Machine Learning-Based App for Self-Evaluation of Teacher-Specific Instructional Style and Tools

Fedor Duzhin; Anders Gustafsson

doi:10.3390/educsci8010007

Accurate Severe vs Non-severe COVID-19 Clinical Type Classification: a Multimodality Machine Learning Study (Preprint)

10.2196/preprints.23948 ◽

2020 ◽

Author(s):

Yuanfang Chen ◽

Liu Ouyang ◽

Forrest S. Bao ◽

Qian Li ◽

Lei Han ◽

...

Keyword(s):

Machine Learning ◽

Laboratory Testing ◽

Predictive Accuracy ◽

Clinical Information ◽

Clinical Decision ◽

Immunological Responses ◽

Self Evaluation ◽

Optimal Outcomes ◽

Clinical Type ◽

Multimodal Features

BACKGROUND Effectively and efficiently diagnosing COVID-19 patients with accurate clinical type is essential to achieve optimal outcomes for the patients as well as reducing the risk of overloading the healthcare system. Currently, severe and non-severe COVID-19 types are differentiated by only a few features, which do not comprehensively characterize the complicated pathological, physiological, and immunological responses to SARS-CoV-2 invasion in different types. In addition, these type-defining features may not be readily testable at time of diagnosis. OBJECTIVE This study aimed to accurately differentiate severe and non-severe COVID-19 clinical types based on multiple medical features and provide reliable predictions for clinical decision support. METHODS In this study, we recruited 214 confirmed COVID-19 patients in non-severe and 148 in severe type. The patients’ clinical (including 26 features), and laboratory testing results (26 features) upon admission were acquired as two input modalities. Exploratory analyses demonstrated that these features differed substantially between two clinical types. Machine learning random forest (RF) models based on all features in each modality as well as top 5 features in each modality combined were developed and validated to differentiate COVID-19 clinical types. RESULTS Using clinical and laboratory results as input independently, RF models achieved 90% and 95% predictive accuracy, respectively. Input features’ importance scores were further evaluated and top five features from each modality were identified (age, hypertension, cardiovascular disease, gender, diabetes; D-Dimer, hsTNI, absolute neutrophil count, IL-6, and LDH, in descending order). Using these top 10 multimodal features as the only input instead of all 52 features combined, RF model was able to achieve 99% predictive accuracy. CONCLUSIONS These findings shed light on how the human body reacts to SARS-CoV-2 invasion as a unity and provide insights on effectively evaluating COVID-19 patient’s severity based on more common medical features when gold-standard features were not available. We suggest that clinical information can be used as an initial screening tool for self-evaluation and triaging, while laboratory testing results are applied when accuracy is the priority.

Download Full-text

Automatic Generation of an Evaluation Model of Regional Disaster Prevention Activities Based on Self-Evaluation Questionnaire

Journal of Disaster Research ◽

10.20965/jdr.2018.p0886 ◽

2018 ◽

Vol 13 (5) ◽

pp. 886-896

Author(s):

Qinglin Cui ◽

◽

Taiyoung Yi ◽

Kan Shimazaki ◽

Hitoshi Taguchi ◽

...

Keyword(s):

Machine Learning ◽

Evaluation Model ◽

Automatic Generation ◽

Disaster Prevention ◽

Review Committee ◽

Evaluation Questionnaire ◽

Self Evaluation ◽

Prevention Activities ◽

Input Variables

Regional disaster prevention activities must be evaluated in terms of their effectiveness and suitability, and then improved on the basis of this evaluation. Those who can evaluate such activities are required to have abundant on-site experience in and extensive knowledge on disaster prevention. However, there is a shortage of such talent, and the training and nurturing thereof requires considerable resources. To address these issues, machine learning was introduced in our previous study to automate the evaluation of such activities. In the present study, we propose the automatic generation of the evaluation model of such activities using the responses of a self-evaluation questionnaire as the input variables. The output variables are the results of a review committee consisting of experts on disaster prevention. This paper describes the application of the model to the fourth Disaster Prevention Map Contest, examines the predicted results, and discusses the application conditions and issues to be resolved.

Download Full-text

Mind wandering as data augmentation: How mental travel supports abstraction

Behavioral and Brain Sciences ◽

10.1017/s0140525x1900311x ◽

2020 ◽

Vol 43 ◽

Author(s):

Myrthe Faber

Keyword(s):

Machine Learning ◽

Data Augmentation ◽

Mental Content ◽

Mind Wandering ◽

Theoretical Framework ◽

Important Addition

Abstract Gilead et al. state that abstraction supports mental travel, and that mental travel critically relies on abstraction. I propose an important addition to this theoretical framework, namely that mental travel might also support abstraction. Specifically, I argue that spontaneous mental travel (mind wandering), much like data augmentation in machine learning, provides variability in mental content and context necessary for abstraction.

Download Full-text

Student self-evaluation in preclinical restorative dentistry

Journal of Dental Education ◽

10.1002/j.0022-0337.1982.46.4.tb01549.x ◽

1982 ◽

Vol 46 (4) ◽

pp. 221-226 ◽

Cited By ~ 3

Author(s):

LS Forehand ◽

WF Vann ◽

DA Shugars

Keyword(s):

Restorative Dentistry ◽

Self Evaluation

Download Full-text

Student Clinicians Self-Evaluating Performance by Reviewing Session Videos and Using a Rubric

Perspectives on Administration and Supervision ◽

10.1044/aas25.2.78 ◽

2015 ◽

Vol 25 (2) ◽

pp. 78-84 ◽

Cited By ~ 2

Author(s):

Holly C. Smith

Keyword(s):

Clinical Education ◽

Crucial Element ◽

Self Evaluation ◽

Pertinent Information ◽

Evaluation Rubrics

Development of self-evaluation skills in student clinicians is a crucial element of clinical education. This article reviews pertinent information regarding supervisors' responsibilities related to teaching supervisees to self-evaluate. Previously identified methods of facilitating these skills are discussed. The use of video self-analyses paired with self-evaluation rubrics is explored.

Download Full-text