1,720,989 research outputs found
Sviluppo e applicazione di tecniche di apprendimento automatico per l'analisi e la classificazione del testo in ambito clinico. Development and Application of Machine Learning Techniques for Text Analyses and Classification in Clinical Research
Full text linkThe content of Electronic Health Records (EHRs) is hugely heterogeneous, depending on the overall health system structure. Possibly, the most present and underused unstructured type of data included in the EHRs is the free-text. Nowadays, with Machine Learning (ML), we can take advantage of automatic models to encode narratives showing performance comparable to the human ones. In this dissertation, the focus is on the investigation of ML Techniques (MLT) to get insights from free-text in clinical settings. We considered two main groups of free-text involved in clinical research. The first is composed of extensive documents like research papers or study protocols. For this group, we considered 14 Systematic Reviews (SRs), including 7,494 studies from PubMed and a whole snapshot of 233,609 trials from ClinicalTrials.gov. Pediatric EHRs compose the second group, for which we considered two sources of data: one of 6,903,035 visits from the Italian Pedianet database, and the second of 2,723 Spanish discharging notes from pediatric Emergency Departments (EDs) of nine hospitals in Nicaragua. The first contribution reported is an automatic system trained to replicate a search from specialized search engines to clinical registries. The model purposed showed very high classification performances (AUC from 93.4% to 99.9% among the 14 SRs), with the added value of a reduced amount of non-relevant studies extracted (mean of 472 and maximum of 2119 additional records compared to 572 and 2680 of the original manual extraction respectively). A comparative study to explore the effect of changing different MLT or methods to manage class imbalance is reported. A whole investigation on pediatric ED visits collected from nine hospitals in Nicaragua was reported, showing a mean accuracy in the classification of discharge diagnoses of 78.31% showing promising performance of an ML for the automatic classification of ED free-text discharge diagnoses in the Spanish language. A further contribution aimed to improve the accuracy of infectious disease detection at the population level. That is a crucial public health issue that can provide the background information necessary for the implementation of effective control strategies, such as advertising and monitoring the effectiveness of vaccination campaigns. Among the two studies reported of classify cases of Varicella-Zoster Virus and types of otitis, both the primary ML paradigms of shallow and deep models were explored. In both cases the results were highly promising; in the latter, reaching performances comparable to the human ones (Accuracy 96.59% compared with 95.91% achieved by human annotators, and balanced F1 score of 95.47% compared with 93.47%). A further relevant side goal achieved rely on the languages investigated. The international research on the use of MLTs to classify EHRs is focused on English-based datasets mainly. Hence, results on non-English databases, like the Italian Pedianet or the Spanish of ED visits considered in the dissertation are essential to assess general applicability of MLTs at a general linguistic level. Showing performances comparable to the human ones, the dissertation highlights the real possibility to start to incorporate ML systems on daily clinical practice to produce a concrete improvement in the health care processes when free-text comes into account
Prediction of treatment outcome in clinical trials under a personalized medicine perspective
Full text linkA central problem in most data-driven personalized medicine scenarios is the estimation of heterogeneous
treatment effects to stratify individuals into subpopulations that differ in their susceptibility to a particular
disease or response to a specific treatment. In this work, with an illustrative example on type 2 diabetes we
showed how the increasing ability to access and analyzed open data from randomized clinical trials (RCTs) allows
to build Machine Learning applications in a framework of personalized medicine. An ensemble machine learning
predictive model is first developed and then applied to estimate the expected treatment response according to the
medication that would be prescribed. Machine learning is quickly becoming indispensable to bridge science and
clinical practice, but it is not sufficient on its own. A collaborative effort is requested to clinicians, statisticians,
and computer scientists to strengthen tools built on machine learning to take advantage of this evidence flow
Feasibility and Reliability of Wearable Devices in Measuring Caloric Intake: Results from a Pilot Study
No full textEarly termination of cardiovascular trials as a consequence of poor accrual: analysis of ClinicalTrials.gov 2006-2015
Full text linkOBJECTIVES:
To present a snapshot of experimental cardiovascular research with a focus on geographical and temporal patterns of early termination due to poor accrual.
SETTING:
The Aggregate Analysis of ClinicalTrials.gov (AACT) database, reflecting ClinicalTrials.gov as of 27 March 2016.
DESIGN:
The AACT database was searched for all cardiovascular clinical trials that started from January 2006 up to December 2015.
RESULTS:
Thirteen thousand and seven hundred twenty-nine cardiovascular trials were identified. Of these, 8900 (65%) were classified as closed studies. Globally, 11% of closed trials were terminated. This proportion varied from 9.6% to 14% for trials recruiting from Europe and Americas, respectively, with a slightly decreasing trend (p=0.02) over the study period. The most common reason for trials failing to complete was poor accrual (41%). Intercontinental trials exhibited lower figures of poor accrual as the reason for their early stopping, as compared with trials recruiting in a single continent (28% vs 44%, p=0.002).
CONCLUSIONS:
Poor accrual significantly challenges the successful completion of cardiovascular clinical trials. Findings are suggestive of a positive effect of globalisation of cardiovascular clinical research on the achievement of enrolment goals within a reasonable time frame
Exploring Applications of Artificial Intelligence in Critical Care Nursing: A Systematic Review
Full text linkBackground: Artificial intelligence (AI) has been increasingly employed in healthcare across diverse domains, including medical imaging, personalized diagnostics, therapeutic interventions, and predictive analytics using electronic health records. Its integration is particularly impactful in critical care, where AI has demonstrated the potential to enhance patient outcomes. This systematic review critically evaluates the current applications of AI within the domain of critical care nursing. Methods: This systematic review is registered with PROSPERO (CRD42024545955) and was conducted in accordance with PRISMA guidelines. Comprehensive searches were performed across MEDLINE/PubMed, SCOPUS, CINAHL, and Web of Science. Results: The initial review identified 1364 articles, of which 24 studies met the inclusion criteria. These studies employed diverse AI techniques, including classical models (e.g., logistic regression), machine learning approaches (e.g., support vector machines, random forests), deep learning architectures (e.g., neural networks), and generative AI tools (e.g., ChatGPT). The analyzed health outcomes encompassed postoperative complications, ICU admissions and discharges, triage assessments, pressure injuries, sepsis, delirium, and predictions of adverse events or critical vital signs. Most studies relied on structured data from electronic medical records, such as vital signs and laboratory results, supplemented by unstructured data, including nursing notes and patient histories; two studies also integrated audio data. Conclusion: AI demonstrates significant potential in nursing, facilitating the use of clinical practice data for research and decision-making. The choice of AI techniques varies based on the specific objectives and requirements of the model. However, the heterogeneity of the studies included in this review limits the ability to draw definitive conclusions about the effectiveness of AI applications in critical care nursing. Future research should focus on more robust, interventional studies to assess the impact of AI on nursing-sensitive outcomes. Additionally, exploring a broader range of health outcomes and AI applications in critical care will be crucial for advancing AI integration in nursing practices
Extending PubMed searches to ClinicalTrials.gov through a machine learning approach for systematic reviews
No full textObjectives: Despite their essential role in collecting and organizing published medical literature, indexed search engines are unable to cover all relevant knowledge. Hence, current literature recommends the inclusion of clinical trial registries in systematic reviews (SRs). This study aims to provide an automated approach to extend a search on PubMed to the ClinicalTrials.gov database, relying on text mining and machine learning techniques. Study Design and Setting: The procedure starts from a literature search on PubMed. Next, it considers the training of a classifier that can identify documents with a comparable word characterization in the ClinicalTrials.gov clinical trial repository. Fourteen SRs, covering a broad range of health conditions, are used as case studies for external validation. A cross-validated support-vector machine (SVM) model was used as the classifier. Results: The sensitivity was 100% in all SRs except one (87.5%), and the specificity ranged from 97.2% to 99.9%. The ability of the instrument to distinguish on-topic from off-topic articles ranged from an area under the receiver operator characteristic curve of 93.4% to 99.9%. Conclusion: The proposed machine learning instrument has the potential to help researchers identify relevant studies in the SR process by reducing workload, without losing sensitivity and at a small price in terms of specificity
Screening PubMed abstracts: is class imbalance always a challenge to machine learning?
Full text linkThe growing number of medical literature and textual data in online repositories led to an exponential increase in the workload of researchers involved in citation screening for systematic reviews. This work aims to combine machine learning techniques and data preprocessing for class imbalance to identify the outperforming strategy to screen articles in PubMed for inclusion in systematic reviews
A first estimation of the impact of public health actions against COVID-19 in Veneto (Italy)
Full text linkBackground Veneto is one of the first Italian regions where the COVID-19 outbreak started spreading. Containment measures were approved soon thereafter. The present study aims at providing a first look at the impact of the containment measures on the outbreak progression in the Veneto region, Italy. Methods A Bayesian changepoint analysis was used to identify the changing speed of the epidemic curve. Then, a piecewise polynomial model was considered to fit the data in the first period before the detected changepoint. In this time interval, that is, the weeks from 27 February to 12 March, a quadratic growth was identified by a generalised additive model (GAM). Finally, the model was used to generate the projection of the expected number of hospitalisations at 2 weeks based on the epidemic speed before the changepoint. Such estimates were then compared with the actual outbreak behaviour. Results The comparison between the observed and predicted hospitalisation curves highlights a slowdown on the total COVID-19 hospitalisations after the onset of containment measures. The estimated daily slowdown effect of the epidemic growth is estimated as 78 hospitalisations per day as of 27 March (95% CI 75 to 81). Conclusions The containment strategies seem to have positively impacted the progression of the COVID-19 epidemic outbreak in Veneto
A pipeline for developing deep learning prognostic prediction models in cardiac magnetic resonance image analysis
Full text linkPatients and healthcare professionals require clinical prediction models to accurately guide healthcare decisions, although an awareness of the limitations of regression-based models has recently increased. Deep learning (DL) has emerged as a promising alternative to traditional regression-based models, due to its ability to effectively analyse heterogeneous types of data, ranging from numerical variables to medical images. Building a DL model presents various challenges, including conceptualizing the clinical problem, selecting appropriate variables and model architecture, and providing explainability. We propose a four-step pipeline for developing DL-based prediction models for cardiac magnetic resonance image analysis. This framework aims to support researchers in exploring DL application across the broad spectrum of cardiology, with a specific focus on advancement in arrhythmic risk prediction. The field of cardiomyopathy faces challenges when assessing arrhythmic risk due to the low accuracy of the current prediction models. Research efforts have focused on developing DL models able to predict major arrhythmic events in dilated cardiomyopathy. While the initial results are promising, further tests are needed before translating these models into clinical practice
Time trends in first hospitalization for heart failure in a community-based population
No full textBACKGROUND:
This study aims to assess time trends in first hospitalization for heart failure (HF) in a community-based population over the period from 1977 to 2014.
METHODS:
Population-based cohort study using resources from the "Martignacco project" started in 1977 and promoted by the WHO. Three thousand and sixty-six subjects were involved in the project with follow-up through December 2014. Estimates were made for age-specific incidence rates for the first hospitalization for HF by birth cohort, calendar period, and gender. To disentangle the effects of age, calendar period, and birth cohort on the overall temporal trend in HF, we performed an age-period-cohort (APC) analysis.
RESULTS:
An incident hospitalization for HF was reported for 427 subjects. In the APC model, a cohort effect with a turning point in 1930 was observed. After 1930, a sharp decrease in the rate ratios (RRs) occurred in among both genders. The estimated RR in the 1940 birth cohort decreased to 0.43, (95% CI 0.19-0.92), in men and to 0.45, (95% CI 0.16-1.26), in women. A residual effect of calendar period on RR was observed with a plateau in 1995 for women and in 2000 for men, followed by a decline.
CONCLUSIONS:
The current findings showed that HF hospitalization incidence has declined over the period considered in subjects over 65 years living in a geographically defined community in Northeast Italy. Moreover, the age of birth, calendar period of diagnosis, and birth cohort play an important role in the incidence of the first hospitalization for HF
- …
