Utilization of Decision Tree Algorithms for Supporting the Prediction of Intensive Care Unit Admission of Myasthenia Gravis: A Machine Learning-Based Approach

Myasthenia gravis (MG), an acquired autoimmune-related neuromuscular disorder that causes muscle weakness, presents with varying severity, including myasthenic crisis (MC). Although MC can cause significant morbidity and mortality, specialized neuro-intensive care can produce a good long-term prognosis. Considering the outcomes of MG during hospitalization, it is critical to conduct risk assessments to predict the need for intensive care. Evidence and valid tools for the screening of critical patients with MG are lacking. We used three machine learning-based decision tree algorithms, including a classification and regression tree, C4.5, and C5.0, for predicting intensive care unit (ICU) admission of patients with MG. We included 228 MG patients admitted between 2015 and 2018. Among them, 88.2% were anti-acetylcholine receptors antibody positive and 4.7% were anti-muscle-specific kinase antibody positive. Twenty clinical variables were used as predictive variables. The C5.0 decision tree outperformed the other two decision tree and logistic regression models. The decision rules constructed by the best C5.0 model showed that the Myasthenia Gravis Foundation of America clinical classification at admission, thymoma history, azathioprine treatment history, disease duration, sex, and onset age were significant risk factors for the development of decision rules for ICU admission prediction. The developed machine learning-based decision tree can be a supportive tool for alerting clinicians regarding patients with MG who require intensive care, thereby improving the quality of care.

Creating a Conversational Agent in Psychotherapy Using Natural Language Processing: Recognizing User Intents (Preprint)

BACKGROUND In recent years there has been a growth of psychological chatbots performing important functions from checking symptoms to providing psychoeducation and guiding self-help exercises. Technologically these chatbots are based on traditional decision-tree algorithms with limited keyword recognition. A key challenge to the development of conversational artificial intelligence is intent recognition or understanding the goal that the user wants to accomplish. The user query on psychological topic is often emotional, highly contextual and non goal-oriented, and therefore may contain vague, mixed or multiple intents. OBJECTIVE In this study we attempt to identify and categorize user intents with relation to psychological topics. METHODS We collected a dataset of 43 000 logs from the iCognito Anti-depression chatbot which consists of user answers to the chatbot questions about the reason of their emotional distress. The data was labeled manually. The BERT model was used for classification. RESULTS We have identified 24 classes of user intents that can be grouped into larger categories, such as: a) intents to improve emotional state; b) intents to improve interpersonal relations; c) intents to improve physical condition; d) intents to solve practical problems; e) intents to make a decision; f) intents to harm oneself or commit suicide; g) intent to blame or criticize oneself. CONCLUSIONS This classification may be used for the development of conversational artificial intelligence in the field of psychotherapy.

Determining residuary resistance per unit weight of displacement with Symbolic Regression and Gradient Boosted Tree algorithms

Determining the residuary resistance per unit weight of displacement is one of the key factors in the design of vessels. In this paper, the authors utilize two novel methods – Symbolic Regression (SR) and Gradient Boosted Trees (GBT) to achieve a model which can be used to calculate the value of residuary resistance per unit weight, of displacement from the longitudinal position of the center of buoyancy, prismatic coefficient, length-displacement ratio, beam-draught ratio, length-beam ratio, and Froude number. This data is given as results of 308 experiments provided as a part of a publicly available dataset. The results are evaluated using the coefficient of determination (R2) and Mean Absolute Percentage Error (MAPE). Pre-processing, in the shape of correlation analysis combined with variable elimination and variable scaling, is applied to the dataset. The results show that while both methods achieve regression results, the result of regression of SR is relatively poor in comparison to GBT. Both methods provide slightly poorer, but comparable results to previous research focussing on the use of “black-box” methods, such as neural networks. The elimination of variables does not show a high influence on the modeling performance in the presented case, while variable scaling does achieve better results compared to the models trained with the non-scaled dataset.

Prospects for $$ {B}_c^{+} $$→ τ +ντ at FCC-ee

This paper presents the prospects for a precise measurement of the branching fraction of the leptonic $$ {B}_c^{+} $$ B c + → τ+ντ decay at the Future Circular Collider (FCC-ee) running at the Z -pole. A detailed description of the simulation and analysis framework is provided. To select signal candidates, two Boosted Decision Tree algorithms are employed and optimised. The first stage suppresses inclusive $$ b\overline{b} $$ b b ¯ , $$ c\overline{c} $$ c c ¯ , and $$ q\overline{q} $$ q q ¯ backgrounds using event-based topological information. A second stage utilises the properties of the hadronic τ+→ π+π+π−$$ \overline{\nu} $$ ν ¯ τ decay to further suppress these backgrounds, and is also found to achieve high rejection for the B+→ τ+ντ background. The number of $$ {B}_c^{+} $$ B c + → τ+ντ candidates is estimated for various Tera-Z scenarios, and the potential precision of signal yield and branching fraction measurements evaluated. The phenomenological impact of such measurements on various New Physics scenarios is also explored.

The Lyme Borreliosis Spatial Footprint in the 21st Century: A Key Study of Slovenia

After mosquitoes, ticks are the most important vectors of infectious diseases. They play an important role in public health. In recent decades, we discovered new tick-borne diseases; additionally, those that are already known are spreading to new areas because of climate change. Slovenia is an endemic region for Lyme borreliosis and one of the countries with the highest incidence of this disease on a global scale. Thus, the spatial pattern of Slovenian Lyme borreliosis prevalence was modelled with 246 indicators and transformed into 24 uncorrelated predictor variables that were applied in geographically weighted regression and regression tree algorithms. The projected potential shifts in Lyme borreliosis foci by 2050 and 2070 were calculated according to the RCP8.5 climate scenario. These results were further applied to developing a Slovenian Lyme borreliosis infection risk map, which could be used as a preventive decision support system.

Diagnostic performance of classification trees and hematological functions in hematologic disorders: an application of multidimensional scaling and cluster analysis

Background Several hematological indices have been already proposed to discriminate between iron deficiency anemia (IDA) and β‐thalassemia trait (βTT). This study compared the diagnostic performance of different hematological discrimination indices with decision trees and support vector machines, so as to discriminate IDA from βTT using multidimensional scaling and cluster analysis. In addition, decision trees were used to determine the diagnostic classification scheme of patients. Methods Consisting of 1178 patients with hypochromic microcytic anemia (708 patients with βTT and 470 patients with IDA), this cross-sectional study compared the diagnostic performance of 43 hematological discrimination indices with classification tree algorithms and support vector machines in order to discriminate IDA from βTT. Moreover, multidimensional scaling and cluster analysis were used to identify the homogeneous subgroups of discrimination methods with similar performance. Results All the classification tree algorithms except the LOTUS tree algorithm showed acceptable accuracy measures for discrimination between IDA and βTT in comparison with other hematological discrimination indices. The results indicated that the CRUISE and C5.0 tree algorithms had better diagnostic performance and efficiency among other discrimination methods. Moreover, the AUC of CRUISE and C5.0 tree algorithms indicated more precise classification with values of 0.940 and 0.999, indicating excellent diagnostic accuracy of such models. Moreover, the CRUISE and C5.0 tree algorithms showed that mean corpuscular volume can be considered as the main variable in discrimination between IDA and βTT. Conclusions CRUISE and C5.0 tree algorithms as powerful methods in data mining techniques can be used to develop accurate differential methods along with other laboratory parameters for the discrimination of IDA and βTT. In addition, the multidimensional scaling method and cluster analysis can be considered as the most appropriate techniques to determine the discrimination indices with similar performance for future hematological studies.