Automatically disambiguating medical acronyms with ontology-aware deep learning

Modern machine learning (ML) technologies have great promise for automating diverse clinical and research workflows; however, training them requires extensive hand-labelled datasets. Disambiguating abbreviations is important for automated clinical note processing; however, broad deployment of ML for this task is restricted by the scarcity and imbalance of labeled training data. In this work we present a method that improves a model’s ability to generalize through novel data augmentation techniques that utilizes information from biomedical ontologies in the form of related medical concepts, as well as global context information within the medical note. We train our model on a public dataset (MIMIC III) and test its performance on automatically generated and hand-labelled datasets from different sources (MIMIC III, CASI, i2b2). Together, these techniques boost the accuracy of abbreviation disambiguation by up to 17% on hand-labeled data, without sacrificing performance on a held-out test set from MIMIC III.

Desarrollo de un sistema web para captura de notas post-operatorias entre unidades de salud remotas

The impact of the use of Information and Communication Technologies (ICT) in the Health Sector, as in many other fields, has made it possible to reform the services aimed at improving medical care, you can see the importance and positive, orderly and modern effect with which patient information is managed through standardized systems for the benefit of the population's health care. Doctors who have a technological tool that allows them to generate daily medical notes, add them to an electronic medical record of the patient and consult them later, have a great advantage over doctors who do not have a system where they can analyze a health history, the indications, diagnoses or treatments described in notes of admission, evolution, discharge, post-operative medical note, or notes of outpatient surgeries, leaving not only the doctor at a disadvantage, but also the patient who is treated without having important information for a higher quality care. This study focuses on the factors that must be addressed for an adequate implementation of an Electronic File System (SEE) in medical units that attend to patients in common, in order to contribute to modernizing the current health systems in the locality by connect two remote medical units through a web system for the management of medical information of patients.

Systemic Inflammation Is Associated With Neurologic Involvement in Pediatric Inflammatory Multisystem Syndrome Associated With SARS-CoV-2

ObjectivePediatric inflammatory multisystem syndrome temporally associated with SARS-CoV-2 (PIMS-TS) is a severe immune-mediated disorder. We aim to report the neurologic features of children with PIMS-TS.MethodsWe identified children presenting to a large children's hospital with PIMS-TS from March to June 2020 and performed a retrospective medical note review, identifying clinical and investigative features alongside short-term outcome of children presenting with neurologic symptoms.ResultsSeventy-five patients with PIMS-TS were identified, 9 (12%) had neurologic involvement: altered conciseness (3), behavioral changes (3), focal neurology deficits (2), persistent headaches (2), hallucinations (2), excessive sleepiness (1), and new-onset focal seizures (1). Four patients had cranial images abnormalities. At 3-month follow-up, 1 child had died, 1 had hemiparesis, 3 had behavioral changes, and 4 completely recovered. Systemic inflammatory and prothrombotic markers were higher in patients with neurologic involvement (mean highest CRP 267 vs 202 mg/L, p = 0.05; procalcitonin 30.65 vs 13.11 μg/L, p = 0.04; fibrinogen 7.04 vs 6.17 g/L, p = 0.07; d-dimers 19.68 vs 7.35 mg/L, p = 0.005). Among patients with neurologic involvement, these markers were higher in those without full recovery at 3 months (ferritin 2284 vs 283 μg/L, p = 0.05; d-dimers 30.34 vs 6.37 mg/L, p = 0.04). Patients with and without neurologic involvement shared similar risk factors for PIMS-TS (Black, Asian and Minority Ethnic ethnicity 78% vs 70%, obese/overweight 56% vs 42%).ConclusionsBroad neurologic features were found in 12% patients with PIMS-TS. By 3-month follow-up, half of these surviving children had recovered fully without neurologic impairment. Significantly higher systemic inflammatory markers were identified in children with neurologic involvement and in those who had not recovered fully.

Educator perspectives on concussion management in the college classroom: a grounded theory introduction to collegiate return-to-learn

ObjectivesTo gather the perspectives of collegiate instructors regarding how concussion is managed within the college classroom. To introduce the themes surrounding collegiate return-to-learn (RTL) and the classroom management of students with concussion.DesignQualitative grounded theory.SettingLarge, public university in the Midwest.ParticipantsTwenty-three college instructors participated in a private, semistructured, audio-recorded, one-on-one interview. Participants included 12 males and 11 females. Interview recordings were transcribed verbatim, followed by an iterative process of open-coding and axial-coding, performed by two researchers.ResultsThree themes emerged from the coded data: (1) awareness—external knowledge of concussion and previous experiences, (2) legitimacy—medical note provided and no note provided and (3) accommodating the student—instructor’s role and feasibility of the accommodation. Psychosocial factors such as small class sizes, graduate-level students and an instructor’s empathy appeared to influence an instructor’s decision making when accommodating a student recovering from concussion.ConclusionThese novel data provide foundational evidence regarding how college instructors perceive and subsequently manage concussion within the classroom, while also offering accuracy to aims of subsequent collegiate RTL investigationsArticle summaryRTL is an emerging field within concussion management, yet is grossly underexplored within the college setting. By utilising a grounded theory approach, this article introduces the themes that dictate the landscape of RTL for a college student.

Inter and intra-observer errors for postoperative total hip radiographic assessment using computer aided design

Plain radiographic assessment of primary total hip arthroplasty following surgery remains to be the commonest radiological assessment. The current paper, studies the accuracy and concordance between observers reviewing these radiographs. A prospective radiographic and medical note review of ten patients who underwent total hip replacement for primary osteoarthritis, with a mean age of 69 years. Early and 6 weeks postoperative x-rays were assessed for hip profile and version profile using computer aided design (CAD) by two observers on two different occasions. The observers were Orthopaedic surgeons who perform arthroplasty of the hip. The results were analyzed statistically. Dimensions, including Femoral offset, medial offset and ilioischial offset showed a high degree of inter- film and intra-film correlation, with inter-class correlation (ICC) over 0.8. Except of the intra-film correlation of ilioischial offset measured on the post- operative films (p=0.067) by the first rater, all the intra and inter film correlation were significantly over the benchmark of 0.6. In terms of stem alignment, cup inclination and cup version, the intra-film correlation by rater n°2 ranges from 0.574 to 0.975 and were significantly over the benchmark of 0.6, except in the case of cup inclination measured on the 6 th? week follow-up ; meanwhile the intra-film correlation by rater n°1 ranges from 0.581 to 0.819 and none were significantly over the benchmark of 0.6. The inter-rater reliability and inter-film correlation showed a dichotomy of results among different dimensions of the measurement. Dimensions of femo- ral offset, medial offset and ilioischial offset showed a substantial degree of reliability in terms of inter-rater reliability, inter-film correlation, and intra-rater/film reliability.

Being Alive in Descartes' Physiology: Animals and Plants, the Immutatio and the Impetus

In René Descartes' works there are four major references to living bodies as objects of his natural philosophy. The first is contained in the Fifth part of the Discours de la Méthode, published in June 1637, where Descartes provides a mechanical explanation of the heartbeat and other living functions of the body. The second is in a bio-medical note collected in the Excerpta anatomica dated November 1637, where he discusses nutrition and growth. The third is the famous claim on the absence of a section on living bodies in the Principia philosophiae, published in 1644. The fourth is in La Description du corps humain, Descartes' late physiology likely dated 1647-1648. In this article, by exploring these passages and contextualizing his physiological observations of animals and plants, I reassemble Descartes' science of life: his dismissal of soul, his mechanical framework, his interpretation of bodily self-maintenance and growth, his understanding of living bodies as integrated and organic systems, and the role of a power such as the immutatio and forces such as the impetus.