni europee e le conseguenti deviazioni.
In una seconda parte sono stati descritti i progetti seguiti durante lo stage in azienda, requisito essenziale per la borsa PON, svolto presso IL Gemelli Digital Medicine & Health S.r.l., una società nata come spin-off dal Policlinico Gemelli. Questa parte descrive le applicazioni più pratiche del PM in ambito sanitario. Vengono decritti i seguenti contributi:
• Collaborazione alla migrazione di una base di dati relativa a pazienti affetti da dislipidemia, nel formato OMOP/OHDSI Common Data Model.
• Partecipazione al progetto GEN-RWD Sandbox per la creazione di una complessa infrastruttura software che consenta l’esecuzione di studi statistici e di addestramento di modelli di ML da parte di soggetti esterni al policlinico Gemelli.
• Sviluppo di una Dashboard di supporto alle attività del Centro di Continuità Assistenziale con lo scopo di monitorare i pazienti fragili (a rischio di lunga ospedalizzazione).
• Implementazione di un modello predittivo della lunghezza di degenza (LOS) per l’identificazione precoce dei pazienti potenzialmente bed-blockers.
• Creazione di un sistema di monitoring della qualità delle scale infermieristiche e la predizione dei valori delle voci di queste.
A questo seguono inoltre altri progetti:
• Collaborazione con il reparto di Radioterapia dell’Istituto Europeo Oncologico per analisi dell’effetto delle sospensioni sui percorsi diagnostici terapeutici dei pazienti trattati con terapia radiante.
● Collaborazione al progetto pMineR indue specifiche parti:
- un formalismo chiamato COW (Cascade Of arroWs) che consente di bilanciare la chiarezza visiva con l’ottimizzazione dello spazio, migliorando la visualizzazione delle tracce e facilitandone l’analisi da parte degli operatori del settore
- pMinShiny una GUI progettata per offrire un ambiente grafico intuitivo e user-friendly agli utenti. Questo strumento è stato ideato per venire incontro alle esigenze di professionisti sanitari non esperti di programmazione consentendo loro di esplorare e analizzare i processi con facilità, utilizzando funzionalità avanzate senza la complessità associata all’ambiente R.
Questa ricerca evidenzia il potenziale del PM nell’ottimizzazione dei percorsi diagnostici, valutando l’aderenza alle linee guida cliniche e migliorando il processo decisionale in ambito sanitario. I progetti svolti dimostrano sia le applicazioni teoriche che pratiche di questa metodologia, dall’analisi dei percorsi diagnostici per i disturbi neurocognitivi al miglioramento della gestione delle risorse ospedaliere.In this dissertation, the research project has been described. The main focus is on the use of Process Mining (PM) in evaluating processes aimed at diagnosing Mild Cognitive Impairment (MCI).
The first step involved contributing to the drafting of the European Consensus Conference on the use of biomarkers in MCI diagnosis. Subsequently, three areas of PM application are described:
-A pilot project, which assessed the diagnostic pathways of patients referred to a Memory Clinic in Geneva.
-The Valico project, which evaluated the adherence of patient pathways from three Italian centers to national recommendations using both an adherence index and conformance checking. Additionally, deviations from expected diagnostic pathways were analysed.
-The Eurovalico project, currently under implementation (pending approval from ethics committees), aims to assess diagnostic pathways in European centers before and after the publication of European recommendations and the resulting deviations.
The second part describes the projects carried out during an industry internship, an essential requirement for the PON scholarship, at Gemelli Digital Medicine & Health S.r.l., a company spun off from Policlinico Gemelli. This section illustrates the practical applications of PM in healthcare, detailing the following contributions:
-Collaboration in migrating a database of patients with dyslipidaemia to the OMOP/OHDSI Common Data Model.
-Participation in the GEN-RWD Sandbox project, aimed at developing a complex software infrastructure enabling external entities to conduct statistical studies and train machine learning models.
-Development of a Dashboard to support the activities of the Continuity of Care Center, designed to monitor high-risk patients (those at risk of prolonged hospitalization).
-Implementation of a predictive model for length of stay (LOS) to enable early identification of potential bed-blocker patients.
-Creation of a nursing scale quality monitoring system and prediction of its score components.
Additionally, other projects include:
-Collaboration with the Radiotherapy Department of the European Institute of Oncology to analyse the impact of treatment suspensions on patients' therapeutic diagnostic pathways.
Contribution to the pMineR project in two specific areas:
-Development of a formalism called COW (Cascade Of arroWs), designed to balance visual clarity with space optimization, improving trace visualization and facilitating analysis by healthcare professionals.
-pMinShiny, a GUI designed to provide an intuitive and user-friendly graphical environment for healthcare professionals with no programming expertise, enabling them to explore and analyse processes with ease, using advanced functionalities without the complexity of the R environment.
This research highlights the potential of Process Mining (PM) in optimizing diagnostic pathways by assessing adherence to clinical guidelines and improving decision-making in healthcare. The projects carried out demonstrate both the theoretical and practical applications of this methodology, from the analysis of diagnostic pathways for neurocognitive disorders to the optimization of hospital resource management
Privacy-by-design GEN-RWD Sandbox for Distributed Multicentric Data Analysis in Healthcare: The Proxy Module
No full textModern data analysis techniques are transforming the healthcare landscape from both research and operational perspectives. Applying statistical analysis, machine learning, data science, and process mining to large databases enables data analysts and clinicians to enhance the quality and precision of their research and care efforts. However, the ingestion and maintenance of high-quality datasets present significant challenges, primarily due to the resource-intensive nature of the task and the difficulty of collecting comprehensive and statistically significant information sets. Multicentric cross-organizational studies, which involve the analysis of datasets collected from various independent data nodes, address this issue; however, concerns regarding privacy and data ownership often hinder the free exchange of data. Among the existing technologies, Distributed Analytics and Federated Learning offer promising solutions to these challenges by facilitating the analysis of large, decentralized datasets while safeguarding patient privacy.In this paper, we present and release as open-source the code of the Proxy Module within the GEN-RWD Sandbox platform, an infrastructure designed for privacy-preserving distributed analytics in healthcare. The module implements essential infrastructural management functions to ensure privacy in a distributed learning environment. A detailed explanation of the module functioning within the platform and test results are provided. The code is available at https://github.com/leonucciarelli/gsproxy.git.</p
Prediction Modelling and Data Quality Assessment for Nursing Scale in a Big Hospital: A Proposal to Save Resources and Improve Data Quality
No full text
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
- …
