RESUMO
In a large (250 registrants) general education lecture course, neuroscience principles were taught by two professors as co-instructors, starting with simple brain anatomy, chemistry, and function, proceeding to basic brain circuits of pleasure and pain, and progressing with fellow expert professors covering relevant philosophical, artistic, marketing, and anthropological issues. With this as a base, the course wove between fields of high relevance to psychology and neuroscience, such as food addiction and preferences, drug seeking and craving, analgesic pain-inhibitory systems activated by opiates and stress, neuroeconomics, unconscious decision-making, empathy, and modern neuroscientific techniques (functional magnetic resonance imaging and event-related potentials) presented by the co-instructors and other Psychology professors. With no formal assigned textbook, all lectures were PowerPoint-based, containing links to supplemental public-domain material. PowerPoints were available on Blackboard several days before the lecture. All lectures were also video-recorded and posted that evening. The course had a Facebook page for after-class conversation and one of the co-instructors communicated directly with students on Twitter in real time during lecture to provide momentary clarification and comment. In addition to graduate student Teaching Assistants (TAs), to allow for small group discussion, ten undergraduate students who performed well in a previous class were selected to serve as discussion leaders. The Discussion Leaders met four times at strategic points over the semester with groups of 20-25 current students, and received one credit of Independent Study, thus creating a course within a course. The course grade was based on weighted scores from two multiple-choice exams and a five-page writing assignment in which each student reviewed three unique, but brief original peer-review research articles (one page each) combined with expository writing on the first and last pages. A draft of the first page, collected early in the term, was returned to each student by graduate TAs to provide individual feedback on scientific writing. Overall the course has run three times at ful or near enrollment capacity despite being held at an 8:00 AM time slot. Student-generated teaching evaluations place it well within the normal range, while this format importantly contributes to budget efficiency permitting the teaching of more required small-format courses (e.g., freshman writing). The demographics of the course have changed to one in which the vast majority of the students are now outside the disciplines of neuroscience or psychology and are taking the course to fulfill a General Education requirement. This pattern allows the wide dissemination of basic neuroscientific knowledge to a general college audience.
RESUMO
Objective To predict changes in the quality of life scores of hemodialysis patients for the coming month and the development of an early warning system using machine learning Methods It was a prospective cohort study (one-month duration) at the dialysis center of a tertiary care hospital in Pakistan. The study started on 1st October 2016. About 78 patients have been enrolled till now. Bachelor of Medicine and Bachelor of Surgery (MBBS) qualified doctors administered a proforma with demographics and the validated Urdu version of World Health Organization Quality Of Life-BREF (WHOQOL-BREF). It was to be repeated after one month to the same patient by the same investigator. Simple statistics were computed using SPSS version 24 (IBM Corp., Armonk, NY) while machine learning was performed using R (version 3.0) and Orange (version 3.1). Results Using machine learning algorithms, two models (classification tree and Naïve Bayes) were generated to predict an increase or decrease of 5% in a patient's WHOQOL-BREF score over one month. The classification tree was selected as the most accurate model with an area under curve (AUC) of 83.3% (accuracy: 81.9%) for the prediction of 5% increase in QOL and an AUC of 76.2% (accuracy: 81.8%) for the prediction of 5% decrease in QOL over the coming month. The factors associated with an increase of QOL by 5% or more over the next month included younger age (<19 years) and higher iron sucrose doses (>278mg/month). Drops in psychological, physical, and social domain scores lead to a decrease of 5% or more in QOL scores over the following month. Conclusion An early warning system, dialysis data interpretation for algorithmic-prediction on quality of life (DIAL) was built for the early detection of deteriorating QOL scores in the hemodialysis population using machine learning algorithms. The model pointed out that working on psychological and environmental domains, in particular, may prevent the drop in QOL scores from occurring. DIAL, if implemented on a larger scale, is expected to help patients in terms of ensuring a better QOL and in reducing the financial burden in the long term.