Professionalism and clinical short answer question marking with machine learning.

Machine learning may assist in medical student evaluation. This study involved scoring short answer questions administered at three centres. Bidirectional encoder representations from transformers were particularly effective for professionalism question scoring (accuracy ranging from 41.6% to 92.5%). In the scoring of 3-mark professionalism questions, as compared with clinical questions, machine learning had a lower classification accuracy (P < 0.05). The role of machine learning in medical professionalism evaluation warrants further investigation.

Medical student knowledge and critical appraisal of machine learning: a multicentre international cross-sectional study.

To utilise effectively tools that employ machine learning (ML) in clinical practice medical students and doctors will require a degree of understanding of ML models. To evaluate current levels of understanding, a formative examination and survey was conducted across three centres in Australia, New Zealand and the United States. Of the 245 individuals who participated in the study (response rate = 45.4%), the majority had difficulty with identifying weaknesses in model performance analysis. Further studies examining educational interventions addressing such ML topics are warranted.

The efficacy of mindful practice in improving diagnosis in healthcare: a systematic review and evidence synthesis.

Despite a variety of definitions of mindfulness, over the past 20 years there have been increasing claims that mindful practice is helpful in improving the accuracy of clinical diagnosis. We performed a systematic review and evidence synthesis in order to: determine the nature and definitions of mindful practice and associated terms; evaluate the quality of evidence for the benefits of mindful practice; and conclude whether mindful practice may reduce diagnostic error. We screened 14397 refereed reports from the five common literature databases, to include 33 reports related to the use of mindful practice in clinical diagnosis. Our evidence synthesis contained no randomised controlled trials (level I evidence) of mindful practice, the majority of supporting evidence (26 reports or 79%) comprised conceptual commentary or opinion (level IV evidence). However, 2 supporting reports constituted controlled studies without randomisation (level IIa), 1 report was quasi-experimental (level IIb), and 4 reports were comparative studies (level III). Thus, we may tentatively conclude that mindful practice appears promising as a method of improving diagnostic accuracy, but that further definitive studies of efficacy are required. We identified a taxonomy of 71 terms related to mindful practice, 7 of which were deemed core terms due to being each cited 5 times or more. The 7 core terms appear to be sufficient to describe the findings at higher levels of evidence in our evidence synthesis, suggesting that future definitive studies of mindful practice should focus on these common core terms in order to promote more generalisable findings.

MUSIC® for Medical Students: Confirming the Reliability and Validity of a Multi-Factorial Measure of Academic Motivation for Medical Education.

Construct: The MUSIC® Inventory measures the construct of academic motivation across five factors: empowerment, usefulness, success, interest, and caring. The factors are defined in terms of the degree the student perceives that they have control over their environment, that the coursework is useful to their future, that they can succeed in the course, that the course and instructional methods are interesting, and that the teacher cares about their wellbeing and their success respectively. Background: A valid measure of medical students' academic motivation would provide medical teachers with a method for evaluating the motivational aspect of their course and provide focus for changes in teaching and learning to improve medical student engagement. While the MUSIC® Inventory structure has been validated in the tertiary setting and with several professional programs, it has not been validated with medical students. The aim of this study was to use both classical test theory and Rasch modeling to assess the reliability and confirm the structure of the five-factor model of the MUSIC® Inventory with medical students. Approach: One-hundred-fifty-two medical students completed the 26-item inventory. Descriptive statistics, internal consistency, correlations between factors, confirmatory factor analysis, and Rasch analysis using the rating scale model were performed to determine reliability and validity. Findings: The five factors showed good internal consistency (Cronbach's alpha .87 - .92). Correlations between factors were moderate to high (r = .38 - .89). Confirmatory factor analysis highlighted inconsistencies in factor loadings of three of the items hypothesized to measure interest. Rasch analysis using the rating scale model showed that all items for each factor had good item fit (0.65 - 1.37). Person separation (2.28 - 2.85) and reliability (.84 -.91) scores indicated that the scales were able to differentiate different levels of respondents. Item separation (2.25 - 6.97) and reliability scores (.83 -.98) indicated that the items of the scales were being differentiated by the respondents. Conclusions: Rasch analysis indicates that the five factors of academic motivation measured by the MUSIC® Inventory account for the response patterns in data from medical students. However, while the factors of empowerment, usefulness, success, and caring showed expected reliability and validity using classical analysis, three of the interest items cross-loaded on to the usefulness factor. Possible reasons may include ambiguity of language for the items or medical students' conception of usefulness and interest. Future research will explore medical students' understanding of the language used to measure these factors in further detail.

Measuring the Quality of Clinical Skills Mobile Apps for Student Learning: Systematic Search, Analysis, and Comparison of Two Measurement Scales.

BACKGROUND: Mobile apps are widely used in health professions, which increases the need for simple methods to determine the quality of apps. In particular, teachers need the ability to curate high-quality mobile apps for student learning. OBJECTIVE: This study aims to systematically search for and evaluate the quality of clinical skills mobile apps as learning tools. The quality of apps meeting the specified criteria was evaluated using two measures-the widely used Mobile App Rating Scale (MARS), which measures general app quality, and the Mobile App Rubric for Learning (MARuL), a recently developed instrument that measures the value of apps for student learning-to assess whether MARuL is more effective than MARS in identifying high-quality apps for learning. METHODS: Two mobile app stores were systematically searched using clinical skills terms commonly found in medical education and apps meeting the criteria identified using an approach based on PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. A total of 9 apps were identified during the screening process. The apps were rated independently by 2 reviewers using MARS and MARuL. RESULTS: The intraclass correlation coefficients (ICCs) for the 2 raters using MARS and MARuL were the same (MARS ICC [two-way]=0.68; P<.001 and MARuL ICC [two-way]=0.68; P<.001). Of the 9 apps, Geeky Medics-OSCE revision (MARS Android=3.74; MARS iOS=3.68; MARuL Android=75; and MARuL iOS=73) and OSCE PASS: Medical Revision (MARS Android=3.79; MARS iOS=3.71; MARuL Android=69; and MARuL iOS=73) scored highly on both measures of app quality and for both Android and iOS. Both measures also showed agreement for the lowest rated app, Patient Education Institute (MARS Android=2.21; MARS iOS=2.11; MARuL Android=18; and MARuL iOS=21.5), which had the lowest scores in all categories except information (MARS) and professional (MARuL) in both operating systems. MARS and MARuL were both able to differentiate between the highest and lowest quality apps; however, MARuL was better able to differentiate apps based on teaching and learning quality. CONCLUSIONS: This systematic search and rating of clinical skills apps for learning found that the quality of apps was highly variable. However, 2 apps-Geeky Medics-OSCE revision and OSCE PASS: Medical Revision-rated highly for both versions and with both quality measures. MARS and MARuL showed similar abilities to differentiate the quality of the 9 apps. However, MARuL's incorporation of teaching and learning elements as part of a multidimensional measure of quality may make it more appropriate for use with apps focused on teaching and learning, whereas MARS's more general rating of quality may be more appropriate for health apps targeting a general health audience. Ratings of the 9 apps by both measures also highlighted the variable quality of clinical skills mobile apps for learning.

Student use of common online resources in a multi-campus medical school.

This article was migrated. The article was marked as recommended. Background: Multi-campus medical schools can differ in medical curriculum delivery due to location specific factors, creating different learning contexts. Common online learning may reduce perceived inequities. Using a shared curriculum structure, we developed two learning resource components (topic-based learning objects and multiple-choice question banks) in Obstetrics and Gynaecology for students in our 3-campus medical school. Objective: We evaluated common learning resource use across different learning contexts. We hypothesised that students with fewer structured learning hours would make greater use of topic-based learning resources due to their perceived utility value. We also explored an alternative hypothesis; that resources more closely linked to assessment (MCQ banks) would encourage a strategic approach to learning and would be used most highly at all campuses. Methods: We assessed student opinion of the value of the resources through a cross-campus online survey, and quantified usage of the resources by analysing learning management system logs. Comparisons of response and usage patterns for the two resource components were conducted to identify if context influenced usage. Results: Survey results (RR = 70%) showed that students across campuses rated the resources as valuable. Usage logs partially supported our hypothesis that learning object usage would be highest at the campus (Campus 3) with the lowest structured learning hours in both the proportion of users (p <0.006) and frequency of access for 16 of the 26 topics (p<0.05). However, the reverse was found to be true for the question bank, with lowest usage of question banks at Campus 3 (p< 0.001). Conclusions: We interpret the results as evidence of difference in the perceived utility value of the learning resources across campuses. Clear differences in usage patterns provide evidence that different learning contexts can influence online resource use, and these contexts should be considered when evaluating the effectiveness of online learning resources.

Development and validation of a 4-color multiplexing spinal muscular atrophy (SMA) genotyping assay on a novel integrated digital PCR instrument.

Digital PCR (dPCR) technology has been proven to be highly sensitive and accurate in detecting copy number variations (CNV). However, a higher-order multiplexing dPCR assay for measuring SMN1 and SMN2 copy numbers in spinal muscular atrophy (SMA) samples has not been reported. Described here is a rapid multiplex SMA dPCR genotyping assay run on a fully integrated dPCR instrument with five optical channels. The hydrolysis probe-based multiplex dPCR assay quantifies SMN1, SMN2, and the total SMN (SMN1 + SMN2) while using RPPH1 gene as an internal reference control. The quadruplex assay was evaluated with characterized control DNA samples and validated with 15 blinded clinical samples from a previously published study. SMN1 and SMN2 copy numbers were completely concordant with previous results for both the control and blinded samples. The dPCR-based SMA copy number determination was accomplished in 90 min with a walk-away workflow identical to real-time quantitative PCR (qPCR). In summary, presented here is a simple higher-order multiplexing solution on a novel digital PCR platform to meet the growing demand for SMA genotyping and prognostics.

A Tool for Rating the Value of Health Education Mobile Apps to Enhance Student Learning (MARuL): Development and Usability Study.

BACKGROUND: To realize the potential for mobile learning in clinical skills acquisition, medical students and their teachers should be able to evaluate the value of an app to support student learning of clinical skills. To our knowledge, there is currently no rubric for evaluation of quality or value that is specific for apps to support medical student learning. Such a rubric might assist students to be more confident in using apps to support their learning. OBJECTIVE: The objective of this study was to develop an instrument that can be used by health professional educators to rate the value of a mobile app to support health professional student learning. METHODS: Using the literature, we developed a list of potential criteria for the evaluation of educational app value, which were then refined with a student group using a modified nominal group technique. The refined list was organized into themes, and the initial rubric, Mobile App Rubric for Learning (MARuL, version 1), was developed. iOS and Android app stores were searched for clinical skills apps that met our inclusion criteria. After the 2 reviewers were trained and the item descriptions were refined (version 2), a random sample of 10 included apps, 5 for each mobile operating system, was reviewed. Interitem and interrater analyses and discussions with the reviewers resulted in refinement of MARuL to version 3. The reviewers completed a review of 41 clinical skills mobile apps, and a second round of interitem and interrater reliability testing was performed, leading to version 4 of the MARuL. RESULTS: Students identified 28 items (from an initial set of 144 possible items) during the nominal group phase, and these were then grouped into 4 themes: teaching and learning, user centered, professional, and usability. Testing and refinement with reviewers reduced the list to 26 items. Internal consistency for MARuL was excellent (α=.96), and the interrater reliability as measured by the intraclass correlation coefficient (ICC) was good (ICC=0.66). CONCLUSIONS: MARuL offers a fast and user-friendly method for teachers to select valuable apps to enhance student learning.

Precision cancer monitoring using a novel, fully integrated, microfluidic array partitioning digital PCR platform.

A novel digital PCR (dPCR) platform combining off-the-shelf reagents, a micro-molded plastic microfluidic consumable with a fully integrated single dPCR instrument was developed to address the needs for routine clinical diagnostics. This new platform offers a simplified workflow that enables: rapid time-to-answer; low potential for cross contamination; minimal sample waste; all within a single integrated instrument. Here we showcase the capability of this fully integrated platform to detect and quantify non-small cell lung carcinoma (NSCLC) rare genetic mutants (EGFR T790M) with precision cell-free DNA (cfDNA) standards. Next, we validated the platform with an established chronic myeloid leukemia (CML) fusion gene (BCR-ABL1) assay down to 0.01% mutant allele frequency to highlight the platform's utility for precision cancer monitoring. Thirdly, using a juvenile myelomonocytic leukemia (JMML) patient-specific assay we demonstrate the ability to precisely track an individual cancer patient's response to therapy and show the patient's achievement of complete molecular remission. These three applications highlight the flexibility and utility of this novel fully integrated dPCR platform that has the potential to transform personalized medicine for cancer recurrence monitoring.

A qualitative study of pain experiences in patients requiring hip and knee arthroplasty.

The aim of this study was to conduct an in-depth investigation of experiences with pain before knee and hip replacement surgery. A total of 20 patients were interviewed, and interpretative phenomenological analysis was used to identify themes. These were as follows: living with pain, pain conceptualised, pain treatments and healthcare system. Pre-surgical pain is very disabling and is viewed as biological. There was an associated loss of independence. Pharmaceutical management is used by all but not entirely effective, psychological therapies are underutilised. Patients were frustrated, angry, and confused about qualifying for surgery. Many areas of care could be improved to help these pre-surgical patients.