Search

Electronic Health Records (EHRs) contain a wealth of unstructured patient data, making it challenging for physicians to do informed decisions. In this paper, we introduce a Natural Language Processing (NLP) approach for the extraction of therapies, diagnosis, and symptoms from ambulatory EHRs of patients with chronic Lupus disease. We aim to demonstrate the effort of a comprehensive pipeline where a rule-based system is combined with text segmentation, transformer-based topic analysis and clinical ontology, in order to enhance text preprocessing and automate rules' identification. Our approach is applied on a sub-cohort of 56 patients, with a total of 750 EHRs written in Italian language, achieving an Accuracy and an F-score over 97% and 90% respectively, in the three extracted domains. This work has the potential to be integrated with EHR systems to automate information extraction, minimizing the human intervention, and providing personalized digital solutions in the chronic Lupus disease domain.

Background: Chronic obstructive pulmonary disease (COPD) is the fourth most important cause of death in high-income countries. Inappropriate use of COPD inhaled therapy, including the low adherence (only 10 %-40 % of patients reporting an adequate compliance) may shrink or even nullify the proven benefits of these medications. As such, an accurate prediction algorithm to assess at national level the risk of COPD exacerbation might be relevant for general practictioners (GPs) to improve patient's therapy., Methods: We formed a cohort of patients aged 45 years or older being diagnosed with COPD in the period between January 2013 to December 2021. Each patient was followed until occurrence of COPD exacerbation up to the end of 2021. Sixteen determinants were adopted to assemble the CopdEX(CEX)-Health Search(HS)core, which was therefore developed and validated through the related two sub-cohorts., Results: We idenfied 63763 patients aged 45 years or older being diagnosed with COPD (mean age: 67.8 (SD:11.7); 57.7 % males).When the risk of COPD exacerbation was estimated via CEX-HScore, its predicted value was equal to 14.22 % over a 6-month event horizon. Discrimination accuracy and explained variation were equal to 66 % (95 % CI: 65-67 %) and 10 % (95 % CI: 9-11 %), respectively. The calibration slope did not significantly differ from the unit (p = 0.514)., Conclusions: The CEX-HScore was featured by fair accuracy for prediction of COPD-related exacerbations over a 6-month follow-up. Such a tool might therefore support GPs to enhance COPD patients' care, and improve their outcomes by facilitating personalized approaches through a score-based decision support system., Competing Interests: Declaration of competing interest FL and EM provided consultancies in protocol preparation for epidemiological studies and data analyses for GSK, AstraZeneca, and Chiesi. FPL provided clinical consultances for GSK, AstraZeneca, and Chiesi. CC provided clinical and scientific consultances for epidemiological studies for GSK, AstraZeneca, and Chiesi. CM received fees as a speaker from AstraZeneca, Sanofi, Novartis, GSK, Chiesi, Menarini, Zambon, Berlin-Chemie. FDM has received honoraria for lectures at national and international meetings, served as a consultant, and received financial support for research from AstraZeneca, Boehringer Ingelheim, Chiesi Farmaceutici, Guidotti/Malesci, GSK, Menarini, Neopharmed Gentili, Novartis, Sanofi and Zambon. EA and MG are employees at AstraZeneca., (Copyright © 2024 Elsevier Ltd. All rights reserved.)

The Italian Network on Congestive Heart Failure (IN-CHF) project, later known as IN-HF Online, was launched in 1995 to provide the Italian cardiology community with a digital tool, standardized across the country, for managing outpatients with heart failure (HF), that enabled the creation of a database for clinical, educational and scientific purposes. During its almost three decades of activity, this observational research program has achieved highly positive scientific results. Indeed, IN-HF fostered professional relationships among individuals working in different centers, established a cultural network for the care of HF patients, periodically updated on the scientific advances, and allowed the assessment of several clinical, epidemiological, and prognostic features. These findings have been published in numerous national and international journals, as summarized in the present overview.

Objective: To develop and validate the Asthma Severity-Health Search (AS-HScore), predicting severe asthma risk in Italian primary care. According to the current asthma treatment guidelines, the AS-HScore intended to serve as a clinical decision support system (CDSS) for General Practitioners (GPs)., Methods: Using the Health Search Database (HSD), a cohort of 32,917 asthma-diagnosed patients between 2013 and 2021 was identified. The AS-HScore was developed using multivariable Cox regression in a two-part cohort: development and validation. Candidate determinants were estimated and linearly combined to form the score; its predictive accuracy was evaluated in the validation sub-cohort., Results: AS-HScore performance in the validation cohort revealed a 73% area under the curve (i.e. discrimination power) and a 22% pseudo-R 2 (explained variation). Calibration slope of 1.07 indicated strong calibration without rejecting the equivalence hypothesis ( p  = 0.157). Estimating a mean 10% (SD: 6.8%) 1-year risk of severe asthma, GPs might be provided with risk thresholds for patient categorization., Conclusion: The AS-HScore emerges as an accurate tool predicting severe asthma risk in the Italian primary care. It therefore shows promising application to enhance asthma care by early identification of severe cases. Implementing a score-based CDSS for Italian GPs holds potential for significantly improving asthma management and patients' outcomes.

Randomised clinical trials, observational studies, and meta-analyses have shown that sodium-glucose cotransporter 2 inhibitors (SGLT2-i) reduce the risk of hospitalisation for heart failure (HF), chronic kidney disease (CKD) progression, and mortality in patients with HF, irrespective of the presence of type 2 diabetes mellitus. However, real-world epidemiology may differ from clinical trial populations, thereby limiting generalisability and delaying the introduction of novel treatments in clinical practice.The aim of the present study was to assess the prevalence of DAPA-HF (Dapagliflozin and Prevention of Adverse Outcomes in Heart Failure) inclusion criteria in a population of HF with reduced ejection fraction (HFrEF) patients enrolled in the Italian Network on Heart Failure (IN-HF) registry.Overall, 3415 IN-HF patients matched the 4744 patients in DAPA-HF, overlapping for most baseline characteristics (e.g. similar average ejection fraction), with a slightly lower prevalence of type 2 diabetes and of HF ischaemic aetiology and a higher percentage of NYHA class II patients. The theoretical eligibility to DAPA-HF in a cardiology setting resulted to be 73%.The availability of an easily accessible database from a large nationwide prospective registry allows to provide insights to clinicians and policy makers on the applicability of the DAPA HF findings to a contemporary population of HFrEF patients followed by cardiologists. It is reasonable to assume that the results of this analysis can be applicable to the entire SGLT2-ir class of drugs.

Objective: To train and test a model predicting chronic kidney disease (CKD) using the Generalized Additive2 Model (GA2M), and compare it with other models being obtained with traditional or machine learning approaches., Materials: We adopted the Health Search Database (HSD) which is a representative longitudinal database containing electronic healthcare records of approximately 2 million adults., Methods: We selected all patients aged 15 years or older being active in HSD between January 1, 2018 and December 31, 2020 with no prior diagnosis of CKD. The following models were trained and tested using 20 candidate determinants for incident CKD: logistic regression, Random Forest, Gradient Boosting Machines (GBMs), GAM, and GA2M. Their prediction performances were compared by calculating Area Under Curve (AUC) and Average Precision (AP)., Results: Comparing the predictive performances of the 7 models, the AUC and AP for GBM and GA2M showed the highest values which were equal to 88.9%, 88.8% and 21.8%, 21.1%, respectively. These 2 models outperformed the others including logistic regression. In contrast to GBMs, GA2M kept the interpretability of variable combinations, including interactions and nonlinearities assessment., Discussion: Although GA2M is slightly less performant than light GBM, it is not "black-box" algorithm, so being simply interpretable using shape and heatmap functions. This evidence supports the fact machine learning techniques should be adopted in case of complex algorithms such as those predicting the risk of CKD., Conclusion: The GA2M was reliably performant in predicting CKD in primary care. A related decision support system might be therefore implemented., (© The Author(s) 2023. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For permissions, please email: journals.permissions@oup.com.)

Purpose: This study sought to describe patient characteristics and treatment patterns among patients with insomnia prescribed trazodone in the United States., Methods: This real-world, retrospective, descriptive cohort study used US commercial insurance claims from July 1, 2009, through June 30, 2019. The index date was the first prescription for trazodone between January 1, 2010, and December 31, 2018, with 6 months for the preindex period and ≥6 months for the postindex period., Findings: Among 5.8 million patients with insomnia, 17.7% were prescribed trazodone, and 357,380 adults (6.2%) and 7564 children (0.1%) met the study eligibility criteria. The mean (SD) age was 48.8 (15.8) years for adults and 14.8 (2.7) years for pediatrics. Most patients were female (229,280 adults [64.2%] and 4481 children [59.2%]). Insomnia due to mental disorder was the most common specific diagnosis. The most common (>25%) comorbid conditions were anxiety, depression, and hypertensive disease, and 1 of 10 had a history of substance abuse. Zolpidem was previously prescribed (73,342 adults [20.5%] and 233 children [3.1%]) and continued to be prescribed. Concomitant antidepressants were most common (216,893 adults [60.7%] and 5414 children [71.6%]), but benzodiazepines (132,740 adults [37.1%] and 1188 children [15.7%]), antiepileptics (115,064 adults [32.2%] and 2103 children [27.8%]), nonbenzodiazepines (90,946 adults [25.4%] and 542 children [7.2%]), and antipsychotics (40,490 adults [11.3%] and 2063 children [27.3%]) were also prescribed., Implications: This study provides current evidence that trazodone use is widespread among patients with insomnia and is often associated with other specific comorbidities, such as psychiatric conditions. A deeper knowledge of the real-world management of patients with insomnia may facilitate steps toward improving sleep quality, daytime functioning, and clinical outcomes for patients., Competing Interests: Declaration of Competing Interest All authors have seen and approved the manuscript. This study was sponsored by Angelini Pharma S.p.A., of which I. Pochiero, M. Gorini, A. Comandini, F. Calisti, G. Di Loreto, and A. Cattaneo are employees. The study was conducted by Labcorp Drug Development, of which T. Knight, K.P. Anastassopoulos, R. Patel, and R. Baik are employees. O. Bruni is a consultant for Fidia Pharma., (Copyright © 2022. Published by Elsevier Inc.)

Aim: The effect of switching from lithium immediate release (Li-IR) to lithium prolonged release (Li-PR) on lithium-induced tremor after 1 and 12 weeks of treatment was evaluated in a randomized, multicenter, open trial, in bipolar patients from the participating sites with a tremor severity ≥2 (Udvalg for Kliniske Undersøgelser [UKU] rating scale) despite optimal lithium titration., Methods: The primary endpoint was the evaluation of tremor by means of the UKU scale after 1 week of treatment. Secondary endpoints included manic Young Mania Rating Scale (YMRS) and depressive symptoms (Montgomery-Asberg Depression Rating Scale), a global assessment of the patient's status (Clinical Global Impression), polyuria/polydipsia (UKU item 3.8) and patient-reported outcomes., Results: Owing to difficulties in including suitable patients the enrollment phase was closed when 73 patients were randomized. Notwithstanding the lower number of patients, in the modified intention-to-treat population (n = 70) the primary endpoint was statistically significant: tremor improved after 1 week in 62.9% in Li-PR group against 20.0% of patients in Li-IR group (p = .0006; two-tailed Fisher's exact test). The difference remained statistically significant after 4 (p = .0031) and 12 weeks (p = .0128). The same analysis performed in the PP population confirmed these results. Among the secondary endpoints, only the factor convenience of the treatment satisfaction questionnaire showed a statistically significant difference between groups. There were no apparent differences in the safety profile of the two formulations., Conclusions: This study is the first comparative documentation of a potential benefit of the prolonged-release formulation in reducing the symptom tremor, a well-known adverse effect of lithium therapy. Indeed, the study results should be interpreted taking into account the sample size lower than planned., (© 2022 The Authors. Brain and Behavior published by Wiley Periodicals LLC.)

Background: High mannose has previously associated with insulin resistance and cardiovascular disease (CVD). Our objective is to establish whether mannose is associated with anatomical evidence of coronary artery disease (CAD)., Methods: Plasma mannose concentrations were measured by liquid chromatography/tandem mass spectrometry in a discovery cohort (n = 513) and a validation cohort (n = 221) of carefully phenotyped individuals. In both cohorts CAD was quantitated using state-of-the-art imaging techniques (coronary computed coronary tomography angiography (CCTA), invasive coronary angiography and optical coherence tomography). Information on subsequent CVD events/death was collected. Associations of mannose with angiographic variables and biomarkers were tested using univariate and multivariate regression models. Survival analysis was performed using the Kaplan-Meier estimator., Results: Mannose was related to indices of CAD and features of plaque vulnerability. In the discovery cohort, mannose was a marker of quantity and quality of CCTA-proven CAD and subjects with a mannose level in the top quartile had a significantly higher risk of CVD events/death (p = 3.6e-5). In the validation cohort, mannose was significantly associated with fibrous cap thickness < 65 μm (odds ratio = 1.32 per each 10 μmol/L mannose change [95% confidence interval, 1.05-1.65]) and was an independent predictor of death (hazard ratio for mannose≥vs < 84.6 μmol/L: 4.0(95%CI, 1.4-11.3), p = 0.006)., Conclusion: The current data add novel evidence that high mannose is a signature of CAD with a vulnerable plaque phenotype, consistently across measures of severity of vessel involvement and independent of the traditional correlates of CVD, and that it is an independent predictor of incident adverse outcomes., (Copyright © 2021 Elsevier B.V. All rights reserved.)