RESUMEN
In recent years, machine learning (ML) has been promisingly applied in many fields of clinical medicine, both for diagnosis and prognosis prediction. Aims of this narrative review were to summarize the basic concepts of ML applied to clinical medicine and explore its main applications in the emergency department (ED) setting, with a particular focus on syncope management. Through an extensive literature search in PubMed and Embase, we found increasing evidence suggesting that the use of ML algorithms can improve ED triage, diagnosis, and risk stratification of many diseases. However, the lacks of external validation and reliable diagnostic standards currently limit their implementation in clinical practice. Syncope represents a challenging problem for the emergency physician both because its diagnosis is not supported by specific tests and the available prognostic tools proved to be inefficient. ML algorithms have the potential to overcome these limitations and, in the future, they could support the clinician in managing syncope patients more efficiently. However, at present only few studies have addressed this issue, albeit with encouraging results.
Asunto(s)
Servicio de Urgencia en Hospital , Síncope , Humanos , Aprendizaje Automático , Pronóstico , Síncope/diagnóstico , Síncope/etiología , Síncope/terapia , TriajeRESUMEN
Syncope is a challenging problem in the emergency department (ED) as the available risk prediction tools have suboptimal predictive performances. Predictive models based on machine learning (ML) are promising tools whose application in the context of syncope remains underexplored. The aim of the present study was to develop and compare the performance of ML-based models in predicting the risk of clinically significant outcomes in patients presenting to the ED for syncope. We enrolled 266 consecutive patients (age 73, IQR 58-83; 52% males) admitted for syncope at three tertiary centers. We collected demographic and clinical information as well as the occurrence of clinically significant outcomes at a 30-day telephone follow-up. We implemented an XGBoost model based on the best-performing candidate predictors. Subsequently, we integrated the XGboost predictors with knowledge-based rules. The obtained hybrid model outperformed the XGboost model (AUC = 0.81 vs. 0.73, p < 0.001) with acceptable calibration. In conclusion, we developed an ML-based model characterized by a commendable capability to predict adverse events within 30 days post-syncope evaluation in the ED. This model relies solely on clinical data routinely collected during a patient's initial syncope evaluation, thus obviating the need for laboratory tests or syncope experienced clinical judgment.
RESUMEN
Predicting clinical deterioration in COVID-19 patients remains a challenging task in the Emergency Department (ED). To address this aim, we developed an artificial neural network using textual (e.g. patient history) and tabular (e.g. laboratory values) data from ED electronic medical reports. The predicted outcomes were 30-day mortality and ICU admission. We included consecutive patients from Humanitas Research Hospital and San Raffaele Hospital in the Milan area between February 20 and May 5, 2020. We included 1296 COVID-19 patients. Textual predictors consisted of patient history, physical exam, and radiological reports. Tabular predictors included age, creatinine, C-reactive protein, hemoglobin, and platelet count. TensorFlow tabular-textual model performance indices were compared to those of models implementing only tabular data. For 30-day mortality, the combined model yielded slightly better performances than the tabular fastai and XGBoost models, with AUC 0.87 ± 0.02, F1 score 0.62 ± 0.10 and an MCC 0.52 ± 0.04 (p < 0.32). As for ICU admission, the combined model MCC was superior (p < 0.024) to the tabular models. Our results suggest that a combined textual and tabular model can effectively predict COVID-19 prognosis which may assist ED physicians in their decision-making process.
Asunto(s)
COVID-19 , Aprendizaje Profundo , Humanos , COVID-19/diagnóstico , Hospitalización , Pronóstico , Servicio de Urgencia en Hospital , Estudios RetrospectivosRESUMEN
BACKGROUND: Virtual patient simulators (VPSs) log all users' actions, thereby enabling the creation of a multidimensional representation of students' medical knowledge. This representation can be used to create metrics providing teachers with valuable learning information. OBJECTIVE: The aim of this study is to describe the metrics we developed to analyze the clinical diagnostic reasoning of medical students, provide examples of their application, and preliminarily validate these metrics on a class of undergraduate medical students. The metrics are computed from the data obtained through a novel VPS embedding natural language processing techniques. METHODS: A total of 2 clinical case simulations (tests) were created to test our metrics. During each simulation, the students' step-by-step actions were logged into the program database for offline analysis. The students' performance was divided into seven dimensions: the identification of relevant information in the given clinical scenario, history taking, physical examination, medical test ordering, diagnostic hypothesis setting, binary analysis fulfillment, and final diagnosis setting. Sensitivity (percentage of relevant information found) and precision (percentage of correct actions performed) metrics were computed for each issue and combined into a harmonic mean (F1), thereby obtaining a single score evaluating the students' performance. The 7 metrics were further grouped to reflect the students' capability to collect and to analyze information to obtain an overall performance score. A methodological score was computed based on the discordance between the diagnostic pathway followed by students and the reference one previously defined by the teacher. In total, 25 students attending the fifth year of the School of Medicine at Humanitas University underwent test 1, which simulated a patient with dyspnea. Test 2 dealt with abdominal pain and was attended by 36 students on a different day. For validation, we assessed the Spearman rank correlation between the performance on these scores and the score obtained by each student in the hematology curricular examination. RESULTS: The mean overall scores were consistent between test 1 (mean 0.59, SD 0.05) and test 2 (mean 0.54, SD 0.12). For each student, the overall performance was achieved through a different contribution in collecting and analyzing information. Methodological scores highlighted discordances between the reference diagnostic pattern previously set by the teacher and the one pursued by the student. No significant correlation was found between the VPS scores and hematology examination scores. CONCLUSIONS: Different components of the students' diagnostic process may be disentangled and quantified by appropriate metrics applied to students' actions recorded while addressing a virtual case. Such an approach may help teachers provide students with individualized feedback aimed at filling competence drawbacks and methodological inconsistencies. There was no correlation between the hematology curricular examination score and any of the proposed scores as these scores address different aspects of students' medical knowledge.
RESUMEN
BACKGROUND: Shortage of human resources, increasing educational costs, and the need to keep social distances in response to the COVID-19 worldwide outbreak have prompted the necessity of clinical training methods designed for distance learning. Virtual patient simulators (VPSs) may partially meet these needs. Natural language processing (NLP) and intelligent tutoring systems (ITSs) may further enhance the educational impact of these simulators. OBJECTIVE: The goal of this study was to develop a VPS for clinical diagnostic reasoning that integrates interaction in natural language and an ITS. We also aimed to provide preliminary results of a short-term learning test administered on undergraduate students after use of the simulator. METHODS: We trained a Siamese long short-term memory network for anamnesis and NLP algorithms combined with Systematized Nomenclature of Medicine (SNOMED) ontology for diagnostic hypothesis generation. The ITS was structured on the concepts of knowledge, assessment, and learner models. To assess short-term learning changes, 15 undergraduate medical students underwent two identical tests, composed of multiple-choice questions, before and after performing a simulation by the virtual simulator. The test was made up of 22 questions; 11 of these were core questions that were specifically designed to evaluate clinical knowledge related to the simulated case. RESULTS: We developed a VPS called Hepius that allows students to gather clinical information from the patient's medical history, physical exam, and investigations and allows them to formulate a differential diagnosis by using natural language. Hepius is also an ITS that provides real-time step-by-step feedback to the student and suggests specific topics the student has to review to fill in potential knowledge gaps. Results from the short-term learning test showed an increase in both mean test score (P<.001) and mean score for core questions (P<.001) when comparing presimulation and postsimulation performance. CONCLUSIONS: By combining ITS and NLP technologies, Hepius may provide medical undergraduate students with a learning tool for training them in diagnostic reasoning. This may be particularly useful in a setting where students have restricted access to clinical wards, as is happening during the COVID-19 pandemic in many countries worldwide.
RESUMEN
We develop various AI models to predict hospitalization on a large (over 110k) cohort of COVID-19 positive-tested US patients, sourced from March 2020 to February 2021. Models range from Random Forest to Neural Network (NN) and Time Convolutional NN, where combination of the data modalities (tabular and time dependent) are performed at different stages (early vs. model fusion). Despite high data unbalance, the models reach average precision 0.96-0.98 (0.75-0.85), recall 0.96-0.98 (0.74-0.85), and F1-score 0.97-0.98 (0.79-0.83) on the non-hospitalized (or hospitalized) class. Performances do not significantly drop even when selected lists of features are removed to study model adaptability to different scenarios. However, a systematic study of the SHAP feature importance values for the developed models in the different scenarios shows a large variability across models and use cases. This calls for even more complete studies on several explainability methods before their adoption in high-stakes scenarios.
Asunto(s)
COVID-19 , COVID-19/epidemiología , Estudios de Cohortes , Hospitalización , Humanos , Redes Neurales de la ComputaciónRESUMEN
BACKGROUND: Enrollment of large cohorts of syncope patients from administrative data is crucial for proper risk stratification but is limited by the enormous amount of time required for manual revision of medical records. AIM: To develop a Natural Language Processing (NLP) algorithm to automatically identify syncope from Emergency Department (ED) electronic medical records (EMRs). METHODS: De-identified EMRs of all consecutive patients evaluated at Humanitas Research Hospital ED from 1 December 2013 to 31 March 2014 and from 1 December 2015 to 31 March 2016 were manually annotated to identify syncope. Records were combined in a single dataset and classified. The performance of combined multiple NLP feature selectors and classifiers was tested. Primary Outcomes: NLP algorithms' accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and F3 score. RESULTS: 15,098 and 15,222 records from 2013 and 2015 datasets were analyzed. Syncope was present in 571 records. Normalized Gini Index feature selector combined with Support Vector Machines classifier obtained the best F3 value (84.0%), with 92.2% sensitivity and 47.4% positive predictive value. A 96% analysis time reduction was computed, compared with EMRs manual review. CONCLUSIONS: This artificial intelligence algorithm enabled the automatic identification of a large population of syncope patients using EMRs.
RESUMEN
ACE-inhibitors (ACE-I) represent effective drugs more and more widely used in acute myocardial infarction (AMI) patients, in post AMI patients and mainly, today, in CHF patients.A complete review of the scientific literature and of all the randomized controlled clinical trials (RCTs), where ACE-I have been tested directly or in association with other drugs, have been performed. ACE-I effects on total mortality (TM) and arrhythmic mortality (AM) and other composite clinical endpoints have been evaluated. It is well known that frequent ventricular arrhythmias (VA) and a high incidence of sudden death (SD) can be documented in CHF patients; nevertheless a direct relationship between VA, TM, and AM has not been clearly demonstrated; neither beneficial effects, on the same endpoints, of the treatment and suppression of ambient VA in CHF. Conversely, sometimes clear negative effects on both TM and AM have been observed. According to individual studies and two recent complete and large metanalysis, ACE-I were unable to reduce AM, but they reduced TM. Furthermore, they can affect and modify many, if not all, of the triggering factors of VA and SD in this context. Differently from ACE-I, betablockers (BB) have been clearly associated with a reduction in TM and AM, in the same context. Thus, at present time, ACE-I, with or without BB, should be considered the standard therapy in all patients with CHF, if not contraindicated. Angiotensin II antagonists (AII-a) probably represent a comparably effective treatment, in all CHF patients and mainly in those patients, suffering from side effects or showing intolerance to ACE-I, but we are still lacking definitive data from RCTs. In many RCTs, conducted with traditional antiarrhythmic drug therapy (ADT), these drugs have been widely used, contributing probably, in a consistent way, to some of the positive results of these studies. All primary and some secondary implantable defibrillators (ICD) RCTs, in the prevention of SD, have included these drugs as the standard treatment of the underlying cardiac disease, with or without CHF. The same therapeutical strategy is regularly applied in all biventricular pacing (BP) RCTs, with or without the ICD. These trials are supposed to assess the reduction in TM and AM, preventing deterioration or progression of CHF and improving the quality of the patients' s life.Finally, according to these clinical evidences, in the last part of the review, we stress the need for a more widespread implementation of ACE-I and AII-a in treating CHF patients.