Stroke Outcome Measurements From Electronic Medical Records: Cross-sectional Study on the Effectiveness of Neural and Nonneural Classifiers.

BACKGROUND: With the rapid adoption of electronic medical records (EMRs), there is an ever-increasing opportunity to collect data and extract knowledge from EMRs to support patient-centered stroke management. OBJECTIVE: This study aims to compare the effectiveness of state-of-the-art automatic text classification methods in classifying data to support the prediction of clinical patient outcomes and the extraction of patient characteristics from EMRs. METHODS: Our study addressed the computational problems of information extraction and automatic text classification. We identified essential tasks to be considered in an ischemic stroke value-based program. The 30 selected tasks were classified (manually labeled by specialists) according to the following value agenda: tier 1 (achieved health care status), tier 2 (recovery process), care related (clinical management and risk scores), and baseline characteristics. The analyzed data set was retrospectively extracted from the EMRs of patients with stroke from a private Brazilian hospital between 2018 and 2019. A total of 44,206 sentences from free-text medical records in Portuguese were used to train and develop 10 supervised computational machine learning methods, including state-of-the-art neural and nonneural methods, along with ontological rules. As an experimental protocol, we used a 5-fold cross-validation procedure repeated 6 times, along with subject-wise sampling. A heatmap was used to display comparative result analyses according to the best algorithmic effectiveness (F1 score), supported by statistical significance tests. A feature importance analysis was conducted to provide insights into the results. RESULTS: The top-performing models were support vector machines trained with lexical and semantic textual features, showing the importance of dealing with noise in EMR textual representations. The support vector machine models produced statistically superior results in 71% (17/24) of tasks, with an F1 score >80% regarding care-related tasks (patient treatment location, fall risk, thrombolytic therapy, and pressure ulcer risk), the process of recovery (ability to feed orally or ambulate and communicate), health care status achieved (mortality), and baseline characteristics (diabetes, obesity, dyslipidemia, and smoking status). Neural methods were largely outperformed by more traditional nonneural methods, given the characteristics of the data set. Ontological rules were also effective in tasks such as baseline characteristics (alcoholism, atrial fibrillation, and coronary artery disease) and the Rankin scale. The complementarity in effectiveness among models suggests that a combination of models could enhance the results and cover more tasks in the future. CONCLUSIONS: Advances in information technology capacity are essential for scalability and agility in measuring health status outcomes. This study allowed us to measure effectiveness and identify opportunities for automating the classification of outcomes of specific tasks related to clinical conditions of stroke victims, and thus ultimately assess the possibility of proactively using these machine learning techniques in real-world situations.

Identifying predictors of unacceptable pain at office hysteroscopy.

STUDY OBJECTIVE: To identify predictors of unacceptable pain during office hysteroscopy without anesthesia. DESIGN: Prospective observational study (Canadian Task Force classification II-2). SETTING: Teaching hospital. PATIENTS: Five hundred fifty-eight women aged 17 to 73 years. INTERVENTION: Elective office hysteroscopy without anesthesia. MEASUREMENTS AND MAIN RESULTS: Pain intensity was assessed via a verbal rating scale (VRS, 0-10). Pain was considered unacceptable when severe during the procedure (VRS ≥7) or moderate to severe at discharge (VRS ≥4). After preliminary statistical analysis, factors including diabetes, age ≤50 years, previous curettage, dyspareunia, severe dysmenorrhea, and hysteroscopist experience were selected to compose 2 binary multivariate models to predict unacceptable pain. As expected, hysteroscopist experience was protective against unacceptable pain during office hysteroscopy (p = .03; adjusted odds ratio [OR], 0.63; 95% confidence interval [CI], 41-96) and also at discharge (p = .002; adjusted OR, 0.48; 95% CI, 30-77). Severe dysmenorrhea was a significant risk factor for pain (cramps) at discharge (p < .001; adjusted OR, 3.07; 95% CI, 1.97-4.78). CONCLUSION: Women with severe dysmenorrhea will benefit from preemptive analgesia regardless of hysteroscopist level of experience because this condition significantly increased the occurrence of unacceptable cramps at discharge.

Detection of paramyxoviruses in Magellanic penguins (Spheniscus magellanicus) on the Brazilian tropical coast.

Aquatic migratory birds are a major vectors by which influenza viruses and paramyxoviruses are spread in nature. Magellanic penguins (Spheniscus magellanicus) are usually present on the southern shores of South America and can swim as far as the southern coast of Brazil in winter. In 2008, however, several Magellanic penguins were observed on the northeastern coast of Brazil. Paramyxoviruses were isolated from Magellanic penguins on the Espírito Santo state coast, approximately 4000 km from their breeding colonies, although influenza viruses were not detected. Among the paramyxoviruses, five Avulavirus isolates belonging to serotype APMV-2 and the serotype APMV-10, which was proposed by Miller et al. (2010), were identified. These results highlight the risks associated with the spread of paramyxoviruses between natural to non-natural habitats by birds exhibiting unusual migration patterns, and they document for the first time the presence of the APMV-2 and APMV-10 serotypes on penguins in Brazil. The local avifauna may become infected with these viruses through close contact between migratory and resident birds. Continued surveillance of virus incidence in these migratory populations of penguins is necessary to detect and prevent the potential risks associated with these unusual migration patterns.