Search

Unstructured clinical notes contain a huge amount of information. We investigated the possibility of harvesting such information through an NLP-based approach. A manually curated ontology is the only resource required to handle all the steps of the process leading from clinical narrative to a structured data warehouse (i2b2). We have tested our approach at the Papa Giovanni XXIII hospital in Bergamo (Italy) on pathology reports collected since 2008. [ABSTRACT FROM AUTHOR]

Abstract Background Suboptimal translation of valid and relevant information in clinical practice is a problem for all health systems. Lack of information independent from commercial influences, limited efforts to actively implement evidence-based information and its limited comprehensibility are important determinants of this gap and may influence an excessive variability in physicians' prescriptions. This is quite noticeable in Italy, where the philosophy and methods of Evidence-Based Medicine still enjoy limited diffusion among practitioners. Academic detailing and pharmacist outreach visits are interventions of proven efficacy to make independent and evidence-based information available to physicians; this approach and its feasibility have not yet been tested on a large scale and, moreover, they have never been formally tested in Italy. Methods/Design Two RCTs are planned: 1) a two-arm cluster RCT, carried out in Emilia-Romagna and Friuli Venezia Giulia, will evaluate the effectiveness of small group meetings, randomising about 150 Primary Care Groups (corresponding to about 2000 GPs) to pharmacist outreach visits on two different topics. Physicians' prescriptions (expressed as DDD per 1000 inhabitants/day), knowledge and attitudes (evaluated through the answers to a specific questionnaire) will be compared for target drugs in the two groups (receiving/not receiving each topic). 2) A three-arm RCT, carried out in Sardinia, will evaluate both the effectiveness of one-to-one meetings (one pharmacist visiting one physician per time) and of a 'new' information format (compared to information already available) on changing physicians' prescription of specific drugs. About 900 single GPs will be randomised into three groups: physicians receiving a visit supported by "traditional" information material, those receiving a visit with "new" information material on the same topic and those not receiving any visit/material. Discussion The two proposed RCTs aim to evaluate the organisational feasibility and barriers to the implementation of independent information programs led by NHS pharmacists. The objective to assess a 10 or 15% decreases in the prescription of the targeted drugs is quite ambitious in such 'natural' settings, which will be minimally altered by the interventions themselves; this in spite of the quite large sample sizes used comparing to other studies of these kind. Complex interventions like these are not easy to evaluate, given the many different variables into play. Anyway, the pragmatic nature of the two RCTs appears to be also one of their major strengths, helping to provide a deeper insight on what is possible to achieve – in terms of independent information – in a National Health System, with special reference to Italy. Trial registration ISRCTN05866587 (cluster RCT) and ISRCTN28525676 (single GPs RCT)

Objectives: Attention deficit hyperactivity disorder (ADHD) is a prevalent childhood disorder, but often goes unrecognised and untreated. To improve access to services, accurate predictions of populations at high risk of ADHD are needed for effective resource allocation. Using a unique linked health and education data resource, we examined how machine learning (ML) approaches can predict risk of ADHD., Design: Retrospective population cohort study., Setting: South London (2007-2013)., Participants: n=56 258 pupils with linked education and health data., Primary Outcome Measures: Using area under the curve (AUC), we compared the predictive accuracy of four ML models and one neural network for ADHD diagnosis. Ethnic group and language biases were weighted using a fair pre-processing algorithm., Results: Random forest and logistic regression prediction models provided the highest predictive accuracy for ADHD in population samples (AUC 0.86 and 0.86, respectively) and clinical samples (AUC 0.72 and 0.70). Precision-recall curve analyses were less favourable. Sociodemographic biases were effectively reduced by a fair pre-processing algorithm without loss of accuracy., Conclusions: ML approaches using linked routinely collected education and health data offer accurate, low-cost and scalable prediction models of ADHD. These approaches could help identify areas of need and inform resource allocation. Introducing 'fairness weighting' attenuates some sociodemographic biases which would otherwise underestimate ADHD risk within minority groups., Competing Interests: Competing interests: None declared., (© Author(s) (or their employer(s)) 2022. Re-use permitted under CC BY. Published by BMJ.)

Receiving timely and appropriate treatment is crucial for better health outcomes, and research on the contribution of specific variables is essential. In the mental health domain, an important research variable is the date of psychosis symptom onset, as longer delays in treatment are associated with worse intervention outcomes. The growing adoption of electronic health records (EHRs) within mental health services provides an invaluable opportunity to study this problem at scale retrospectively. However, disease onset information is often only available in open text fields, requiring natural language processing (NLP) techniques for automated analyses. Since this variable can be documented at different points during a patient's care, NLP methods that model clinical and temporal associations are needed. We address the identification of psychosis onset by: 1) manually annotating a corpus of mental health EHRs with disease onset mentions, 2) modelling the underlying NLP problem as a paragraph classification approach, and 3) combining multiple onset paragraphs at the patient level to generate a ranked list of likely disease onset dates. For 22/31 test patients (71%) the correct onset date was found among the top-3 NLP predictions. The proposed approach was also applied at scale, allowing an onset date to be estimated for 2483 patients.

Objective: To evaluate the susceptibility to coronavirus disease 2019 (COVID-19) in patients with autoimmune conditions treated with antimalarials in a population-based study., Methods: All residents treated with chloroquine (CQ)/hydroxychloroquine (HCQ) from July through December 2019 and living in 3 provinces of Regione Emilia-Romagna were identified by drug prescription registries and matched with the registry containing all residents living in the same areas who have had swabs and tested positive for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Odds ratios (ORs) and 95% confidence intervals (95% CIs) were calculated., Results: A total of 4,408 patients were identified. The prevalence of patients receiving antimalarials was 0.85 per 1,000 men and 3.3 per 1,000 women. The cumulative incidence of testing during the study period was 2.7% in the general population and 3.8% among those receiving CQ or HCQ, while the cumulative incidence of testing positive was 0.55% in the general population and 0.70% among those receiving CQ/HCQ. Multivariate models showed that those receiving CQ/HCQ had a slightly higher probability of being tested compared to the general population (OR 1.09 [95% CI 0.94-1.28]), the same probability of being diagnosed as having COVID-19 (OR 0.94 [95% CI 0.66-1.34]), and a slightly lower probability of being positive once tested (OR 0.83 [95% CI 0.56-1.23]). None of the differences were significant., Conclusion: Our findings do not support the use of antimalarials as a prophylactic treatment of COVID-19., (© 2020, American College of Rheumatology.)

Chronic fatigue syndrome (CFS) is a long-term illness with a wide range of symptoms and condition trajectories. To improve the understanding of these, automated analysis of large amounts of patient data holds promise. Routinely documented assessments are useful for large-scale analysis, however relevant information is mainly in free text. As a first step to extract symptom and condition trajectories, natural language processing (NLP) methods are useful to identify important textual content and relevant information. In this paper, we propose an agnostic NLP method of extracting segments of patients' clinical histories in CFS assessments. Moreover, we present initial results on the advantage of using these segments to quantify and analyse the presence of certain clinically relevant concepts.

A serious obstacle to the development of Natural Language Processing (NLP) methods in the clinical domain is the accessibility of textual data. The mental health domain is particularly challenging, partly because clinical documentation relies heavily on free text that is difficult to de-identify completely. This problem could be tackled by using artificial medical data. In this work, we present an approach to generate artificial clinical documents. We apply this approach to discharge summaries from a large mental healthcare provider and discharge summaries from an intensive care unit. We perform an extensive intrinsic evaluation where we (1) apply several measures of text preservation; (2) measure how much the model memorises training data; and (3) estimate clinical validity of the generated text based on a human evaluation task. Furthermore, we perform an extrinsic evaluation by studying the impact of using artificial text in a downstream NLP text classification task. We found that using this artificial data as training data can lead to classification results that are comparable to the original results. Additionally, using only a small amount of information from the original data to condition the generation of the artificial data is successful, which holds promise for reducing the risk of these artificial data retaining rare information from the original data. This is an important finding for our long-term goal of being able to generate artificial clinical data that can be released to the wider research community and accelerate advances in developing computational methods that use healthcare data., Competing Interests: Competing interestsThe authors declare no competing interests., (© The Author(s) 2020.)

Background: Duration of untreated psychosis (DUP) is an important clinical construct in the field of mental health, as longer DUP can be associated with worse intervention outcomes. DUP estimation requires knowledge about when psychosis symptoms first started (symptom onset), and when psychosis treatment was initiated. Electronic health records (EHRs) represent a useful resource for retrospective clinical studies on DUP, but the core information underlying this construct is most likely to lie in free text, meaning it is not readily available for clinical research. Natural Language Processing (NLP) is a means to addressing this problem by automatically extracting relevant information in a structured form. As a first step, it is important to identify appropriate documents, i.e., those that are likely to include the information of interest. Next, temporal information extraction methods are needed to identify time references for early psychosis symptoms. This NLP challenge requires solving three different tasks: time expression extraction, symptom extraction, and temporal "linking". In this study, we focus on the first step, using two relevant EHR datasets., Results: We applied a rule-based NLP system for time expression extraction that we had previously adapted to a corpus of mental health EHRs from patients with a diagnosis of schizophrenia (first referrals). We extended this work by applying this NLP system to a larger set of documents and patients, to identify additional texts that would be relevant for our long-term goal, and developed a new corpus from a subset of these new texts (early intervention services). Furthermore, we added normalized value annotations ("2011-05") to the annotated time expressions ("May 2011") in both corpora. The finalized corpora were used for further NLP development and evaluation, with promising results (normalization accuracy 71-86%). To highlight the specificities of our annotation task, we also applied the final adapted NLP system to a different temporally annotated clinical corpus., Conclusions: Developing domain-specific methods is crucial to address complex NLP tasks such as symptom onset extraction and retrospective calculation of duration of a preclinical syndrome. To the best of our knowledge, this is the first clinical text resource annotated for temporal entities in the mental health domain.

For patients with a diagnosis of schizophrenia, determining symptom onset is crucial for timely and successful intervention. In mental health records, information about early symptoms is often documented only in free text, and thus needs to be extracted to support clinical research. To achieve this, natural language processing (NLP) methods can be used. Development and evaluation of NLP systems requires manually annotated corpora. We present a corpus of mental health records annotated with temporal relations for psychosis symptoms. We propose a methodology for document selection and manual annotation to detect symptom onset information, and develop an annotated corpus. To assess the utility of the created corpus, we propose a pilot NLP system. To the best of our knowledge, this is the first temporally-annotated corpus tailored to a specific clinical use-case.

Clinical narratives are a valuable source of information for both patient care and biomedical research. Given the unstructured nature of medical reports, specific automatic techniques are required to extract relevant entities from such texts. In the natural language processing (NLP) community, this task is often addressed by using supervised methods. To develop such methods, both reliably-annotated corpora and elaborately designed features are needed. Despite the recent advances on corpora collection and annotation, research on multiple domains and languages is still limited. In addition, to compute the features required for supervised classification, suitable language- and domain-specific tools are needed. In this work, we propose a novel application of recurrent neural networks (RNNs) for event extraction from medical reports written in Italian. To train and evaluate the proposed approach, we annotated a corpus of 75 cardiology reports for a total of 4365 mentions of relevant events and their attributes (e.g., the polarity). For the annotation task, we developed specific annotation guidelines, which are provided together with this paper. The RNN-based classifier was trained on a training set including 3335 events (60 documents). The resulting model was integrated into an NLP pipeline that uses a dictionary lookup approach to search for relevant concepts inside the text. A test set of 1030 events (15 documents) was used to evaluate and compare different pipeline configurations. As a main result, using the RNN-based classifier instead of the dictionary lookup approach allowed increasing recall from 52.4% to 88.9%, and precision from 81.1% to 88.2%. Further, using the two methods in combination, we obtained final recall, precision, and F1 score of 91.7%, 88.6%, and 90.1%, respectively. These experiments indicate that integrating a well-performing RNN-based classifier with a standard knowledge-based approach can be a good strategy to extract information from clinical text in non-English languages., (Copyright © 2019 Elsevier Inc. All rights reserved.)

Objective: In this work, we propose an ontology-driven approach to identify events and their attributes from episodes of care included in medical reports written in Italian. For this language, shared resources for clinical information extraction are not easily accessible., Materials and Methods: The corpus considered in this work includes 5432 non-annotated medical reports belonging to patients with rare arrhythmias. To guide the information extraction process, we built a domain-specific ontology that includes the events and the attributes to be extracted, with related regular expressions. The ontology and the annotation system were constructed on a development set, while the performance was evaluated on an independent test set. As a gold standard, we considered a manually curated hospital database named TRIAD, which stores most of the information written in reports., Results: The proposed approach performs well on the considered Italian medical corpus, with a percentage of correct annotations above 90% for most considered clinical events. We also assessed the possibility to adapt the system to the analysis of another language (i.e., English), with promising results., Discussion and Conclusion: Our annotation system relies on a domain ontology to extract and link information in clinical text. We developed an ontology that can be easily enriched and translated, and the system performs well on the considered task. In the future, it could be successfully used to automatically populate the TRIAD database., (Copyright © 2017 Elsevier B.V. All rights reserved.)

Medical reports often contain a lot of relevant information in the form of free text. To reuse these unstructured texts for biomedical research, it is important to extract structured data from them. In this work, we adapted a previously developed information extraction system to the oncology domain, to process a set of anatomic pathology reports in the Italian language. The information extraction system relies on a domain ontology, which was adapted and refined in an iterative way. The final output was evaluated by a domain expert, with promising results.

Background: There are limited data on the characterization of medication-related visits (MRVs) to the emergency department (ED) in pediatric patients in Italy. We have estimated the frequency, severity, and classification of MRVs to the ED in pediatric patients., Methods: We retrospectively analyzed data for children seeking medical evaluation for a MRV over an 8 years period. A medication-related ED visit was identified by using a random pharmacist assessment, emergency physician assessment, and in case of conflicting events, by a third investigators random assessment., Results: In this study, regarding a single tertiary center in Italy, on a total of 147,643 patients from 0 to 14 years old, 497 medication-related visits were found, 54% of which occurred in children from 0 to 2 years of age. Severity was classified as mild in 21.6% of cases, moderate in 67.2% of cases, and severe in 11.2% of cases. The most common events were related to drug use without indication (51%), adverse drug reactions (30.3%), supratherapeutic dosage (13.2%) and improper drug selection (4.5%). The medication classes most frequently implicated in an ADE were anti-infective drugs for systemic use (28.9%), central nervous system agents (22.3%) and respiratory system drugs (10.8%). The most common symptom manifestations were dermatologic conditions (46.1%), general disorder and administration site conditions (29.7%) and gastrointestinal symptoms (16.0%)., Conclusions: To our knowledge, this is the first study in Italy evaluating the epidemiologic characteristics of MRVs confirming a significant cause of healthcare contact resulting in ED visits and hospital admissions with associated resource utilization. Our results suggests further future prospective, large-sample sized, and multicenter research is necessary to better understand the impact of MRVs and to develop strategies to provide care plans and monitor patients to prevent medication-related visits., Trial Registration: Not applicable.

Objectives: This survey aims at highlighting the latest trends (2012-2014) on the development, use, and evaluation of Information and Communication Technologies (ICT) based decision support systems (DSSs) in medicine, with a particular focus on patient-centered and personalized care., Methods: We considered papers published on scientific journals, by querying PubMed and Web of ScienceTM. Included studies focused on the implementation or evaluation of ICT-based tools used in clinical practice. A separate search was performed on computerized physician order entry systems (CPOEs), since they are increasingly embedding patient-tailored decision support., Results: We found 73 papers on DSSs (53 on specific ICT tools) and 72 papers on CPOEs. Although decision support through the delivery of recommendations is frequent (28/53 papers), our review highlighted also DSSs only based on efficient information presentation (25/53). Patient participation in making decisions is still limited (9/53), and mostly focused on risk communication. The most represented medical area is cancer (12%). Policy makers are beginning to be included among stakeholders (6/73), but integration with hospital information systems is still low. Concerning knowledge representation/management issues, we identified a trend towards building inference engines on top of standard data models. Most of the tools (57%) underwent a formal assessment study, even if half of them aimed at evaluating usability and not effectiveness., Conclusions: Overall, we have noticed interesting evolutions of medical DSSs to improve communication with the patient, consider the economic and organizational impact, and use standard models for knowledge representation. However, systems focusing on patient-centered care still do not seem to be available at large.