Automated Scoring in Medical Licensing

2020 ◽  
pp. 445-468
Author(s):  
Melissa J. Margolis ◽  
Brian E. Clauser
Author(s):  
Gurpreet Dhaliwal ◽  
Karen E. Hauer

AbstractMany medical schools have reconsidered or eliminated clerkship grades and honor society memberships. National testing organizations announced plans to eliminate numerical scoring for the United States Medical Licensing Examination Step 1 in favor of pass/fail results. These changes have led some faculty to wonder: “How will we recognize and reward excellence?” Excellence in undergraduate medical education has long been defined by high grades, top test scores, honor society memberships, and publication records. However, this model of learner excellence is misaligned with how students learn or what society values. This accolade-driven view of excellence is perpetuated by assessments that are based on gestalt impressions influenced by similarity between evaluators and students, and assessments that are often restricted to a limited number of traditional skill domains. To achieve a new model of learner excellence that values the trainee’s achievement, growth, and responsiveness to feedback across multiple domains, we must envision a new model of teacher excellence. Such teachers would have a growth mindset toward assessing competencies and learning new competencies. Actualizing true learner excellence will require teachers to change from evaluators who conduct assessments of learning to coaches who do assessment for learning. Schools will also need to establish policies and structures that foster a culture that supports this change. In this new paradigm, a teacher’s core duty is to develop talent rather than sort it.


2021 ◽  
Vol 4 (1) ◽  
Author(s):  
Salman Sohrabi ◽  
Danielle E. Mor ◽  
Rachel Kaletsky ◽  
William Keyes ◽  
Coleen T. Murphy

AbstractWe recently linked branched-chain amino acid transferase 1 (BCAT1) dysfunction with the movement disorder Parkinson’s disease (PD), and found that RNAi-mediated knockdown of neuronal bcat-1 in C. elegans causes abnormal spasm-like ‘curling’ behavior with age. Here we report the development of a machine learning-based workflow and its application to the discovery of potentially new therapeutics for PD. In addition to simplifying quantification and maintaining a low data overhead, our simple segment-train-quantify platform enables fully automated scoring of image stills upon training of a convolutional neural network. We have trained a highly reliable neural network for the detection and classification of worm postures in order to carry out high-throughput curling analysis without the need for user intervention or post-inspection. In a proof-of-concept screen of 50 FDA-approved drugs, enasidenib, ethosuximide, metformin, and nitisinone were identified as candidates for potential late-in-life intervention in PD. These findings point to the utility of our high-throughput platform for automated scoring of worm postures and in particular, the discovery of potential candidate treatments for PD.


2009 ◽  
Vol 178 (2) ◽  
pp. 323-326 ◽  
Author(s):  
Jon Pham ◽  
Sara M. Cabrera ◽  
Carles Sanchis-Segura ◽  
Marcelo A. Wood
Keyword(s):  

Sign in / Sign up

Export Citation Format

Share Document