Search

Machine learning models used to predict postoperative mortality rarely include intraoperative factors. Several intraoperative factors like hypotension (IOH), vasopressor-inotropes, and cardiopulmonary bypass (CPB) time are significantly associated with postoperative outcomes. The authors explored the ability of machine learning models incorporating intraoperative risk factors to predict mortality after cardiac surgery.Retrospective study.Tertiary hospital.A total of 5,015 adults who underwent cardiac surgery from 2008 to 2016.None.The intraoperative phase was divided into the following: (1) CPB, (2) outside CPB, and (3) total surgery for quantifying IOH only. Phase-specific IOH parameters (area under the curve for mean arterial pressure65 mmHg), vasopressor-inotropes (norepinephrine equivalents), duration, and cross-clamp time, along with preoperative risk factors ,were incorporated into the models. The primary outcome was mortality. The following 5 models were applied to 3 intraoperative phases separately: (1) logistic regression, (2) random forests, (3) neural networks, (4) support vector machines, and (5) extreme gradient boosting (XGB). Mortality was predicted using area under the receiver operating characteristic curve. Of 5,015 patients included, 112 (2.2%) died. XGB model from the outside-CPB phase predicted mortality better with area under the receiver operating characteristic curve, 95% confidence interval (CI): 0.88(0.83-0.94); positive predictive value, 0.10(0.06-0.15); specificity 0.85 (0.83-0.87) and sensitivity 0.75 (0.57-0.90).XGB machine learning model from IOH outside the CPB phase seemed to offer a better discrimination, sensitivity, specificity, and positive predictive value compared with other models. Machine learning models incorporating intraoperative adverse factors might offer better predictive ability for risk stratification and triaging of patients after cardiac surgery.

Predictive maintenance approaches result in shorter interventions, less downtime and less maintenance and production costs, leading to more sustainable manufacturing and increasing earnings. Machine learning and data mining approaches are now popular in this field, producing data-driven models that can provide insights regarding equipment behavior, identify anomalies, and generate predictions that can be used to support decision-making processes. In this paper, we propose a service-oriented architecture that adapts a predictive maintenance reference architecture to the domain of the flexible packaging market. Focusing on the data analytics services required for predictive maintenance, the proposed architecture was assessed by conducting a case-study using real-world data. To detect faults in the company’s coextrusion film blowing machines, we devised a predictive maintenance methodology whereby the isolation forest algorithm is used to detect potentially anomalous data points and the anomaly threshold is defined by computing the interquartile range of anomaly scores. To compensate for the fact that single anomalies are unlikely to be of significance, when deploying the isolation forest model in real time the percentage of anomalies detected within a given time interval is monitored. An alarm is issued by the system should that percentage exceed a specific cutoff. Experimental results show the described approach is successful in distinguishing anomalous data from normal data in non-stationary time-series.

Proactive Maintenance practices are becoming more standard in industrial environments, with a direct and profound impact on the competitivity within the sector. These practices demand the continuous monitorization of industrial equipment, which generates extensive amounts of data. This information can be processed into useful knowledge with the use of machine learning algorithms. However, before the algorithms can effectively be applied, the data must go through an exploratory phase: assessing the meaning of the features and to which degree they are redundant. In this paper, we present the findings of the analysis conducted on a real-world dataset from a metallurgic company. A number of data analysis and feature selection methods are employed, uncovering several relationships, which are systematized in a rule-based model, and reducing the feature space from an initial 47-feature dataset to a 32-feature dataset.

Background Medical notes are a rich source of patient data; however, the nature of unstructured text has largely precluded the use of these data for large retrospective analyses. Transforming clinical text into structured data can enable large-scale research studies with electronic health records (EHR) data. Natural language processing (NLP) can be used for text information retrieval, reducing the need for labor-intensive chart review. Here we present an application of NLP to large-scale analysis of medical records at 2 large hospitals for patients hospitalized with COVID-19. Objective Our study goal was to develop an NLP pipeline to classify the discharge disposition (home, inpatient rehabilitation, skilled nursing inpatient facility [SNIF], and death) of patients hospitalized with COVID-19 based on hospital discharge summary notes. Methods Text mining and feature engineering were applied to unstructured text from hospital discharge summaries. The study included patients with COVID-19 discharged from 2 hospitals in the Boston, Massachusetts area (Massachusetts General Hospital and Brigham and Women’s Hospital) between March 10, 2020, and June 30, 2020. The data were divided into a training set (70%) and hold-out test set (30%). Discharge summaries were represented as bags-of-words consisting of single words (unigrams), bigrams, and trigrams. The number of features was reduced during training by excluding n-grams that occurred in fewer than 10% of discharge summaries, and further reduced using least absolute shrinkage and selection operator (LASSO) regularization while training a multiclass logistic regression model. Model performance was evaluated using the hold-out test set. Results The study cohort included 1737 adult patients (median age 61 [SD 18] years; 55% men; 45% White and 16% Black; 14% nonsurvivors and 61% discharged home). The model selected 179 from a vocabulary of 1056 engineered features, consisting of combinations of unigrams, bigrams, and trigrams. The top features contributing most to the classification by the model (for each outcome) were the following: “appointments specialty,” “home health,” and “home care” (home); “intubate” and “ARDS” (inpatient rehabilitation); “service” (SNIF); “brief assessment” and “covid” (death). The model achieved a micro-average area under the receiver operating characteristic curve value of 0.98 (95% CI 0.97-0.98) and average precision of 0.81 (95% CI 0.75-0.84) in the testing set for prediction of discharge disposition. Conclusions A supervised learning–based NLP approach is able to classify the discharge disposition of patients hospitalized with COVID-19. This approach has the potential to accelerate and increase the scale of research on patients’ discharge disposition that is possible with EHR data.

The risk stratification of patients in the emergency department begins at triage. It is vital to stratify patients early based on their severity, since undertriage can lead to increased morbidity, mortality and costs. Our aim was to present a new approach to assist healthcare professionals at triage in the stratification of patients and in identifying those with higher risk of ICU admission. Adult patients assigned Manchester Triage System (MTS) or Emergency Severity Index (ESI) 1 to 3 from a Portuguese and a United States Emergency Departments were analyzed. Variables routinely collected at triage were used and natural language processing was applied to the patient chief complaint. Stratified random sampling was applied to split the data in train (70%) and test (30%) sets and 10-fold cross validation was performed for model training. Logistic regression, random forests, and a random undersampling boosting algorithm were used. We compared the performance obtained with the reference model-using only triage priorities-with the models using additional variables. For both hospitals, a logistic regression model achieved higher overall performance, yielding areas under the receiver operating characteristic and precision-recall curves of 0.91 (95% CI 0.90-0.92) and 0.30 (95% CI 0.27-0.33) for the United States hospital and of 0.85 (95% CI 0.83-0.86) and 0.06 (95% CI 0.05-0.07) for the Portuguese hospital. Heart rate, pulse oximetry, respiratory rate and systolic blood pressure were the most important predictors of ICU admission. Compared to the reference models, the models using clinical variables and the chief complaint presented higher recall for patients assigned MTS/ESI 3 and can identify patients assigned MTS/ESI 3 who are at risk for ICU admission.

Emergency department triage is the first point in time when a patient’s acuity level is determined. The time to assign a priority at triage is short and it is vital to accurately stratify patients at this stage, since under-triage can lead to increased morbidity, mortality and costs. Our aim was to present a model that can assist healthcare professionals in triage decision making, namely in the stratification of patients through the risk prediction of a composite critical outcome—mortality and cardiopulmonary arrest. Our study cohort consisted of 235826 adult patients triaged at a Portuguese Emergency Department from 2012 to 2016. Patients were assigned to emergent, very urgent or urgent priorities of the Manchester Triage System (MTS). Demographics, clinical variables routinely collected at triage and the patients’ chief complaint were used. Logistic regression, random forests and extreme gradient boosting were developed using all available variables. The term frequency–inverse document frequency (TF-IDF) natural language processing weighting factor was applied to vectorize the chief complaint. Stratified random sampling was used to split the data into train (70%) and test (30%) data sets. Ten-fold cross validation was performed in train to optimize model hyper-parameters. The performance obtained with the best model was compared against the reference model—a regularized logistic regression trained using only triage priorities. Extreme gradient boosting exhibited good calibration properties and yielded areas under the receiver operating characteristic and precision-recall curves of 0.96 (95% CI 0.95-0.97) and 0.31 (95% CI 0.26-0.36), respectively. The predictors ranked with higher importance by this model were the Glasgow coma score, the patients’ age, pulse oximetry and arrival mode. Compared to the reference, the extreme gradient boosting model using clinical variables and the chief complaint presented higher recall for patients assigned MTS-3 and can identify those who are at risk of the composite outcome.

As a consequence of the increasing competitivity in the current economic environment, Proactive Maintenance practices are gradually becoming more common in industrial environments. In order to implement these practices, large amounts of heterogeneous information must be analysed, such that knowledge about the status of the equipment can be acquired. However, for this data to be of use and before it can be processed by machine learning algorithms, it must go through an exploratory phase. During this step, relationships in the data, redundancy of features and possible meanings can be assessed. In this paper, a number of these procedures are employed, resulting in the discovery of meaningful information. Moreover, a subset of features is selected for future analysis, allowing for the reduction of the feature space from 47 to 32 features.

This paper examines the experience of a distance-training course for 250 Brazilians mathematics teachers, developed by the School of Education of the State University of Campinas (UNICAMP - Brazil). Such program uses a LMS developed with focus on a collaborative learning methodology. We discuss the data related to technological tools evaluated by students as critical as the role of the tutor. Questionnaires were applied to obtain data and the results were analysed through content and frequency response. The results show that participants considered essential to solve problems together and indicated the importance of interactive spaces where educational professionals share experiences. Also, the tutor's skill can significantly contribute inside the LMS, becoming a mediator to the process by using this methodology.

The aim of this work is to identify groups of patients with similar patterns that are related to a higher risk of readmission to an Intensive Care Unit (ICU). Patients readmissions to ICUs are introduced as a problem associated with increased mortality, morbidity and costs, which complicates the performance of a good clinical management and medical diagnosis. To approach the readmissions classification problem, Fuzzy C-Means (FCM) clustering algorithm was implemented to find the different groups of patients. A multimodel approach was developed using these groups and the best clustering division was assessed through different objective functions. Two decision criteria were used for the multimodel approach, an a priori decision and an a posteriori decision. The data used, from MIMIC II database, consisted on the arithmetic means of time series of variables - acquired during the last 24 hours before discharge. The multimodel using the a priori and the aposteriori decisions were able to predict readmissions with an average AUC of 0.74 and 0.75, respectively. Consequently, the multimodel results overcame the results of previous predictive models developed for the classification of readmissions outcome.

PCMAT (Mathematics Collaborative Learning Platform) is a collaborative adaptive learning tool based on progressive assessment for Mathematics in Basic Schools. The learning platform is based on a constructivist approach, assessing the user knowledge and presenting contents and activities adapted to the characteristics and learning style of the student. The intelligent behavior of such platform depends on the existence of a tentative description of the student – the student model (SM). The contents of this model and the student most prominent learning style are used by a domain and interaction model to select the most appropriate response to student actions. The SM is used to select the more appropriate learning object according to the student learning stage. However, this selection demands for the access to metadata describing the contents of the learning object. This need leaded to the application of a standard to describe the learning objects (LO). The authoring of LO corresponds to one major maintenance costs present in these applications. PCMAT is able to generate several instances of the same learning object through the parameterization of some features of the learning object. The platform is also able to process student responses in natural language. This project shows how techniques from Adaptive Hypermedia System (AHS) field can improve e-learning based systems in a basic school environment.

This paper introduces the PCMAT platform project and, in particular, one of its components, the PCMAT Metadata Authoring Tool. This is an educational web application that allows the project metadata creators to write the metadata associated to each learning object without any concern for the metadata schema semantics. Furthermore it permits the project managers to add or delete elements to the schema, without having to rewrite or compile any code.