Comparison by multivariate auto-regressive method of seizure prediction for real patients and virtual patients

2021 ◽  
Vol 68 ◽  
pp. 102725
Author(s):  
Ines Assali ◽  
Ines Jlassi ◽  
Mouna Aissi ◽  
Ahmed Ghazi Blaiech ◽  
Marcel Carrère ◽  
...  
2014 ◽  
Vol 15 (3) ◽  
pp. 404-425 ◽  
Author(s):  
Marjorie McShane

Mental model ascription – also called mindreading – is the process of inferring the mental states of others, which happens as a matter of course in social interactions. But although ubiquitous, mindreading is presumably a highly variable process: people mindread to different extents and with different results. We hypothesize that human mindreading ability relies on a large number of personal and contextual features: the inherent abilities of specific individuals, their current physical and mental states, their knowledge of the domain of discourse, their familiarity with the interlocutor, the risks associated with an incorrect assessment of intent, and so on. This paper presents a theory of mindreading that models diverse artificial intelligent agents using an inventory of parameters and value sets that represent traits of humans and features of discourse contexts. Examples are drawn from Maryland Virtual Patient, a prototype system that will permit medical trainees to diagnose and treat cognitively modeled virtual patients with the optional assistance of a virtual tutor. Since real patients vary greatly with respect to physiological and cognitive features, so must a society of virtual patients. Modeling such variation is one of the goals of the overall OntoAgent program of research and development.


2018 ◽  
Vol 42 (1) ◽  
pp. 15-20 ◽  
Author(s):  
Akriti Gupta ◽  
Satendra Singh ◽  
Farah Khaliq ◽  
Upreet Dhaliwal ◽  
S. V. Madhu

In the country presently, preclinical medical students are not routinely exposed to real patients. Thus, when they start clinical postings, they are found to have poor clinical reasoning skills. Simulated virtual patients (SVPs) can improve clinical skills without endangering real patients. This pilot study describes the development of two SVPs in endocrine physiology and their validation in terms of acquisition of clinical knowledge and student engagement. Two SVPs, Nandini Sharma (unintentional weight gain) and Sunil Yadav (polyuria), were created and published on the i-Human Patients platform through an iterative, interdisciplinary, and transdisciplinary collaborative process using the conceptual framework of Kim et al. (Kim S, Phillips WR, Pinsky L, Brock D, Phillips K, Keary J. Med Educ 40: 867–876, 2006). After internal and external peer validation, the SVPs were piloted on 40 students (20 students per virtual patient) over 2 wk. A cognitive pretest was conducted before exposure, and a posttest soon after. Faculty and student feedback were collected. Faculty found SVPs authentic, helpful as teaching-learning tools, and useful for giving feedback and for assessment. Students found SVPs more engaging than paper cases and helpful in developing clinical reasoning and in imparting clinical exposure. Pretest and posttest scores indicated knowledge gain ( P < 0.01). Although challenging to create, SVPs created on the i-Human Patients platform improved learning in endocrine physiology and were well accepted by students and faculty as a means to provide early clinical exposure. More SVPs can be developed through collaboration between stakeholder departments and integrated into the curriculum for greater benefit.


2016 ◽  
Vol 1 (2) ◽  
pp. 24
Author(s):  
David Kan

Purpose: This study access liquidity management with the aim of determining its effect on returns of shareholders. Ex-post factor design was adopted. Data on ROE, ROA, Log of Sales and EPS were collected from the selected Banks financial statement and Nigerian Stock Exchange statistical bulletin. ROA and ROE proxied performance while EPS proxied returns to shareholders. Liquidity stood for liquidity management.Purpose: The study covered a period of 2000-2014. Unit root was used to test the data for stationarity issue and where there was unit root problem, the data were differenced. Auto-regressive method was also applied to solve auto-regression issues. Linear regression and Pearson correlation were used to test the hypotheses.Results: The result showed that there is no significant relationship between liquidity management and Nigerian quoted Banks performance as well as return of Shareholders.Recommendation; the researcher therefore recommended that policies should be put in place to reduce the cost of loan and encourage investment in Nigeria.


2014 ◽  
Vol 37 (2) ◽  
pp. 202-202 ◽  
Author(s):  
Alvaro Proaño ◽  
Eloy F Ruiz

Sign in / Sign up

Export Citation Format

Share Document